Performance evaluation method and device for digital government project

Abstract

The invention provides a performance evaluation method and device for a digital government project. The method comprises the following steps: acquiring to-be-evaluated digital government project data; processing the to-be-evaluated digital government project data based on the performance evaluation model to obtain a performance evaluation result; wherein the performance evaluation model constructs a mathematical model by taking sample multi-source data of a digital government project as input and taking a performance evaluation score as output, and updates the mathematical model according to causal relationship information among the sample multi-source data to obtain the performance evaluation model; the performance evaluation score is determined based on the performance evaluation index corresponding to the sample multi-source data and the optimized weight factor. According to the method, the accuracy of digital government project performance evaluation is improved, and reliable data support is provided for digital government project management and maintenance.

Description

Technical Field

[0001] The present invention relates to the technical field of performance evaluation, and particularly to a performance evaluation method and device for digital government projects. Background Art

[0002] In the context of the rapid development of the current digital era, the scientific evaluation of the performance of digital government projects has become an important issue faced by institutions at all levels.

[0003] In related technologies, traditional performance evaluation methods for digital government projects mainly rely on static analysis of qualitative and quantitative indicators. By determining a series of indicators, such as project completion progress, service coverage, user satisfaction, etc., to evaluate digital government projects. However, traditional performance evaluation methods for digital government projects may have the evaluation results lagging behind the actual progress of the project, and cannot provide effective support for decision-making in a timely manner. Secondly, the static analysis method lacks consideration of the system's dynamic changes and complexity, and it is difficult to comprehensively reflect the actual effects of digital government projects. There may be poor real-time performance of the performance evaluation results, low reliability of the evaluation results, and reduced work efficiency of relevant institutions. Summary of the Invention

[0004] The present invention provides a performance evaluation method and device for digital government projects, which are used to solve the defects of poor real-time performance and inaccurate evaluation results when the existing technology uses static analysis methods for performance evaluation of digital government projects, and improve the accuracy of performance evaluation of digital government projects.

[0005] The present invention provides a performance evaluation method for digital government projects, including: Obtaining data of the digital government project to be evaluated; Processing the data of the digital government project to be evaluated based on a performance evaluation model to obtain a performance evaluation result; wherein, the performance evaluation model constructs a mathematical model with the sample multi-source data of the digital government project as the input and the performance evaluation score as the output, and updates the mathematical model according to the causal relationship information between the sample multi-source data to obtain a performance evaluation model; the performance evaluation score is determined based on the performance evaluation indicators corresponding to the sample multi-source data and the optimized weight factors.

[0006] According to a performance evaluation method for digital government projects provided by the present invention, the performance evaluation model is obtained through the following steps: Performing system dynamics analysis on the sample multi-source data to obtain a social governance mutual promotion dynamics model, and performing causal relationship analysis on the sample multi-source data to obtain the causal relationship information; wherein, the social governance mutual promotion dynamics model is used to represent the relationship between the internal structure and behavior of the digital government project; the social governance mutual promotion dynamics model includes multiple data variables; Perform correlation statistics and analysis on the multiple data variables, and calculate multiple performance evaluation indicators from multiple performance evaluation dimensions according to the analysis results; wherein, the multiple performance evaluation dimensions include at least one of service quality, service efficiency, innovation degree, and social impact factor; Calculate the performance evaluation score based on the multiple performance evaluation indicators according to the optimized weight factors, construct a mathematical model with the sample multi-source data as the input and the performance evaluation score as the output, and update the mathematical model according to the causal relationship information to obtain the performance evaluation model.

[0007] According to a performance evaluation method for digital government projects provided by the present invention, the optimized weight factors are determined through the following steps: Obtain the subjective and objective feedback information of users on the digital government project; Use an intelligent quantitative scoring algorithm to analyze the subjective and objective feedback information to obtain the optimized weights.

[0008] According to a performance evaluation method for digital government projects provided by the present invention, wherein the causal relationship analysis of the sample multi-source data to obtain the causal relationship information includes: Collect the text data corresponding to the digital government project, and the text data includes at least one of policy documents, project reports, and user feedback; Perform semantic analysis on the text data based on the Bert model to obtain the causal relationship information.

[0009] According to a performance evaluation method for digital government projects provided by the present invention, the calculation of the performance evaluation score based on the multiple performance evaluation indicators according to the optimized weight factors includes: Perform quantitative evaluation on each performance evaluation indicator based on the historical data of the digital government project to obtain multiple performance evaluation indicator scores; Perform weighted summation on the multiple performance evaluation indicator scores based on the optimized weight factors to obtain the comprehensive performance score.

[0010] According to a performance evaluation method for digital government projects provided by the present invention, the correlation statistics and analysis of the multiple data variables include: Perform principal component analysis and correlation analysis on the multiple data variables in the social governance mutual promotion dynamics model, and extract multiple key factors and core evaluation indicators; Use a causal relationship analysis method to analyze the causal associations between the multiple key factors and core indicators to obtain the analysis results.

[0011] The present invention also provides a performance evaluation device for digital government projects, including: A data acquisition module for acquiring data of the digital government project to be evaluated; A performance evaluation module for processing the data of the digital government project to be evaluated based on a performance evaluation model to obtain a performance evaluation result; wherein, the performance evaluation model constructs a mathematical model by taking the sample multi-source data of the digital government project as input and the performance evaluation score as output, and updates the mathematical model according to the causal relationship information between the sample multi-source data to obtain a performance evaluation model; the performance evaluation score is determined based on the performance evaluation indicators corresponding to the sample multi-source data and the optimized weight factors.

[0012] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the performance evaluation method of the digital government project as described in any one of the above is implemented.

[0013] The present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the performance evaluation method of the digital government project as described in any one of the above is implemented.

[0014] The present invention also provides a computer program product, including a computer program. When the computer program is executed by a processor, the performance evaluation method of the digital government project as described in any one of the above is implemented.

[0015] The performance evaluation method and device for digital government projects provided by the present invention construct a mathematical model by taking the sample multi-source data of the digital government project as input and the performance evaluation score calculated from the performance evaluation indicators corresponding to the sample multi-source data and the optimized weight factors as output, and perform performance analysis on the data of the digital government project to be evaluated by using the performance evaluation model obtained by updating the mathematical model according to the causal relationship information between the sample multi-source data, which improves the accuracy of the performance evaluation of digital government projects and provides reliable data support for the management and maintenance of digital government projects. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0017] Figure 1 It is a schematic flowchart of the performance evaluation method for digital government projects provided by the present invention.

[0018] Figure 2 It is a schematic structural diagram of the performance evaluation device for the digital government project provided by the present invention.

[0019] Figure 3 It is a schematic structural diagram of the electronic device provided by the present invention. Detailed implementation manners

[0020] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below with reference to the accompanying drawings in the present invention. Apparently, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present invention without any creative work belong to the scope of protection of the present invention.

[0021] Below in conjunction with Figure 1 - Figure 2 Describe the performance evaluation method and its device for the digital government project of the present invention.

[0022] Figure 1 It is a schematic flowchart of the performance evaluation method for the digital government project provided by the present invention. As Figure 1 shown, the method includes the following: Step 110, obtain the data of the digital government project to be evaluated.

[0023] In this step, the data of the digital government project to be evaluated can be the data of the digital government project generated historically or the data of the digital government project collected in real time.

[0024] In this step, the multi-source data samples of the digital government project include government service data, user behavior data, social and economic data, etc.

[0025] In this embodiment, the government service data includes handling matters, handling processes, service efficiency, etc.; in this embodiment, relevant data is collected through channels such as the government public data platform and the online government service system.

[0026] In this embodiment, the user behavior data can collect the usage data of users for government services through methods such as user research, online questionnaires, and user behavior tracking, and record key indicators such as the access frequency, usage duration, and service evaluation of users.

[0027] In this embodiment, the social and economic data can collect the social and economic data related to the digital government project from official publications such as the statistics bureau and yearbooks. For example, the social and economic data includes but is not limited to indicators such as GDP, population statistics, education level, and infrastructure development.

[0028] Step 120: Process the data of the digital government project to be evaluated based on the performance evaluation model to obtain the performance evaluation result. Among them, the performance evaluation model constructs a mathematical model with the sample multi-source data of the digital government project as the input and the performance evaluation score as the output, and updates the mathematical model according to the causal relationship information between the sample multi-source data to obtain the performance evaluation model. The performance evaluation score is determined based on the performance evaluation indicators corresponding to the sample multi-source data and the optimized weight factors.

[0029] In this step, the performance evaluation model is obtained through the following steps: (1) Conduct a system dynamics analysis on the sample multi-source data to obtain a social governance mutual promotion dynamics model, and conduct a causal relationship analysis on the sample multi-source data to obtain causal relationship information. Among them, the social governance mutual promotion dynamics model is used to represent the relationship between the internal structure and behavior of the digital government project. The social governance mutual promotion dynamics model includes multiple data variables.

[0030] In this embodiment, the acquisition method of the sample multi-source data is the same as that of the above-mentioned data of the digital government project to be evaluated, and will not be elaborated in this embodiment.

[0031] In this embodiment, conduct a system dynamics analysis on the sample multi-source data of the digital government project to obtain a social governance mutual promotion dynamics model, and conduct a causal relationship analysis on the sample multi-source data to obtain causal relationship information. Among them, the social governance mutual promotion dynamics model is used to represent the relationship between the internal structure and behavior of the digital government project. The social governance mutual promotion dynamics model includes multiple data variables.

[0032] In this embodiment, the system dynamics model can be used to analyze the causal relationships and feedback mechanisms in the data, determine the key variables and interaction relationships, construct the framework of the social governance mutual promotion dynamics model, and form the initial analysis framework, that is, the social governance mutual promotion dynamics model. Through the system dynamics model, reveal the relationship between the internal structure and behavior of the digital government project, and at the same time provide support for predicting the future development trend of the project, and provide a forward-looking basis for the project planning and decision-making. In this embodiment, the causal relationship analysis of the sample multi-source data to obtain causal relationship information includes: collecting the text data corresponding to the digital government project, and the text data includes at least one of policy documents, project reports, and user feedback; based on the Bert model, conduct semantic analysis on the text data to obtain causal relationship information.

[0033] In this embodiment, after obtaining the corresponding text data, the collected data can be integrated, the data format and measurement standard can be unified, missing values can be filled, outliers can be smoothed, and necessary data conversion and standardization processing can be carried out to improve the quality of the text data.

[0034] Specifically, the above-mentioned policy documents can collect policy documents related to digital government projects from government official websites, policy release platforms, etc., ensuring that the collected policy documents cover key information such as project goals, implementation plans, and expected outcomes; the above-mentioned project reports can obtain project progress reports, mid-term evaluation reports, final reports, etc. from government departments, project implementation units, or relevant research institutions; the reports should include project implementation status, effectiveness evaluation, problems and challenges, etc.; the above-mentioned user feedback can be collected through channels such as social media, online surveys, and public forums; the user feedback should cover content such as user satisfaction, service experience, and improvement suggestions.

[0035] In this embodiment, the above text data can be subjected to text cleaning, text clause segmentation, and standardization processing. For example, text cleaning includes removing irrelevant characters, HTML tags, stop words, etc., and only retaining useful text information; text clause segmentation includes splitting the collected text data into independent sentences or paragraphs for subsequent analysis; text standardization includes unifying the format and expression of the text, such as date format, proper nouns, etc., thereby reducing the impact of abnormal data in the text data on subsequent text information extraction and improving the quality of the text data.

[0036] In this embodiment, a Bert pre-trained model suitable for Chinese text analysis is selected, and the preprocessed text data is input into the Bert model to obtain the deep semantic representation of the text.

[0037] For example, using the last hidden state output by the Bert model, the vector representation of each sentence is obtained, and then a classifier or sequence labeling model is used to extract causal relationship information from the text based on the sentence embedding. For example, the Bert model can be fine-tuned on sentences to identify causal relationship trigger words (such as "because", "so", etc.) and the corresponding causal entities; finally, according to the model output results, the trigger words expressing causal relationships in the text are identified, thereby determining the causal entities connected by the trigger words, that is, the cause and the result, and finally judging whether the identified entity pair constitutes a causal relationship through the model.

[0038] In this embodiment, let the sample multi-source data set be D = {D1, D2,..., Dn}, where Di represents different types of data. Through the system dynamics model function G(D), the initial analysis framework A1 = G(D) is obtained, that is, the social governance mutual promotion dynamics model.

[0039] (2) Conduct correlation statistics and analysis on multiple data variables, and calculate multiple performance evaluation indicators from multiple performance evaluation dimensions according to the analysis results; among them, the multiple performance evaluation dimensions include at least one of service quality, service efficiency, innovation degree, and social impact factor.

[0040] In this embodiment, the quality of service indicator is used to represent the satisfaction degree of users with the digital government project, and can be obtained through data such as user satisfaction surveys, service complaint rates, service response times, etc.; for example, user satisfaction can be measured by the scores (1 point - 5 points) in the questionnaire survey, and the service response time can be calculated by the average response time in the system log.

[0041] In this embodiment, the service efficiency indicator is used to represent the efficiency of the digital government project in handling affairs, and is usually measured by the transaction processing time, service completion rate, etc., and can be obtained through data such as the transaction processing time, service completion rate, resource utilization rate, etc. in the system log; for example, the transaction processing time can be calculated by the average processing time in the system log, and the service completion rate can be measured by the ratio of the number of completed transactions to the total number of transactions.

[0042] In this embodiment, the innovation degree indicator is used to represent the performance of the digital government project in terms of technological innovation, and can be obtained through data such as the number of new technology applications in the project, the number of innovation projects, the number of patents, etc.; for example, the number of new technology applications can be counted through the technology application list in the project report, and the number of innovation projects can be calculated by the number of innovation projects in the project classification.

[0043] In this embodiment, the social impact factor is used to represent the degree of impact of the digital government project on society, and can be obtained through data such as the number of media reports, public participation, social benefit evaluation, etc.; for example, the number of media reports can be counted through the number of relevant reports in the news database, and the public participation can be measured by the discussion volume on social media or the number of users participating in activities.

[0044] In this embodiment, through in-depth analysis and statistics of the initial analysis framework A1, important contents such as key influencing factors and core indicators are obtained, and A2 is formed.

[0045] Specifically, the correlation statistics and analysis of multiple data variables include: performing principal component analysis and correlation analysis on multiple data variables in the social governance mutual promotion dynamics model, extracting multiple key factors and core evaluation indicators; using the causal relationship analysis method to analyze the causal association between multiple key factors and core indicators to obtain the analysis results.

[0046] In this embodiment, principal component analysis and correlation analysis are performed on the data in A1, extracting key factors and core indicators that have an important impact on the performance of the digital government project to form A2; at the same time, the causal relationship analysis method is used to preliminarily explore the causal association between these key factors and core indicators.

[0047] Let the data variables in A1 be X = {X1, X2,..., Xm}. Through the principal component analysis function F(X) and the correlation analysis function K(X), we obtain A2 = F(X) ∩ K(X).

[0048] In this embodiment, in combination with the characteristics and goals of the digital government project, performance evaluation indicators are determined from multiple dimensions, such as service quality, efficiency improvement, innovation ability, and social impact, etc.; each indicator is defined and described in detail to ensure the measurability and operability of the indicators.

[0049] For example, assume the performance evaluation index system is I = {I1, I2,..., Ik}, where Ii represents different performance evaluation indicators.

[0050] (3) Calculate the performance evaluation score based on multiple performance evaluation indicators according to the optimized weight factors, construct a mathematical model with the sample multi-source data as the input and the performance evaluation score as the output, and update the mathematical model according to the causal relationship information to obtain the performance evaluation model.

[0051] In this embodiment, in order to comprehensively consider the impact of multiple indicators on performance evaluation, initial weight factors can be set for multiple performance evaluation indicators.

[0052] For example, based on literature research and historical experience, combined with expert opinions, initial weights can be determined for each indicator; weight factors can also be set according to the actual needs of users.

[0053] Specifically, by consulting relevant academic literature, policy documents, and industry standards, summarize the indicators and their weight factors for the performance evaluation of digital government projects; then, combined with the experience of successful digital government project cases in history, sort out a set of candidate performance evaluation index libraries C1; invite experts to evaluate the importance of each indicator, and continuously adjust and optimize the index weights through methods such as the Delphi method to ensure the scientificity and rationality of the weight setting.

[0054] Let the set of initial weights obtained from literature research and historical experience be W0 = {W01, W02,..., W0k}, and the set of weights adjusted through expert evaluation and the Delphi method be W = {W1, W2,..., Wk}.

[0055] In this embodiment, after determining each performance evaluation indicator and the corresponding weight factor, the weighted sum formula can be used to calculate multiple performance evaluation indicators and the corresponding weight factors to obtain a comprehensive evaluation indicator, and then perform linear fitting with different sample multi-source data as the input and different performance evaluation scores as the output to obtain the corresponding mathematical model. Finally, use the above causal relationship information as a regularization term to update the model parameters of the mathematical model to obtain the final performance evaluation model.

[0056] In this embodiment, the data of the digital government project to be evaluated is input into the performance evaluation model to obtain the corresponding performance evaluation result. This performance evaluation method can provide accurate performance information for the managers of digital government projects, helping them better understand the advantages and disadvantages of the projects. Managers can allocate resources reasonably according to the evaluation results, invest more resources in the areas with better performance, and at the same time make targeted improvements and optimizations to the areas with poor performance.

[0057] For example, if a certain digital government project scores low in terms of service quality, the manager can increase the investment in service improvement, including increasing personnel training, optimizing service processes, etc., so as to improve the overall performance of the project and achieve the optimal allocation of resources.

[0058] The performance evaluation method for digital government projects provided by the present invention constructs a mathematical model by taking the sample multi-source data of digital government projects as input and the performance evaluation score calculated from the performance evaluation indicators corresponding to the sample multi-source data and the optimized weight factors as output, and performs performance analysis on the data of the digital government project to be evaluated by using the performance evaluation model obtained after updating the mathematical model according to the causal relationship information between the sample multi-source data, which improves the accuracy of digital government project performance evaluation and provides reliable data support for digital government project management and maintenance.

[0059] In some embodiments, the optimized weight factor is determined through the following steps: obtaining the subjective and objective feedback information of users on digital government projects; analyzing the subjective and objective feedback information by using an intelligent quantitative scoring algorithm to obtain the optimized weight.

[0060] In this embodiment, the subjective and objective feedback information can be collected by means of issuing questionnaires and inviting expert evaluations.

[0061] In this embodiment, an intelligent quantitative scoring algorithm is used to combine the subjective and objective feedback information to optimize the weights of performance evaluation indicators, ensuring that the weight setting is more scientific and reasonable, thereby improving the accuracy of performance evaluation results.

[0062] In this embodiment, the specific analysis steps of the intelligent quantitative scoring algorithm are as follows: 1. Data collection: First, collect the subjective and objective feedback information of users on digital government projects. Subjective feedback can be obtained through questionnaires, user interviews, etc., and objective feedback can be obtained through system logs, user behavior data, etc.

[0063] 2. Data preprocessing: Clean and standardize the collected subjective and objective feedback information. For subjective feedback, perform text cleaning (removing irrelevant characters, stop words, etc.) and sentiment analysis; for objective feedback, handle missing values and outliers to ensure data quality.

[0064] 3. Quantitative scoring: Use natural language processing techniques (such as sentiment analysis algorithms) to convert subjective feedback text into sentiment scores. For objective feedback, statistical methods (such as mean, median, etc.) are used for quantification.

[0065] 4. Weight optimization: Train a model (such as a neural network) based on historical data to learn the non-linear relationships between indicators. For the Analytic Hierarchy Process (AHP), the relative importance weights of each indicator can be calculated by constructing a judgment matrix. Use the reserved test data set to verify the accuracy of the model, and adjust the weights of each indicator according to the model output results to ensure that the sum of the weights is 1 and each weight is between 0 and 1.

[0066] 5. Weight adjustment: Adjust the weights of each indicator according to the model output results. For example, if a certain indicator shows a strong influence in historical data, its weight can be appropriately increased; otherwise, its weight can be decreased.

[0067] For example, assume there are the following three performance evaluation indicators: service quality (I1), service efficiency (I2), and innovation degree (I3). The initial weights are W1 = 0.4, W2 = 0.3, and W3 = 0.3 respectively.

[0068] First, collect user feedback on service quality, service efficiency, and innovation degree through questionnaires and system logs; then use the sentiment analysis algorithm to convert the user feedback on service quality into a sentiment score, assuming the score is 0.8; calculate the score of service efficiency through system logs as 0.9; calculate the score of innovation degree through project reports as 0.7; then, use historical data to train a neural network model and find that service quality has a greater impact on overall performance, so adjust W1 to 0.5, W2 to 0.3, and W3 to 0.2; finally, calculate the comprehensive performance score according to the optimized weights: P = 0.5 * 0.8 + 0.3 * 0.9 + 0.2 * 0.7 = 0.81.

[0069] Through the above steps, the intelligent quantitative scoring algorithm can dynamically adjust the weights of each indicator according to user feedback and historical data, so as to obtain a more scientific and reasonable performance evaluation result.

[0070] In this embodiment, let the set of subjective and objective feedback information be F = {F1, F2,..., Fi}, and the intelligent quantitative scoring algorithm function be S(W, F), then the optimized weight W' = S(W, F).

[0071] The performance evaluation method for digital government projects provided by the embodiments of the present invention obtains the subjective and objective feedback information of users on digital government projects; uses an intelligent quantitative scoring algorithm to analyze the subjective and objective feedback information to obtain optimized weights, and then combines multiple performance evaluation indicators for performance evaluation, further improving the accuracy of the performance evaluation results.

[0072] Further, calculating the performance evaluation score based on multiple performance evaluation indicators according to the optimized weight factors includes: quantitatively evaluating each performance evaluation indicator based on the historical data of the digital government project to obtain multiple performance evaluation indicator scores. Performing weighted summation on the multiple performance evaluation indicator scores based on the optimized weight factors to obtain the comprehensive performance score.

[0073] In this embodiment, according to the determined performance evaluation index system, relevant data of the digital government project are collected, each index is quantitatively evaluated, and corresponding scores are given.

[0074] Let the set of multiple performance evaluation indicator scores be S = {S1, S2,..., Sk}, where Si represents the score of the i-th indicator.

[0075] In this embodiment, according to the weights and scores of each performance evaluation indicator, the weighted summation method is used to calculate the comprehensive performance score of the digital government project; the comprehensive performance score can comprehensively reflect the performance level of the digital government project and provide a strong basis for project management and decision-making.

[0076] Let the comprehensive performance score be P, then P = Σ(Wi' * Si), where Wi' is the optimized index weight and Si is the index score.

[0077] In this embodiment, the Bert semantic enhancement causal relationship analysis method is used to accurately identify and quantify the causal relationships between influencing factors. By analyzing the text data related to the digital government project, the causal relationship information therein is extracted, and finally this causal relationship information is incorporated into the performance evaluation model to construct a performance evaluation model based on causal relationships, making the evaluation results more accurate and reliable.

[0078] Let the text data set be T = {T1, T2,..., Tm}, and the Bert semantic enhancement causal relationship analysis function be B(T), then the causal relationship information C = B(T).

[0079] Incorporating the causal relationship information C into the performance evaluation model further optimizes the comprehensive performance score P' = P + C.

[0080] The intelligent quantitative scoring algorithm adopted in this embodiment should be continuously optimized and improved to adapt to the characteristics and requirements of different digital government projects.

[0081] The performance evaluation method for digital government projects provided by the embodiments of the present invention quantifies and evaluates each performance evaluation index based on the historical data of digital government projects to obtain scores for multiple performance evaluation indexes; weights and sums the scores of multiple performance evaluation indexes based on the optimized weight factors to obtain a comprehensive performance score, improving the reliability of multiple performance evaluation indexes, thereby enhancing the accuracy of performance evaluation results.

[0082] The performance evaluation device for digital government projects provided by the present invention will be described below. The performance evaluation device for digital government projects described below can be correspondingly referred to the performance evaluation method for digital government projects described above.

[0083] The performance evaluation device provided by the present invention will be described below. The performance evaluation device described below can be correspondingly referred to the performance evaluation method described above.

[0084] Figure 2 is a schematic structural diagram of the performance evaluation device provided by the present invention. As Figure 2 shown, the performance evaluation device includes: a data acquisition module 210 and a performance evaluation module 220.

[0085] The data acquisition module 210 is used to acquire data of the digital government project to be evaluated; The performance evaluation module 220 is used to process the data of the digital government project to be evaluated based on the performance evaluation model to obtain a performance evaluation result; wherein, the performance evaluation model constructs a mathematical model with the sample multi-source data of the digital government project as the input and the performance evaluation score as the output, and updates the mathematical model according to the causal relationship information between the sample multi-source data to obtain the performance evaluation model; the performance evaluation score is determined based on the performance evaluation indexes corresponding to the sample multi-source data and the optimized weight factors.

[0086] The performance evaluation device for digital government projects provided by the embodiments of the present invention constructs a mathematical model with the sample multi-source data of the digital government project as the input and the performance evaluation score calculated from the performance evaluation indexes corresponding to the sample multi-source data and the optimized weight factors as the output, and performs performance analysis on the data of the digital government project to be evaluated by the performance evaluation model obtained by updating the mathematical model according to the causal relationship information between the sample multi-source data, improving the accuracy of digital government project performance evaluation, and at the same time providing reliable data support for the management and maintenance of digital government projects.

[0087] Figure 3 is a schematic structural diagram of the electronic device provided by the present invention. As Figure 3As shown in the figure, the electronic device may include: a processor 310, a communications interface 320, a memory 330, and a communication bus 340. Among them, the processor 310, the communications interface 320, and the memory 330 complete communication with each other through the communication bus 340. The processor 310 can call the logical instructions in the memory 330 to execute the performance evaluation method for digital government projects. The method includes: obtaining the data of the digital government project to be evaluated; processing the data of the digital government project to be evaluated based on the performance evaluation model to obtain a performance evaluation result; where the performance evaluation model constructs a mathematical model with the sample multi-source data of the digital government project as the input and the performance evaluation score as the output, and updates the mathematical model according to the causal relationship information between the sample multi-source data to obtain the performance evaluation model; the performance evaluation score is determined based on the performance evaluation indicators corresponding to the sample multi-source data and the optimized weight factors.

[0088] In addition, when the logical instructions in the above-mentioned memory 330 are implemented in the form of software functional units and sold or used as an independent product, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0089] On the other hand, the present invention also provides a computer program product. The computer program product includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the performance evaluation method for digital government projects provided by the above-mentioned various methods. The method includes: obtaining the data of the digital government project to be evaluated; processing the data of the digital government project to be evaluated based on the performance evaluation model to obtain a performance evaluation result; where the performance evaluation model constructs a mathematical model with the sample multi-source data of the digital government project as the input and the performance evaluation score as the output, and updates the mathematical model according to the causal relationship information between the sample multi-source data to obtain the performance evaluation model; the performance evaluation score is determined based on the performance evaluation indicators corresponding to the sample multi-source data and the optimized weight factors.

[0090] In another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements a performance evaluation method for a digital government project provided by the above-mentioned various methods. The method includes: obtaining data of the digital government project to be evaluated; processing the data of the digital government project to be evaluated based on a performance evaluation model to obtain a performance evaluation result; wherein, the performance evaluation model constructs a mathematical model with the sample multi-source data of the digital government project as the input and the performance evaluation score as the output, and updates the mathematical model according to the causal relationship information between the sample multi-source data to obtain the performance evaluation model; the performance evaluation score is determined based on the performance evaluation indicators corresponding to the sample multi-source data and the optimized weight factors.

[0091] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0092] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disc, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0093] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A performance evaluation method for a digital government project, characterized in that: include: Obtain data on digital government projects to be evaluated; The digital government project data to be evaluated is processed based on the performance evaluation model to obtain a performance evaluation result; wherein the performance evaluation model constructs a mathematical model by taking sample multi-source data of the digital government project as input and a performance evaluation score as output, and updates the mathematical model according to the causal relationship information between the sample multi-source data to obtain the performance evaluation model; the performance evaluation score is determined based on the performance evaluation index corresponding to the sample multi-source data and the optimized weight factor.

2. The performance evaluation method of the digital government project according to claim 1 is characterized in that: The performance evaluation model is obtained through the following steps: Performing system dynamics analysis on the sample multi-source data to obtain a social governance mutual promotion dynamics model, and performing causal relationship analysis on the sample multi-source data to obtain the causal relationship information; wherein the social governance mutual promotion dynamics model is used to represent the relationship between the internal structure and behavior of the digital government project; the social governance mutual promotion dynamics model includes multiple data variables; Performing correlation statistics and analysis on the multiple data variables, and calculating multiple performance evaluation indicators from multiple performance evaluation dimensions according to the analysis results; wherein the multiple performance evaluation dimensions include at least one of service quality, service efficiency, innovation and social impact factor; The performance evaluation score is calculated based on the multiple performance evaluation indicators according to the optimized weight factors, and a mathematical model is constructed with the sample multi-source data as input and the performance evaluation score as output, and the mathematical model is updated according to the causal relationship information to obtain the performance evaluation model.

3. The performance evaluation method for a digital government project according to claim 1 or 2, characterized in that: The optimized weight factor is determined by the following steps: Obtaining subjective and objective feedback from users on the digital government project; An intelligent quantitative scoring algorithm is used to analyze the subjective and objective feedback information to obtain the optimized weight.

4. The performance evaluation method of a digital government project according to claim 2 is characterized in that: The causal relationship analysis is performed on the sample multi-source data to obtain the causal relationship information, including: Collecting text data corresponding to the digital government project, wherein the text data includes at least one of a policy document, a project report, and user feedback; The text data is semantically analyzed based on the Bert model to obtain the causal relationship information.

5. The performance evaluation method of a digital government project according to claim 2 is characterized in that: Calculating the performance evaluation score based on the multiple performance evaluation indicators according to the optimized weight factors includes: Based on the historical data of the digital government project, each performance evaluation indicator is quantitatively evaluated to obtain multiple performance evaluation indicator scores; The scores of the multiple performance evaluation indicators are weighted and summed based on the optimized weight factors to obtain a comprehensive performance score.

6. The performance evaluation method of a digital government project according to claim 2 is characterized in that: The performing correlation statistics and analysis on the multiple data variables comprises: Conduct principal component analysis and correlation analysis on multiple data variables in the social governance mutual promotion dynamics model to extract multiple key factors and core evaluation indicators; The causal relationship analysis method is used to analyze the causal relationship between the multiple key factors and core indicators to obtain the analysis results.

7. A performance evaluation device for a digital government project, characterized in that: include: Data acquisition module, used to obtain the data of digital government projects to be evaluated; A performance evaluation module is used to process the digital government project data to be evaluated based on a performance evaluation model to obtain a performance evaluation result; wherein the performance evaluation model constructs a mathematical model by taking sample multi-source data of digital government projects as input and a performance evaluation score as output, and updates the mathematical model according to the causal relationship information between the sample multi-source data to obtain a performance evaluation model; the performance evaluation score is determined based on the performance evaluation index corresponding to the sample multi-source data and the optimized weight factor.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, it implements the performance evaluation method of the digital government project as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it implements the performance evaluation method of the digital government project as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, it implements the performance evaluation method of the digital government project as described in any one of claims 1 to 6.

Images