Electronic government affair big data processing system and method

Abstract

The invention belongs to the technical field of electronic government affair big data processing, and discloses an electronic government affair big data processing system and method. The system comprises a traffic data acquisition module, a depth data acquisition module, a data interaction extraction module, a traffic quantitative prediction module, an auxiliary decision generation module, a causal reasoning interpretation module, a vulnerable group inclination module and a data distinguishing processing module, and is used for analyzing feature vectors to obtain a congestion prediction value, analyzing the congestion prediction value, and obtaining a traffic prediction result. The method comprises the following steps: analyzing a congestion prediction value, obtaining an auxiliary decision report according to an analysis result, performing causal inference on the auxiliary decision report, combining an inference result with the auxiliary decision report to obtain a causal inference report, performing calculation based on region type data and complaint evaluation data, and correcting the congestion prediction value according to a calculation result to obtain a prediction correction value. The method has the remarkable advantages of being high in traffic condition prediction accuracy, high in data mining capacity and large in management balance effect.

Description

Technical Field

[0001] The present invention relates to the technical field of e-government big data processing, and more specifically, to an e-government big data processing system and method. Background Art

[0002] E-government refers to a new management model in which state organs comprehensively apply modern information technology, network technology, and office automation technology to conduct office work, management, and provide public services to society in their government activities. The broad scope of e-government should include all state agencies, while the narrow sense of e-government mainly includes administrative agencies at all levels that directly undertake the management of national public affairs and social affairs. Thanks to the rapid development of science and technology, electronic government processing has been widely used. Among them, whether urban traffic is smooth is not only related to the operation of the city, but also closely related to people's travel and life.

[0003] The patent application publication number CN117892849B discloses an e-government big data processing optimization method and system. It is composed of a permission label module, a conflict alignment module, a data set fusion module, a permission matching module and a distributed authorization module, and can implement any e-government big data processing optimization method described in the present invention. The internal structure of the system cooperates with each other. By adopting the mapping of different user permissions of a large amount of data in the e-government system with the department's corresponding regional level, the difficulty of permission search of a large amount of department's corresponding regional business data is reduced for subsequent authorization matching and distributed storage of sensitive data. Targeted encryption measures with different sensitivities are performed on the data, and adaptive processing is performed on the data before distributed data, which reduces the time spent on encryption and decryption of a large amount of sensitive data in the e-government big data, thereby simplifying the operation process of the e-government big data processing optimization system.

[0004] However, although the above-mentioned e-government big data processing optimization method and system have reduced the time consumption of encryption and decryption of a large amount of sensitive data in e-government big data to a certain extent by setting up multiple modules, thereby achieving the purpose of simplifying the operation process of the e-government big data processing optimization system, there are many directions of e-government processing. Among them, traffic is the core vein of the city. Whether the city’s traffic is smooth is directly related to the operation of the city and people’s travel life. Therefore, how to effectively deal with traffic pressure through the e-government big data processing system has become a major problem that needs to be solved in the current e-government processing direction.

[0005] In view of this, the present invention proposes an e-government big data processing system and method to solve the above problems. Summary of the Invention

[0006] In order to overcome the above-mentioned defects of the prior art and achieve the above-mentioned objectives, the present invention provides the following technical solutions, including: Traffic data collection module, used to collect traffic data sets, including traffic flow data, average vehicle speed data, road occupancy data and event data; Deep data collection module, used to collect deep data sets, including policy impact data, remote sensing congestion data and complaint assessment data; The data interaction extraction module is used to preprocess the traffic data set and the depth data set, and extract feature data to obtain feature vectors; Furthermore, the steps of preprocessing the traffic dataset and the depth dataset and extracting feature data include: Q1: Complete data cleaning of all sub-data items in the basic data set by removing outliers, and normalize all sub-data items in the basic data set to the range of [0, 1] according to the normalization formula; Q2: Congestion risk is calculated based on average vehicle speed data and road occupancy data. The specific calculation formula is: ; Obtain congestion risk characteristic data ,in, is the average vehicle speed data, is the maximum possible speed, is the road occupancy data; Q3: Calculate the potential impact using traffic flow data and incident data. The specific formula is: ; Obtain potential impact characteristic data ,in, For traffic flow data, event occurrence data; Q4: Social factor characteristics are extracted by combining policy impact data and complaint assessment data. The specific calculation formula for extraction is: ; Obtaining social factor characteristic data ,in, For policy impact data, Evaluating data for complaint purposes; Q5: By calculating remote sensing congestion data Subtract the absolute value of the event occurrence data to obtain the verification feature data ; Q6: Traffic pressure is calculated based on congestion risk characteristic data, social factor characteristic data, and remote sensing congestion data. The specific calculation formula is: ; Obtain traffic pressure characteristic data ; Q7: Package congestion risk feature data, potential impact feature data, social factor feature data, verification feature data, and traffic pressure feature data to obtain a feature vector; Traffic quantification prediction module, used to analyze the feature vector and obtain the congestion prediction value; Furthermore, the step of analyzing the feature vector includes: Step 1: Obtain a set of historical feature vectors stored in the database, compare them with the current time based on the timestamp, and group the comparison results into corresponding groups from small to large. The labeled results are L1, L2, L3, ..., Ln, and the labeled results are used as the sample set; Step 2: Divide the sample set into a 70% training set, a 15% test set, and a 15% validation set, and establish the first traffic congestion prediction model based on the sample set; Step 3: Input the historical feature vector and the feature vector into the traffic congestion prediction model for calculation. The specific calculation formula is: ; Get the first congestion prediction value ,in, is the number of integrated models, is the Sigmoid activation function, is the number of decision trees in a single ensemble model, For the The dynamic weight factor of a decision tree, For the In the group integration model A gradient boosted decision tree, is the eigenvector, is the attention mechanism weight factor, is the multi-head self-attention function, For the historical feature vectors of the group ensemble model; Step 4: Calculate the error value based on the first congestion prediction value in step 3. The specific calculation formula is: ; Get the error value ,in, is the sample size, is the real congestion value; Step 5: Based on the error value in step 4, a judgment is made according to an error threshold. When the error value is less than or equal to the error threshold, a traffic congestion prediction model is output. When the error value is greater than the error threshold, the process returns to step 3 to retrain the first traffic congestion prediction model. Step 6: Input the feature vector into the traffic congestion prediction model and output the congestion prediction value; Step 7: Output the congestion prediction value to the auxiliary decision generation module; A decision-making support module is used to analyze the congestion prediction value and generate a decision-making support report based on the analysis results; Furthermore, the congestion prediction value is analyzed, and a decision-making support report is obtained based on the analysis results, including: Based on traffic threshold interval (R1, R2); When the congestion prediction value is less than R1, a congestion report and emergency instructions are generated; when the congestion prediction value is greater than or equal to R1 and less than R2, a medium report and optimization instructions are generated; when the congestion prediction value is greater than or equal to R2, a normal report is generated; Normal reports include a description of the predicted good traffic conditions and ask staff to monitor according to the preset workflow; A moderate report includes optimization instructions and states that traffic conditions are predicted to be moderate, and staff are asked to monitor for escalating congestion. The congestion report includes emergency instructions and states that traffic congestion is predicted, and asks staff to immediately arrange for management personnel to go to the scene to direct traffic; The optimization instruction contains a set of characters representing the optimization that triggers the semaphore; The emergency instructions consist of a set of characters representing the best route to the congestion site; Pack normal reports, medium reports and congestion reports to obtain decision-making support reports; The causal reasoning interpretation module is used to perform causal inference on the auxiliary decision report and obtain a causal reasoning report based on the inference results and the auxiliary decision report; Furthermore, the method of making causal inference on the decision support report and combining the decision support report with the inference results includes: When the decision support report is a medium report or a congestion report, the causal reasoning mechanism is triggered; The causal inference mechanism is based on a causal inference rule library, which inputs feature vectors, traffic datasets, and depth datasets for comparison and outputs inference results. Integrate the inference results into the corresponding auxiliary decision report to obtain a causal reasoning report; A module that prioritizes disadvantaged groups is used to perform calculations based on regional type data and complaint assessment data, and to modify congestion prediction values based on the calculation results to obtain modified prediction values. Furthermore, the method of performing calculations based on the area type data and the complaint evaluation data and correcting the congestion prediction value according to the calculation results includes: Substitute the area type data and complaint assessment data into the calculation formula: ; Get the forecast correction value ,in, is the congestion prediction value, is the correction factor, Complaint assessment data for remote areas, Complaint evaluation data for the central region; when When it is less than 0.8, the prediction correction value is returned to the auxiliary decision generation module to replace the congestion prediction value; The data differentiation processing module is used to store key data sets in the database, display causal reasoning reports through a visualization panel, identify causal reasoning reports, and perform processing based on the identification results; Furthermore, the causal reasoning report is identified and processed according to the identification result, including: When the causal reasoning report is a medium report, an optimization instruction is sent to the intelligent controller; When the causal reasoning report is a congestion report, the emergency instruction is sent to the intelligent route generation tool to obtain the emergency route, and the emergency route is output to the staff receiving end; Key datasets include traffic datasets, depth datasets, feature vectors, decision support reports, causal reasoning reports, and prediction corrections; Furthermore, S1: collecting a traffic data set, the traffic data set includes traffic flow data, average vehicle speed data, road occupancy data and event occurrence data; S2: Collect deep data sets, including policy impact data, remote sensing congestion data, and complaint assessment data; S3: Preprocess the traffic dataset and depth dataset, and extract feature data to obtain feature vectors; S4: Analyze the feature vector to obtain the congestion prediction value; S5: Analyze the congestion prediction value and obtain a decision-making support report based on the analysis results; S6: Perform causal inference on the decision support report, and obtain a causal inference report based on the inference results and the decision support report; S7: performing calculations based on the area type data and the complaint evaluation data, and correcting the congestion prediction value according to the calculation results to obtain a corrected prediction value; S8: Store the key data set in a database, display the causal reasoning report through a visualization panel, identify the causal reasoning report, and perform processing based on the identification results.

[0007] The technical effects and advantages of the e-government big data processing system and method of the present invention are as follows: The present invention collects traffic data sets, which include traffic flow data, average vehicle speed data, road occupancy data, and event occurrence data; collects depth data sets, which include policy impact data, remote sensing congestion data, and complaint assessment data; preprocesses the traffic data sets and the depth data sets, extracts feature data, obtains feature vectors, analyzes the feature vectors, obtains congestion prediction values, analyzes the congestion prediction values, and obtains an auxiliary decision report based on the analysis results; performs causal inference on the auxiliary decision report, and obtains a causal reasoning report based on the inference results and the auxiliary decision report; performs calculations based on regional type data and complaint assessment data, and corrects the congestion prediction value based on the calculation results to obtain a prediction correction value; stores key data sets in a database, displays the causal reasoning report through a visualization panel, and identifies the causal reasoning report; And processing is performed based on the recognition results, so that the system can quantify and predict traffic pressure based on multi-source data, providing valuable core data support for staff to solve traffic congestion. In addition, the present invention also provides corresponding decision-making suggestion support through further in-depth mining of congestion prediction values, thereby greatly reducing the workload of staff and effectively reducing the time cost required for decision-making. At the same time, through causal reasoning explanation of congestion conditions, it can intuitively provide staff with the main reasons for user conditions, assisting staff to solve congestion conditions as soon as possible, and, by tilting data on marginal areas, effectively reducing policy discrimination caused by traditional "data bias", thereby effectively balancing the management differences between central and non-central areas. Overall, the present invention has the significant advantages of high traffic condition prediction accuracy, strong data mining capabilities and large management balance effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 This is a schematic diagram of an e-government big data processing system of the present invention; Figure 2 This is a schematic diagram of an e-government big data processing method of the present invention. DETAILED DESCRIPTION

[0009] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0010] The terms used in the embodiments of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The singular forms "a," "an," "the," and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms, and unless the context clearly indicates otherwise, "a plurality" generally includes at least two.

[0011] As used herein, the words "if" and "if" may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to the determination" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)," depending on the context.

[0012] In addition, the step sequence in the following method embodiments is only an example and not a strict limitation.

[0013] In fact, the server-side device deployed by the e-government big data processing system may be composed of one or more devices. The above-mentioned e-government big data processing system can be implemented as: a business instance, a virtual machine, and a hardware device. For example, the e-government big data processing system can be implemented as a business instance deployed on one or more devices in a cloud node. Simply put, the e-government big data processing system can be understood as a software deployed on a cloud node, which is used to provide an e-government big data processing system for each user terminal. Alternatively, the e-government big data processing system can also be implemented as a virtual machine deployed on one or more devices in a cloud node. The virtual machine is installed with application software for managing each user terminal. Alternatively, the e-government big data processing system can also be implemented as a server-side composed of many hardware devices of the same or different types, and one or more hardware devices are set up to provide an e-government big data processing system for each user terminal.

[0014] In terms of implementation, the e-government big data processing system and the user end are mutually compatible. Specifically, if the e-government big data processing system is an application installed on a cloud service platform, the user end is the client that establishes a communication connection with the application. Alternatively, if the e-government big data processing system is implemented as a website, the user end is implemented as a webpage. Alternatively, if the e-government big data processing system is implemented as a cloud service platform, the user end is implemented as a mini-program within an instant messaging application.

[0015] like Figure 1 1 is a system architecture diagram of an e-government big data processing system provided by one embodiment of the present invention.

[0016] The e-government big data processing system of the present invention can be set in a cloud server. In terms of implementation, it can be used as one or more service devices, or it can be installed as an application on the cloud (such as a mobile service operator's server, server cluster, etc.), or it can be developed as a website. According to the functions implemented, the e-government big data processing system can include a traffic data acquisition module, a depth data acquisition module, a data interaction extraction module, a traffic quantitative prediction module, an auxiliary decision generation module, a causal reasoning interpretation module, a disadvantaged group inclination module and a data differentiation processing module. The module of the present invention can also be referred to as a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0017] In the embodiment of the present invention, in the e-government big data processing system, each of the above modules can be implemented independently and called with other modules. The call here can be understood as a module that can connect to multiple modules of another type and provide corresponding services to the multiple modules connected to it. For example, the sharing evaluation module can call the same information collection module to obtain the information collected by the information collection module. Based on the above characteristics, in the e-government big data processing system provided by the embodiment of the present invention, the scope of application of the e-government big data processing system architecture can be adjusted by adding modules and directly calling them without modifying the program code, thereby realizing cluster-based horizontal expansion, so as to achieve the purpose of quickly and flexibly expanding the e-government big data processing system. In actual applications, the above modules can be set in the same device or different devices, or they can be set in virtual devices, such as service instances in cloud servers. Example 1

[0018] See also Figure 1 As shown, the e-government big data processing system described in this embodiment includes: The traffic data collection module is used to collect traffic data sets, which include traffic flow data, average vehicle speed data, road occupancy data and event occurrence data; It should be explained that the number of vehicles passing through a specified area per unit time is collected through ground-sensing coil sensors to obtain traffic flow data; the average vehicle speed in a specified area is collected through a microwave radar speed meter to obtain average vehicle speed data; the road space occupancy rate in a specified area is collected through a video detection camera to obtain road occupancy data; and the abnormal events in a specified area are collected through an AI event detection camera to obtain event occurrence data. Abnormal events refer to situations such as vehicle accidents or construction fences. However, when an abnormal event is detected, the output value of the event transmission data is 1. The depth data acquisition module is used to collect depth data sets, which include policy impact data, remote sensing congestion data and complaint assessment data; It should be explained that the sentiment value of policy texts is collected through the government database API interface to obtain policy impact data. The sentiment value of policy texts refers to the analysis of keywords through the BERT model. For example, behavior restrictions are negative and travel subsidies are positive, with negative values of 0 and positive values of 1. The congestion density of visible light images in a specified area is collected through drone remote sensing equipment, and the congestion ratio is calculated by segmenting vehicle pixels to obtain remote sensing congestion data. The congestion ratio is assigned a value. When the congestion ratio reflects smooth traffic, the remote sensing congestion data takes a value of 0, and when the congestion ratio reflects congestion, the remote sensing congestion data takes a value of 1. The emotional tendencies of citizens' voices in hotline recordings are collected through the intelligent voice analysis platform, and scores are output based on the ASR text-to-text tool and the LSTM sentiment analysis model to obtain complaint evaluation data. The score scale is -1 to 1, with -1 being negative and 1 being positive. The data interaction extraction module is used to preprocess the traffic data set and the depth data set, and extract feature data to obtain feature vectors; Furthermore, the steps of preprocessing the traffic dataset and the depth dataset and extracting feature data include: Q1: Complete data cleaning of all sub-data items in the basic data set by removing outliers, and normalize all sub-data items in the basic data set to the range of [0, 1] according to the normalization formula; It should be explained that removing outliers means, for example, that the road occupancy data is negative; the basic data set includes the traffic data set and the depth data set; the specific expression formula of the normalization formula is: ,in is the normalized value, Any sub-data item of the basic data, is the historical maximum value of any sub-data item, is the historical minimum value of any sub-data item; normalization is used to eliminate the dimensions of all sub-data items in the basic data set; Q2: Congestion risk is calculated based on average vehicle speed data and road occupancy data. The specific calculation formula is: ; Obtain congestion risk characteristic data ,in, is the average vehicle speed data, is the maximum possible speed, is the road occupancy data; Q3: Calculate the potential impact using traffic flow data and incident data. The specific formula is: ; Obtain potential impact characteristic data ,in, For traffic flow data, event occurrence data; Q4: Social factor characteristics are extracted by combining policy impact data and complaint assessment data. The specific calculation formula for extraction is: ; Obtaining social factor characteristic data ,in, For policy impact data, Evaluating data for complaint purposes; Q5: By calculating remote sensing congestion data Subtract the absolute value of the event occurrence data to obtain the verification feature data ; Q6: Traffic pressure is calculated based on congestion risk characteristic data, social factor characteristic data, and remote sensing congestion data. The specific calculation formula is: ; Obtain traffic pressure characteristic data ; Q7: Package congestion risk feature data, potential impact feature data, social factor feature data, verification feature data, and traffic pressure feature data to obtain a feature vector; It should be explained that the sub-data items used in the basic data involved in steps Q2 to Q6 and all subsequent modules are all data values after data cleaning and data normalization; The traffic quantification prediction module is used to analyze the characteristic vector to obtain the congestion prediction value; Furthermore, the steps of analyzing the feature vector include: Step 1: Obtain a set of historical feature vectors stored in the database, compare them with the current time based on the timestamp, and group the comparison results into corresponding groups from small to large. The labeled results are L1, L2, L3, ..., Ln, and the labeled results are used as the sample set; Step 2: Divide the sample set into a 70% training set, a 15% test set, and a 15% validation set, and establish the first traffic congestion prediction model based on the sample set; Step 3: Input the historical feature vector and the feature vector into the traffic congestion prediction model for calculation. The specific calculation formula is: ; Get the first congestion prediction value ,in, is the number of integrated models, is the Sigmoid activation function, is the number of decision trees in a single ensemble model, For the The dynamic weight factor of a decision tree, For the In the group integration model A gradient boosted decision tree, is the eigenvector, is the attention mechanism weight factor, is the multi-head self-attention function, For the historical feature vectors of the group ensemble model; It needs to be explained that the Sigmoid activation function is used to constrain the output values immediately within the brackets to be within the range of (0,1); Step 4: Calculate the error value based on the first congestion prediction value in step 3. The specific calculation formula is: ; Get the error value ,in, is the sample size, is the real congestion value; Step 5: Based on the error value in step 4, a judgment is made according to an error threshold. When the error value is less than or equal to the error threshold, a traffic congestion prediction model is output. When the error value is greater than the error threshold, the process returns to step 3 to retrain the first traffic congestion prediction model. It should be explained that the error threshold is determined manually and input into the system; Step 6: Input the feature vector into the traffic congestion prediction model and output the congestion prediction value; Step 7: Output the congestion prediction value to the auxiliary decision generation module; The auxiliary decision generating module is used to analyze the congestion prediction value and generate an auxiliary decision report based on the analysis result; Furthermore, the congestion prediction value is analyzed and a decision-making support report is obtained based on the analysis results, including: Based on traffic threshold interval (R1, R2); It should be explained that the traffic threshold interval is determined manually and input into the system; When the congestion prediction value is less than R1, a congestion report and emergency instructions are generated; when the congestion prediction value is greater than or equal to R1 and less than R2, a medium report and optimization instructions are generated; when the congestion prediction value is greater than or equal to R2, a normal report is generated; Normal reports include a description of the predicted good traffic conditions and ask staff to monitor according to the preset workflow; A moderate report includes optimization instructions and states that traffic conditions are predicted to be moderate, and staff are asked to monitor for escalating congestion. The congestion report includes emergency instructions and states that traffic congestion is predicted, and asks staff to immediately arrange for management personnel to go to the scene to direct traffic; The optimization instruction contains a set of characters representing the optimization that triggers the semaphore; The emergency instructions consist of a set of characters representing the best route to the congestion site; Pack normal reports, medium reports and congestion reports to obtain decision-making support reports; The causal reasoning interpretation module is used to perform causal inference on the auxiliary decision report and obtain a causal reasoning report based on the inference results and the auxiliary decision report; Furthermore, the causal inference of the decision-making support report and the combination of the inference results with the decision-making support report include: When the decision support report is a medium report or a congestion report, the causal reasoning mechanism is triggered; The causal inference mechanism is based on a causal inference rule library, which inputs feature vectors, traffic datasets, and depth datasets for comparison and outputs inference results. It should be explained that the causal inference rule base is a preset data comparison table. For example, when the congestion risk characteristic data is greater than 0.6 and the event occurrence data is 1, the inference result output is that the traffic accident event caused the congestion; Integrate the inference results into the corresponding auxiliary decision report to obtain a causal reasoning report; The disadvantaged group bias module is used to perform calculations based on the area type data and the complaint assessment data, and to correct the congestion prediction value according to the calculation results to obtain a corrected prediction value; Furthermore, methods for performing calculations based on the area type data and complaint assessment data and correcting the congestion prediction value based on the calculation results include: Substitute the area type data and complaint assessment data into the calculation formula: ; Get the forecast correction value ,in, is the congestion prediction value, is the correction factor, Complaint assessment data for remote areas, Complaint evaluation data for the central region; It should be explained that the regional type data is used to divide the data collection area into urban central areas and urban remote areas; when When it is less than 0.8, the prediction correction value is returned to the auxiliary decision generation module to replace the congestion prediction value; The data differentiation processing module is used to store the key data sets in the database, display the causal reasoning report through the visualization panel, identify the causal reasoning report, and process it according to the identification results; Furthermore, the causal reasoning report is identified and processed according to the identification result, including: When the causal reasoning report is a medium report, an optimization instruction is sent to the intelligent controller; When the causal reasoning report is a congestion report, the emergency instruction is sent to the intelligent route generation tool to obtain the emergency route, and the emergency route is output to the staff receiving end; Key datasets include traffic datasets, depth datasets, feature vectors, decision support reports, causal reasoning reports, and prediction corrections; This embodiment has the beneficial effects of collecting traffic data sets, which include traffic flow data, average vehicle speed data, road occupancy data and event occurrence data; collecting depth data sets, which include policy impact data, remote sensing congestion data and complaint evaluation data; preprocessing the traffic data sets and the depth data sets, and extracting feature data to obtain feature vectors; analyzing the feature vectors to obtain congestion prediction values; analyzing the congestion prediction values, and obtaining an auxiliary decision report based on the analysis results; performing causal inference on the auxiliary decision report, and obtaining a causal reasoning report based on the inference results and the auxiliary decision report; performing calculations based on regional type data and complaint evaluation data, and correcting the congestion prediction value based on the calculation results to obtain a prediction correction value; storing the key data sets in a database; displaying the causal reasoning report through a visualization panel; and performing causal reasoning on the causal reasoning report. Identification and processing based on the identification results enable the system to quantify and predict traffic pressure based on multi-source data, providing valuable core data support for staff to solve traffic congestion. In addition, the present invention also provides corresponding decision-making suggestion support through further in-depth mining of congestion prediction values, thereby greatly reducing the workload of staff and effectively reducing the time cost required for decision-making. At the same time, through the causal reasoning explanation of congestion conditions, it can intuitively provide staff with the main reasons for the occurrence of user conditions, assisting staff to solve congestion conditions as soon as possible, and, by tilting data on marginal areas, effectively reducing the policy discrimination caused by traditional "data bias", thereby effectively balancing the management differences between central and non-central areas. Overall, the present invention has the significant advantages of high traffic condition prediction accuracy, strong data mining capabilities and large management balance effect. Example 2

[0019] See also Figure 2 As shown, for parts not described in detail in this embodiment, please refer to the description of embodiment 1. A method for processing e-government big data is provided, the method comprising: S1: collecting a traffic data set, the traffic data set comprising traffic flow data, average vehicle speed data, road occupancy data, and event occurrence data; S2: Collect deep data sets, including policy impact data, remote sensing congestion data, and complaint assessment data; S3: Preprocess the traffic dataset and depth dataset, and extract feature data to obtain feature vectors; S4: Analyze the feature vector to obtain the congestion prediction value; S5: Analyze the congestion prediction value and obtain a decision-making support report based on the analysis results; S6: Perform causal inference on the decision support report, and obtain a causal inference report based on the inference results and the decision support report; S7: performing calculations based on the area type data and the complaint evaluation data, and correcting the congestion prediction value according to the calculation results to obtain a corrected prediction value; S8: Store the key data set in a database, display the causal reasoning report through a visualization panel, identify the causal reasoning report, and perform processing based on the identification results. Example 3

[0020] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0021] Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the claims are intended to be embraced therein. Any reference to a figure in a claim should not be construed as limiting the claim to which it relates.

[0022] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, techniques, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results.

[0023] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices recited in a system claim may also be implemented by a single unit or device through software or hardware. Terms such as "first" and "second" are used to indicate names and do not imply any particular order.

[0024] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. An e-government big data processing system, characterized in that: The system includes: a traffic quantitative prediction module, an auxiliary decision generation module, a causal reasoning explanation module and a disadvantaged group inclination module, wherein: The traffic quantification prediction module is used to analyze the characteristic vector to obtain the congestion prediction value; The auxiliary decision generating module is used to analyze the congestion prediction value and generate an auxiliary decision report based on the analysis result; The causal reasoning interpretation module is used to perform causal inference on the auxiliary decision report and obtain a causal reasoning report based on the inference results and the auxiliary decision report; The disadvantaged group inclination module is used to perform calculations based on the area type data and the complaint evaluation data, and to correct the congestion prediction value according to the calculation results to obtain a prediction correction value.

2. The e-government big data processing system according to claim 1, characterized in that: The system further comprises: a traffic data acquisition module, a depth data acquisition module, a data interaction extraction module and a data differentiation processing module, wherein: The traffic data collection module is used to collect traffic data sets, which include traffic flow data, average vehicle speed data, road occupancy data and event occurrence data; The depth data acquisition module is used to collect depth data sets, which include policy impact data, remote sensing congestion data and complaint assessment data; The data interaction extraction module is used to preprocess the traffic data set and the depth data set, and extract feature data to obtain feature vectors; The data differentiation processing module is used to store the key data sets in the database, display the causal reasoning report through the visualization panel, identify the causal reasoning report, and process it according to the identification result.

3. The e-government big data processing system according to claim 2, characterized in that: The steps of preprocessing the traffic dataset and depth dataset and extracting feature data include: Q1: Complete data cleaning of all sub-data items in the basic data set by removing outliers, and normalize all sub-data items in the basic data set to the range of [0, 1] according to the normalization formula; Q2: Congestion risk is calculated based on average vehicle speed data and road occupancy data. The specific calculation formula is: ; Get congestion risk characteristic data ,in, is the average vehicle speed data, is the maximum possible speed, is the road occupancy data; Q3: Calculate the potential impact using traffic flow data and incident data. The specific formula is: ; Get potential impact characteristic data ,in, For traffic flow data, event occurrence data; Q4: Social factor characteristics are extracted by combining policy impact data and complaint assessment data. The specific calculation formula for extraction is: ; Obtain social factor characteristic data ,in, For policy impact data, Evaluating data for complaint purposes; Q5: By calculating remote sensing congestion data Subtract the absolute value of the event occurrence data to obtain the verification feature data ; Q6: Traffic pressure is calculated based on congestion risk characteristic data, social factor characteristic data, and remote sensing congestion data. The specific calculation formula is: ; Get traffic pressure characteristic data ; Q7: Package the congestion risk feature data, potential impact feature data, social factor feature data, verification feature data, and traffic pressure feature data to obtain a feature vector.

4. The e-government big data processing system according to claim 1, characterized in that: The steps to analyze the feature vector include: Step 1: Obtain a set of historical feature vectors stored in the database, compare them with the current time based on the timestamp, and group the comparison results into corresponding groups from small to large. The labeled results are L1, L2, L3, ..., Ln, and the labeled results are used as the sample set; Step 2: Divide the sample set into a 70% training set, a 15% test set, and a 15% validation set, and establish the first traffic congestion prediction model based on the sample set; Step 3: Input the historical feature vector and the feature vector into the traffic congestion prediction model for calculation. The specific calculation formula is: ; Get the first congestion prediction value ,in, is the number of integrated models, is the Sigmoid activation function, is the number of decision trees in a single ensemble model, For the The dynamic weight factor of a decision tree, For the In the group integration model A gradient boosted decision tree, is the eigenvector, is the attention mechanism weight factor, is the multi-head self-attention function, For the historical feature vectors of the group ensemble model; Step 4: Calculate the error value based on the first congestion prediction value in step 3. The specific calculation formula is: ; Get the error value ,in, is the sample size, is the real congestion value; Step 5: Based on the error value in step 4, a judgment is made according to an error threshold. When the error value is less than or equal to the error threshold, a traffic congestion prediction model is output. When the error value is greater than the error threshold, the process returns to step 3 to retrain the first traffic congestion prediction model. Step 6: Input the feature vector into the traffic congestion prediction model and output the congestion prediction value; Step 7: Output the congestion prediction value to the auxiliary decision generation module.

5. The e-government big data processing system according to claim 1, characterized in that: Methods for analyzing the congestion prediction value and obtaining a decision-making support report based on the analysis results include: Based on traffic threshold interval (R1, R2); When the congestion prediction value is less than R1, a congestion report and emergency instructions are generated; when the congestion prediction value is greater than or equal to R1 and less than R2, a medium report and optimization instructions are generated; when the congestion prediction value is greater than or equal to R2, a normal report is generated; Normal reports include a description of the predicted good traffic conditions and ask staff to monitor according to the preset workflow; A moderate report includes optimization instructions and states that traffic conditions are predicted to be moderate, and staff are asked to monitor for escalating congestion. The congestion report includes emergency instructions and states that traffic congestion is predicted, and asks staff to immediately arrange for management personnel to go to the scene to direct traffic; The optimization instruction contains a set of characters representing the optimization that triggers the semaphore; The emergency instructions consist of a set of characters representing the best route to the congestion site; Normal reports, medium reports and congestion reports are packaged to obtain a decision-making support report.

6. The e-government big data processing system according to claim 1, characterized in that: Methods for making causal inferences on the decision-making support report and combining the decision-making support report with the inference results include: When the decision support report is a medium report or a congestion report, the causal reasoning mechanism is triggered; The causal inference mechanism is based on a causal inference rule library, which inputs feature vectors, traffic datasets, and depth datasets for comparison and outputs inference results. Integrate the inference results into the corresponding auxiliary decision report to obtain a causal reasoning report.

7. The e-government big data processing system according to claim 1, characterized in that: Methods for calculating based on area type data and complaint assessment data and revising congestion prediction values based on the calculation results include: Substitute the area type data and complaint assessment data into the calculation formula: ; Get the forecast correction value ,in, is the congestion prediction value, is the correction factor, Complaint assessment data for remote areas, Complaint evaluation data for the central region; when When it is less than 0.8, the prediction correction value is returned to the auxiliary decision generation module to replace the congestion prediction value.

8. The e-government big data processing system according to claim 2, characterized in that: Methods for identifying causal reasoning reports and processing them based on the identification results include: When the causal reasoning report is a medium report, an optimization instruction is sent to the intelligent controller; When the causal reasoning report is a congestion report, the emergency instruction is sent to the intelligent route generation tool to obtain the emergency route, and the emergency route is output to the staff receiving end; Key datasets include traffic datasets, depth datasets, feature vectors, decision support reports, causal reasoning reports, and prediction correction values.

9. A method for processing e-government big data, implemented according to an e-government big data processing system according to any one of claims 1 to 9, characterized in that: The following steps are included: S1: Collect traffic data sets, which include traffic flow data, average vehicle speed data, road occupancy data, and event data; S2: Collect deep data sets, including policy impact data, remote sensing congestion data, and complaint assessment data; S3: Preprocess the traffic dataset and depth dataset, and extract feature data to obtain feature vectors; S4: Analyze the feature vector to obtain the congestion prediction value; S5: Analyze the congestion prediction value and obtain a decision-making support report based on the analysis results; S6: Perform causal inference on the decision support report, and obtain a causal inference report based on the inference results and the decision support report; S7: performing calculations based on the area type data and the complaint evaluation data, and correcting the congestion prediction value according to the calculation results to obtain a corrected prediction value; S8: Store the key data set in a database, display the causal reasoning report through a visualization panel, identify the causal reasoning report, and perform processing based on the identification results.

Images