Urban operation management system for resource allocation based on big data

Abstract

The invention relates to the technical field of city management, and discloses a city operation management system for resource allocation based on big data. Comprising data acquisition, data storage and preprocessing, data security protection, continuous model optimization, data analysis and prediction, multi-department collaborative linkage, resource allocation decision making, execution and feedback, and visual display and interaction, and the data security protection comprises transmission encryption, authority management and data backup and recovery. According to the urban operation management system for resource allocation based on big data, through encryption transmission, multi-level authority management and regular remote backup, by means of professional evaluation groups, an online learning technology and a model fusion strategy, an informatization platform is built, a collaborative process and a plan are formulated, department barriers are broken, a visual platform is built, and an interaction function is added; therefore, the effects of comprehensively guaranteeing the data security, optimizing the model in real time according to the new data, quickly responding to complex conditions and collaboratively working can be achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of urban management, and in particular to an urban operation and management system for resource allocation based on big data. Background Art

[0002] With the acceleration of urbanization and the continuous expansion of urban scale, urban operation and management are facing many challenges. The urban operation and management system based on big data for resource allocation is a comprehensive platform that integrates advanced technologies and aims to improve urban management efficiency and resource utilization accuracy.

[0003] In traditional urban operations and management, data transmission is mostly unencrypted and easily stolen or tampered with. Data storage lacks strict authority management. Predictive models are mostly built based on a small amount of historical data and simple algorithms, making it difficult to handle complex and changeable urban data. The information systems of various urban management departments (such as transportation, health, education, municipal administration, etc.) are independent of each other, data formats are not unified, and there is a lack of effective sharing mechanisms. Summary of the Invention

[0004] (1) Technical problems solved

[0005] In response to the shortcomings of the existing technology, the present invention provides an urban operation and management system based on big data for resource allocation, which has the advantages of being able to fully ensure data security, optimize models based on new data in real time, respond quickly to complex situations, and work collaboratively, thereby solving the problems mentioned in the above background technology.

[0006] (2) Technical solution

[0007] To achieve the above-mentioned objectives, the present invention provides the following technical solutions: an urban operation and management system for resource allocation based on big data, including data collection, data storage and preprocessing, data security protection, continuous model optimization, data analysis and prediction, multi-department collaboration, resource allocation decision-making, execution and feedback, visual display and interaction. The data security protection includes transmission encryption, authority management and data backup and recovery. The continuous model optimization includes model evaluation, online learning and model fusion. The multi-department collaboration includes platform construction and process and plan formulation. The visual display and interaction includes platform construction and interactive function development.

[0008] Preferably, the data collection includes traffic data collection, pedestrian flow data collection, population distribution data collection and meteorological data collection, and a variety of technical means are comprehensively used to widely collect real-time and basic data in multiple fields such as urban traffic, population, and meteorology, so as to provide sufficient and diverse information materials for in-depth analysis and decision-making in subsequent links.

[0009] Preferably, the data storage and preprocessing include data storage, data cleaning, data conversion and data labeling, orderly storing the massive amount of raw data collected, using a variety of technical means to improve data quality, standardizing data formats and adding clear identification, laying a solid foundation for subsequent data analysis and processing, and facilitating efficient query and in-depth analysis.

[0010] Preferably, the data analysis and prediction include traffic flow analysis and prediction and public resource demand analysis and prediction. Professional data analysis algorithms and tools are used to deeply mine and analyze key data such as urban traffic flow and public resource demand, accurately predict traffic congestion conditions and changes in public resource demand, provide scientific and reliable reference basis for subsequent resource allocation decisions, and assist in the rational allocation of urban resources.

[0011] Preferably, the resource allocation decision-making includes rule setting and plan generation. Based on pre-set rules and in-depth data analysis results, scientific optimization algorithms are used to accurately formulate allocation plans for various resources such as transportation and public services, so as to achieve reasonable and efficient allocation of resources, improve resource utilization efficiency, meet the living needs of urban residents, and improve residents' life satisfaction.

[0012] Preferably, the execution and feedback include plan execution, feedback data collection, and data integration and circulation, to achieve a closed-loop management model for resource allocation from plan formulation to actual execution, and then to optimization based on feedback data. Through real-time feedback data, the implementation effect of the resource allocation plan can be timely understood, and subsequent resource allocation decisions can be continuously adjusted and optimized, thereby continuously improving the accuracy of resource allocation and the overall level of urban operation management.

[0013] Compared with the existing technology, the present invention provides an urban operation management system for resource allocation based on big data, which has the following beneficial effects:

[0014] This urban operation and management system, which allocates resources based on big data, uses encrypted transmission, multi-level authority management and regular off-site backup, with the help of professional assessment teams, online learning technology and model fusion strategies to build an information platform, formulate collaborative processes and plans, break down departmental barriers, construct a visualization platform and add interactive functions, so as to achieve the purpose of comprehensively ensuring data security, optimizing models according to new data in real time, responding quickly to complex situations and working collaboratively. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a schematic diagram of the overall framework structure of the present invention. DETAILED DESCRIPTION

[0016] 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.

[0017] See also Figure 1 , an urban operation and management system for resource allocation based on big data, including data collection, data storage and preprocessing, data security protection, continuous model optimization, data analysis and prediction, multi-department collaboration, resource allocation decision-making, execution and feedback, visual display and interaction, data security protection includes transmission encryption, authority management and data backup and recovery, continuous model optimization includes model evaluation, online learning and model fusion, multi-department collaboration includes platform construction and process and plan formulation, visual display and interaction includes platform construction and interactive function development, using encrypted transmission protocol, encrypting data during transmission from the collection end to the storage end to prevent it from being stolen or tampered with during transmission, and establishing multiple A hierarchical data access permission system assigns different access levels according to different user roles (system administrators, data analysts, business executives, etc.). For example, medical resource data is only authorized to health management departments and specific medical data analysts. Data is backed up regularly off-site to deal with data loss risks such as hardware failures and natural disasters. At the same time, a data recovery plan is formulated to ensure that key data can be quickly restored in the event of data loss or damage, ensuring data security throughout its lifecycle, preventing sensitive information leakage, maintaining the stable operation of the city operation management system, protecting citizens' private data, avoiding trust crises caused by data leaks, preventing malicious tampering with data from affecting decision-making accuracy, and ensuring the reliability of data-based decisions such as resource allocation;

[0018] A dedicated model evaluation team is set up for the continuous optimization of the model. The team regularly evaluates the performance of the data analysis and prediction model every week. By comparing the model prediction results with the actual data, the accuracy, recall rate and other indicators are calculated to determine whether optimization is needed. Online learning technology is used to adjust the parameters of the model in real time based on new data. For example, when the traffic flow prediction model finds that the actual flow rate deviates greatly from the prediction, the new flow data is automatically incorporated for retraining. Model fusion technology is introduced to fuse multiple different types of prediction models (such as deep learning neural network models and traditional time series analysis models). The prediction results of multiple models are combined (average or weighted average) to obtain more accurate results. The accuracy of model predictions is continuously improved, so that resource allocation decisions are based on more reliable analysis. Accurate traffic flow predictions can enable traffic police to deploy police forces in a timely and reasonable manner to alleviate congestion. Accurate public resource demand predictions make resource allocation more reasonable, avoid resource waste or shortages, and improve the overall operational efficiency of the city.

[0019] The multi-departmental collaborative work step builds a cross-departmental collaborative work platform, breaking down data barriers between departments and enabling data sharing and real-time communication between urban management departments such as transportation, health, education, and municipal administration. For example, if the transportation department predicts that a certain area will be congested due to a large-scale event, it can use the platform to notify surrounding schools to adjust their dismissal times and develop cross-departmental collaborative work processes and emergency plans.

[0020] The visualization display and interactive steps build a visualization platform for urban operation and management, using 3D modeling, VR and AR technologies to intuitively and vividly present the distribution, operation status and resource allocation process of various types of urban resources. Decision makers can use VR to immersively view the real-time status of urban traffic flow and understand congested areas and surrounding roads. The platform adds interactive functions, and users (decision makers and citizens) can click and zoom to view detailed data of specific areas. Citizens can view the use of public facilities near their homes and future resource allocation plans. Decision makers can adjust resource allocation plans in real time through interaction and see the adjustment effect simulation on the visualization interface, which makes it convenient for decision makers to intuitively understand the overall picture of the city, assist in quick and accurate decision-making, enhance citizens' understanding and participation in urban operation and management, and improve the democracy and scientific nature of decision-making. For example, decision makers can quickly identify problem areas and adjust plans in a timely manner. Citizen participation can make resource allocation more in line with the actual needs of residents.

[0021] Data collection includes traffic data collection, passenger flow data collection, population distribution data collection and meteorological data collection. It comprehensively uses a variety of technical means to widely collect real-time and basic data in multiple fields such as urban traffic, population, and meteorology, providing sufficient and diverse information materials for in-depth analysis and decision-making in subsequent links.

[0022] Through the above technical solution, traffic flow sensors are densely deployed at key nodes of urban roads (such as crossroads and intersections of main roads). These sensors use geomagnetic induction, video recognition and other technologies to accurately collect data such as traffic volume, speed and vehicle type every five minutes. At the entrances and exits of parks, libraries, shopping malls and other places with frequent personnel flow, infrared sensing or image recognition traffic monitoring equipment is installed to count the number of people entering and leaving in real time, and through analysis equipment to record information such as the length of stay of people and peak entry and exit times. Cooperation is reached with mobile operators to obtain mobile phone signaling data, and with the help of big data analysis technology, the interaction signals between mobile phone base stations and user mobile phones are analyzed, and the population distribution dynamics in different areas of the city are updated every hour. At the same time, every Community demographic data is collected regularly every month, covering the number of permanent residents, age structure, household registration information, etc., to ensure the comprehensiveness and accuracy of population distribution data. Using web crawler technology, according to the set daily scheduled tasks, real-time meteorological data is captured from the official website of the authoritative meteorological department, including key meteorological indicators such as temperature, precipitation probability, wind speed and direction, and humidity. Comprehensive data from multiple fields of the city are collected to provide rich materials for subsequent analysis. Accurate traffic flow data can help traffic management departments predict congestion in advance and reasonably plan diversion plans. Population distribution data helps to rationally allocate public resources, such as setting up schools and hospitals according to densely populated areas. Weather data can be used to predict the impact on traffic, energy consumption, etc., and make preparations in advance.

[0023] Data storage and preprocessing include data storage, data cleaning, data conversion and data labeling. The massive amount of raw data collected is stored in an orderly manner, and a variety of technical means are used to improve data quality. The data format is standardized and clear identification is added to lay a solid foundation for subsequent data analysis and processing, and facilitate efficient query and in-depth analysis.

[0024] Through the above technical solution, a distributed database architecture is adopted, a special data cleaning program is written, and an outlier detection algorithm (such as the 3σ principle based on statistics and the isolation forest algorithm) is used to screen and delete noise data that exceeds a reasonable range (such as negative vehicle speed and extremely large outliers in pedestrian flow) and completely repeated data. Data conversion tools (such as the ETL tool Kettle) are used to uniformly convert data in different formats into a format suitable for analysis. For example, text format time data collected by certain devices is converted into a timestamp format that can be recognized by the database; character data in different encoding formats are unified into UTF-8 encoding, and meaningful annotations are added to the data based on the data's field, purpose and business needs. Data is reasonably stored for fast query and analysis, improving data processing efficiency, cleaning and conversion of data to improve data quality, removing interference factors, unifying the data format to facilitate subsequent analysis algorithm processing, and labeling data to facilitate classification management and targeted analysis, providing more accurate support for decision-making in different fields.

[0025] Data analysis and forecasting include traffic flow analysis and forecasting and public resource demand analysis and forecasting. By using professional data analysis algorithms and tools, we conduct in-depth mining and analysis of key data such as urban traffic flow and public resource demand, accurately predict traffic congestion conditions and changes in public resource demand, and provide a scientific and reliable reference for subsequent resource allocation decisions, thus facilitating the rational allocation of urban resources.

[0026] Through the above technical solution, a time series analysis algorithm is applied to traffic flow data, and the hourly traffic flow data of the past week to one month is used as a training set. A model is constructed to predict the changes in traffic flow in each section in the next 1-3 hours, and the congested sections, congestion start time and estimated duration are output. For population distribution and public resource demand data, a clustering algorithm is used to divide urban areas. A comprehensive analysis of the age structure, occupational distribution, and historical public resource usage of the population in different regions is conducted to identify demand patterns and predict the demand for public resources in each region in the next week. For example, it is determined that areas with a large number of elderly people have a large demand for medical resources, and the demand for educational resources is concentrated near school districts. This provides a scientific basis for resource allocation decisions, and by knowing the traffic congestion sections and times in advance, traffic diversion resources can be allocated in advance, public resource demand can be accurately predicted, and resource allocation can be reasonably planned, such as arranging school places and hospital beds in advance, thereby improving the level of public services.

[0027] Resource allocation decision-making includes rule setting and plan generation. Based on pre-set rules and in-depth data analysis results, scientific optimization algorithms are used to accurately formulate allocation plans for various resources such as transportation and public services, achieve reasonable and efficient allocation of resources, improve resource utilization efficiency, meet the living needs of urban residents, and improve residents' life satisfaction.

[0028] Through the above technical solution, resource allocation rules are pre-established and entered into the system. For example, when traffic is congested, the traffic volume on a certain road section exceeds 80% of the maximum carrying capacity, triggering the allocation mechanism. Based on data analysis and prediction results, an optimization algorithm is used to calculate the allocation plan. When a sharp increase in traffic volume in a certain area is predicted, the surrounding police force, traffic light control potential, etc. are comprehensively considered to generate a plan for allocating the number of traffic police and adjusting the green light duration of traffic lights at surrounding intersections. In terms of public resources, taking school degree allocation as an example, when the number of children enrolled in a school district exceeds the degree supply by 10%, the decision-making module formulates a plan for allocating the number of teachers and adding temporary classrooms based on the remaining degrees in surrounding schools and the availability of teachers, to ensure that resources are allocated scientifically and reasonably, avoid subjective arbitrariness based on data and rules, reasonably allocate traffic resources to alleviate congestion, ensure smooth roads, accurately allocate public resources to meet residents' needs, improve the efficiency of public resource utilization, and improve residents' life satisfaction.

[0029] Execution and feedback include plan execution, feedback data collection, and data integration and circulation, realizing a closed-loop management model for resource allocation from plan formulation to actual execution, and then to optimization based on feedback data. Through real-time feedback data, we can timely understand the implementation effect of the resource allocation plan, continuously adjust and optimize subsequent resource allocation decisions, and continuously improve the accuracy of resource allocation and the overall level of urban operation management.

[0030] Through the above technical solution, the resource allocation decision plan is sent to the corresponding execution department or equipment through a specific interface, the traffic allocation plan is sent to the traffic police command center to arrange traffic police, and the signal light timing adjustment instruction is sent to the traffic light control equipment. During execution, feedback data is collected in real time through various sensors. The traffic flow sensor feedbacks the changes in traffic flow after the deployment of traffic police and adjustment of traffic lights every ten minutes. The hospital bed usage sensor feedbacks the occupancy and vacancy of beds every hour. After the feedback data is integrated, it enters the data storage and preprocessing link to provide a basis for the next round of decision optimization, realize closed-loop management of resource allocation, optimize decisions based on feedback, and timely understand the allocation effect. For example, changes in traffic flow reflect whether traffic diversion is effective. Hospital bed feedback helps to reasonably adjust medical resources, and continuously improve the accuracy of resource allocation and the level of urban operation management.

[0031] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. An urban operations management system for resource allocation based on big data, including data collection, data storage and preprocessing, data security protection, continuous model optimization, data analysis and prediction, multi-department collaboration, resource allocation decision-making, execution and feedback, and visual display and interaction. It is characterized by: The data security protection includes transmission encryption, permission management, and data backup and recovery; the continuous model optimization includes model evaluation, online learning, and model fusion; the multi-department collaboration includes platform construction and process and plan formulation; and the visual display and interaction includes platform construction and interactive function development.

2. The urban operation management system for resource allocation based on big data according to claim 1, characterized in that: The data collection includes traffic data collection, passenger flow data collection, population distribution data collection and meteorological data collection. It comprehensively uses a variety of technical means to widely collect real-time and basic data in multiple fields such as urban traffic, population, and meteorology, providing sufficient and diverse information materials for in-depth analysis and decision-making in subsequent links.

3. The urban operation management system for resource allocation based on big data according to claim 1 is characterized by: The data storage and preprocessing include data storage, data cleaning, data conversion and data labeling. The massive amount of raw data collected is stored in an orderly manner, and a variety of technical means are used to improve data quality, standardize data formats and add clear identification, laying a solid foundation for subsequent data analysis and processing, and facilitating efficient query and in-depth analysis.

4. The urban operation management system for resource allocation based on big data according to claim 1 is characterized by: The data analysis and prediction mentioned above include traffic flow analysis and prediction and public resource demand analysis and prediction. Professional data analysis algorithms and tools are used to deeply mine and analyze key data such as urban traffic flow and public resource demand, accurately predict traffic congestion conditions and changes in public resource demand, provide scientific and reliable reference basis for subsequent resource allocation decisions, and assist in the rational allocation of urban resources.

5. The urban operation management system for resource allocation based on big data according to claim 1 is characterized by: The resource allocation decision-making includes rule setting and plan generation. Based on pre-set rules and in-depth data analysis results, scientific optimization algorithms are used to accurately formulate allocation plans for various resources such as transportation and public services, so as to achieve reasonable and efficient allocation of resources, improve resource utilization efficiency, meet the living needs of urban residents, and improve residents' life satisfaction.

6. The urban operation management system for resource allocation based on big data according to claim 1 is characterized by: The execution and feedback include plan execution, feedback data collection, and data integration and circulation, realizing a closed-loop management model for resource allocation from plan formulation to actual execution, and then to optimization based on feedback data. Through real-time feedback data, we can timely understand the implementation effect of the resource allocation plan, continuously adjust and optimize subsequent resource allocation decisions, and continuously improve the accuracy of resource allocation and the overall level of urban operation management.

Images