Traffic infrastructure digitization method and system and storage medium
By analyzing transportation demand and service supply data, and generating regulatory strategies to achieve supply and demand matching, the problem of insufficient supply and demand matching capabilities of transportation infrastructure is solved, and service utilization and infrastructure efficiency are improved.
Patent Information
- Application Number
- CN202410990822.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-23
- Publication Date
- 2024-12-03
AI Technical Summary
The insufficient supply and demand matching capacity of transportation infrastructure makes it difficult to achieve overall supply and demand regulation, limiting the scale effect of digital transformation and the integrated development of industrial transformation.
By obtaining traffic demand data, traffic environment data and service supply data, conduct correlation, gap, competition and risk analysis, build a combination optimization function for traffic supply and demand matching, generate regulatory strategies and execute them to achieve supply and demand matching.
It has improved the supply and demand matching capability of transportation infrastructure services, and achieved efficient utilization of limited service supply, which is equivalent to the expansion of transportation infrastructure and safety and efficiency improvement.
Smart Images

Figure CN119067345A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of intelligent transportation technology, and more specifically, to a method, system and storage medium for digitalizing transportation infrastructure. Background Art
[0002] Promoting the digital transformation and upgrading of transportation infrastructure can give full play to the amplification, superposition and multiplication effects of digital technology, and effectively improve the long-term supply quality and efficiency of transportation infrastructure. It plays an important role and significance in promoting the high-quality development of transportation and supporting the creation of digital industry clusters with international competitiveness.
[0003] At present, the digital transformation of transportation infrastructure still has problems such as the failure to effectively exert scale effects, insufficient industrial integration and development, and the lack of a coordinated guarantee mechanism. The focus of existing digital transformation work is on the introduction of smart devices and advanced technologies to achieve intelligent transformation of local services, and it is difficult to regulate supply and demand from the overall perspective. Transportation infrastructure serves the public's travel, and its function is to provide services. Services can be decomposed from two dimensions: the demand side and the supply side. The core contradiction of services is the contradiction between supply and demand. Therefore, how to improve the supply and demand matching capabilities of transportation infrastructure services is a technical problem that technicians in this field need to solve urgently. Summary of the invention
[0004] The embodiments of the present application provide a method, system and storage medium for digitalizing transportation infrastructure, so as to at least solve the technical problem of insufficient supply and demand matching capability of transportation infrastructure services in related technologies.
[0005] A method for digitalizing transportation infrastructure provided in an embodiment of the present application includes:
[0006] Data acquisition step, acquiring traffic demand data based on demand-side equipment, acquiring traffic environment data based on environment-side equipment, and acquiring traffic service supply data based on supply-side service entities;
[0007] a control strategy calculation step, performing a traffic demand and traffic service supply-demand matching calculation under traffic environment constraints based on the traffic demand data, traffic environment data, and traffic service supply data, and obtaining a control strategy for traffic demand and / or traffic service supply;
[0008] The control strategy execution step obtains the control strategy of the traffic demand and / or traffic service supply, converts the control strategy into instructions, and sends them to the service entity on the supply side for execution.
[0009] In an optional embodiment, the traffic demand and traffic service supply-demand matching calculation under traffic environment constraints is performed according to the traffic demand data, traffic environment data, and traffic service supply data, including:
[0010] Perform correlation analysis, gap analysis, competition analysis and risk analysis on the traffic demand data, traffic environment data and traffic service supply data, obtain correlation analysis results, gap analysis results, competition analysis results and risk analysis results respectively, and use the correlation analysis results, gap analysis results, competition analysis results and risk analysis results as prior knowledge and calculation parameters for traffic supply and demand matching calculation;
[0011] Supply and demand matching calculations are performed based on the traffic demand data, traffic environment data, traffic service supply data, the traffic supply and demand matching prior knowledge, and calculation parameters to obtain a control strategy for the traffic demand and / or traffic service supply.
[0012] In an optional embodiment, after acquiring the traffic demand data, the traffic environment data, and the traffic service supply data, the method further includes:
[0013] The historical traffic demand data, traffic environment data and traffic service supply data are grouped according to time characteristics, and statistical operations are performed on various types of data in the same group to obtain the expectation and extreme value of the grouped data;
[0014] Determine whether the absolute difference between the extreme value of the real-time traffic demand data, traffic environment data, and traffic service supply data and the corresponding grouped data is less than a preset first threshold;
[0015] Determine whether the expected absolute difference between the real-time traffic demand data, traffic environment data, and traffic service supply data and the corresponding grouped data is greater than a preset second threshold;
[0016] If the absolute difference between the data and the extreme value is less than a preset first threshold, and / or the absolute difference between the data and the expectation is greater than a preset second threshold, a warning message is issued.
[0017] In an optional embodiment, the step of correlation analysis includes:
[0018] Extract the time series data of the traffic parameters to be analyzed within the analysis period as the target sequence;
[0019] Extract the time series data of other traffic parameters during the analysis period as the source series;
[0020] Determining the correlation between the source sequence and the target sequence;
[0021] Using time series data of one or more other traffic parameters that meet the correlation determination as a source sequence group;
[0022] Establishing a mapping function between the source sequence group and the target sequence;
[0023] The mapping function is used to indicate the corresponding relationship between traffic demand and traffic service supply, or to predict traffic demand data and traffic service supply data.
[0024] In an optional embodiment, the step of gap analysis includes:
[0025] Obtaining priority information in forecasted traffic demand data and forecasted traffic service supply data;
[0026] According to the correspondence between the traffic demand and the traffic service supply, the target traffic service supply data satisfying the traffic demand data predicted for each priority level is calculated, and the target traffic demand data that can be satisfied by the traffic service supply data predicted for each priority level is calculated;
[0027] Calculate the difference between the predicted traffic service supply data of each priority and the target traffic service supply data, record it as a first difference sequence, calculate the difference between the predicted traffic demand data of each priority and the target traffic demand data, record it as a second difference sequence;
[0028] The first difference sequence and the second difference sequence are gap analysis results.
[0029] In an optional embodiment, the step of competition analysis includes:
[0030] When there are multiple service providers that can meet a certain traffic demand, the multiple service providers are determined to be in a competitive relationship;
[0031] The competition coefficient is obtained according to the product of the share of the service provider entity for the same traffic demand and the cost-effectiveness ratio of the service provider entity;
[0032] The competition relationship and the competition coefficient are competition analysis results;
[0033] Among them, the cost-effectiveness ratio is the output-input ratio of the transportation service entity in meeting unit transportation demand.
[0034] In an optional embodiment, the risk analysis step includes:
[0035] Calculate the risk coefficient of different service supply quantities provided by the transportation service entity according to the corresponding relationship between the transportation demand and the transportation service supply;
[0036] Among them, the risk coefficient of the service entity is calculated by the difference between the traffic demand undertaken by the service entity and its corresponding upper limit of traffic demand. The smaller the difference, the greater the risk coefficient;
[0037] The risk coefficient of the transportation service entity is a risk analysis result.
[0038] In an optional embodiment, a traffic demand and traffic service supply-demand matching calculation is performed under traffic environment constraints according to the traffic demand data, traffic environment data, and traffic service supply data to obtain a traffic demand and / or traffic service supply control strategy, including:
[0039] Constructing a transportation supply and demand matching combination optimization function based on the transportation demand data, transportation environment data, and transportation service supply data;
[0040] The traffic supply and demand matching combination optimization function takes the competition analysis results as the solution space, the traffic environment data, competition analysis, and risk analysis results as constraints, and the gap analysis results as the optimization target.
[0041] The traffic supply and demand matching combined optimization function is solved, and the obtained solution is the regulation strategy of traffic demand and / or traffic service supply.
[0042] In an optional embodiment, the control strategy execution step further includes:
[0043] Receiving the control strategy of the traffic demand and / or traffic service supply and the adjustment strategy of the control strategy of the regulatory body;
[0044] The adjustment strategy is used to adjust the control strategy of the traffic demand and / or traffic service supply, decode and calculate, and obtain an instruction to instruct the traffic service entity to execute.
[0045] In an optional embodiment, after the control strategy execution step, the method further includes:
[0046] Collecting the operation status data fed back by the service entity on the supply side or the equipment on the demand side after executing the control strategy;
[0047] The control strategy is adjusted according to the fed-back operating status data.
[0048] According to another aspect of the embodiment of the present application, a transportation infrastructure digitization system is provided, including:
[0049] The facility layer is used to obtain traffic demand data based on demand-side equipment, traffic environment data based on environment-side equipment, and traffic service supply data based on supply-side service entities;
[0050] A calculation layer, for performing a matching calculation between traffic demand and traffic service supply and demand under traffic environment constraints according to the traffic demand data, traffic environment data, and traffic service supply data, and obtaining a control strategy for traffic demand and / or traffic service supply;
[0051] The application layer is used to obtain the control strategy of the traffic demand and / or traffic service supply output by the computing layer, convert the control strategy into instructions, and send them to the service entity on the supply side for execution.
[0052] According to another aspect of the embodiments of the present application, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the above-mentioned transportation infrastructure digitization method when running.
[0053] The technical solution provided by the embodiments of the present application may have the following beneficial effects:
[0054] The solution provided by this application collects traffic demand data, traffic environment data, and traffic service supply data, matches supply and demand based on the collected data, and obtains a control strategy for traffic demand and / or traffic service supply. By regulating the service entities on the supply side according to the output control strategy, it is possible to achieve efficient matching of demand and service, enable limited service supply to meet more demand, or flexibly adjust service supply according to changes in demand, thereby improving service utilization, which is equivalent to achieving the expansion of traffic infrastructure and simultaneously bringing the advantages of safety and efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0055] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:
[0056] Figure 1 is a flow chart of an optional method for digitalizing transportation infrastructure according to an embodiment of the present application;
[0057] Figure 2 It is a mapping relationship diagram between the digital transformation of transportation infrastructure and the digital transformation of business according to an embodiment of the present application;
[0058] Figure 3 It is a logical relationship diagram of various functional modules of an intelligent brain according to an embodiment of the present application;
[0059] Figure 4 It is a technical architecture diagram of the digital transformation of transportation infrastructure according to an embodiment of the present application. DETAILED DESCRIPTION
[0060] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.
[0061] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0062] Transportation infrastructure serves the public and its function is to provide services. Services can be decomposed from two dimensions: demand side and supply side. The core contradiction of services is the contradiction between supply and demand. The core of service capability is reflected in the matching efficiency of demand and service supply. The higher the matching efficiency, the less supply can meet more demand, or meet higher priority demand, so as to achieve the purpose of intelligent expansion of transportation infrastructure and safety and efficiency improvement. Therefore, the core requirement of the digital transformation of transportation infrastructure is to improve the supply and demand matching ability of transportation infrastructure services.
[0063] In order to improve the supply-demand matching capability of transportation infrastructure, we must first have the ability to perceive and understand service demand and supply. Figure 2 As shown in the figure, data and knowledge from the demand side enable us to monitor and gain insights into demand, such as predicting the development of demand; at the same time, data and knowledge of services are carried out on the supply side to monitor and gain insights into services. For example, the capabilities of services can be evaluated; in the intelligent stage, based on a high level of insight into demand and supply, we can achieve efficient matching of demand and services. Generally speaking, the supply of services is always limited. If the limited supply of services can meet more demands, or the supply of services can be flexibly adjusted according to changes in demand, the utilization rate of services will be substantially improved, which is equivalent to expanding the capacity of transportation infrastructure and bringing the advantages of safety and efficiency at the same time.
[0064] The following is combined with Figure 1The method for digitalizing the transportation infrastructure in the embodiment of the present application is described in detail. Figure 1 As shown, the method mainly includes the following steps:
[0065] S101 is a data acquisition step, which is to acquire traffic demand data based on demand-side equipment, acquire traffic environment data based on environment-side equipment, and acquire traffic service supply data based on supply-side service entities.
[0066] Among them, demand-side devices are used to sense the demand for transportation, such as flow sensors and vehicle positioning sensors. Traffic demand data, such as vehicle location information and traffic flow information, are collected through demand-side devices. The traffic operation environment is also an important reference data dimension for the capacity of transportation infrastructure. Environmental sensors include traffic weather sensors, traffic event sensors, and real-time road condition sensors. The traffic operation environment is collected through environmental-side devices.
[0067] On the other hand, it also includes services, facilities and equipment on the supply side, which are referred to as service entities in the embodiments of this application, and provide services to the travel groups, such as service areas, traffic guidance signs, gas stations, etc. In order to realize the digital transformation of transportation infrastructure, it is necessary to transform the service entities online, networked and intelligent. The goal of the transformation is to have the functions of uploading its working status, receiving and executing instructions, and feedback on the execution effect of instructions.
[0068] like Figure 4 As shown, for the service entities A, B, C, ..., K on the supply side, adaptation modules A', B', C', ..., K' are installed respectively. By modifying the software and hardware of the service entities, the software and hardware functions of the adaptation modules can be integrated to form a unified software and hardware entity with the following three capabilities:
[0069] 1) Online capability: The operating parameters of the service entity are collected and sent to the monitoring server through the adaptation module, so that the service entity itself and the operating process can be perceived online.
[0070] 2) Networking capability: After the service entity goes online, it can exchange data and collaborate with other similar or heterogeneous service entities and the control background through the bus, so that the service entity can run in a network environment, have networking capabilities, and be empowered by the entire digital system.
[0071] 3) Intelligent capabilities: The adaptation module accepts instructions sent by the application to the service entity, calls the service entity's functions for execution, feeds back the execution results and accepts the optimized instructions. The above iterative process enables the service entity and the service entity group to be empowered by the entire digital system, releasing the optimal service efficiency, thereby enabling the service entity to have intelligent capabilities.
[0072] Among them, the methods of online, networked and intelligent transformation should be based on the existing foundation and transformation cost of the service entity, and the transformation method should be flexibly selected. The embodiments of this application are not specifically limited.
[0073] For example, if the service entity is a person, equipping the person with a smart terminal can achieve the purpose of transformation. The smart terminal can report the person's location, sense the person's running trajectory and operation behavior, so that they have online capabilities; the person can communicate with the background and other people through the smart terminal, and coordinate data and actions, so that they have network capabilities; the person can accept and execute background instructions, feedback the execution effect and iterate and optimize, and at the same time, they can accept the knowledge and information assistance of the background, exert greater subjective initiative, and make them have intelligent capabilities.
[0074] If the service entity is an infrastructure, such as a parking space in a service area, the purpose of transformation can be achieved by equipping it with a smart ground lock. The sensor on the smart ground lock can sense whether there is a vehicle parked above, so that the background can monitor the status of the parking space online, making the parking space have online capabilities; the smart ground lock is a node in the local area network of the service area, and its network module can exchange data with the background, making the parking space have networking capabilities; the smart ground lock can accept background instructions to close or open the parking space, so that the parking space has the ability to regulate parking resources, thus having intelligent capabilities.
[0075] Optionally, if the service entity is a software function, a probe is installed to interact with the data bus, exposing a calling interface to the adapter module, and the adapted module calls to execute related instruction functions and other operations, thereby realizing the online perception, networked operation and intelligent calling capabilities of the service operation data.
[0076] It should be pointed out that some service entities also have the ability to perceive demand. For example, the service at a gas station also reflects the demand for refueling, which will not be elaborated here.
[0077] S102 is a control strategy calculation step, which calculates the traffic demand and traffic service supply-demand matching under traffic environment constraints based on traffic demand data, traffic environment data, and traffic service supply data to obtain a control strategy for traffic demand and / or traffic service supply.
[0078] In an optional embodiment, an intelligent brain is provided to realize perception monitoring and mining analysis of data, achieve supply and demand matching, and obtain regulation strategies.
[0079] Smart brain is the core value of realizing the digital transformation of transportation facilities, and is also the key to integrating various services and exerting scale effect and synergy efficiency. Smart brain carries the three stages of digital transformation, which are implemented in the business capabilities of smart brain, namely holographic perception, knowledge mining and smart decision-making. Among them, holographic perception includes the monitoring capabilities of traffic demand, environment and service supply; knowledge mining includes the capabilities of correlation analysis, gap analysis, competition analysis and risk analysis; smart decision-making includes the matching of traffic demand and service supply and demand, strategy generation, and multi-level collaboration.
[0080] In one embodiment, holographic perception realizes the perception and monitoring functions of the demand side, the environment side, and the service supply side. By collecting data from the demand side and the environment side perception devices, the perception and monitoring of traffic demand and traffic operation environment can be realized. Through the online transformation of service entities, the data of the supply side service entities can be collected to realize the perception and monitoring of the operation status of traffic services.
[0081] Furthermore, the holographic perception of the present application also includes data boundary insight capabilities. After obtaining traffic demand data, traffic environment data, and traffic service supply data, the historical traffic demand data, traffic environment data, and traffic service supply data are grouped according to time characteristics, and statistical operations are performed on various types of data in the same group to obtain the expectations and extreme values of the grouped data. For example, for a certain type of traffic scenario, the historical data of related sensors are grouped according to characteristic days, such as weekdays, weekends, holidays, etc. and time slices, such as hours, flat peaks, etc. Statistical operations are performed on the data in the same group to obtain the expectations, extreme values, and other results of the grouped data. After summarizing the above results, the expected sequence and extreme value sequence of the characteristic days organized according to the time slice sequence are obtained.
[0082] Further, determine whether the absolute difference between the extreme values of the real-time traffic demand data, traffic environment data and traffic service supply data and their corresponding grouped data is less than a preset first threshold; determine whether the expected absolute difference between the real-time traffic demand data, traffic environment data and traffic service supply data and their corresponding grouped data is greater than a preset second threshold.
[0083] If the absolute difference between the data and the extreme value is less than the preset first threshold, and / or the absolute difference between the data and the expectation is greater than the preset second threshold, a warning message is issued. The data refers to the real-time acquired traffic demand data, traffic environment data, and traffic service supply data. For example, when the number of parking lots in the service area parking lot in the real-time acquired traffic service supply data is close to the historical extreme value, a warning message is issued.
[0084] The expected sequence and extreme value sequence of this application can be used as a reference for daily monitoring data. When the perceived real-time data approaches or exceeds the data extreme value, or seriously deviates from the data expectation, an early warning is issued in time. For example, when the flow value is abnormally high (close to the maximum value or deviates from the expectation) or abnormally low (close to the minimum value or deviates from the expectation), an early warning is issued for the abnormal flow value in time.
[0085] In an optional embodiment, the traffic demand and traffic service supply and demand matching calculation under traffic environment constraints are performed based on traffic demand data, traffic environment data, and traffic service supply data, including: performing correlation analysis, gap analysis, competition analysis, and risk analysis based on traffic demand data, traffic environment data, and traffic service supply data, respectively obtaining correlation analysis results, gap analysis results, competition analysis results, and risk analysis results, and using the correlation analysis results, gap analysis results, competition analysis results, and risk analysis results as prior knowledge and calculation parameters for traffic supply and demand matching calculation; in the embodiment of the present application, prior knowledge refers to the mapping function in the correlation analysis, and the mapping function is used to indicate the corresponding relationship between traffic demand and traffic service supply, or to predict traffic demand data, traffic environment data, and traffic service supply data. Prior knowledge also includes service supply entities with competitive relationships obtained from competition analysis, analysis methods for competition coefficients of each competing service entity, and analysis methods for risk coefficients of each competing service entity in risk analysis. Calculation parameters refer to all parameter data obtained from correlation analysis, gap analysis, competition analysis, and risk analysis. Supply and demand matching calculations are performed based on traffic demand data, traffic environment data, traffic service supply data, prior knowledge of traffic supply and demand matching, and calculation parameters to obtain a control strategy for traffic demand and / or traffic service supply.
[0086] The step of correlation analysis includes: extracting the time series data of the traffic parameter to be analyzed within the analysis period as the target sequence; extracting the time series data of other traffic parameters within the analysis period as the source sequence. For example, the traffic parameter to be analyzed is the traffic flow, and the time series data of other traffic parameters within the analysis period are extracted as the source sequence. The other traffic parameters can be real-time road condition data, traffic weather data, traffic event data, etc. After obtaining the source sequence of other traffic parameters, one or more other traffic parameters related to the target sequence are used as the source sequence group, and the source sequence and the target sequence are subjected to correlation determination, for example, by using the Pearson correlation coefficient. The time series data of one or more other traffic parameters that meet the correlation determination are used as the source sequence group; and a mapping function between the source sequence group and the target sequence is established. For example, the mapping function is established by using regression analysis. The mapping function is used to indicate the corresponding relationship between traffic demand and traffic service supply, or to predict traffic demand data and traffic service supply data.
[0087] In an exemplary scenario, the correlation mapping function can indicate the correspondence between traffic demand and the traffic service supply required to meet the demand. For example, the correspondence between the traffic flow at the entrance of a service area and the number of parking spaces and the total parking occupancy time. On the other hand, based on the correlation mapping function, the source sequence group data of another time period is input to predict the target sequence data results. Typical scenarios include predicting traffic demand (flow) in combination with environmental changes; predicting service capacity based on environmental changes. For example, estimating the impact of power outages on the service capacity of a service area.
[0088] In an optional embodiment, the step of gap analysis includes: obtaining priority information in predicted traffic demand data and predicted traffic service supply data; calculating target traffic service supply data that satisfies each priority predicted traffic demand data according to the corresponding relationship between traffic demand and traffic service supply, and calculating target traffic demand data that can be satisfied by each priority predicted traffic service supply data; calculating the difference between each priority predicted traffic service supply data and the target traffic service supply data, recorded as a first difference sequence, and calculating the difference between each priority predicted traffic demand data and the target traffic demand data, recorded as a second difference sequence; the first difference sequence and the second difference sequence are the gap analysis results.
[0089] In one embodiment, traffic demand and traffic service supply are predicted for a certain type of traffic scenario, and quantitative analysis can be performed based on the correlation analysis results between demand and service supply: for a given predicted traffic demand, the required target traffic service supply is calculated based on the correlation analysis results, and the target traffic service supply is subtracted from the predicted traffic service supply and the absolute value is obtained to obtain the gap in the predicted traffic service supply; for a given predicted traffic service supply, the target traffic demand that can be met is calculated based on the correlation analysis results, and the target traffic demand is subtracted from the predicted traffic demand and the absolute value is obtained to obtain the gap in the predicted traffic demand.
[0090] Gap analysis can take into account the priorities of different traffic demands and traffic service supplies, so it is necessary to grade and calibrate traffic demands and traffic service supplies. For a certain type of traffic scenario, classification operations are performed based on the data parameters of relevant sensors to grade and calibrate traffic demands and service supplies. The difference between the predicted traffic service supply data of each priority and the target traffic service supply data is calculated, recorded as the first difference sequence, and the difference between the predicted traffic demand data of each priority and the target traffic demand data is calculated, recorded as the second difference sequence; the first difference sequence and the second difference sequence are the results of gap analysis.
[0091] For example, in the scenario of stranded vehicle rescue, the rescue needs of different vehicles are prioritized based on the length of time the vehicles have been on the highway; in the service area charging scenario, the service capabilities of different charging piles are differentiated based on technical parameters such as charging voltage and current of the charging piles.
[0092] For a certain type of traffic scenario, for a given type of traffic demand, the combined optimization process of supply and demand matching takes reducing the supply and demand gap of all traffic service entities that meet the traffic demand as the optimization goal. When the traffic demand is greater than the traffic service supply, the supply and demand matching can modify the optimization goal to reduce the supply and demand gap of traffic demands that exceed the set priority, while ignoring traffic demands that are lower than the set priority.
[0093] In an optional embodiment, the competition analysis step includes: when there are multiple service supply entities that meet a certain traffic demand, determining that the multiple service supply entities are in a competitive relationship; obtaining a competition coefficient based on the product of the service supply entity's share of the same traffic demand and the service supply entity's cost-effectiveness ratio; the competition relationship and the competition coefficient are the results of the competition analysis; wherein the cost-effectiveness ratio is the output-input ratio of the traffic service entity in meeting unit traffic demand.
[0094] Among them, the share ratio refers to the share ratio of the service entity obtained according to the ratio of the number of times the service entity is used in the historical data to the total number of times. The share reflects the competitiveness. For users, it reflects the convenience of the service. For management, it reflects the cost of demand regulation and the cost-effectiveness of service implementation. The cost-effectiveness of service implementation refers to the output-input ratio of the service entity to meet unit demand. For example, in emergency response scenarios, due to differences in the rescue capabilities of different teams (assessed by the time from receiving the order to completing the response), there are differences in rescue costs (input expectations) and recovered economic losses from tolls (output expectations). Priority is given to teams with a high cost-effectiveness ratio = output expectation / input expectation for rescue.
[0095] Facing a certain type of traffic scenario, for a given type of traffic demand, competition analysis discovers the substitutability of different service entities that meet the traffic demand, thereby providing a solution space for the combinatorial optimization process of supply and demand matching. The supply and demand matching process can allocate traffic demand that exceeds the capacity of a certain traffic service entity to other service entities that can meet the traffic demand and have surplus service capacity, thereby reducing the supply and demand gap of all traffic service entities that meet the traffic demand.
[0096] In addition, the results of competition analysis can help alleviate the problem of inefficient allocation of demand and services due to uneven distribution. For example, for service facilities that compete with each other, such as parallel highways and adjacent service areas, the competitiveness and share relationship of different service facilities can be quantified based on the results of competition analysis when different facilities serve a certain type of travel demand, guiding facility transformation, scheduling and competitive operation to achieve full utilization of resources.
[0097] In an optional embodiment, the risk analysis step includes: calculating the risk coefficient of different service supply quantities provided by the transportation service entity based on the corresponding relationship between traffic demand and transportation service supply; wherein the risk coefficient of the service entity is calculated by the difference between the traffic demand borne by the service entity and its corresponding upper limit of traffic demand, and the smaller the difference, the greater the risk coefficient; the risk coefficient of the transportation service entity is the risk analysis result.
[0098] Driven by the results of competition analysis, the combinatorial optimization function will prioritize traffic demand to service entities with high competitiveness, so that the service pressure of the traffic entity quickly approaches its upper limit, which in turn leads to risks such as damage to the traffic entity, environmental degradation, and a sharp drop in service capacity. The purpose of risk analysis and risk coefficients is to balance the side effects of competition analysis results and prevent the demand from being overly concentrated on one or several service entities during the process of supply and demand matching, which puts them in a risky state.
[0099] Furthermore, based on the traffic demand data, traffic environment data, and traffic service supply data, a traffic supply and demand matching combination optimization function is constructed; wherein, the traffic supply and demand matching combination optimization function uses the competition analysis results as the solution space, the traffic environment data, competition analysis, and risk analysis results as constraints, and the gap analysis results as the optimization target.
[0100] The optimization goal is to reduce the gap between demand and supply, increase the weighted competitiveness of service entities, and reduce the total risk coefficient of service entities. Among them, the weighted competitiveness of service entities is obtained by the product of the competition coefficient of different service entities and the allocated demand share. The goal is to allocate more demand shares to competitive service entities, improve the user's service experience, and reduce the cost of regulation. The risk coefficient of the service entity is obtained by risk analysis, and the total coefficient is the accumulation of the risk coefficients of different service entities.
[0101] The constraints of combinatorial optimization are that the traffic environment constraints are met and different service entities are in a competitive relationship.
[0102] Furthermore, the combined optimization function of traffic supply and demand matching is solved, and the obtained solution is the regulation strategy of traffic demand and / or traffic service supply.
[0103] By solving the supply and demand combination optimization problem, we can achieve an efficient match between traffic demand and traffic service supply, meet demands of different priorities with services of different qualities, meet as many demands as possible with as few services as possible, and keep the utilization rate of different infrastructures at a reasonable level.
[0104] In an optional embodiment, the problem of multi-level collaboration should be considered in the process of supply and demand matching. Applications at different levels have different scheduling capabilities and permissions for service resources. Multi-level collaboration enables the possibility of combining multiple service entities through collaborative process authorization as input for supply and demand matching, significantly expanding the solution space of supply and demand matching and helping to obtain better supply and demand matching results.
[0105] For a certain traffic scenario, the strategy generation module generates a demand induction strategy based on the supply and demand matching results, directs a specific share of demand to the corresponding service entity, and generates a management and control strategy for the excess demand.
[0106] In order to facilitate understanding of the supply and demand matching method of the present application, the following Figure 3 Further description. Figure 3 As shown, this application models the core work of the smart brain as a combinatorial optimization problem of matching the supply and demand of traffic demand and service supply under the constraints of a traffic environment. Solving this problem requires the use of prior knowledge and analysis results of correlation analysis, gap analysis, competition analysis and risk analysis. Among them, correlation analysis reads the historical and real-time monitoring data of traffic demand, environment and service, generates traffic demand forecast data, traffic environment forecast data, traffic service forecast data, and the corresponding relationship between traffic demand and service supply and demand; gap analysis reads the results of correlation analysis, analyzes the degree of mismatch between traffic demand and traffic service, and provides optimization targets for the combined optimization of supply and demand matching; competition analysis calculates the competition and substitution relationship between different traffic services that meet the same traffic demand, and provides a solution space for the combined optimization of supply and demand matching; risk analysis obtains the service risk constraints of different traffic service entities based on the corresponding relationship between supply and demand; traffic environment prediction, competition analysis between different service entities, and risk analysis of different service entities jointly provide constraints for the combined optimization process of supply and demand matching, so that under the constraints of the traffic environment, the most optimized supply and demand matching scheme is generated, which is the optimal scheme for multi-objective combined optimization such as reducing the mismatch between traffic demand and traffic service, reducing the cost of supply and demand scheduling, and reducing the risk of service entities.
[0107] S103 is a control strategy execution step, which obtains the control strategy of traffic demand and / or traffic service supply, converts the control strategy into instructions, and sends them to the service entity on the supply side for execution.
[0108] The embodiment of the present application sets up an application layer to receive the policy output of the intelligent brain, convert it into instructions and send it to the services, facilities and equipment on the supply side for execution.
[0109] It should be pointed out that the strategy defined in this application is different from the instructions generated by the application system. The strategy is the goal of the instruction execution, and the instruction is the measure to achieve the strategy. For example, in order to alleviate the congestion of the accident section of X Expressway, the strategy has two parts. One is to direct 20% of the traffic flow within 10 kilometers upstream of the current X Expressway to Y Expressway; at the same time, the flow rate above 10 kilometers is limited by 30%. The strategy is sent to the induction screen control intelligent application respectively, and the induction screen control intelligent application decodes the strategy into the release information "Vehicles in the directions of Z1 and Z2 can detour to Y Expressway" (assuming that the vehicles in the directions of Z1 and Z2 that accept detours are estimated to account for 20%); the toll station control intelligent application decodes the strategy into an instruction: close the entrances of X, Y, Z... toll stations for 1 hour to implement the above two strategies.
[0110] In addition, the intelligent application provides an interactive interface with business personnel, and receives supervision and adjustment of strategies by business personnel, etc. For example, it receives the control strategy of traffic demand and / or traffic service supply and the adjustment strategy of the control strategy of the regulatory subject; uses the adjustment strategy to adjust the control strategy of traffic demand and / or traffic service supply, decodes and calculates, and obtains instructions for the traffic service entity to execute.
[0111] like Figure 4 As shown in the figure, in addition to receiving the strategy of the smart brain as input, the smart application also receives the capabilities of the smart brain in two dimensions: holographic perception and knowledge mining. That is, users can log in to the interactive interface to view the data collected at the facility level, the results of correlation analysis, gap analysis, risk analysis, and competition analysis, etc.
[0112] From the user's perspective, smart applications can be divided into two application domains: internal and external. They can improve management efficiency internally and service levels externally.
[0113] In an optional embodiment, after the control strategy execution step, the method further includes: collecting operating status data fed back by the supply-side service entity or the demand-side device after executing the control strategy; and adjusting the control strategy according to the fed back operating status data.
[0114] According to another aspect of the embodiments of the present application, a transportation infrastructure digitization system for implementing the above-mentioned transportation infrastructure digitization method is also provided. Figure 4 As shown in the figure, the transformed transportation infrastructure presents a "1+1+N" architecture, which includes 1 set of smart facilities (facility layer), 1 smart brain (computing layer) and N smart applications (application layer).
[0115] The facility layer includes demand-side and environment-side sensing devices, as well as supply-side services, facilities, and equipment. Supply-side service entities can be intelligently upgraded by adding adapter modules. They are used to obtain traffic demand data, traffic environment data, and traffic service supply data.
[0116] The computing layer is used to calculate the matching of traffic demand and traffic service supply and demand under traffic environment constraints based on traffic demand data, traffic environment data, and traffic service supply data, and obtain the control strategy of traffic demand and / or traffic service supply.
[0117] The computing layer is used for demand monitoring, environmental monitoring, and service monitoring, and then conducts correlation analysis, gap analysis, competition analysis, and risk analysis based on the monitoring data, and then matches supply and demand to generate regulation strategies.
[0118] The application layer is used to obtain the traffic demand and / or traffic service supply control strategy output by the computing layer, convert the control strategy into instructions, and send it to the service entity on the supply side for execution.
[0119] This application systematically presents the overall architecture, key functional components and information interaction methods of the digital transformation of transportation infrastructure. By completing key data elements and business capabilities and reconstructing processes, various services, facilities and equipment are organically integrated under a low-cost transformation model, addressing the shortcomings of existing digital transformation methods such as insufficient scale effect, insufficient integration and insufficient synergy efficiency. It has guiding significance for the construction of smart highways and smart service areas.
[0120] It should be noted that the traffic infrastructure digitization system provided in the above embodiment only uses the division of the above functional modules as an example when executing the traffic infrastructure digitization method. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the traffic infrastructure digitization system provided in the above embodiment and the traffic infrastructure digitization method embodiment belong to the same concept, and the implementation process thereof is detailed in the method embodiment, which will not be repeated here.
[0121] According to another aspect of the embodiments of the present application, a computer-readable storage medium corresponding to the method for digitizing transportation infrastructure provided in the aforementioned embodiments is also provided, on which a computer program (i.e., a program product) is stored. When the computer program is run by a processor, it will execute the method for digitizing transportation infrastructure provided in any of the aforementioned embodiments.
[0122] It should be noted that examples of computer-readable storage media may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical or magnetic storage media, which are not listed here one by one.
[0123] The computer-readable storage medium provided in the above-mentioned embodiments of the present application and the method for digitalizing transportation infrastructure provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.
[0124] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0125] The above embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present invention. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention patent shall be subject to the attached claims.
Claims
1. A digital approach to transportation infrastructure, It is characterized in that include: Data acquisition step, acquiring traffic demand data based on demand-side equipment, acquiring traffic environment data based on environment-side equipment, and acquiring traffic service supply data based on supply-side service entities; a control strategy calculation step, performing a traffic demand and traffic service supply-demand matching calculation under traffic environment constraints based on the traffic demand data, traffic environment data, and traffic service supply data, and obtaining a control strategy for traffic demand and / or traffic service supply; The control strategy execution step obtains the control strategy of the traffic demand and / or traffic service supply, converts the control strategy into instructions, and sends them to the service entity on the supply side for execution.
2. The method according to claim 1, It is characterized in that The traffic demand and traffic service supply-demand matching calculation under traffic environment constraints is performed according to the traffic demand data, traffic environment data, and traffic service supply data, including: Perform correlation analysis, gap analysis, competition analysis and risk analysis on the traffic demand data, traffic environment data and traffic service supply data, obtain correlation analysis results, gap analysis results, competition analysis results and risk analysis results respectively, and use the correlation analysis results, gap analysis results, competition analysis results and risk analysis results as prior knowledge and calculation parameters for traffic supply and demand matching calculation; Supply and demand matching calculations are performed based on the traffic demand data, traffic environment data, traffic service supply data, the traffic supply and demand matching prior knowledge, and calculation parameters to obtain a control strategy for the traffic demand and / or traffic service supply.
3. The method according to claim 1, It is characterized in that After obtaining traffic demand data, traffic environment data, and traffic service supply data, it also includes: The historical traffic demand data, traffic environment data and traffic service supply data are grouped according to time characteristics, and statistical operations are performed on various types of data in the same group to obtain the expectation and extreme value of the grouped data; Determine whether the absolute difference between the extreme value of the real-time traffic demand data, traffic environment data, and traffic service supply data and the corresponding grouped data is less than a preset first threshold; Determine whether the expected absolute difference between the real-time traffic demand data, traffic environment data, and traffic service supply data and the corresponding grouped data is greater than a preset second threshold; If the absolute difference between the data and the extreme value is less than a preset first threshold, and / or the absolute difference between the data and the expectation is greater than a preset second threshold, a warning message is issued.
4. The method according to claim 2, It is characterized in that The step of correlation analysis comprises: Extract the time series data of the traffic parameters to be analyzed within the analysis period as the target sequence; Extract the time series data of other traffic parameters during the analysis period as the source series; Determining the correlation between the source sequence and the target sequence; Using time series data of one or more other traffic parameters that meet the correlation determination as a source sequence group; Establishing a mapping function between the source sequence group and the target sequence; The mapping function is used to indicate the corresponding relationship between traffic demand and traffic service supply, or to predict traffic demand data and traffic service supply data.
5. The method according to claim 4, It is characterized in that The steps of the gap analysis include: Obtaining priority information in forecasted traffic demand data and forecasted traffic service supply data; According to the correspondence between the traffic demand and the traffic service supply, the target traffic service supply data satisfying the traffic demand data predicted for each priority level is calculated, and the target traffic demand data that can be satisfied by the traffic service supply data predicted for each priority level is calculated; Calculate the difference between the predicted traffic service supply data of each priority and the target traffic service supply data, record it as a first difference sequence, calculate the difference between the predicted traffic demand data of each priority and the target traffic demand data, record it as a second difference sequence; The first difference sequence and the second difference sequence are gap analysis results.
6. The method according to claim 2, It is characterized in that The steps of the competition analysis include: When there are multiple service providers that can meet a certain traffic demand, the multiple service providers are determined to be in a competitive relationship; The competition coefficient is obtained according to the product of the share of the service provider entity for the same traffic demand and the cost-effectiveness ratio of the service provider entity; The competition relationship and the competition coefficient are competition analysis results; Among them, the cost-effectiveness ratio is the output-input ratio of the transportation service entity in meeting unit transportation demand.
7. The method according to claim 4, It is characterized in that The steps of risk analysis include: Calculate the risk coefficient of different service supply quantities provided by the transportation service entity according to the corresponding relationship between the transportation demand and the transportation service supply; Among them, the risk coefficient of the service entity is calculated by the difference between the traffic demand undertaken by the service entity and its corresponding upper limit of traffic demand. The smaller the difference, the greater the risk coefficient; The risk coefficient of the transportation service entity is a risk analysis result.
8. The method according to claim 2, It is characterized in that According to the traffic demand data, traffic environment data, and traffic service supply data, traffic demand and traffic service supply and demand matching calculations are performed under traffic environment constraints to obtain a traffic demand and / or traffic service supply control strategy, including: Constructing a transportation supply and demand matching combination optimization function based on the transportation demand data, transportation environment data, and transportation service supply data; The traffic supply and demand matching combination optimization function takes the competition analysis results as the solution space, the traffic environment data, competition analysis, and risk analysis results as constraints, and the gap analysis results as the optimization target. The traffic supply and demand matching combined optimization function is solved, and the obtained solution is the regulation strategy of traffic demand and / or traffic service supply.
9. The method according to claim 1, It is characterized in that The control strategy execution step also includes: Receiving the control strategy of the traffic demand and / or traffic service supply and the adjustment strategy of the control strategy of the regulatory body; The adjustment strategy is used to adjust the control strategy of the traffic demand and / or traffic service supply, decode and calculate, and obtain an instruction to instruct the traffic service entity to execute.
10. The method according to claim 1, It is characterized in that After the control strategy execution step, the method further includes: Collecting the operation status data fed back by the service entity on the supply side or the equipment on the demand side after executing the control strategy; The control strategy is adjusted according to the fed-back operating status data.
11. A digital system for transportation infrastructure, It is characterized in that include: The facility layer is used to obtain traffic demand data based on demand-side equipment, traffic environment data based on environment-side equipment, and traffic service supply data based on supply-side service entities; A calculation layer, for performing a matching calculation between traffic demand and traffic service supply and demand under traffic environment constraints according to the traffic demand data, traffic environment data, and traffic service supply data, and obtaining a control strategy for traffic demand and / or traffic service supply; The application layer is used to obtain the control strategy of the traffic demand and / or traffic service supply output by the computing layer, convert the control strategy into instructions, and send them to the service entity on the supply side for execution.
12. A computer readable medium, It is characterized in that Computer-readable instructions are stored thereon, and the computer-readable instructions are executed by a processor to implement a method for digitizing a transportation infrastructure as described in any one of claims 1 to 10.
