Urban resource integration system and method based on digital model

Abstract

The invention discloses an urban resource integration system and method based on a digital model, and relates to the technical field of traffic flow monitoring. A road section needing to be predicted is acquired and set as a target road section, discrete data outside a fluctuation range are screened out, the discrete data are divided into first-class discrete feature data and second-class discrete feature data according to data features, and the first-class discrete feature data and the second-class discrete feature data are stored in a database; constructing a first association model through the association between the first type of discrete feature data features and the first historical event features, obtaining a second type of historical events occurring in a time period corresponding to the second type of discrete feature data, and establishing a second association model through the association between the second type of historical features and the corresponding data change rate; and obtaining a first prediction value of the traffic flow of the target road section, performing time feature extraction on the target time, calculating the influence of the target road section on the first prediction value at the target time through the first correlation model and the second correlation model, and obtaining a traffic flow prediction value of the target road section at the target time.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic flow monitoring, and in particular to a city resource integration system and method based on a digital model. Background Art

[0002] Traffic flow data is an important part of urban municipal data. Under the existing technical framework, by detecting traffic flow data and forecasting traffic flow information, traffic flow prediction information can be applied to many aspects of actual production and life. In the existing technology, it is common to predict traffic flow numbers based on the correlation between time and space, such as time series-based traffic flow prediction models and traffic flow prediction models combining long and short cycles.

[0003] The prediction models in the existing technology lack the ability to integrate traffic data for specific scenarios, such as the impact of holidays or gatherings on traffic flow. The usual time prediction models will ignore the impact of data at these specific times because there is no strict mathematical logic between these traffic flow data, but the impact of data at these specific times is very important for the prediction results. Summary of the invention

[0004] The purpose of the present invention is to provide a city resource integration system and method based on digital model to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solution: a method for integrating urban resources based on digital models. The method comprises:

[0006] Step S100: setting a road section to be predicted in an urban road as a target road section, setting a fluctuation range of historical data of the target road section, filtering out discrete data outside the fluctuation range, and dividing the discrete data into first-category discrete feature data and second-category discrete feature data according to data features;

[0007] Step S200: obtaining the first type of historical events occurring in the time period corresponding to the first type of discrete feature data from the historical event records, and constructing a first association model through the connection between the first type of discrete feature data and the first historical event features in the time dimension;

[0008] Step S300: obtaining the second type of historical events occurring in the time period corresponding to the second type of discrete feature data from the historical event records, and establishing a second association model by associating the second type of historical features with the corresponding data change rate;

[0009] Step S400: predicting the road section information and time information in the request information for predicting traffic flow through a prediction model based on time period changes to obtain a first prediction value of the traffic flow of the target road section;

[0010] Step S500: extract time features of the target time, calculate the influence of the target section at the target time on the first prediction value through the first association model and the second association model, obtain the traffic flow prediction value of the target section at the target time, and use the traffic flow prediction value as the traffic flow prediction result of the target section at the target time.

[0011] Furthermore, step S100 includes:

[0012] Step S101: acquiring historical traffic flow data of a target road section, acquiring a functional relationship of traffic flow of the target road section changing with time, setting a fluctuation range of the functional relationship, and setting data outside the fluctuation range of the functional relationship in the historical traffic flow data as discrete data;

[0013] Step S102: setting a data selection interval with a time length of T0, dividing a plurality of discrete data into a discrete data group through the data selection interval, wherein the discrete data with the largest absolute value of difference with the functional relationship in each discrete data group is aligned with the midpoint of the corresponding data selection interval;

[0014] By designing the alignment method of the data selection interval, it is helpful to obtain the range of historical data that needs to calculate the degree of data discreteness more quickly, reduce the amount of calculation and the number of comparisons in the process of traversing the data, align the discrete data with the largest absolute value of the difference between the functional relationship in each discrete data group with the midpoint of the corresponding data selection interval, and retain the change characteristics of the data in the interval. On the basis of easier implementation of the solution, the calculation results are in line with reality;

[0015] Step S103: Calculate the variance of historical data in each data discrete group and set a discrete degree management threshold. When the variance of historical data in a data discrete group is less than the discrete degree management threshold, it is determined to be first-category discrete feature data. When the variance of historical data in a data discrete group is greater than the discrete degree management threshold, it is determined to be second-category discrete feature data.

[0016] Further, step S200 includes:

[0017] Step S201: feature labeling of time periods corresponding to each first-category discrete feature data, and constructing a model of time features and data features of the first-category discrete feature data by a machine learning method, wherein the data features of the first-category discrete feature data are the differences between the first-category data and the boundary of the fluctuation range;

[0018] Step S202: feature labeling of each first-category historical event, classifying the features of the first-category historical events occurring at different times by a classification algorithm, and obtaining first-event feature models of the first-category historical events occurring at different time periods;

[0019] Step S203: Associating the data features of the first type of discrete feature data and the first event features in the same time period in the time dimension to obtain a first association model of three factors: time features, time features and event features of the first type of discrete feature data.

[0020] The first type of historical events refers to a type of event that usually has an impact on traffic flow after it occurs, and some of these events have similar impact patterns after they occur. The common characteristics of these events are found, and these common characteristics are linked to the impact on traffic flow to form a first association model. When the predicted target time includes the event features in the first association model, the impact of the event features on traffic flow is added to the traffic flow prediction value.

[0021] Furthermore, step S300 includes:

[0022] Step S301: subtracting the interval corresponding to the historical data within the fluctuation range of the functional relationship from the data selection interval corresponding to the second type of discrete feature data, to obtain the data variation interval corresponding to each second type of discrete feature data;

[0023] Step S302: Calculate the data change rate of each second-category discrete feature data in the corresponding data change interval, where the data change rate of the kth second-category discrete feature data in the corresponding data change interval is R k , Among them, C j represents the difference between the jth second-category discrete feature data of the kth second-category discrete feature data in the corresponding data variation interval and the boundary of the fluctuation range, T k represents the interval length of the data change interval corresponding to the k-th second-category discrete feature data, wherein the data change interval corresponding to the k-th second-category discrete feature data includes h second-category discrete feature data;

[0024] Step S303: each second-category historical event is feature-labeled, and the features of the second-category historical event are associated with the corresponding data change rate, so as to obtain a second association model of the impact of historical events occurring in different time periods on the traffic flow change rate;

[0025] The second type of association model represents the impact of events that may occur on traffic flow in the target section at the target time. The second type of historical events has a certain probability of occurrence, so the probability of occurrence is quantified when calculating the mathematical expectation of the occurrence of the second type of historical events.

[0026] Furthermore, step S400 includes:

[0027] Step S401: obtaining request information for predicting traffic flow, setting the road section for which traffic flow prediction is to be performed in the request information as the target road section, and setting the time for requesting traffic flow prediction as the target time;

[0028] Step S402: predicting the traffic flow of the target road section at the target time by using the periodic prediction model to obtain a first prediction value of the target road section at the target time.

[0029] Furthermore, step S500 includes:

[0030] Step S501: perform feature comparison on the target time, obtain the first event feature in the feature corresponding to the target time, and calculate the impact value Q of the first event feature corresponding to the target time on the traffic flow according to the first association model. * , Among them, d represents the total number of first event features in the target time corresponding features, q j represents the difference between the first event feature in the feature corresponding to the j-th target time and the boundary of the fluctuation range;

[0031] Step S502: obtaining the mathematical expectation of the second type of historical events occurring at the target time, and calculating the flow change coefficient β of the target road section at the target time, β=E×R, where E represents the mathematical expectation of the second type of historical events occurring at the target time, and R represents the data change rate corresponding to the second type of historical events;

[0032] Step S503: Calculate the traffic flow prediction value Q2 of the target road section at the target time, where Q2 = β × (Q1 + Q * ), where Q1 represents the first predicted value of the target segment at the target time.

[0033] In order to better implement the above method, a city resource integration system based on digital model is also proposed. The system includes: a data feature extraction module, an association model management module and a traffic flow prediction module, wherein the data feature extraction module is used to extract data features from historical data and classify the data features, the association model management module is used to establish corresponding data models according to data with different features, and the traffic flow prediction module is used to calculate the traffic flow prediction value.

[0034] Furthermore, the data feature extraction module includes: a historical data acquisition unit, a discrete degree calculation unit and a discrete feature determination unit, wherein the historical data acquisition unit is used to acquire historical data of traffic flow, the discrete degree calculation unit is used to calculate the discrete degree of data in the data selection interval, and the discrete feature determination unit is used to judge data features and classify the data features.

[0035] Furthermore, the association model management module includes: an event feature management unit, a first event feature model management unit, a first association model management unit, a data change rate calculation unit and a second association model management unit, wherein the event feature management unit is used to obtain annotation information of event features, the first event feature model management unit is used to construct a first event feature model, the first association model management unit is used to construct a first association model, the data change rate calculation unit is used to calculate the data change rate of the second type of discrete feature data in the corresponding data change interval, and the second association model management unit is used to manage the second association model.

[0036] Furthermore, the traffic flow prediction module includes: a first prediction value calculation unit, a traffic flow impact value calculation unit, a flow variation coefficient calculation unit, and a traffic flow prediction value calculation unit, wherein the first prediction value calculation unit is used to calculate the first prediction value, the traffic flow impact value calculation unit is used to calculate the impact value of the first event feature corresponding to the target time on the traffic flow, the flow variation coefficient calculation unit is used to calculate the flow variation coefficient of the target section at the target time, and the traffic flow prediction value calculation unit is used to calculate the traffic flow prediction value of the target section at the target time.

[0037] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: based on the existing traffic flow prediction, the present invention analyzes the impact of non-periodic events on traffic flow to improve the traffic flow data integration capability of the traffic prediction model, extracts event features that affect traffic flow, and when the prediction time includes characteristic events that affect traffic flow, adds the impact of characteristic events on traffic flow on the basis of the existing traffic prediction, further considers the mathematical expectation of the occurrence of discrete incidental events, and combines the impact of incidental time on traffic flow trends to make the prediction results more in line with reality. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0039] Figure 1 It is a structural schematic diagram of a city resource integration system based on a digital model in the patent of the present invention;

[0040] Figure 2It is a flow chart of a method for integrating urban resources based on a digital model in the patent of the present invention.

[0041] Figure 3 It is a schematic diagram of selecting the first type of discrete feature data of a method for integrating urban resources based on a digital model in the patent of the present invention;

[0042] Figure 4 It is a schematic diagram for selecting the second type of discrete feature data in a method for integrating urban resources based on a digital model in the patent of the present invention. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0044] See also Figure 1 , Figure 2 , Figure 3 and Figure 4 , the present invention provides a technical solution:

[0045] Methods include:

[0046] Step S100: setting a road section to be predicted in an urban road as a target road section, setting a fluctuation range of historical data of the target road section, filtering out discrete data outside the fluctuation range, and dividing the discrete data into first-category discrete feature data and second-category discrete feature data according to data features;

[0047] Wherein, step S100 includes:

[0048] Step S101: acquiring historical traffic flow data of a target road section, acquiring a functional relationship of traffic flow of the target road section changing with time, setting a fluctuation range of the functional relationship, and setting data outside the fluctuation range of the functional relationship in the historical traffic flow data as discrete data;

[0049] Step S102: setting a data selection interval with a time length of T0, dividing a plurality of discrete data into a discrete data group through the data selection interval, wherein the discrete data with the largest absolute value of difference with the functional relationship in each discrete data group is aligned with the midpoint of the corresponding data selection interval;

[0050] Step S103: Calculate the variance of historical data in each data discrete group and set a discrete degree management threshold. When the variance of historical data in a data discrete group is less than the discrete degree management threshold, it is determined to be first-category discrete feature data. When the variance of historical data in a data discrete group is greater than the discrete degree management threshold, it is determined to be second-category discrete feature data.

[0051] Step S200: obtaining the first type of historical events occurring in the time period corresponding to the first type of discrete feature data from the historical event records, and constructing a first association model through the connection between the first type of discrete feature data and the first historical event features in the time dimension;

[0052] Wherein, step S200 includes:

[0053] Step S201: feature labeling of time periods corresponding to each first-category discrete feature data, and constructing a model of time features and data features of the first-category discrete feature data by a machine learning method, wherein the data features of the first-category discrete feature data are the differences between the first-category data and the boundary of the fluctuation range;

[0054] Step S202: feature labeling of each first-category historical event, classifying the features of the first-category historical events occurring at different times by a classification algorithm, and obtaining first-event feature models of the first-category historical events occurring at different time periods;

[0055] Step S203: Associating the data features of the first type of discrete feature data and the first event features in the same time period in the time dimension to obtain a first association model of three factors: time features, time features and event features of the first type of discrete feature data.

[0056] In the specific implementation process, special dates, holidays or dates of gatherings can be selected as the characteristic time of the first type of historical events, and the first type of historical events can be marked with characteristics. Figure 3 A schematic diagram showing the selection of a first type of discrete feature data.

[0057] Step S300: obtaining the second type of historical events occurring in the time period corresponding to the second type of discrete feature data from the historical event records, and establishing a second association model by associating the second type of historical features with the corresponding data change rate;

[0058] Wherein, step S300 includes:

[0059] Step S301: subtracting the interval corresponding to the historical data within the fluctuation range of the functional relationship from the data selection interval corresponding to the second type of discrete feature data, to obtain the data variation interval corresponding to each second type of discrete feature data;

[0060] Step S302: Calculate the data change rate of each second-category discrete feature data in the corresponding data change interval, wherein the data change rate of the k-th second-category discrete feature data in the corresponding data change interval is Rk, Wherein, Cj represents the difference between the j-th second-category discrete feature data in the corresponding data change interval of the k-th second-category discrete feature data and the boundary of the fluctuation range, Tk represents the interval length of the data change interval corresponding to the k-th second-category discrete feature data, and the data change interval corresponding to the k-th second-category discrete feature data includes h second-category discrete feature data;

[0061] Step S303: each second-category historical event is feature-labeled, and the features of the second-category historical event are associated with the corresponding data change rate to obtain a second association model of the impact of historical events occurring in different time periods on the traffic flow change rate.

[0062] In the specific implementation process, accidental events such as weather changes or traffic accidents are selected as the second type of historical events. Figure 4 A schematic diagram showing the selection of a second type of discrete feature data.

[0063] Step S400: predicting the road section information and time information in the request information for predicting traffic flow through a prediction model based on time period changes to obtain a first prediction value of the traffic flow of the target road section;

[0064] Step S401: obtaining request information for predicting traffic flow, setting the road section for which traffic flow prediction is to be performed in the request information as the target road section, and setting the time for requesting traffic flow prediction as the target time;

[0065] Step S402: predicting the traffic flow of the target road section at the target time by using the periodic prediction model to obtain a first prediction value of the target road section at the target time.

[0066] Step S500: extracting time features from the target time, calculating the influence of the target section at the target time on the first prediction value through the first association model and the second association model, obtaining the traffic flow prediction value of the target section at the target time, and using the traffic flow prediction value as the traffic flow prediction result of the target section at the target time;

[0067] Wherein, step S500 includes:

[0068] Step S501: perform feature comparison on the target time, obtain the first event feature in the feature corresponding to the target time, and calculate the impact value Q of the first event feature corresponding to the target time on the traffic flow according to the first association model. * , Among them, d represents the total number of first event features in the target time corresponding features, q j represents the difference between the first event feature in the feature corresponding to the j-th target time and the boundary of the fluctuation range;

[0069] Step S502: obtaining the mathematical expectation of the second type of historical events occurring at the target time, and calculating the flow change coefficient β of the target road section at the target time, β=E×R, where E represents the mathematical expectation of the second type of historical events occurring at the target time, and R represents the data change rate corresponding to the second type of historical events;

[0070] Step S503: Calculate the traffic flow prediction value Q2 of the target road section at the target time, where Q2 = β × (Q1 + Q * ), where Q1 represents the first predicted value of the target segment at the target time.

[0071] The system includes:

[0072] Data feature extraction module, association model management module and traffic flow prediction module;

[0073] The data feature extraction module is used to extract data features from historical data and classify the data features. The data feature extraction module includes: a historical data acquisition unit, a discrete degree calculation unit and a discrete feature determination unit. The historical data acquisition unit is used to acquire historical data of traffic flow, the discrete degree calculation unit is used to calculate the discrete degree of data in the data selection interval, and the discrete feature determination unit is used to determine the data features and classify the data features.

[0074] The associated model management module is used to establish a corresponding data model according to data with different characteristics, wherein the associated model management module includes: an event feature management unit, a first event feature model management unit, a first associated model management unit, a data change rate calculation unit and a second associated model management unit, wherein the event feature management unit is used to obtain the annotation information of the event feature, the first event feature model management unit is used to construct the first event feature model, the first associated model management unit is used to construct the first associated model, the data change rate calculation unit is used to calculate the data change rate of the second type of discrete feature data in the corresponding data change interval, and the second associated model management unit is used to manage the second associated model;

[0075] Among them, the traffic flow prediction module is used to calculate the traffic flow prediction value, wherein the traffic flow prediction module includes: a first prediction value calculation unit, a traffic flow impact value calculation unit, a flow change coefficient calculation unit, and a traffic flow prediction value calculation unit, wherein the first prediction value calculation unit is used to calculate the first prediction value, the traffic flow impact value calculation unit is used to calculate the impact value of the first event feature corresponding to the target time on the traffic flow, the flow change coefficient calculation unit is used to calculate the flow change coefficient of the target section at the target time, and the traffic flow prediction value calculation unit is used to calculate the traffic flow prediction value of the target section at the target time.

[0076] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0077] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for integrating urban resources based on digital models, characterized in that: The method comprises the following steps: Step S100: setting a road section in an urban road for which traffic flow prediction is required as a target road section, setting a fluctuation range of historical data of the target road section, filtering out discrete data outside the fluctuation range, and dividing the discrete data into first-category discrete feature data and second-category discrete feature data according to data features; Step S200: obtaining the first type of historical events occurring in the time period corresponding to the first type of discrete feature data from the historical event records, and constructing a first association model through the connection between the first type of discrete feature data and the first historical event features in the time dimension; Step S300: obtaining the second type of historical events occurring in the time period corresponding to the second type of discrete feature data from the historical event records, and establishing a second association model by associating the second type of historical features with the corresponding data change rate; Step S400: predicting the road section information and time information in the request information for predicting traffic flow through a prediction model based on time period changes to obtain a first prediction value of the traffic flow of the target road section; Step S500: extract time features of the target time, calculate the influence of the target section at the target time on the first prediction value through the first association model and the second association model, obtain the traffic flow prediction value of the target section at the target time, and use the traffic flow prediction value as the traffic flow prediction result of the target section at the target time.

2. The urban resource integration method based on digital model according to claim 1, characterized in that: Step S100 includes: Step S101: acquiring historical traffic flow data of a target road section, acquiring a functional relationship of traffic flow of the target road section changing with time, setting a fluctuation range of the functional relationship, and setting data outside the fluctuation range of the functional relationship in the historical traffic flow data as discrete data; Step S102: setting a data selection interval with a time length of T0, dividing a plurality of discrete data into a discrete data group through the data selection interval, wherein the discrete data with the largest absolute value of difference with the functional relationship in each discrete data group is aligned with the midpoint of the corresponding data selection interval; Step S103: Calculate the variance of historical data in each data discrete group and set a discrete degree management threshold. When the variance of historical data in a data discrete group is less than the discrete degree management threshold, it is determined to be first-category discrete feature data. When the variance of historical data in a data discrete group is greater than the discrete degree management threshold, it is determined to be second-category discrete feature data.

3. The urban resource integration method based on digital model according to claim 2 is characterized by: Step S200 includes: Step S201: feature labeling of time periods corresponding to each first-category discrete feature data, and constructing a model of time features and data features of the first-category discrete feature data by a machine learning method, wherein the data features of the first-category discrete feature data are the differences between the first-category data and the boundary of the fluctuation range; Step S202: feature labeling of each first-category historical event, classifying the features of the first-category historical events occurring at different times by a classification algorithm, and obtaining first-event feature models of the first-category historical events occurring at different time periods; Step S203: Associating the data features of the first type of discrete feature data and the first event features in the same time period in the time dimension to obtain a first association model of three factors: time features, time features and event features of the first type of discrete feature data.

4. The urban resource integration method based on digital model according to claim 3 is characterized by: Step S300 includes: Step S301: subtracting the interval corresponding to the historical data within the fluctuation range of the functional relationship from the data selection interval corresponding to the second type of discrete feature data, to obtain the data variation interval corresponding to each second type of discrete feature data; Step S302: Calculate the data change rate of each second-category discrete feature data in the corresponding data change interval, where the data change rate of the kth second-category discrete feature data in the corresponding data change interval is R k , Among them, C j represents the difference between the jth second-category discrete feature data of the kth second-category discrete feature data in the corresponding data variation interval and the boundary of the fluctuation range, T k represents the interval length of the data change interval corresponding to the k-th second-category discrete feature data, wherein the data change interval corresponding to the k-th second-category discrete feature data includes h second-category discrete feature data; Step S303: each second-category historical event is feature-labeled, and the features of the second-category historical event are associated with the corresponding data change rate to obtain a second association model of the impact of historical events occurring in different time periods on the traffic flow change rate.

5. The urban resource integration method based on digital model according to claim 4 is characterized by: Step S400 includes: Step S401: obtaining request information for predicting traffic flow, setting the road section for which traffic flow prediction is to be performed in the request information as the target road section, and setting the time for requesting traffic flow prediction as the target time; Step S402: predicting the traffic flow of the target road section at the target time by using the periodic prediction model to obtain a first prediction value of the target road section at the target time.

6. The urban resource integration method based on digital model according to claim 5 is characterized by: Step S500 includes: Step S501: perform feature comparison on the target time, obtain the first event feature in the feature corresponding to the target time, and calculate the impact value Q of the first event feature corresponding to the target time on the traffic flow according to the first association model. * , Among them, d represents the total number of first event features in the target time corresponding features, q j represents the difference between the first event feature in the feature corresponding to the j-th target time and the boundary of the fluctuation range; Step S502: obtaining the mathematical expectation of the second type of historical events occurring at the target time, and calculating the flow change coefficient β of the target road section at the target time, β=E×R, where E represents the mathematical expectation of the second type of historical events occurring at the target time, and R represents the data change rate corresponding to the second type of historical events; Step S503: Calculate the traffic flow prediction value Q2 of the target road section at the target time, where Q2 = β × (Q1 + Q * ), where Q1 represents the first predicted value of the target segment at the target time.

7. An urban resource integration system for use in the urban resource integration method based on a digital model as claimed in any one of claims 1 to 6, characterized in that: The system includes the following modules: Data feature extraction module, association model management module and traffic flow prediction module, wherein the data feature extraction module is used to extract data features from historical data and classify the data features, the association model management module is used to establish corresponding data models according to data with different features, and the traffic flow prediction module is used to calculate the traffic flow prediction value.

8. The urban resource integration system according to claim 7, characterized in that: The data feature extraction module includes: a historical data acquisition unit, a discrete degree calculation unit and a discrete feature determination unit, wherein the historical data acquisition unit is used to acquire historical data of traffic flow, the discrete degree calculation unit is used to calculate the discrete degree of data in the data selection interval, and the discrete feature determination unit is used to judge data features and classify the data features.

9. The urban resource integration system according to claim 8, characterized in that: The association model management module includes: an event feature management unit, a first event feature model management unit, a first association model management unit, a data change rate calculation unit and a second association model management unit, wherein the event feature management unit is used to obtain annotation information of event features, the first event feature model management unit is used to construct a first event feature model, the first association model management unit is used to construct a first association model, the data change rate calculation unit is used to calculate the data change rate of the second type of discrete feature data in the corresponding data change interval, and the second association model management unit is used to manage the second association model.

10. The urban resource integration system according to claim 9, characterized in that: The traffic flow prediction module includes: a first prediction value calculation unit, a traffic flow impact value calculation unit, a flow variation coefficient calculation unit, and a traffic flow prediction value calculation unit, wherein the first prediction value calculation unit is used to calculate the first prediction value, the traffic flow impact value calculation unit is used to calculate the impact value of the first event feature corresponding to the target time on the traffic flow, the flow variation coefficient calculation unit is used to calculate the flow variation coefficient of the target section at the target time, and the traffic flow prediction value calculation unit is used to calculate the traffic flow prediction value of the target section at the target time.

Images