WO2022257190A1 - 一种基于量子游走的行为轨迹序列多特征模拟方法 - Google Patents

一种基于量子游走的行为轨迹序列多特征模拟方法 Download PDF

Info

Publication number
WO2022257190A1
WO2022257190A1 PCT/CN2021/102009 CN2021102009W WO2022257190A1 WO 2022257190 A1 WO2022257190 A1 WO 2022257190A1 CN 2021102009 W CN2021102009 W CN 2021102009W WO 2022257190 A1 WO2022257190 A1 WO 2022257190A1
Authority
WO
WIPO (PCT)
Prior art keywords
feature
sequence
sequences
behavior
quantum
Prior art date
Application number
PCT/CN2021/102009
Other languages
English (en)
French (fr)
Inventor
俞肇元
罗文�
张季一
袁林旺
王增杰
Original Assignee
南京师范大学
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 南京师范大学 filed Critical 南京师范大学
Publication of WO2022257190A1 publication Critical patent/WO2022257190A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N10/00—Quantum computing, i.e. information processing based on quantum-mechanical phenomena
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30241—Trajectory

Definitions

  • the invention relates to the technical fields of quantum mechanics and traffic geography, in particular to a multi-feature simulation method of a behavior trajectory sequence based on quantum walks.
  • online car-hailing trajectory data not only records its driving trajectory, but also contains road traffic conditions, urban residents' travel patterns, urban structure and other social issues.
  • the sequence of online car-hailing behavior trajectories is the aggregation result of behavior trajectories at different spatial and temporal scales, reflecting the state or degree of online car-hailing behavior trajectories changing over time at different spatial scales.
  • Most of the current research on behavior trajectories focuses on the feature extraction and feature recognition of the trajectory data itself, seldom considers its structure and characteristics from the temporal and spatial distribution of behavioral trajectory sequences, and insufficient consideration is given to the spatiotemporal differentiation of behavioral trajectory sequences.
  • the technical problem to be solved by the present invention is to provide a multi-feature simulation method of behavior trajectory sequence based on quantum walk, based on the transformation and combination characteristics between individual behavior and group behavior, using quantum walk to simulate similar individuals from the perspective of multi-scale analysis feature structure, and realize the simulation of behavior trajectory.
  • the present invention provides a multi-feature simulation method of behavior trajectory sequence based on quantum walk, including the following steps:
  • step (1) generating the feature sequence of the complete set is specifically as follows: based on the basic assumption of quantum walk, in the inner city system gridded into m ⁇ n blocks, all possible distributions of behavioral features are defined as The ground state of the quantum walk is denoted as:
  • Equation (3) the dynamic evolution of the state vector depends on the adjacency matrix A, which is transformed into a matrix from the perspective of discrete points, and the state vector is effectively solved by matrix operations; so far, the ensemble feature based on quantum walk is constructed Sequence generation models.
  • the parameters are constantly adjusted based on the following rules: 2000 quantum walks are performed on the 56 blocks in the research area, and the control parameters are increased from 0.01 to 20 with an interval of 0.01; finally, all possible The characteristic sequence of the quantum walk realizes the generation of the complete characteristic sequence of the quantum walk.
  • the screening feature sequence is specifically: use the ReliefF feature selection algorithm to screen the behavioral trajectory feature sequence, and under the constraints of the actual behavioral trajectory time sequence S, the complete set of feature sequences generated in step (1) Perform ReliefF feature subset screening, which is expressed as:
  • Equation (4) Based on the weight of each feature, use the feature selection algorithm in Equation (4) to select from the ensemble feature sequence Filter out N feature sequences with larger feature weights, denoted as in
  • four sets of feature sequence sets with different numbers are screened from the full set of feature sequences at one time according to the size of the feature weights, and the corresponding numbers of feature sequences are 5, 10, 20 and 30 respectively.
  • step (3) constructing a feature sequence mapping mechanism is specifically: based on step (2) screening the obtained modality
  • the aliasing coupling relationship between the behavior track sequence and the behavior mode is respectively established, and expressed as:
  • the experimental configuration in the experimental verification is specifically as follows: the research area is gridded into 0.01 ° x 0.01 ° blocks, a total of 56, and the network car-hailing every ten minutes in each block is counted Traffic time series, the length is 144, and the final processing obtains the required experimental data;
  • s i is the actual behavior track sequence; is the simulated behavior track sequence; is the average value of the actual behavior trajectory sequence; l is the number of simulated samples.
  • the present invention analyzes the behavior track sequence from the perspective of multi-scale and multi-feature analysis, explores the coupling relationship between behavior track features and behavior track aggregation data, and constructs a robust multi-feature simulation of behavior track sequence method, and trying to apply it to intelligent transportation, resource and environmental protection, urban planning, social perception, etc., is a major breakthrough in the direction of behavioral trajectory modeling and simulation.
  • Fig. 1 is a schematic flow chart of the method of the present invention.
  • Fig. 2 is a schematic diagram of the simulation results of the behavior track sequence of the five feature sequences of the present invention.
  • Fig. 3 is a schematic diagram of the simulation results of behavior track sequences of 10 feature sequences of the present invention.
  • Fig. 4 is a schematic diagram of the simulation results of behavior track sequences of 20 feature sequences of the present invention.
  • Fig. 5 is a schematic diagram of the simulation results of behavior track sequences of 30 feature sequences of the present invention.
  • Fig. 6 is a schematic diagram of the accuracy evaluation of the simulation results of the behavior trajectory sequence of the five feature sequences of the present invention.
  • Fig. 7 is a schematic diagram of the accuracy evaluation of the simulation results of the behavior trajectory sequence of the 10 feature sequences of the present invention.
  • Fig. 8 is a schematic diagram of the accuracy evaluation of the simulation results of the behavior trajectory sequence of 20 feature sequences in the present invention.
  • Fig. 9 is a schematic diagram of the accuracy evaluation of the simulation results of the behavior track sequence of 30 feature sequences in the present invention.
  • a multi-feature simulation method for behavior trajectory sequences based on quantum walks includes the following steps:
  • the present invention abstracts drivers with the same or similar behavior trajectories as a class of quantized particles, then the movement process of such drivers on different grids can be described as the movement of particles between blocks
  • a class of behavior trajectories corresponds to a collapse of the quantized particle transfer process.
  • the quantum walk control parameter is the only parameter to generate a single feature sequence, which directly determines the structure of the feature sequence, that is, the structural characteristics of the corresponding probability distribution. Therefore, it is only necessary to continuously change the control parameters of the quantum walk to generate a complete set of feature sequences.
  • the movement process of drivers with the same or similar behavioral trajectories can be described as the transfer process of quantized particles between blocks in the study area, which is described by quantum walk.
  • the key is that under the given parameters, the walker starts from the fixed block and performs quantum tour on the basic skeleton composed of the adjacency matrix (topological structure) of the research area after gridding. Go, forming the dynamic evolution of the probability distribution of behavioral characteristics over time under a single type of behavioral trajectory.
  • a Hilbert space H composed of ground states is firstly defined, and the superposition state formed by the linear combination of ground states is also in this space. Therefore, the state
  • the dynamic evolution of the state vector depends on the adjacency matrix A, and the differential equations containing complex coefficients are difficult to solve directly. Therefore, it is transformed into a matrix from the perspective of discrete points, and the state vector is efficiently solved by matrix operations. So far, a quantum walk-based ensemble feature sequence generation model has been constructed.
  • the parameters are constantly adjusted based on the following rules: 2000 quantum walks are performed on 56 blocks in the research area, and the control parameters are increased from 0.01 to 20 with an interval of 0.01. In the end, all possible feature sequences of 56 blocks were obtained, realizing the generation of the full set of feature sequences of quantum walks.
  • the ensemble feature sequence generated in step 1 is only a general set of feature sequences, and it does not yet have the ability to reveal the heterogeneity of behavior trajectories between different blocks. Therefore, under the constraints of the actual behavior trajectory sequence, based on specific feature sequence screening criteria, adaptive analysis can obtain the feature sequence set containing the behavior trajectory characteristics of a specific block.
  • the mapping coupling relationship of behavior trajectory sequence lays the foundation.
  • the present invention uses the ReliefF feature selection algorithm to screen the behavior trajectory feature sequence, and under the constraints of the actual behavior trajectory time sequence S, the complete set of feature sequences generated by step (1) To filter the subset of ReliefF features, it can be expressed as:
  • Equation (4) Based on the weight of each feature, use the feature selection algorithm in Equation (4) to select from the ensemble feature sequence Filter out N feature sequences with larger feature weights, denoted as in
  • the feature sequence represents the probability that particles with the same or similar walking trajectories appear in different blocks, and there is a conversion mapping mechanism with the actual behavior trajectory sequence. Therefore, based on the eigenmodes of each block screened in step (2), the aliasing coupling relationship between the behavior trajectory sequence and the eigenmodes is established, and the mapping transformation from the simulated characteristic sequence to the actual behavior trajectory sequence is realized, and the fitting accuracy is achieved. Purpose.
  • step (2) Based on the obtained modes of step (2) screening The aliasing coupling relationship between the behavior track sequence and the behavior mode is respectively established, and expressed as:
  • This invention adopts the local area of the Second Ring Road of Chengdu in November 2016 (104.04214°E-104.12214°E, 30.65294°N-30.72294°N, GCJ- 02 coordinate system) trajectory data as the original data.
  • Data preprocessing is divided into two steps: first, the research area is gridded into 0.01°x0.01° blocks (56 in total), and then the time series of online car-hailing traffic every ten minutes in each block is counted (the length is 144), the final processing obtained the required experimental data.
  • the present invention When generating the feature sequence of the complete set, the present invention performs 2000 quantum walks on the research area block, and its control parameters are increased from 0.01 to 20 at intervals of 0.01. In order to explore the different granularity characteristics of the behavior track sequence, the present invention selects 5, 10, 20 and 30 feature sequences respectively to perform feature analysis and modeling simulation on the behavior track sequence. In order to compare and evaluate the effect of the simulation, the present invention selects the coefficient of determination (Coefficient of Determination, R 2 ) as an evaluation index, which is specifically defined as:
  • s i is the actual behavior track sequence; is the simulated behavior track sequence; is the average value of the actual behavior trajectory sequence; l is the number of simulated samples.
  • Figures 2-9 show the simulation results obtained by selecting 5, 10, 20 and 30 feature sequences and the accuracy evaluation of the simulation results, respectively.
  • the results show that the five feature sequences can basically simulate the overall change trend of the behavior trajectory sequence, and the modeling accuracy is 0.6026-0.9524, which can reveal the dominant distribution structure of the behavior trajectory sequence in a day.
  • the simulation effect of some blocks is relatively poor, such as N26, N40, and N49, and it is difficult to predict the fluctuations in the 0-48 period. This may be related to the spatial distribution of the stations, that is, there are few main roads near these three stations.
  • the modeling accuracies of 10, 20 and 30 feature sequences are 0.6926-0.9494, 0.6926-0.9913, 0.6926-0.9966, respectively, and the modeling accuracy of some sites with simple behavior trajectory features is no longer affected by the number of feature sequences, indicating that the its characteristics and laws. Since this method is a data-driven method, the introduced feature sequences may have collinearity, and the simulation results also have overfitting problems. Therefore, it is necessary to further optimize the feature sequence screening rules and improve the mapping transformation mechanism between feature sequences and behavior trajectory sequences.

Abstract

一种基于量子游走的行为轨迹序列多特征模拟方法，包括如下步骤：(1)生成全集特征序列；(2)筛选特征序列；(3)构建特征序列映射机制；(4)实验验证。基于个体行为与群体行为间的转化组合特性，从多尺度解析的视角利用量子游走模拟同类个体的特征结构，并实现对行为轨迹的模拟。

Description

一种基于量子游走的行为轨迹序列多特征模拟方法 技术领域
本发明涉及量子力学和交通地理技术领域，尤其是一种基于量子游走的行为轨迹序列多特征模拟方法。
背景技术
大数据、物联网与精密定位技术的发展推动了城市感知的进步。随着社会活动的与日俱增，网约车轨迹数据不仅记录了其行车轨迹，还蕴藏着道路交通状态、城市居民出行规律、城市结构及其他社会问题。网约车行为轨迹序列是行为轨迹在不同时空尺度下的聚合结果，反映了网约车行为轨迹在不同空间尺度之下随时间的变化状态或程度。当前对行为轨迹的研究大多集中于对轨迹数据本身的特征提取与特征识别，较少从行为轨迹序列的时空分布来考虑其结构和特征，对行为轨迹序列的时空分异规律考虑不足。
基于数据挖掘手段，当前对行为轨迹数据研究主要有城市规划和社会感知两个方向。在城市规划方向上，大多利用行为轨迹数据发现、识别并评估静态城市规划和城市结构。对于社会感知，大部分学者基于行为轨迹数据对城市内人群活动的动态变化、移动模式进行分析和监测。以上两个方向已有较多成熟的研究成果。近年来，各领域的学者都不断试图从行为轨迹数据中挖掘新的知识与经验，研究改进了各种理论方法，可将其归纳为四类：空间统计、时间序列方法、图论与复杂网络，以及机器学习。以上模型方法大多基于行为轨迹数据本身开展研究工作，取得了丰硕的研究成果，但对行为轨迹的聚合数据研究较少。
发明内容
本发明所要解决的技术问题在于，提供一种基于量子游走的行为轨迹序列多特征模拟方法，基于个体行为与群体行为间的转化组合特性，从多尺度解析的视角利用量子游走模拟同类个体的特征结构，并实现对行为轨迹的模拟。
为解决上述技术问题，本发明提供一种基于量子游走的行为轨迹序列多特征模拟方法，包括如下步骤：
(1)生成全集特征序列；
(2)筛选特征序列；
(3)构建特征序列映射机制；
(4)实验验证。
优选的，步骤(1)中，生成全集特征序列具体为：基于量子游走的基本假设，在格网化为m×n个区块的城市内部系统中，将行为特征所有可能的分布定义为量子游走的基态，记为：
Figure PCTCN2021102009-appb-000001
表示驾驶员在不同区块间的移动在量子游走模拟中体现为粒子在不同结点间的转移；
定义一个由基态构成的希尔伯特空间H，且由基态线性组合而成的叠加态同样处于该空间中；因此，量子游走的状态|δ(k)>被定义为所有基态的线性叠加：
Figure PCTCN2021102009-appb-000002
其中|a i(k)|∈[0,1]，表示驾驶员在给定时间处于状态|i>的概率幅；根据随机性假设，基于酉变换，将状态向量|δ(k)>随时间的演化表示如下：
Figure PCTCN2021102009-appb-000003
如式(3)所示，状态向量的动态演变取决于邻接矩阵A，从离散点的视角将其转化为矩阵，并通过矩阵运算有效求解状态向量；至此，构建了基于量子游走的全集特征序列生成模型。
优选的，基于以下规则不断调整参数：在研究区域的56个区块上进行2000次量子游走，其控制参数从0.01增加至20，且间隔为0.01；最终，得到了56个区块所有可能的特征序列，实现了量子游走的全集特征序列生成。
优选的，步骤(2)中，筛选特征序列具体为：以ReliefF特征选择算法来筛选行为轨迹特征序列，在实际行为轨迹时间序S的约束下，对步骤(1)生成的全集特征序列
Figure PCTCN2021102009-appb-000004
进行ReliefF特征子集筛选，将其表示为：
Figure PCTCN2021102009-appb-000005
基于每个特征的权重，使用式(4)中的特征选择算法从全集特征序列
Figure PCTCN2021102009-appb-000006
中筛选N个特征权重较大的特征序列，记为
Figure PCTCN2021102009-appb-000007
其中
Figure PCTCN2021102009-appb-000008
优选的，依据特征权重大小一次从全集特征序列中筛选了四组不同数量的特征序列集合，相应的特征序列数分别为5、10、20和30。
优选的，步骤(3)中，构建特征序列映射机制具体为：基于步骤(2)筛选所得模态
Figure PCTCN2021102009-appb-000009
分别建立了行为轨迹序列与行为模态间的混叠耦合关系，并将其表示为：
Figure PCTCN2021102009-appb-000010
优选的，步骤(4)中，实验验证中的实验配置具体为：将研究区域格网化为0.01°x0.01°的区块，共56个，统计各区块内每十分钟的网约车流量时间序列，长度为144，最终处理得到了所需实验数据；
在生成全集特征序列时，在研究区域区块上进行了2000次量子游走，其控制参数以0.01的间隔从0.01增加至20，分别选取5、10、20和30个特征序列对行为轨迹序列进行特征解析和建模模拟，选取决定系数R 2作为评价的指标，具体定义为：
Figure PCTCN2021102009-appb-000011
其中，s i为实际行为轨迹序列；
Figure PCTCN2021102009-appb-000012
为模拟得到的行为轨迹序列；
Figure PCTCN2021102009-appb-000013
为实际行为轨迹序列的平均值；l为模拟样本个数。
本发明的有益效果为：本发明从多尺度多特征解析的视角分析行为轨迹序列，探索行为轨迹特征与行为轨迹聚合数据之间的耦合关系，构建强鲁棒性的行为轨迹序列的多特征模拟方法，并尝试将其应用于智能交通、资源与环境保护、城市规划、社会感知等方面，是行为轨迹建模与模拟方向上的一大突破。
附图说明
图1为本发明的方法流程示意图。
图2为本发明5个特征序列的行为轨迹序列模拟结果示意图。
图3为本发明10个特征序列的行为轨迹序列模拟结果示意图。
图4为本发明20个特征序列的行为轨迹序列模拟结果示意图。
图5为本发明30个特征序列的行为轨迹序列模拟结果示意图。
图6为本发明5个特征序列的行为轨迹序列模拟结果精度评定示意图。
图7为本发明10个特征序列的行为轨迹序列模拟结果精度评定示意图。
图8为本发明20个特征序列的行为轨迹序列模拟结果精度评定示意图。
图9为本发明30个特征序列的行为轨迹序列模拟结果精度评定示意图。
具体实施方式
如图1所示，一种基于量子游走的行为轨迹序列多特征模拟方法，包括如下步骤：
(1)生成全集特征序列；
(2)筛选特征序列；
(3)构建特征序列映射机制；
(4)实验验证。
为满足量子游走的基本假设，本发明将具有相同或相似行为轨迹的驾驶员抽象为一类量子化粒子，则此类驾驶员在不同格网上的运动过程可描述为粒子在区块间的转移过程，一类行为轨迹对应于量子化粒子转移过程的一次坍塌。在未对系统施加观测时，粒子会以一定的概率出现在多个可能的区块，形成该粒子出现在各区块的概率随时间的动态演化过程，从而模拟得到与此类行为轨迹序列对应的单一特征序列。
然而，城市内部行为轨迹结构复杂，不同区域间异质性强，单一特征序列难以表征城市内部行为轨迹序列的多模态、繁结构特征。因此，考虑制备具有不同结构、不同振荡特性的全集特征序列，是行为轨迹序列特征解析与建模模拟的“基”。在实现上，量子游走控制参数是生成单一特征序列的唯一参数，它直接决定了特征序列的结构，即相应概率分布的结构特征。因此，只需不断变化量子游走的控制参数，即可生成全集特征序列。
具有相同或相似行为轨迹的驾驶员的运动过程可描述为量子化粒子在研究区域区块间的转移过程，并用量子游走加以描述。在特征序列生成的过程中，其关键是在给定的参数下，游走者从固定的区块出发，在格网化后研究区域的邻接矩阵(拓扑结构)构成的基本骨架上进行量子游走，形成单一类型行为轨迹下行为特征概率分布随时间的动态演化。
基于量子游走的基本假设，在格网化为m×n个区块的城市内部系统中，可将行为特征所有可能的分布定义为量子游走的基态，记为：
Figure PCTCN2021102009-appb-000014
表示驾驶员在不同区块间的移动在量子游走模拟中体现为粒子在不同结点间的转移。
为了让粒子能够动态调整出现在不同区块的概率，首先定义一个由基态构成的希尔伯特空间H，且由基态线性组合而成的叠加态同样处于该空间中。因此，量子游走的状态|δ(k)>可以被定义为所有基态的线性叠加：
Figure PCTCN2021102009-appb-000015
其中|a i(k)|∈[0,1]，表示驾驶员在给定时间处于状态|i>的概率幅。不同于经典随机游走，量子游走不是一个马尔科夫链。根据随机性假设，基于酉变换，可将状态向量|δ(k)>随时间的演化表示如下：
Figure PCTCN2021102009-appb-000016
如式(3)所示，状态向量的动态演变取决于邻接矩阵A，且含有复数系数的微分方程是难以直接求解的。因此，从离散点的视角将其转化为矩阵，并通过矩阵运算有效求解状态向量。至此，构建了基于量子游走的全集特征序列生成模型。
在本发明中，基于以下规则不断调整参数：在研究区域的56个区块上进行2000次量子游走，其控制参数从0.01增加至20，且间隔为0.01。最终，得到了56个区块所有可能的特征序列，实现了量子游走的全集特征序列生成。
虽然城市内部行为轨迹复杂，但受制于客观条件限制，部分理想特征序列几乎不可能存在于实际行为轨迹序列中。城市土地利用、功能区划分等改善了人群的行为特征，加大了区块间行为轨迹序列的异质性，因此不同区块上的特征序列具有一定差异。步骤1生成的全集特征序列只是一个通用的特征序列集合，还不具备揭示不同区块间行为轨迹异质性的能力。因此，在实际行为轨迹序列的约束下，基于特定的特征序列筛选准则， 自适应解析得到蕴含特定区块行为轨迹特征的特征序列集合，为揭示各区块行为轨迹多尺度特征和探索特征序列与实际行为轨迹序列的映射耦合关系奠定基础。
本发明以ReliefF特征选择算法来筛选行为轨迹特征序列，在实际行为轨迹时间序S的约束下，对步骤(1)生成的全集特征序列
Figure PCTCN2021102009-appb-000017
进行ReliefF特征子集筛选，可将其表示为：
Figure PCTCN2021102009-appb-000018
基于每个特征的权重，使用式(4)中的特征选择算法从全集特征序列
Figure PCTCN2021102009-appb-000019
中筛选N个特征权重较大的特征序列，记为
Figure PCTCN2021102009-appb-000020
其中
Figure PCTCN2021102009-appb-000021
在本发明中，依据特征权重大小一次从全集特征序列中筛选了四组不同数量的特征序列集合，相应的特征序列数分别为5、10、20和30。
在本发明中，特征序列表征的是具有相同或相似游走轨迹的粒子出现在不同区块的概率，与实际行为轨迹序列还存在一个转化映射机制。因此，基于步骤(2)筛选所得的各区块的特征模态，建立行为轨迹序列与特征模态间的混叠耦合关系，实现模拟的特征序列向实际行为轨迹序列的映射转化，达到拟合的目的。
基于步骤(2)筛选所得模态
Figure PCTCN2021102009-appb-000022
分别建立了行为轨迹序列与行为模态间的混叠耦合关系，并将其表示为：
Figure PCTCN2021102009-appb-000023
本发明采用盖亚数据开放计划(https://gaia.didichuxing.com)提供的2016年11月成都市二环局部区域(104.04214°E-104.12214°E，30.65294°N-30.72294°N，GCJ-02坐标系)轨迹数据作为原始数据。数据预处理分为两步：首先将该研究区域格网化为0.01°x0.01°的区块(共56个)，然后统计各区块内每十分钟的网约车流量时间序列(长度为144)，最终处理得到了所需实验数据。
在生成全集特征序列时，本发明在研究区域区块上进行了2000次量子游走，其控制参数以0.01的间隔从0.01增加至20。为探究行为轨迹序列的不同颗粒度特征，本发明分别选取5、10、20和30个特征序列对行为轨迹序列进行特征解析和建模模拟。为 了对比评价模拟的效果，本发明选取决定系数(Coefficient of Determination,R 2)作为评价的指标，具体定义为：
Figure PCTCN2021102009-appb-000024
其中，s i为实际行为轨迹序列；
Figure PCTCN2021102009-appb-000025
为模拟得到的行为轨迹序列；
Figure PCTCN2021102009-appb-000026
为实际行为轨迹序列的平均值；l为模拟样本个数。
以56个区块内每十分钟的网约车流量时间序列作为实验数据，完成了行为轨迹序列的模拟实验。图2-图9分别表示选择5、10、20和30个特征序列得到的模拟结果以及模拟结果精度评定。结果表明，5个特征序列基本能模拟行为轨迹序列的总体变化趋势，建模精度为0.6026-0.9524，能揭示行为轨迹序列在一天内的主导分布结构。但部分区块模拟效果相对较差，如N26、N40、N49，难以预测出0-48时段的波动情况，这可能与站点的空间分布有关，即这三个站点附近主干道路较少，对其特征揭示不足，模拟效果相对较差。此外，5个特征序列的模拟结果对细节的捕捉尚存不足，难以反应轨迹序列的高频振荡。随着特征序列逐渐增多，模拟效果逐步提升，对微小振荡的捕捉效果也得以提升。10、20和30个特征序列建模精度分别为0.6926-0.9494，0.6926-0.9913，0.6926-0.9966，部分行为轨迹特征简单的站点的建模精度不再受特征序列数目的影响，表明已完全揭示了其特征和规律。由于该方法是数据驱动的方法，引入的特征序列可能存在共线性，模拟结果也存在过拟合问题，因此需进一步优化特征序列筛选规则，完善特征序列与行为轨迹序列间的映射转化机制。

Claims (7)

  1. 一种基于量子游走的行为轨迹序列多特征模拟方法，其特征在于，包括如下步骤：
    (1)生成全集特征序列；
    (2)筛选特征序列；
    (3)构建特征序列映射机制；
    (4)实验验证。
  2. 如权利要求1所述的基于量子游走的行为轨迹序列多特征模拟方法，其特征在于，步骤(1)中，生成全集特征序列具体为：基于量子游走的基本假设，在格网化为m×n个区块的城市内部系统中，将行为特征所有可能的分布定义为量子游走的基态，记为：
    Figure PCTCN2021102009-appb-100001
    表示驾驶员在不同区块间的移动在量子游走模拟中体现为粒子在不同结点间的转移；
    定义一个由基态构成的希尔伯特空间H，且由基态线性组合而成的叠加态同样处于该空间中；因此，量子游走的状态|δ(k)>被定义为所有基态的线性叠加：
    Figure PCTCN2021102009-appb-100002
    其中|a i(k)|∈[0,1]，表示驾驶员在给定时间处于状态|i>的概率幅；根据随机性假设，基于酉变换，将状态向量|δ(k)>随时间的演化表示如下：
    Figure PCTCN2021102009-appb-100003
    如式(3)所示，状态向量的动态演变取决于邻接矩阵A，从离散点的视角将其转化为矩阵，并通过矩阵运算有效求解状态向量；至此，构建了基于量子游走的全集特征序列生成模型。
  3. 如权利要求2所述的基于量子游走的行为轨迹序列多特征模拟方法，其特征在于，基于以下规则不断调整参数：在研究区域的56个区块上进行2000次量子游走，其 控制参数从0.01增加至20，且间隔为0.01；最终，得到了56个区块所有可能的特征序列，实现了量子游走的全集特征序列生成。
  4. 如权利要求1所述的基于量子游走的行为轨迹序列多特征模拟方法，其特征在于，步骤(2)中，筛选特征序列具体为：以ReliefF特征选择算法来筛选行为轨迹特征序列，在实际行为轨迹时间序S的约束下，对步骤(1)生成的全集特征序列
    Figure PCTCN2021102009-appb-100004
    进行ReliefF特征子集筛选，将其表示为：
    Figure PCTCN2021102009-appb-100005
    基于每个特征的权重，使用式(4)中的特征选择算法从全集特征序列
    Figure PCTCN2021102009-appb-100006
    中筛选N个特征权重较大的特征序列，记为
    Figure PCTCN2021102009-appb-100007
    其中
    Figure PCTCN2021102009-appb-100008
  5. 如权利要求4所述的基于量子游走的行为轨迹序列多特征模拟方法，其特征在于，依据特征权重大小一次从全集特征序列中筛选了四组不同数量的特征序列集合，相应的特征序列数分别为5、10、20和30。
  6. 如权利要求1所述的基于量子游走的行为轨迹序列多特征模拟方法，其特征在于，步骤(3)中，构建特征序列映射机制具体为：基于步骤(2)筛选所得模态
    Figure PCTCN2021102009-appb-100009
    分别建立了行为轨迹序列与行为模态间的混叠耦合关系，并将其表示为：
    Figure PCTCN2021102009-appb-100010
  7. 如权利要求1所述的基于量子游走的行为轨迹序列多特征模拟方法，其特征在于，步骤(4)中，实验验证中的实验配置具体为：将研究区域格网化为0.01°x0.01°的区块，共56个，统计各区块内每十分钟的网约车流量时间序列，长度为144，最终处理得到了所需实验数据；
    在生成全集特征序列时，在研究区域区块上进行了2000次量子游走，其控制参数以0.01的间隔从0.01增加至20，分别选取5、10、20和30个特征序列对行为轨迹序列进行特征解析和建模模拟，选取决定系数R 2作为评价的指标，具体定义为：
    Figure PCTCN2021102009-appb-100011
    其中，s i为实际行为轨迹序列；
    Figure PCTCN2021102009-appb-100012
    为模拟得到的行为轨迹序列；
    Figure PCTCN2021102009-appb-100013
    为实际行为轨迹序列的平均值；l为模拟样本个数。
PCT/CN2021/102009 2021-06-08 2021-06-24 一种基于量子游走的行为轨迹序列多特征模拟方法 WO2022257190A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110636508.0A CN113393488A (zh) 2021-06-08 2021-06-08 一种基于量子游走的行为轨迹序列多特征模拟方法
CN202110636508.0 2021-06-08

Publications (1)

Publication Number Publication Date
WO2022257190A1 true WO2022257190A1 (zh) 2022-12-15

Family

ID=77618733

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/102009 WO2022257190A1 (zh) 2021-06-08 2021-06-24 一种基于量子游走的行为轨迹序列多特征模拟方法

Country Status (2)

Country Link
CN (1) CN113393488A (zh)
WO (1) WO2022257190A1 (zh)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113392583A (zh) * 2021-06-08 2021-09-14 南京师范大学 一种基于量子游走的海面高度模拟方法
CN114429077A (zh) * 2021-12-09 2022-05-03 南京师范大学 一种基于量子游走的时间序列多尺度分析方法
CN114648433A (zh) * 2022-03-21 2022-06-21 南京师范大学 一种基于量子游走的网约车流量多尺度特征解析方法
CN115470913A (zh) * 2022-09-29 2022-12-13 南京师范大学 基于量子游走的pir传感器网络行为轨迹的重构方法及装置

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107705212A (zh) * 2017-07-07 2018-02-16 江苏开放大学 一种基于粒子群随机游走的角色识别方法
US20190072968A1 (en) * 2017-09-01 2019-03-07 International Business Machines Corporation Generating driving behavior models
CN109598432A (zh) * 2018-11-28 2019-04-09 北京航空航天大学 一种基于城市特征的车辆轨迹数据模拟方法
CN111126611A (zh) * 2019-12-09 2020-05-08 南京师范大学 一种顾及目的地选择的高速通行流量分布模拟量子计算方法
CN112614336A (zh) * 2020-11-19 2021-04-06 南京师范大学 一种基于量子随机游走的交通流模态拟合方法
CN112614335A (zh) * 2020-11-17 2021-04-06 南京师范大学 一种基于生成-滤波机制的交通流特征模态分解方法

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110363229B (zh) * 2019-06-27 2021-07-27 岭南师范学院 一种基于改进RReliefF和mRMR相结合的人体特征参数选择方法
CN110689437A (zh) * 2019-10-08 2020-01-14 湖北电信工程有限公司 一种基于随机森林的通信施工项目财务风险预测方法
CN111222290B (zh) * 2020-01-13 2024-04-09 浙江工业大学 一种基于多参数特征融合的大型设备剩余使用寿命预测方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107705212A (zh) * 2017-07-07 2018-02-16 江苏开放大学 一种基于粒子群随机游走的角色识别方法
US20190072968A1 (en) * 2017-09-01 2019-03-07 International Business Machines Corporation Generating driving behavior models
CN109598432A (zh) * 2018-11-28 2019-04-09 北京航空航天大学 一种基于城市特征的车辆轨迹数据模拟方法
CN111126611A (zh) * 2019-12-09 2020-05-08 南京师范大学 一种顾及目的地选择的高速通行流量分布模拟量子计算方法
CN112614335A (zh) * 2020-11-17 2021-04-06 南京师范大学 一种基于生成-滤波机制的交通流特征模态分解方法
CN112614336A (zh) * 2020-11-19 2021-04-06 南京师范大学 一种基于量子随机游走的交通流模态拟合方法

Also Published As

Publication number Publication date
CN113393488A (zh) 2021-09-14

Similar Documents

Publication Publication Date Title
WO2022257190A1 (zh) 一种基于量子游走的行为轨迹序列多特征模拟方法
CN109508360B (zh) 一种基于元胞自动机的地理多元流数据时空自相关分析方法
CN110263111B (zh) 基于先验知识的土地利用/覆被信息时空监测方法
WO2021114594A1 (zh) 一种顾及目的地选择的高速通行流量分布模拟量子计算方法
Roodposhti et al. Towards automatic calibration of neighbourhood influence in cellular automata land-use models
CN109165664A (zh) 一种基于生成对抗网络的属性缺失数据集补全与预测方法
CN110517482B (zh) 一种基于3d卷积神经网络的短时交通流预测方法
CN110288202A (zh) 一种城市公园绿地设施状态评估优化方法
CN105931116A (zh) 基于深度学习机制的自动化信用评分系统及方法
WO2022104696A1 (zh) 一种基于量子随机游走的交通流模态拟合方法
CN105893483A (zh) 大数据挖掘过程模型总体框架的构造方法
CN113885398B (zh) 一种基于可微推理的水循环智能感知与监控系统
Ye et al. Hybrid agent modeling in population simulation: Current approaches and future directions
WO2024031520A1 (zh) 一种基于生成对抗网络的人群移动预测方法
Dai et al. Spatio-temporal deep learning framework for traffic speed forecasting in IoT
CN112528359A (zh) 一种基于议价模型和蚁群优化算法的城市扩张模拟方法
Zhang et al. Graph convolutional networks-based super-resolution land cover mapping
Cheng et al. Understanding urban growth system: Theories and methods
CN113159371B (zh) 基于跨模态数据融合的未知目标特征建模与需求预测方法
Norte Pinto et al. Cellular automata and urban studies: A literature survey
CN113989544A (zh) 一种基于深度图卷积网络的群体发现方法
WO2023178581A1 (zh) 一种基于量子游走的网约车流量多尺度特征解析方法
Yang Construction of graduate behavior dynamic model based on dynamic decision tree algorithm
He et al. Modeling multi-type urban landscape dynamics along the horizontal and vertical dimensions
CN113299068A (zh) 一种融合社会力模型与粒子群算法的交通路网拥堵状态预测方法及系统

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21944696

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE