A traffic travel next location prediction method and device based on multi-adaptive hypergraph cooperation

Abstract

The application belongs to the field of next location prediction of urban resident traffic, and discloses a traffic next location prediction method and device based on multi-adaptive hypergraph cooperation, which comprises the following steps: constructing an interactive hypergraph and a directed hypergraph based on individual traffic trajectory sequences, constructing a geographic hypergraph based on location geographic feature data, updating the interactive hypergraph and the geographic hypergraph to obtain an adaptive interactive hypergraph and an adaptive geographic hypergraph, obtaining a location overall embedding matrix and an individual overall embedding matrix based on the hypergraph, and outputting the first k positions with the highest probability as the prediction result of the next travel location of the individual through a normalization function according to the location overall embedding matrix and the individual overall embedding matrix. The application has high accuracy and strong robustness for location prediction.

Description

Technical Field

[0001] This invention belongs to the field of next location prediction for urban residents' travel, and specifically relates to a method and apparatus for next location prediction for travel based on multi-adaptive hypergraph collaboration. Background Technology

[0002] Early research on next-location prediction in transportation primarily focused on sequence modeling, with typical methods including Markov chains, recurrent neural networks, and attention mechanisms. In recent years, Graph Neural Networks (GNNs) have demonstrated outstanding performance in modeling complex human travel patterns. They can efficiently model complex graph data by learning high-quality node representations, effectively improving the accuracy of next-location prediction. Existing research has explored various complex graph structures to model the complex dependencies between individual movement and location, including hypergraphs, knowledge graphs, directed graphs, and multi-relation graphs. Simultaneously, several new GNNs have been proposed to extract information from various complex graph data. Despite significant progress in graph-based next-location prediction research, some problems remain. Taking hypergraph structures as an example, the existing problems can be summarized into the following three aspects.

[0003] First, existing research largely relies on static individual travel trajectories and location geographic features to construct hypergraphs, resulting in a rigid graph structure that limits the model's ability to characterize complex individual travel behaviors and location geographic features. This makes it difficult to capture dynamic individual movement patterns and perceived distances between locations. Specifically, perceived distance refers to the effective distance actually perceived by an individual during travel; it depends not only on physical distance in geographic space but is also influenced by factors such as mode of transportation and route selection. Therefore, the models have limitations in terms of the diversity of location predictions and travel convenience. For example... Figure 1 As shown, after visiting the restaurant, the individual's next destination is a store; although store 2 is closer to the residence, the static historical travel trajectory (solid line) may guide the model to predict that the individual's next location is store 1. Similarly, although store 3 is closer in perceived distance (5 minutes by bus is less than 20 minutes on foot), the model may predict store 2, which is closer to the residence, because it only considers the geographical distance between locations.

[0004] Secondly, noise and sparsity in individual historical location check-in data can easily lead to unreliable hyperedges and nodes in the hypergraph, thereby perturbing the hypergraph structure and affecting the accuracy of the model in learning individual travel patterns. For example... Figure 1 As shown, the cinema is a noisy location in a static trajectory, which does not align with individual travel preferences. Nevertheless, the model may still predict the cinema based on historical trajectories, thereby influencing subsequent store predictions and increasing the probability of store 1 (rather than store 2 or store 3) being predicted.

[0005] Finally, individual travel behavior is influenced by a variety of factors, including individual habits, geographical features, and the temporal sequence of visits. However, most graph-based methods use only a single graph to model individual travel patterns, or use multiple graphs for collaborative modeling, without considering the sequential modeling of travel trajectories. For example, a single hypergraph constructed solely from individual travel trajectories, without sequential modeling of these trajectories, can only capture individual travel habits and cannot adequately account for the influence of other factors. Therefore, models that rely on a single graph or neglect sequential modeling struggle to comprehensively understand individual travel patterns. Summary of the Invention

[0006] The purpose of this invention is to provide a method and apparatus for predicting the next location in transportation based on multi-adaptive hypergraph collaboration, which has high accuracy and strong robustness in location prediction.

[0007] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0008] Firstly, a method for predicting the next location in transportation trips based on multi-adaptive hypergraph collaboration is provided, including:

[0009] Interactive and directed hypergraphs are constructed based on individual travel trajectory sequences, and geographic hypergraphs are constructed based on location-specific geographic feature data.

[0010] The interaction hypergraph and geographic hypergraph are updated based on the feature similarity between each location, and a graph structure enhancement strategy is introduced during the update process. Finally, the updated adaptive interaction hypergraph and adaptive geographic hypergraph are output.

[0011] A trajectory sequence encoder is used to model individual traffic travel trajectory sequences to form an individual sequence embedding matrix;

[0012] Interactive hypergraphs and adaptive interactive hypergraphs are processed by interactive hypergraph convolutional blocks to obtain positional interactive embedding matrices and adaptive positional interactive embedding matrices, and individual interactive embedding matrices are extracted and generated based on the positional interactive embedding matrices.

[0013] Directed hypergraphs are processed using directed hypergraph convolutional blocks to obtain position-directed embedding matrices, and individual directed embedding matrices are extracted and generated based on these position-directed embedding matrices.

[0014] Geographic hypergraphs and adaptive geographic hypergraphs are processed using geographic hypergraph convolutional blocks to obtain location geographic embedding matrices and adaptive location geographic embedding matrices, and individual geographic embedding matrices are generated based on the location geographic embedding matrices.

[0015] The location interaction embedding matrix, the location directed embedding matrix, and the location geographic embedding matrix are aggregated to obtain the overall location embedding matrix. The individual sequence embedding matrix, the individual interaction embedding matrix, the individual directed embedding matrix, and the individual geographic embedding matrix are aggregated to obtain the overall individual embedding matrix.

[0016] Based on the overall location embedding matrix and the overall individual embedding matrix, the top k positions with the highest probabilities are output as the prediction results of the individual's next travel location through a normalization function.

[0017] Several alternative methods are provided below, but they are not intended as additional limitations on the overall solution above. They are merely further additions or optimizations. Provided there are no technical or logical contradictions, each alternative method can be combined individually with respect to the overall solution above, or multiple alternative methods can be combined with each other.

[0018] Preferably, the set of hyperedges in the interactive hypergraph consists of individuals, and the set of nodes in the interactive hypergraph consists of locations. Individuals are used as hyperedges to connect all locations visited by the individuals, and connection weights are assigned between individuals and locations in the interactive hypergraph based on the number of times the individuals visit the locations.

[0019] The set of hyperedges in the directed hypergraph consists of source positions, and the set of nodes in the directed hypergraph consists of target positions. The source position is used as a hyperedge to connect all target positions corresponding to the source position, and a connection weight is assigned between the source position and the target position in the directed hypergraph based on the position index interval.

[0020] The set of hyperedges and the set of nodes in the geographic hypermap are both composed of locations. Each location is the center, and adjacent locations are identified within a predefined geographic distance threshold. The center location is used as the hyperedge to connect all adjacent locations.

[0021] Preferably, the update process of the interactive hypergraph is as follows:

[0022] Construct an interaction similarity matrix based on the location interaction embedding matrix;

[0023] For each individual, extract the individuals with the highest similarity based on the interaction similarity matrix that do not belong to the current individual. The extracted location Each location is added to the current individual's individual travel trajectory sequence to obtain the travel trajectory extended sequence;

[0024] Based on the locations involved in the extended travel trajectory sequence, an interaction similarity submatrix is ​​extracted from the interaction similarity matrix, and the submatrix with the lowest similarity is identified. Each location was analyzed, and the least similar sequence in the extended travel trajectory was removed. From each location, a corrected travel trajectory sequence is obtained;

[0025] A graph structure enhancement strategy is used to randomly perturb the travel trajectory correction sequence, and the interaction hypergraph is reconstructed based on the randomly perturbated travel trajectory correction sequence, which is denoted as the adaptive interaction hypergraph.

[0026] Preferably, the update process of the geographic hypermap is as follows:

[0027] Construct a geographic similarity matrix based on the location geographic embedding matrix;

[0028] The adjustment factor is obtained by subtracting the geographical similarity matrix from a matrix in which all elements are 1.

[0029] The adjustment factor is multiplied element by element by the geographic distance matrix to obtain the perceptual distance matrix, which is composed of the geographic distances between each pair of locations.

[0030] The perception distance matrix is ​​randomly perturbed using a graph structure enhancement strategy.

[0031] Based on the perceptual distance matrix after random perturbation, neighboring locations are identified within a predefined perceptual distance threshold, with each location as the center, to obtain the location neighbor set;

[0032] A graph structure enhancement strategy is used to randomly perturb the location neighbor set, and the center position is used as a hyperedge to connect all adjacent positions in the randomly perturbated location neighbor set.

[0033] Preferably, the trajectory sequence encoder includes a time sub-encoder and a sequence sub-encoder. The step of using the trajectory sequence encoder to model individual traffic travel trajectory sequences to form an individual sequence embedding matrix includes:

[0034] The time sub-encoder uses the time2vector method to encode the time index in each individual's traffic trajectory sequence to obtain a time embedding vector. The time embedding vector is then concatenated with the learnable location embedding vector to obtain the trajectory sequence embedding matrix.

[0035] The sequence sub-encoder uses a Transformer encoder to process each trajectory sequence embedding matrix. The output of the Transformer encoder is then averaged to obtain the embeddings of each volume sequence.

[0036] The individual sequence embeddings of all individuals are aggregated to form an individual sequence embedding matrix.

[0037] Preferably, the step of extracting and generating an individual interaction embedding matrix based on the location interaction embedding matrix includes: taking all location interaction embeddings belonging to the same individual in the location interaction embedding matrix, and performing average aggregation on all location interaction embeddings of the same individual to obtain individual interaction embeddings, and aggregating the individual interaction embeddings of all individuals to form an individual interaction embedding matrix.

[0038] The step of extracting and generating an individual directed embedding matrix based on the position directed embedding matrix includes: taking all position directed embeddings belonging to the same individual in the position directed embedding matrix, and performing average aggregation on all position directed embeddings of the same individual to obtain individual directed embeddings, and aggregating the individual directed embeddings of all individuals to form an individual directed embedding matrix.

[0039] The step of extracting and generating an individual geographic embedding matrix based on the location geographic embedding matrix includes: taking all location geographic embeddings belonging to the same individual in the location geographic embedding matrix, and performing average aggregation on all location geographic embeddings of the same individual to obtain individual geographic embeddings, and aggregating the individual geographic embeddings of all individuals to form an individual geographic embedding matrix.

[0040] Preferably, during the training and updating process of the trajectory sequence encoder, interactive hypergraph convolutional block, directed hypergraph convolutional block, and geographic hypergraph convolutional block, the total loss function includes total contrastive learning loss, cross-entropy loss, and KL divergence loss.

[0041] Preferably, the total contrastive learning loss includes: the contrastive learning loss between the location interaction embedding matrix and the adaptive location interaction embedding matrix, the geographical contrastive learning loss between the location geographic embedding matrix and the adaptive location geographic embedding matrix, the contrastive-directed contrastive learning loss between the individual interaction embedding matrix and the individual directed embedding matrix, the contrastive-geographical contrastive learning loss between the individual interaction embedding matrix and the individual geographic embedding matrix, and the directed geographical contrastive learning loss between the individual directed embedding matrix and the individual geographic embedding matrix.

[0042] Preferably, the KL divergence loss includes:

[0043] Construct an interaction similarity matrix based on the location interaction embedding matrix;

[0044] Construct a directed similarity matrix based on the position-directed embedding matrix;

[0045] Construct a geographic similarity matrix based on the location geographic embedding matrix;

[0046] The KL divergence between the interaction similarity matrix and the directed similarity matrix, as well as the KL divergence between the geographic similarity matrix and the directed similarity matrix, are calculated to form the KL divergence loss.

[0047] The second aspect: provides a traffic next location prediction device based on multi-adaptive hypergraph collaboration, including a processor and a memory storing a number of computer instructions, wherein the computer instructions, when executed by the processor, implement the steps of the traffic next location prediction method based on multi-adaptive hypergraph collaboration.

[0048] The present invention proposes a method and apparatus for predicting next location of travel based on multi-adaptive hypergraph collaboration (MAHCN), which has the following advantages compared with the prior art:

[0049] (1) An Adaptive Hypergraphs Update Module (AHUM) is proposed to dynamically update the graph structures of the interaction hypergraph and the geographic hypergraph, thereby enhancing the representation of the complex dependencies between individual travel preferences and location. In this process, the graph structure solidification problem caused by static individual travel trajectories and location geographic features is gradually alleviated, enabling the model to output more diverse and convenient locations.

[0050] (2) The Perturbation-Driven Augmentation Strategy (PDAS) is integrated into AHUM. This strategy uses a hyperparameter to control the degree of perturbation, and implements the random removal and addition of hyperedges and nodes to simulate perturbed hypergraph structures, thereby enhancing the model's ability to model imperfect graph structures.

[0051] (3) A Multiple Hypergraphs Collaboration Module (MHCM) is proposed to model the impact of multidimensional factors on individual travel behavior. This module not only considers the temporal patterns in trajectory sequences, but also uses contrastive learning to achieve collaborative modeling of multiple hypergraphs, thereby providing a more comprehensive understanding of individual travel behavior patterns. Attached Figure Description

[0052] Figure 1 This is a schematic diagram illustrating the interference of fixed graph structures and data noise on store forecasts.

[0053] Figure 2 This is a flowchart of a traffic travel next location prediction method based on multi-adaptive hypergraph collaboration according to the present invention;

[0054] Figure 3 This is a flowchart of the adaptive interactive hypergraph update submodule of the present invention;

[0055] Figure 4 The figure shows the experimental results of the hypergraph construction method of the present invention.

[0056] Figure 5 This is a visualization of the t-SNE results of the location embedding in the NYC dataset of this invention. Detailed Implementation

[0057] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0058] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to limit the invention.

[0059] Example 1:

[0060] Accurate prediction of human travel patterns is crucial for many downstream applications, such as traffic management, pandemic control, and personalized service recommendations. The core task is to predict an individual's next location based on historical travel data. Existing research widely employs graph neural networks and their derived complex graph structures to characterize individual travel behavior patterns. However, these methods still face numerous challenges, such as graph structure rigidity, noise and sparsity in check-in data, and insufficient consideration of multidimensional factors influencing individual travel preferences, leading to limited predictive model performance. To address these issues, this invention proposes a method for predicting the next location of travel based on multi-adaptive hypergraph collaboration. First, a multi-type hypergraph based on an adaptive hypergraph update mechanism is constructed. By dynamically optimizing the structures of the interaction hypergraph and the geographic hypergraph, the impact of graph structure rigidity is mitigated, thereby enhancing its ability to represent the complex dependencies between individual travel preferences and location. Second, a perturbation-based graph structure enhancement strategy is introduced to learn individual travel preferences within perturbed hypergraph structures, improving the model's ability to model imperfect graph structures. Furthermore, contrastive learning is used to strengthen the collaborative relationships between multiple hypergraphs, thereby enhancing the model's multi-factor modeling capabilities.

[0061] like Figure 2The present embodiment of the traffic travel next location prediction method based on multi-adaptive hypergraph collaboration includes the following three key modules: 1) Initial Hypergraph Construction Module (IHCM): This module constructs three initial hypergraphs (interaction hypergraph, directed hypergraph, and geographic hypergraph) based on individual traffic travel trajectory and location geographic feature data to capture complex individual travel behavior patterns. 2) Adaptive Hypergraph Update Module (AHUM): This module dynamically adjusts the structure of the interaction hypergraph and geographic hypergraph, and introduces the PDAS strategy to simulate the perturbed hypergraph structure, thereby improving the prediction model's ability to model imperfect graph structures. 3) Multi-Hypergraph Collaboration Module (MHCM): This module extracts and integrates information from trajectory sequences and multiple hypergraphs, and uses a collaborative contrastive learning mechanism to enhance the model's multi-factor modeling ability. Specifically, the method of this invention includes the following steps:

[0062] Step 1: Construct an interactive hypergraph and a directed hypergraph based on individual travel trajectory sequences, and construct a geographic hypergraph based on location geographic feature data.

[0063] Individual travel trajectory sequences are spatiotemporal sequence data, mainly composed of an ordered combination of timestamps and geographic coordinates. Attributes such as travel mode and stops can also be added, representing the locations an individual has traversed from a preset time period to the current moment. Geographic feature data describes the attributes, environment, and related information of a geographic location, and can be used to integrate and generate a set of locations.

[0064] Pick and Let them represent the set of individuals and the set of locations, respectively. The total number of individuals, This represents the total number of positions. Each position... Corresponding to a spatial location in the real world, using latitude and longitude coordinates express, Represents latitude and longitude coordinates. Represents latitude and longitude coordinates. Individual. Individual travel trajectories in sequence It means that, among them Represents an individual exist Location accessed at any time , It is the length of an individual's travel trajectory sequence.

[0065] The next position prediction task aims to predict individual The k locations for the next trip can be represented by a nonlinear prediction function. As shown in formula (1).

[0066] (1)

[0067] in, It is a probability vector that records an individual The probability of visiting each location next; It is a function All parameters are included. Based on the predicted access probability, this embodiment sorts all positions in descending order and selects the top k positions to form a prediction result list.

[0068] Individual travel behavior patterns are highly complex and difficult to fully represent using a single graph structure. Therefore, this embodiment constructs an interaction hypergraph, a directed hypergraph, and a geographic hypergraph to capture the interaction relationships between individuals and locations, the directed transfer relationships between locations, and the geographic feature associations between locations, respectively.

[0069] (1) Interactive Hypergraph: Interactive Hypergraph It is constructed based on individual travel trajectory sequences, where the super-edge set Composed of individuals, a set of nodes Composed of locations, each individual is used as a hyperedge to connect all locations visited by that individual, and connection weights are assigned between individuals and locations in the interaction hypergraph based on the number of times each individual visits a location.

[0070] like Figure 2 As shown in the IHCM module, individual Location visited , and Therefore, in In the middle, super-border Connected nodes , and Furthermore, since individuals have different preferences for different locations, the degree of preference for a particular location increases with the number of times it is visited. Therefore, in the process of constructing the interactive hypergraph, this embodiment assigns different connection weights to individuals and locations, as shown in formula (2).

[0071] (2)

[0072] in, express medium-sized individuals and location Connection weights; Indicates individual travel trajectory Middle position The number of times it was accessed; Indicates individual travel trajectory Middle position The number of times it was accessed.

[0073] (2) Directed Hypergraph: Directed hypergraph based on individual travel trajectory sequences Construction. Specifically, two locations visited sequentially in an individual's travel trajectory sequence are represented as directed tuples (source location, target location). Used to characterize the directed transfer relationship between each source location and its corresponding target location. In the superedge set Composed of source locations, a set of nodes It consists of target locations, with the source location as the hyperedge connecting all target locations corresponding to the source location, and assigns connection weights between the source location and the target location in the directed hypergraph based on the location index interval.

[0074] like Figure 2 As shown in the IHCM module, individual The locations visited were... , and And individuals The locations visited were... , and Therefore, the source location Corresponding to three directed tuples: , and Therefore, in In the middle, super-border Connected nodes , and .

[0075] Considering that there is usually a stronger correlation between positions with close index intervals in the trajectory, this embodiment proposes a connection weight calculation method based on the position index interval to quantify the tightness of the directed transfer relationship, as shown in formula (3).

[0076] (3)

[0077] in, Indicates source location and target location exist Connection weights in the data; and They represent and The index value in an individual's travel trajectory sequence. If multiple identical directed tuples exist, then... The weight values ​​of the corresponding connections are accumulated.

[0078] (3) Geographic Hypermap: Geographic Hypermap Location-based geographic feature data construction, where hyperedge sets and node set All locations are determined by their positions. First, the geographic distances between all locations are calculated using the Haversine formula based on latitude and longitude, forming a geographic distance matrix. Then, centered on each location, within a predefined geographic distance threshold... The inner part identifies its adjacent positions, and uses the center position as a hyperedge to connect all adjacent positions. For example... Figure 2 As shown in the IHCM module, in In the equation (4), the center position is used as a hyperedge, connecting all its adjacent positions.

[0079] (4)

[0080] in, Indicates position and Geographical distance between them; yes The set of neighbors.

[0081] Step 2: Update the interaction hypergraph and geographic hypergraph based on the similarity between locations, and introduce graph structure enhancement strategies during the update process to finally output the updated adaptive interaction hypergraph and adaptive geographic hypergraph.

[0082] The initial interaction hypergraph and geographic hypergraph are constructed based on static individual travel trajectories and location geographic features, resulting in a rigid graph structure that struggles to capture dynamic individual travel preferences and perceived distances between locations. To address this, the AHUM module dynamically adjusts the structure of the two hypergraphs using an adaptive interaction hypergraph update submodule (AHUM-I) and an adaptive geographic hypergraph update submodule (AHUM-G), thereby enhancing the representation of the complex dependencies between individual travel preferences and locations. This allows the model to predict more diverse and convenient locations. Simultaneously, the PDAS strategy is integrated with both submodules to promote hypergraph structure optimization, resulting in an enhanced hypergraph. Figure 3 The specific process of the AHUM-I module integrating the PDAS strategy is demonstrated.

[0083] (1) Adaptive interactive hypergraph update submodule:

[0084] Existing research typically constructs a graph adjacency matrix using the similarity of embedding vectors between locations. In contrast, the AHUM-I module proposed in this embodiment directly adjusts the structure of the interactive hypergraph based on a similarity matrix formed from the interactive embeddings of locations, such as... Figure 3As shown. Specifically, the AHUM-I module first generates a location interaction embedding matrix using the interaction hypergraph convolutional blocks from the MHCM module, and then constructs an interaction similarity matrix based on the location interaction embedding matrix. The AHUM-I module uses a weighted cosine similarity function to calculate the similarity between the embedding vectors at each position, as shown in formula (5).

[0085] (5)

[0086] in, Represents the positional interaction embedding matrix; This represents a learnable weight matrix; Represents the Hadamard product. This indicates the transpose operation. Describes the Euclidean norm. This indicates that the transpose operation is performed first, and then the Euclidean norm is calculated.

[0087] Next, this module according to The values ​​are sorted. To reveal an individual's potential travel preferences, this module, based on the sorting results, extracts the most similar individuals that do not belong to the current individual from the interaction similarity matrix for each individual. The extracted location Each location is added to the current individual's travel trajectory sequence to obtain the travel trajectory extension sequence, thus achieving trajectory extension. Value and length of travel trajectory sequence Relevant, and proportional Reduce. Furthermore, since the structure of the interaction hypergraph is independent of the access time of each location, this process does not consider... The access times and their order of locations within the travel trajectory. The generation process is shown in formula (6).

[0088] (6)

[0089] in, yes The element in the array represents the position. and Interaction similarity between them; This is the lower bound of the average interaction similarity. Among them, the ones with the highest similarity but not belonging to the current individual... The location is determined by extracting individual travel trajectory sequences from the interaction similarity matrix. Each position With a sequence of travel routes that do not belong to an individual's travel trajectory Location The interaction similarity is calculated, and the average of all extracted interaction similarities is taken. As a position Extended similarity is used to calculate all sequences of traffic trajectories that do not belong to individual travel trajectories. The expanded similarity of the positions is taken, and the expanded similarity is greater than 1. And the largest One position.

[0090] Subsequently, the module from Extract each Corresponding interaction similarity submatrix This submatrix only describes middle The interaction similarity between each location. Based on the similarity submatrix, determine the location with the lowest similarity in the interaction similarity submatrix. Each location, and remove the extended sequence of travel trajectories. The one with the lowest similarity Based on the given location, a travel trajectory correction sequence is obtained, enabling the correction of individual travel trajectories and maintaining their length within a specified range. Obtain the travel trajectory correction sequence. The generation process is shown in formula (7).

[0091] (7)

[0092] in, This is the upper bound of the maximum interaction similarity. Among them, the one with the lowest similarity in the interaction similarity submatrix is ​​determined. The method for determining the location is as follows: for the extended sequence of travel trajectories Each position in Take the position in the interaction similarity submatrix. Related interaction similarity The maximum value in the sequence is used as the similarity to remove the line trajectory extension sequence. Remove those with similarity less than And the lowest One position.

[0093] Finally, based on the obtained travel trajectory correction sequence Refactoring To achieve interactive hypergraph The update is denoted as the adaptive interactive hypergraph. .

[0094] (2) Adaptive hypermap update submodule:

[0095] First, this module constructs a geographic similarity matrix based on the location geographic embedding matrix. Its construction method is similar to Similarly. Next, the module utilizes... Calculate the perceived distance between locations instead of the original geographic distance calculated by the Haversine formula.

[0096] Specifically, this module first utilizes a matrix where all elements are 1. minus This yields the inverse of the geographical similarity, with the corresponding numerical range being... Convert to This is to facilitate subsequent sensing distance calculation. Then, the module will adjust the factor. Geographic distance matrix Element-wise multiplication yields the perceptual distance matrix. Next, the module reconstructs the location based on the sensing distance matrix. Neighbor set To achieve a hypergraph Adaptive updates are performed. During this process, the adjustment factor is controlled. The impact on sensing distance, the sensing distance threshold is set to The above process is shown in formulas (8) and (9).

[0097] (8)

[0098] (9)

[0099] in, yes The element in the array represents the position. and The perceived distance between them.

[0100] (3) Perturbation-based graph structure enhancement strategy:

[0101] In real-world check-in data, noisy locations and sparse trajectories are common. To enhance the robustness of the prediction model, the PDAS strategy simulates the perturbed hypergraph structure by adding or removing hyperedges and nodes during AHUM-I and AHUM-G processes, thus constructing an enhanced adaptive hypergraph.

[0102] Specifically, in the AHUM-I module, the PDAS policy uses perturbation... Implement the addition and removal of hyperedges and nodes to enhance adaptive hypergraphs. The process is as follows Figure 3 As shown, the PDAS strategy is used to randomly perturb the travel trajectory correction sequence, and the interactive hypergraph is reconstructed based on the randomly perturbed travel trajectory correction sequence. In the AHUM-G module, the PDAS strategy is implemented by perturbing... and To enhance the adaptive hypergraph, dynamic adjustments to hyperedges and nodes are implemented. The process involves: First, randomly perturbing the sensing distance matrix using the PDAS strategy. Then, based on this perturbed matrix, identifying neighboring locations within a predefined sensing distance threshold, centered at each location, to obtain a neighborhood set. Finally, randomly perturbing the neighborhood set using the graph PDAS strategy, using the center location as a hyperedge to connect all neighboring locations within the perturbed neighborhood set. In the MHCM module, two enhanced adaptive hypergraphs are used. and As hypergraphs and By comparing the views, and then using comparative learning, the model's ability to model imperfect graph structures can be enhanced.

[0103] Individual travel behavior patterns are influenced by a variety of factors, including individual habits, geographical features, and the order of visits. In the MHCM module, a trajectory sequence encoder and a hypergraph convolutional network were designed to extract information from trajectory sequences and multiple hypergraphs, respectively. A contrastive learning framework was also constructed to enhance the model's multi-factor modeling capabilities, thereby improving the MHCM module's ability to capture the diversity and dynamic characteristics of individual travel preferences.

[0104] Step 3: Use a trajectory sequence encoder to model individual traffic travel trajectory sequences to form an individual sequence embedding matrix.

[0105] While multiple hypergraphs can effectively capture individual travel behavior patterns and geographical relationships, they fail to capture temporal patterns within trajectory sequences. To address this deficiency, this embodiment further designs a trajectory sequence encoder for modeling individual travel trajectory sequences. The time pattern is described. The encoder consists of a time sub-encoder and a sequence sub-encoder.

[0106] The time sub-encoder uses the time2vector method to... The time index is encoded. Specifically, the time... Transform into a dimension Embedded vector Embedded vectors The Middle The calculation method for each element is shown in formula (10).

[0107] (10)

[0108] in, This refers to the time2vector function; Represents the sinusoidal activation function; and are learnable parameters. The encoded temporal embedding is concatenated with the embeddings in the learnable position embedding matrix one by one, and finally forms the trajectory sequence embedding matrix .

[0109] The sequence sub - encoder is implemented based on the Transformer framework to model the temporal patterns in, as shown in formulas (11), (12) and (13).

[0110] (11)

[0111] (12)

[0112] (13)

[0113] Among them, represents the Transformer encoder, including the multi - head self - attention mechanism and the point - wise feed - forward network; and represent the input and output embedding matrices of the Transformer encoder; represents the th input feature embedding; represents the th sequence embedding; represents the th index encoding, which is used to inject the index order information in the individual traffic travel trajectory sequence into the Transformer encoder; represents the th output feature embedding; represents element - wise addition; represents the individual sequence embedding obtained after average pooling.

[0114] Finally, the sequence embeddings of all individuals are aggregated to form the individual sequence embedding matrix .

[0115] Step 4. Use the interactive hypergraph convolutional network to process the interactive hypergraph and the adaptive interactive hypergraph respectively to obtain the position interactive embedding matrix and the adaptive position interactive embedding matrix, and extract and generate the individual interactive embedding matrix based on the position interactive embedding matrix; use the directed hypergraph convolutional network to process the directed hypergraph to obtain the position directed embedding matrix, and extract and generate the individual directed embedding matrix based on the position directed embedding matrix; use the geographical hypergraph convolutional network to process the geographical hypergraph and the adaptive geographical hypergraph respectively to obtain the position geographical embedding matrix and the adaptive position geographical embedding matrix, and extract and generate the individual geographical embedding matrix.

[0116] To extract high-order information from the constructed multiple hypergraphs and obtain high-quality node representations, this embodiment uses the incidence matrix to represent a hypergraph containing nodes and hyperedges. In this embodiment, there are [[ID= twelve]] , , which are respectively , and corresponding incidence matrices, and based on this, a hypergraph convolutional network is constructed. This network consists of an interactive hypergraph convolutional block, a directed hypergraph convolutional block, and a geographical hypergraph convolutional block, and each convolutional block stacks hypergraph propagation layers. The definition of the hypergraph propagation layer is shown in formula (14).

[0117] (14)

[0118] where and respectively represent the input and output node feature matrices of the th layer; represents the non-linear activation function; represents the diagonal matrix of the node degree; represents the diagonal matrix of the hyperedge weight; represents the diagonal matrix of the hyperedge cardinality; represents the learnable convolutional parameter matrix of the th layer; represents the residual connection parameter matrix of the th layer; is the dimension of the output node feature vector of the th layer. For the adaptive hypergraph and , the element values of their incidence matrices are 0 or 1, while for the adaptive hypergraph and as well as , the elements of the incidence matrix are the connection weights between nodes and hyperedges, and their specific calculations are shown in Formulas (2) and (3).

[0119] The operations of the interactive hypergraph convolution block on the adaptive hypergraph and are shown in Formulas (15), (16), and (17).

[0120] (15)

[0121] (16)

[0122] (17)

[0123] Among them, represents the hypergraph propagation layers stacked in the interactive hypergraph convolution block; and respectively represent the position embedding matrices corresponding to the adaptive hypergraphs and , which are used as the initial node feature matrices and and input to the first hypergraph propagation layer; and represent the node feature matrices output by the last hypergraph propagation layer, which are used to update the position embedding matrices .

[0124] The method of processing the adaptive hypergraph by the directed hypergraph convolution block, and the method of processing the adaptive hypergraph , by the geographical hypergraph convolution block are similar to the method of processing the adaptive hypergraph , by the interactive hypergraph convolution block.

[0125] The updated position embedding matrices , and are respectively used to construct the interaction similarity matrix , the directed similarity matrix and the geographical similarity matrix . Among them, the calculation methods of and are similar to , as shown in Formula (5). And according to the position embedding matrices , and generate the individual interaction embedding matrix , the individual directed embedding matrix and the individual geographical embedding matrix , and the generation processes are similar, both being: taking all the position embeddings belonging to the same individual in the position embedding matrix, and performing average aggregation (adding and taking the average) on all the position embeddings of the same individual to obtain the individual embedding, and aggregating all the individual embeddings to form the individual embedding matrix.

[0126] Step 5: Aggregate the position interaction embedding matrix, the position directed embedding matrix, and the position geographical embedding matrix to obtain the position overall embedding matrix , and aggregate the individual sequence embedding matrix, the individual interaction embedding matrix, the individual directed embedding matrix, and the individual geographical embedding matrix to obtain the individual overall embedding matrix .

[0127] Step 6: According to the position overall embedding matrix and the individual overall embedding matrix, output the top k positions with the highest probability through the normalization function as the prediction result of the individual's next travel position.

[0128] This embodiment is based on contrastive learning of multi-hypergraph collaboration to implement the training and update of the trajectory sequence encoder, the interactive hypergraph convolutional network, the directed hypergraph convolutional network, and the geographical hypergraph convolutional network. The multi-hypergraph collaboration contrastive learning framework simultaneously includes the contrast between the hypergraph and its augmented hypergraph, as well as the contrast between different hypergraphs.

[0129] The contrast with the augmented hypergraph is based on the position embedding matrix, and its purpose is to learn more robust hypergraph node representations. The adaptive hypergraph and The contrastive learning loss between them is defined as shown in formula (18).

[0130] (18)

[0131] Among them, represents the position interaction embedding matrix of the adaptive hypergraph ; and respectively represent the embeddings of position in the position interaction embedding matrix and the adaptive position interaction embedding matrix to form a positive sample pair; represents the embedding of position in and form a negative sample pair; represents the cosine similarity function; is the temperature hyperparameter. The contrastive learning loss between the adaptive hypergraph and is defined as , based on the position geographical embedding matrix and an adaptive position geographical embedding matrix is calculated, and its calculation method is the same as that of similar.

[0132] Hypergraph ( , and ) The contrast optimization between them improves the multi-factor modeling ability of the model. This process is based on the individual embedding matrices , and , which are respectively generated by the embeddings at the corresponding positions in the individual travel trajectory sequences. The contrast learning losses , and are calculated between every two of the three hypergraphs, and adding the three together can obtain , as shown in Formulas (19) and (20).

[0133] (19)

[0134] (20)

[0135] where , and respectively represent the contrast learning losses between the adaptive hypergraph and , and , and ; and respectively represent the embeddings of individual u in and , and the two form a positive sample pair; represents the embedding of individual v in , and form a negative sample pair; and are calculated in a similar way to similar.

[0136] Therefore, the total contrast learning loss is obtained as shown in Formula (21).

[0137] (21)

[0138] Based on the position embedding matrices , and and the individual embedding matrices , , and , this embodiment uses an average aggregation method to obtain a position global embedding matrix and an individual global embedding matrix , as shown in formulas (22) and (23).

[0139] (22)

[0140] (23)

[0141] Next, calculate the next position prediction probability distribution of the individual , as shown in formula (24).

[0142] (24)

[0143] Among them, represents the global embedding of the individual in The prediction loss uses the cross-entropy function to measure the difference between the predicted value and the true label

[0144] (25) Among them, if the next visit of individual u is the

[0145] th position, then is equal to 1, otherwise it is equal to 0. In addition, the update of the adaptive hypergraph depends on the embedding quality of the position, which may lead to suboptimal solutions and training difficulties in the early stage. To alleviate this problem, this embodiment introduces the KL divergence loss

[0146] , and regularizes the similarity matrices and in the AHUM module, so as to optimize the update process of the hypergraph. Specifically, calculate the KL divergence between the interaction similarity matrix and the directed similarity matrix, and the KL divergence between the geographical similarity matrix and the directed similarity matrix, and form the KL divergence loss, as shown in formula (26).

[0147] (26) Among them,

[0148] calculates the KL divergence between two probability distributions; represents the distribution of the directed transfer relationship of the th position; represents the directed similarity matrix.

[0149] In summary, by combining the prediction loss , the total contrastive learning loss and the KL divergence loss , the definition of the total loss is shown in formula (27).

[0150] (27)

[0151] where , and are weight hyperparameters used to balance multiple losses; represents the regularization of all parameters.

[0152] To visually demonstrate the advantages of the method of the present invention, the following experiments are carried out:

[0153] (1) Experimental settings:

[0154] (1-1) Datasets:​​​​​​​​​​​​​​​​​​​​FPMC (Factorized Personalized Markov Chain): A hybrid method that combines matrix factorization with Markov chains to decompose individual travel preferences and model sequential behavior.

[0162] PRME (Personalized Ranking with Metric Embedding): A personalized ranking method that achieves next location prediction through metric embedding.

[0163] STGN (Spatial-Temporal Gated Network): An enhanced LSTM based on temporal gating and distance gating for capturing individuals' sequential preferences.

[0164] LSTPM (Long-Short Term Preference Modeling with Contextual Non-Local Networks and Geographically Expanded RNNs): A framework that models individuals' long-term and short-term travel preferences respectively through contextual non-local networks and geographically expanded recurrent neural networks to improve the performance of next location prediction.

[0165] STAN (Spatial-Temporal Attention Network): Adopts a two-layer attention mechanism to capture point-to-point spatio-temporal interactions and aggregate relevant locations, thereby explicitly modeling the correlation between non-adjacent locations and non-consecutive visits.

[0166] SGRec (Sequence and Graph-based Recommendation): A GNN-based method that extracts collaborative information from individual traffic travel trajectories to model multi-level sequential preference patterns.

[0167] GETNext (Graph-Enhanced Transformer for Next POI Recommendation): A graph-enhanced Transformer model that uses collaborative signals in the global trajectory flow graph to predict individuals' future movements.

[0168] HCCF (Hypergraph-based Collaborative Filtering with Contrastive Learning): A self-supervised collaborative filtering method that effectively combines hypergraph structures with contrastive learning to capture both local and global collaborative relationships.

[0169] DisenPOI (Disentangled Dual-Graph Framework for POI Recommendation): A disentangled dual-graph framework combined with contrastive learning that can learn interpretable representations from sequence graphs and geographical graphs respectively.

[0170] AGRAN (Adaptive Graph Representation Learning for Dynamic PreferenceModeling): By learning the dynamic similarity features between different location embedding vectors to adaptively adjust the graph structure, it can accurately capture the dynamic individual travel preferences.

[0171] STHGCN (Spatial-Temporal Hypergraph Convolutional Network): A hypergraph-based Transformer model that can capture the high-order collaborative relationships between the target individual's traffic travel trajectory and those of other different individuals to alleviate the cold start problem.

[0172] DCHL (Decoupled Contrastive Learning on Hypergraph for POIRecommendation): A contrastive learning method based on hypergraph decoupling that effectively alleviates the problem of individual representation entanglement and improves the modeling ability of complementary recommendation effects.

[0173] To achieve a fair comparison with methods that do not utilize category information, this embodiment removes the modules related to category information in SGRec, GETNext, and STHGCN.

[0174] (1-3) Evaluation metrics:

[0175] This embodiment uses two evaluation metrics: Recall@k and NDCG@k (Normalized Discounted Cumulative Gain) to evaluate the prediction performance of the proposed MAHCN and baseline methods. Among them, Recall@k measures whether the first k positions in the prediction result list contain the true label of the individual; NDCG@k evaluates the sorting accuracy of the prediction results, and k takes values of 5 and 10. Both metrics are positive metrics, and the larger the value, the better the model performance.

[0176] (1-4) Experimental settings:

[0177] The proposed MAHCN in this embodiment is implemented based on the PyTorch framework, and all experiments are completed on a server equipped with NVIDIA Tesla A800 GPUs and Intel Xeon Platinum 8358 CPUs @ 2.60GHz. The main hyperparameters and training configurations are as follows:

[0178] Dimensions of location and individual embeddings are 128, and the dimension of time embedding is 64. The number of hypergraph propagation layers in the hypergraph convolution block is 3, and the temperature hyperparameter is 0.3. The configuration of the Transformer encoder is 2 layers, and the number of attention heads is 4. The predefined thresholds 、 and are 2.5, 0.1, and 0.0 respectively. The model uses the Adam optimizer for gradient optimization, and the learning rate and the decay rate of the learning rate are set to and . The batch size is 128, the maximum number of training epochs is 100, the patience for early stopping is 10, and the minimum number of epochs is 50.

[0179] (2) Comparative experiments:

[0180] Table 2 shows the comparative experiment results of MAHCN and baseline methods. Among them, the metrics (Recall and NDCG) are represented by their first letters.

[0181] Table 2 Comparative experiment results on three datasets

[0182]

[0183] Based on the experimental results in Table 2, the following conclusions can be drawn:

[0184] (1) Among all the baseline methods, graph-based methods (SGRec, GETNext, HCCF, DisenPOI, AGRAN, STHGCN, DCHL) are all superior to sequence-based methods (FPMC, PRME, STGN, LSTPM, STAN). The reason is that graph-based methods can fully utilize the correlation of access locations between different individuals, thus capturing the collaborative relationship between individuals from a global perspective.

[0185] [[ID=]](2) On the three datasets, the proposed MAHCN is superior to all baseline methods, indicating its outstanding overall prediction performance and good effectiveness and robustness.

[0186] (3) STAN with self-attention mechanism is significantly better than other sequence-based methods, indicating that compared with sequence models such as RNN, the self-attention mechanism can more effectively model individual traffic travel trajectory sequences.

[0187] (4) Compared with other graph-based methods, the hypergraph-based methods (HCCF, STHGCN, DCHL) have better overall prediction performance, indicating that the hypergraph structure is more helpful for capturing high-order collaborative information between individual traffic travel trajectories.

[0188] [[ID=z6]](5) Compared with other graph-based methods (excluding hypergraph-based methods), AGRAN using only a single graph structure has better prediction performance, indicating that through GSL, the topological structure of the graph is optimized, thereby enhancing its node representation ability.

[0189] (6) Compared with the NYC dataset, the improvement in the prediction performance of MAHCN on the TKY and CA datasets is slightly lower. This shows that on datasets with a relatively small data scale such as NYC, the adaptive hypergraph constructed in this invention has a better graph structure and can better model the travel behavior patterns of individuals.

[0190] (3) Ablation experiment:

[0191] To evaluate the contribution of each module of the model to the overall prediction performance, this experiment conducted ablation experiments on several variants of MAHCN on different datasets, and the results are shown in Table 3. The specific variant model designs are as follows:

[0192] w / o AHUM-I: This variant model removes the AHUM-I module.

[0193] w / o AHUM-G: This variant model removes the AHUM-G module.

[0194] w / o PDAS: This variant model removes the PDAS strategy.

[0195] w / o MHCM-CL: This variant model removes the contrastive learning framework in the AHUM module.

[0196] Table 3 Ablation experiment results of different variant models of MAHCN

[0197]

[0198] Based on the experimental results in Table 3, this experiment draws the following conclusions:

[0199] (1) The prediction performance of the variant models w / o AHUM-I and w / o AHUM-G is weaker than that of MAHCN, indicating that the adaptive update of the hypergraph optimizes and [[ID=z2]] structure and enhanced its node representation ability. In addition, on the TKY and CA datasets, the performance of the variant models w / o AHUM-I and w / o AHUM-G decreased more significantly, indicating that as the scale of the graph increases, the weakening effect of graph structure solidification on node representation ability becomes more prominent.

[0200] (2) The prediction performance of the variant model w / o PDAS is weaker than that of MAHCN, indicating that the PDAS strategy can effectively simulate hypergraph structure perturbations and significantly improve the robustness of the model in scenarios where check-in data is generally noisy and sparse.

[0201] (3) The prediction performance of the variant w / o MHCM-CL is weaker than that of MAHCN, indicating that by integrating the interaction relationship between individuals and locations, the directed transfer relationship between locations, and the geographical feature association relationship of locations, the contrastive learning framework can effectively promote the collaboration between hypergraphs, thereby enhancing the multi-factor modeling ability of the model. In addition, compared with the other two datasets, the performance of this variant decreased more significantly on the TKY dataset because the average number of visits to each location in the TKY dataset is higher and the relationship between locations and individuals is more complex. In this case, hypergraph collaboration is particularly important for comprehensively understanding the travel behavior patterns of individuals.

[0202] (4) Analysis experiments on hypergraph construction and update

[0203] To evaluate the effectiveness of the proposed hypergraph construction method, this experiment is designed as follows: Remove the connection weights in the interaction hypergraph and the directed hypergraph, and construct geographical hypergraphs by setting different geographical distance thresholds , respectively. The experimental results are as Figure 4 shown.

[0204] As Figure 4 shown in the first and second columns of, the weights based on the number of visits enable the interaction hypergraph to accurately depict the preference characteristics of individuals for specific locations, while the weights based on the location index interval effectively quantify the directed transfer relationship between locations in the directed hypergraph. The results show that both weighting methods can construct more effective hypergraphs, thereby enhancing the overall prediction performance of MAHCN. As Figure 4 shown in the third column of, the influence of different values on the model performance can be ignored, indicating that the proposed AHUM-G module is insensitive to fluctuations in the geographical distance threshold and has strong robustness.

[0205] In addition, to further analyze the impact of the hypergraph update method on the hypergraph structure, this experiment used t-SNE to visualize the feature embeddings of all locations in the NYC dataset, as Figure 5As shown. Compared with the fixed hypergraph structure, the overall embedding distribution of the positions generated by the adaptive hypergraph structure is more uniform, indicating that the hypergraph update method can effectively optimize the graph structure, thus generating node representations with higher quality.

[0206] The comparative experimental results on three real check-in datasets show that the proposed MAHCN in this invention shows higher accuracy and stronger robustness in the next location prediction task compared with the existing advanced baseline methods, and has superior next location prediction performance.

[0207] Embodiment 2:

[0208] This embodiment provides a traffic travel next location prediction device based on multi-adaptive hypergraph collaboration, including a processor and a memory storing a number of computer instructions. When the computer instructions are executed by the processor, the steps of the traffic travel next location prediction method based on multi-adaptive hypergraph collaboration are implemented.

[0209] For the specific limitations of the traffic travel next location prediction device based on multi-adaptive hypergraph collaboration, reference can be made to the limitations of the traffic travel next location prediction method based on multi-adaptive hypergraph collaboration in the above text, which will not be elaborated here.

[0210] The memory and the processor are directly or indirectly electrically connected to achieve data transmission or interaction. For example, these components can be electrically connected to each other through one or more communication buses or signal lines. The memory stores a computer program that can run on the processor, and the processor realizes the method of this invention by running the computer program stored in the memory.

[0211] Among them, the memory can be, but is not limited to, a random access memory (RAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), etc. The memory is used to store the program, and the processor executes the program after receiving the execution instruction. [[ID=,19]]

[0212] The processor may be an integrated circuit chip with the ability to process data. The above-mentioned processor may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0213] The technical features of the above-mentioned embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0214] The above-mentioned embodiments only represent several implementation manners of the present invention. The description is relatively specific and detailed, but it cannot be understood as a limitation on the scope of the invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the appended claims.

Claims

1. A method for predicting the next location of travel based on multi-adaptive hypergraph collaboration, characterized in that, include: Interactive and directed hypergraphs are constructed based on individual travel trajectory sequences, and geographic hypergraphs are constructed based on location-specific geographic feature data. The set of hyperedges in the interactive hypergraph consists of individuals, and the set of nodes in the interactive hypergraph consists of locations. Individuals are used as hyperedges to connect all locations visited by an individual, and connection weights are assigned between individuals and locations in the interactive hypergraph based on the number of times an individual visits a location. The set of hyperedges in the directed hypergraph consists of source locations, and the set of nodes in the directed hypergraph consists of target locations. Source locations are used as hyperedges to connect all target locations corresponding to the source locations, and connection weights are assigned between source locations and target locations in the directed hypergraph based on location index intervals. The set of hyperedges and the set of nodes in the geographic hypermap are both composed of locations. Each location is used as the center, and adjacent locations are identified within a predefined geographic distance threshold. The center location is used as the hyperedge to connect all adjacent locations. The interaction hypergraph and geographic hypergraph are updated based on the feature similarity between each location, and a graph structure enhancement strategy is introduced during the update process. Finally, the updated adaptive interaction hypergraph and adaptive geographic hypergraph are output. A trajectory sequence encoder is used to model individual traffic travel trajectory sequences to form an individual sequence embedding matrix; Interactive hypergraphs and adaptive interactive hypergraphs are processed by interactive hypergraph convolutional blocks to obtain positional interactive embedding matrices and adaptive positional interactive embedding matrices, and individual interactive embedding matrices are extracted and generated based on the positional interactive embedding matrices. Directed hypergraphs are processed using directed hypergraph convolutional blocks to obtain position-directed embedding matrices, and individual directed embedding matrices are extracted and generated based on these position-directed embedding matrices. Geographic hypergraphs and adaptive geographic hypergraphs are processed using geographic hypergraph convolutional blocks to obtain location geographic embedding matrices and adaptive location geographic embedding matrices, and individual geographic embedding matrices are generated based on the location geographic embedding matrices. The location interaction embedding matrix, the location directed embedding matrix, and the location geographic embedding matrix are aggregated to obtain the overall location embedding matrix. The individual sequence embedding matrix, the individual interaction embedding matrix, the individual directed embedding matrix, and the individual geographic embedding matrix are aggregated to obtain the overall individual embedding matrix. Based on the overall location embedding matrix and the overall individual embedding matrix, the top k positions with the highest probabilities are output as the prediction results of the individual's next travel location through a normalization function.

2. The next location prediction method for transportation trips based on multi-adaptive hypergraph collaboration according to claim 1, characterized in that, The update process of the interactive hypergraph is as follows: Construct an interaction similarity matrix based on the location interaction embedding matrix; For each individual, extract the individuals with the highest similarity based on the interaction similarity matrix that do not belong to the current individual. The extracted location Each location is added to the current individual's individual travel trajectory sequence to obtain the travel trajectory extended sequence; Based on the locations involved in the extended travel trajectory sequence, an interaction similarity submatrix is ​​extracted from the interaction similarity matrix, and the submatrix with the lowest similarity is identified. Each location was analyzed, and the least similar sequence in the extended travel trajectory was removed. From each location, a corrected travel trajectory sequence is obtained; A graph structure enhancement strategy is used to randomly perturb the travel trajectory correction sequence, and the interaction hypergraph is reconstructed based on the randomly perturbated travel trajectory correction sequence, which is denoted as the adaptive interaction hypergraph.

3. The next location prediction method for traffic travel based on multi-adaptive hypergraph collaboration according to claim 1, characterized in that, The update process of the hypermap is as follows: Construct a geographic similarity matrix based on the location geographic embedding matrix; The adjustment factor is obtained by subtracting the geographical similarity matrix from a matrix in which all elements are 1. The adjustment factor is multiplied element by element by the geographic distance matrix to obtain the perceptual distance matrix, which is composed of the geographic distances between each pair of locations. The perception distance matrix is ​​randomly perturbed using a graph structure enhancement strategy. Based on the perceptual distance matrix after random perturbation, neighboring locations are identified within a predefined perceptual distance threshold, with each location as the center, to obtain the location neighbor set; A graph structure enhancement strategy is used to randomly perturb the location neighbor set, and the center position is used as a hyperedge to connect all adjacent positions in the randomly perturbated location neighbor set.

4. The next location prediction method for traffic travel based on multi-adaptive hypergraph collaboration according to claim 1, characterized in that, The trajectory sequence encoder includes a time sub-encoder and a sequence sub-encoder. The process of using the trajectory sequence encoder to model individual traffic travel trajectory sequences to form an individual sequence embedding matrix includes: The time sub-encoder uses the time2vector method to encode the time index in each individual's traffic trajectory sequence to obtain a time embedding vector. The time embedding vector is then concatenated with the learnable location embedding vector to obtain the trajectory sequence embedding matrix. The sequence sub-encoder uses a Transformer encoder to process each trajectory sequence embedding matrix. The output of the Transformer encoder is then averaged to obtain the embeddings of each volume sequence. The individual sequence embeddings of all individuals are aggregated to form an individual sequence embedding matrix.

5. The next location prediction method for traffic travel based on multi-adaptive hypergraph collaboration according to claim 1, characterized in that, The step of extracting and generating an individual interaction embedding matrix based on the location interaction embedding matrix includes: taking all location interaction embeddings belonging to the same individual in the location interaction embedding matrix, and performing average aggregation on all location interaction embeddings of the same individual to obtain individual interaction embeddings, and aggregating the individual interaction embeddings of all individuals to form an individual interaction embedding matrix. The step of extracting and generating an individual directed embedding matrix based on the position directed embedding matrix includes: taking all position directed embeddings belonging to the same individual in the position directed embedding matrix, and performing average aggregation on all position directed embeddings of the same individual to obtain individual directed embeddings, and aggregating the individual directed embeddings of all individuals to form an individual directed embedding matrix. The step of extracting and generating an individual geographic embedding matrix based on the location geographic embedding matrix includes: taking all location geographic embeddings belonging to the same individual in the location geographic embedding matrix, and performing average aggregation on all location geographic embeddings of the same individual to obtain individual geographic embeddings, and aggregating the individual geographic embeddings of all individuals to form an individual geographic embedding matrix.

6. The next location prediction method for traffic travel based on multi-adaptive hypergraph collaboration according to claim 1, characterized in that, During the training and update process of the trajectory sequence encoder, interactive hypergraph convolutional block, directed hypergraph convolutional block, and geographic hypergraph convolutional block, the total loss function includes total contrastive learning loss, cross-entropy loss, and KL divergence loss.

7. The next location prediction method for transportation trips based on multi-adaptive hypergraph collaboration according to claim 6, characterized in that, The total contrastive learning loss includes: the contrastive learning loss between the location interaction embedding matrix and the adaptive location interaction embedding matrix, the geographic contrastive learning loss between the location geographic embedding matrix and the adaptive location geographic embedding matrix, the contrastive-directed contrastive learning loss between the individual interaction embedding matrix and the individual directed embedding matrix, the contrastive-geographical contrastive learning loss between the individual interaction embedding matrix and the individual geographic embedding matrix, and the contrastive-geographical contrastive learning loss between the individual directed embedding matrix and the individual geographic embedding matrix.

8. The next location prediction method for traffic travel based on multi-adaptive hypergraph collaboration according to claim 6, characterized in that, The KL divergence loss includes: Construct an interaction similarity matrix based on the location interaction embedding matrix; Construct a directed similarity matrix based on the position-directed embedding matrix; Construct a geographic similarity matrix based on the location geographic embedding matrix; The KL divergence between the interaction similarity matrix and the directed similarity matrix, as well as the KL divergence between the geographic similarity matrix and the directed similarity matrix, are calculated to form the KL divergence loss.

9. A traffic travel next-location prediction device based on multi-adaptive hypergraph collaboration, comprising a processor and a memory storing a plurality of computer instructions, characterized in that, When the computer instructions are executed by the processor, they implement the steps of the next location prediction method for transportation based on multi-adaptive hypergraph collaboration as described in any one of claims 1 to 8.

Images