Method, system, medium and device for accessibility assessment based on traffic travel willingness

Abstract

The application discloses a kind of reachability evaluation method, system, medium, equipment based on traffic travel willingness, and the present method is based on real travel willingness data, identifies the crowd of actual use facility, makes evaluation result more close to reality.Constructed the associated dataset of travel willingness and facility use, the mapping relationship between travel demand and facility supply is established, which provides data basis for subsequent multidimensional analysis.The calculation of personalized travel time fully considers the actual travel mode of each travel record, rather than uniformly adopting a certain preset mode, so that the reachability calculation is more in line with the real travel behavior of individuals.Meanwhile, the actual service travel total and theoretical service range are calculated, and evaluation indexes are generated based on the comparison between the two, revealing the difference between the actual service efficiency and theoretical reachability of the facility, and providing quantitative basis for identifying facility use problems.

Description

Technical Field

[0001] This invention relates to the field of urban transportation planning technology, and in particular to methods, systems, media, and equipment for accessibility assessment based on travel intentions. Background Technology

[0002] Accessibility assessment is a crucial tool in transportation planning, urban public service facility allocation, and land use planning. Traditional accessibility assessment methods are mainly divided into three categories: accessibility indicators, threshold indicators, and continuity indicators.

[0003] Accessibility metrics are typically used to measure the proportion of the population that can reach a certain type of facility within a certain time frame, such as "the proportion of the population that can reach a bus stop within a ten-minute walk"; threshold metrics are used to assess the population size that can reach key areas such as employment centers within a specific travel time, such as "the proportion of workers that can reach a major employment center within a 45-minute drive"; continuity metrics focus on the time required to complete a specific journey under a specific mode of transportation.

[0004] However, the aforementioned traditional assessment methods mainly focus on the supply-side characteristics of the transportation system, such as departure frequency, route length, and number of vehicles, making it difficult to answer the fundamental question of the extent to which the transportation system meets people's daily travel needs.

[0005] Specifically, existing accessibility metrics and thresholds reflect the population size covered by a facility, not the population size actually using it. For example, a subway station within a 10-minute walk may cover a large population, but most of them may not actually use the station; those who do use it may be within a 15-minute walk. Therefore, traditional accessibility calculation methods fail to reflect the actual accessibility of facilities for users and cannot identify existing accessibility problems, making it difficult to propose effective improvement measures. Similar issues exist in the accessibility analysis of public service facilities such as education and healthcare, as well as employment opportunities. Summary of the Invention

[0006] In order to overcome the shortcomings of existing technologies, which are unable to reflect the accessibility of facilities to the actual population using them and the actual problems in accessibility, thus making it difficult to propose effective improvement measures.

[0007] In a first aspect, the present invention provides an accessibility assessment method based on travel intention, comprising the following steps: Acquire facility data, multimodal transportation network data, and residents' travel intention data for the target area; the residents' travel intention data includes multiple travel records, each including the origin, purpose, destination, and mode of travel. The travel purpose is matched with facility data to establish a correspondence between travel purpose and facility type. Based on the destination of each travel record, the actual facility instance used in the travel record is identified, and a dataset relating travel intention and facility use is constructed. Based on the associated dataset, the multimodal transportation network data, and the travel mode of each travel record, the travel time from the origin of each travel record to its corresponding facility instance, matching the travel mode, is calculated; based on the travel time, the total number of trips actually served by each facility instance within a preset time threshold is calculated, and the theoretical service range of each facility instance based on the multimodal transportation network within the preset time threshold is calculated. Based on the comparison between the total number of trips actually served and the theoretical service range, an accessibility assessment index is generated.

[0008] Optionally, matching travel destinations with facility data includes the following steps: Perform semantic analysis on the stated travel purpose to extract destination keywords; Semantic analysis is performed on the facility names and facility categories in the facility data to extract facility keywords; Calculate the semantic similarity between the destination keyword and the facility keyword. When the similarity exceeds a preset threshold, establish a correspondence between the travel destination and the facility type.

[0009] Optionally, identifying the actual facility instance used by each travel record based on its destination location includes the following steps: Spatial matching is performed between the destination coordinates of each travel record and the geographical coordinates of each facility in the facility data; When the distance between the destination coordinates and the coordinates of a facility is less than a preset distance threshold, it is determined that the travel record actually uses the facility as a facility instance.

[0010] Optionally, calculating the total number of trips actually served by each facility instance within a preset time threshold includes the following steps: Based on the travel time matching the travel mode for each travel record in the associated dataset, travel records with travel times less than a preset time threshold are filtered out. The filtered travel records are counted by facility instance to obtain the total number of trips actually served by each facility instance; The total number of trips is aggregated according to facility type, travel purpose, or travel mode to generate categorized total number of trips.

[0011] Optionally, generating the reachability assessment metric includes the following steps: The analysis combines the origin of the actual total number of trips served with the theoretical service range. Identify a first group of people and a second group of people. The first group of people are those whose travel origin is outside the theoretical service area and who actually use the facility. The second group of people are those whose travel origin is within the theoretical service area and who have no travel records matching the facility in the associated dataset. Based on the travel records of the first group of people in the associated dataset, a statistical index of intention-driven travel proportion is calculated; based on the spatial distribution of the second group of people, a supply mismatch index is calculated.

[0012] Optionally, the theoretical service range is calculated based on a time impedance model of a multimodal transportation network, which dynamically adjusts the travel time of various modes of transportation according to different travel periods.

[0013] Optionally, the multimodal transportation network data includes pedestrian networks, cycling networks, driving networks, and public transportation networks.

[0014] Secondly, the present invention provides an accessibility assessment system based on travel intention, comprising: The data acquisition module is used to acquire facility data, multimodal transportation network data, and residents' travel intention data for the target area; the residents' travel intention data includes multiple travel records, and the travel records include the origin, purpose, and mode of travel. The association construction module is used to match the travel purpose with facility data, establish the correspondence between travel purpose and facility type, and identify the actual facility instance used by each travel record based on the destination location of the travel record, and construct an association dataset of travel intention and facility use; The calculation module is used to calculate the travel time from the origin of each travel record to its corresponding facility instance, matching the travel mode, based on the multi-modal transportation network data and the travel mode of each travel record; and to calculate the total number of actual trips served by each facility instance within a preset time threshold based on the travel time, and to calculate the theoretical service range of each facility instance based on the multi-modal transportation network within the preset time threshold. The evaluation module is used to generate accessibility evaluation indicators based on the comparison between the total number of trips actually served and the theoretical service range.

[0015] Thirdly, a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the method described in the first aspect.

[0016] Fourthly, an electronic device includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus. Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the steps of the method according to any one of claims 1-7.

[0017] The beneficial effects of this invention are: it realizes the transformation from "the population covered by the facility" to "the population actually using the facility." Traditional methods only calculate the population size within a certain range around the facility, assuming that everyone will use the facility; while this method, based on real travel intention data, identifies the people who actually use the facility, making the assessment results closer to reality. A dataset linking travel intention and facility usage is constructed, establishing a mapping relationship between travel demand and facility supply, providing a data foundation for subsequent multi-dimensional analysis. The calculation of personalized travel time fully considers the actual travel mode of each travel record, rather than uniformly adopting a certain preset method, making accessibility calculation more consistent with individual real travel behavior. Simultaneously, it calculates the actual total number of service trips and the theoretical service range, and generates evaluation indicators based on the comparison of the two, revealing the difference between the actual service efficiency and theoretical accessibility of the facility, providing a quantitative basis for identifying facility usage problems. Attached Figure Description

[0018] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0019] Figure 1 This is a flowchart of the present invention; Figure 2 This is another flowchart of the present invention. Detailed Implementation

[0020] The following will clearly and completely describe the concept, specific structure, and technical effects of the present invention in conjunction with embodiments and accompanying drawings, so as to fully understand the purpose, features, and effects of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, not all of them. Other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are all within the scope of protection of the present invention. Furthermore, all connections / linkages involved in the patent do not simply refer to direct contact between components, but rather to the ability to form a better connection structure by adding or reducing connecting accessories according to specific implementation conditions. The various technical features in this invention can be combined interactively without contradicting each other.

[0021] This invention provides a method for accessibility assessment based on travel intention, comprising the following steps: S1. Obtain facility data, multimodal transportation network data, and residents' travel intention data for the target area; the residents' travel intention data includes multiple travel records, and the travel records include the origin, purpose, destination, and mode of travel; S2. Match the travel purpose with the facility data to establish a correspondence between travel purpose and facility type, and identify the actual facility instance used by the travel record based on the destination of each travel record to construct a dataset of association between travel intention and facility use; S3. Based on the associated dataset, the multimodal transportation network data, and the travel mode of each travel record, calculate the travel time from the travel origin of each travel record to its corresponding facility instance that matches the travel mode; based on the travel time, calculate the total number of trips actually served by each facility instance within a preset time threshold, and calculate the theoretical service range of each facility instance based on the multimodal transportation network within the preset time threshold. S4. Based on the comparison between the total number of trips actually served and the theoretical service range, generate an accessibility assessment index.

[0022] Specifically, first, three types of basic data are obtained: facility data (such as location information of schools, hospitals, subway stations, etc.), multi-modal transportation network data (road network information such as walking, cycling, driving, and public transportation), and residents' travel intention data (including multiple real travel records, each of which records the origin, destination, purpose, and mode of travel).

[0023] Secondly, the travel purpose is matched with the facility type to establish a correspondence; simultaneously, based on the destination coordinates of each travel record, the actual facility instance visited by that travel record is identified, thus constructing an associated dataset. This dataset links each travel record with the actual facility instance used and the matching relationship between travel purpose and facility type, forming a mapping between travel intention and facility usage.

[0024] Then, based on this associated dataset, combined with multimodal transportation network data and the travel mode recorded in each travel record, a personalized travel time matching the travel mode is calculated for each travel record from its origin to its corresponding facility instance.

[0025] Next, based on the calculated travel time, the total number of trips actually served by each facility instance within a preset time threshold (such as 15 minutes or 30 minutes) is counted; at the same time, based on the same multimodal transportation network, the theoretical service range of each facility instance within the same time threshold (i.e. the area that can be reached from the facility within the time threshold) is calculated.

[0026] Finally, the actual total number of trips served is compared with the theoretical service range to generate accessibility assessment indicators, which reflect the relationship between the actual use of facilities and their theoretical accessibility.

[0027] This application represents a shift from "the population covered by the facility" to "the population actually using the facility." Traditional methods only calculate the population size within a certain radius of the facility, assuming everyone will use it; while this method identifies the actual users of the facility based on real travel intention data, making the assessment results closer to reality. A dataset linking travel intention and facility usage was constructed, establishing a mapping relationship between travel demand and facility supply, providing a data foundation for subsequent multi-dimensional analysis. The calculation of personalized travel time fully considers the actual travel mode of each travel record, rather than uniformly adopting a certain preset method, making accessibility calculation more consistent with individual travel behavior. Simultaneously, the total actual service trips and theoretical service range are calculated, and evaluation indicators are generated based on the comparison between the two, revealing the difference between the actual service effectiveness and theoretical accessibility of the facility, providing a quantitative basis for identifying facility usage problems.

[0028] In some embodiments, matching travel purpose with facility data includes the following steps: Perform semantic analysis on the stated travel purpose to extract destination keywords; Semantic analysis is performed on the facility names and facility categories in the facility data to extract facility keywords; Calculate the semantic similarity between the destination keyword and the facility keyword. When the similarity exceeds a preset threshold, establish a correspondence between the travel destination and the facility type.

[0029] Specifically, firstly, semantic analysis is performed on the purpose of each trip in the associated dataset to extract core keywords that represent that purpose of the trip. For example, keywords such as "school" and "pick up children" are extracted from "go to school to pick up children".

[0030] Secondly, semantic analysis is performed on the facility names and categories of each facility in the facility data, and core keywords that can represent the characteristics of the facility are extracted. For example, keywords such as "primary school" and "school" are extracted from the categories "Peking University Affiliated Primary School" and "primary school".

[0031] Then, the semantic similarity between the destination keywords extracted from the travel purpose and the facility keywords extracted from each facility is calculated. Semantic similarity calculation can employ methods such as word vector models, semantic dictionaries, or deep learning to quantify the closeness of the two sets of keywords in the semantic space.

[0032] The target keywords and facility keywords are mapped to vectors using a word vector model, and the cosine similarity between them is calculated. The formula for calculating the cosine similarity is as follows: Similarity = cos(θ) = (A·B) / (||A|| ||B||) = (∑A_i B_i) / (√∑A_i² ×√∑B_i²) Where A is the vector representation of the target keyword, A = [A1, A2, ..., A n ], where B is the vector representation of the facility keywords, B = [B1, B2, ..., B n ], where n is the vector dimension, A_i is the i-th component of vector A, B_i is the i-th component of vector B, ||A|| is the magnitude of vector A, ||B|| is the magnitude of vector B, and the cosine similarity ranges from [-1, 1]. The larger the value, the higher the semantic similarity between the two vectors. When the cosine similarity exceeds a preset similarity threshold, a correspondence is established between the travel purpose and the facility type. The preset similarity threshold is selected from at least one of 0.6, 0.7, or 0.8.

[0033] Finally, when the calculated semantic similarity exceeds a preset threshold, the travel purpose is considered to be highly semantically related to the facility, thus establishing a correspondence between the travel purpose and the facility type. For example, the travel purpose of "going to school" is associated with facility types such as "primary school" and "middle school".

[0034] By employing semantic analysis technology, intelligent matching of travel purpose and facility type is achieved, solving the matching challenge between the diversity of travel purpose expressions and the standardization of facility classification in travel survey data. Semantic similarity calculation can handle linguistic phenomena such as synonyms, near-synonyms, and hyponyms; for example, it can correctly match different expressions such as "seeking medical treatment," "receiving medical care," and "treatment" with the facility type "hospital," improving the accuracy and robustness of the matching. A preset threshold mechanism provides adjustable matching strictness, allowing for adjustments to the accuracy requirements of matching according to different application scenarios, enhancing the method's flexibility and adaptability.

[0035] In some embodiments, identifying instances of facilities actually used by each travel record based on its destination location includes the following steps: Spatial matching is performed between the destination coordinates of each travel record and the geographical coordinates of each facility in the facility data; When the distance between the destination coordinates and the coordinates of a facility is less than a preset distance threshold, it is determined that the travel record actually uses the facility as a facility instance.

[0036] Specifically, firstly, for each travel record, the coordinates of its destination are obtained, and then the spatial distance between the destination and the geographical coordinates of all facilities in the facility data is calculated to achieve spatial matching.

[0037] Secondly, a preset distance threshold (such as 50 meters or 100 meters) is set. When the distance between the destination coordinates of a travel record and the coordinates of a facility is less than the threshold, it is determined that the travel record actually used the facility, and the facility is taken as the facility instance corresponding to the travel record.

[0038] By using spatial matching methods, abstract travel records are associated with specific facility instances, achieving a precise match between travel demand and facility supply. The preset distance threshold takes into account the reasonable walking distance between the destination and the facility entrance in actual travel, avoiding misjudgments caused by POI coordinate positioning deviations or facility entrance location offsets.

[0039] Furthermore, for travel records where a corresponding facility cannot be found through direct spatial matching (e.g., the destination is located inside a large shopping mall, while the mall's POI is located in the center of the building, which is relatively far away), an indirect matching method is used: based on the facility type corresponding to the travel destination, all facilities of that type are filtered from the facility data, and then the distance between the destination coordinates and these facilities is calculated. The closest facility is identified as the actual facility instance used by the travel record. For cases where direct matching is not possible, a "nearest facility" principle is used for remedial matching, maximizing the use of travel data, reducing data loss, and ensuring the rationality of the matching by filtering based on the facility type corresponding to the travel destination.

[0040] In some embodiments, calculating the total number of trips actually served by each facility instance within a preset time threshold includes the following steps: Based on the travel time matching the travel mode for each travel record in the associated dataset, travel records with travel times less than a preset time threshold are filtered out. The filtered travel records are counted by facility instance to obtain the total number of trips actually served by each facility instance; The total number of trips is aggregated according to facility type, travel purpose, or travel mode to generate categorized total number of trips.

[0041] First, calculate the travel time for each travel record and set a preset time threshold (e.g., 15 minutes, 30 minutes, 45 minutes). Then, filter out all travel records from the associated dataset whose travel time is less than this threshold; these records represent actual trips that occurred within an acceptable time range.

[0042] Secondly, the filtered travel records are grouped and counted by facility instance, that is, the number of travel records associated with each facility instance and whose travel time is less than the threshold is counted to obtain the total number of travels actually served by each facility instance within the time threshold.

[0043] Finally, based on the analysis requirements, the total number of trips mentioned above is aggregated in multiple dimensions: it can be aggregated by facility category (such as the total number of trips for all primary schools, the total number of trips for all hospitals), by trip purpose (such as the total number of commuting trips, the total number of medical trips), or by travel mode (such as the total number of walking trips, the total number of public transport trips), generating categorized total number of trips for analysis in different dimensions.

[0044] By filtering through time thresholds, the system focuses on actual trips within acceptable travel time ranges, making the assessment results more consistent with people's actual tolerance for travel time. Statistics on total trips by facility instance accurately reflect the service load of each specific facility, identifying facilities with excessive service pressure or underutilization. Multi-dimensional aggregation provides flexible analytical perspectives: aggregation by facility category can be used for overall industry assessment, aggregation by travel purpose can be used for travel demand analysis, and aggregation by travel mode can be used for modal share assessment, meeting the needs of different application scenarios.

[0045] In some embodiments, generating accessibility assessment metrics includes the following steps: The analysis combines the origin of the actual total number of trips served with the theoretical service range. Identify a first group of people and a second group of people. The first group of people are those whose travel origin is outside the theoretical service area and who actually use the facility. The second group of people are those whose travel origin is within the theoretical service area and who have no travel records matching the facility in the associated dataset. Based on the travel records of the first group of people in the associated dataset, a statistical index of intention-driven travel proportion is calculated; based on the spatial distribution of the second group of people, a supply mismatch index is calculated.

[0046] First, obtain the locations of all originating points corresponding to the total actual number of trips served, as well as the theoretical service range of each facility instance calculated, and then perform spatial overlay analysis on the two.

[0047] Secondly, the first group represents those whose travel origins are outside the theoretical service area of ​​the facility but who actually use it. Their travel behavior exceeds the predicted range of theoretical accessibility, reflecting a strong desire to travel. The second group represents those whose travel origins are within the theoretical service area of ​​the facility, but for whom no travel records in the associated dataset match the facility. These individuals could theoretically and easily use the facility, but in reality, they do not.

[0048] Then, based on the travel records of the first group of people in the associated dataset, we statistically analyze their number, travel characteristics, and other information to calculate the proportion of intention-driven travel, such as the proportion of the first group of people in the total number of people served by the facility.

[0049] Finally, based on the spatial distribution of the second group of people, we analyze their distribution characteristics within the theoretical service area and calculate the supply mismatch index, such as the proportion of the second group of people in the total population within the theoretical service area, or their degree of spatial aggregation.

[0050] By identifying the first group (users outside the designated area), the study revealed the phenomenon of "intention-driven travel," meaning people may be willing to spend more time than theoretically expected to use more attractive facilities. This provides a new perspective for facility classification and attractiveness assessment. By identifying the second group (non-users within the designated area), the study discovered the problem of "supply mismatch," where theoretically accessible facilities are not actually used due to various reasons (such as incompatible facility types, poor service quality, preference for other facilities, etc.), providing a clear direction for facility optimization. The intention-driven travel percentage index and the supply mismatch index, as quantitative tools, can intuitively reflect the actual attractiveness and service effectiveness of facilities, providing data support for planning decisions.

[0051] In some embodiments, the theoretical service range is calculated based on a time impedance model of a multimodal transportation network, wherein the time impedance model dynamically adjusts the travel time of various modes of transportation according to different travel periods.

[0052] Specifically, the calculation of the theoretical service range is based on a time impedance model of a multimodal transportation network. The core of this model is the calculation of road segment travel time, which is not a fixed value but dynamically changes with the travel time during different travel periods. The time impedance model dynamically adjusts the road segment travel time for various modes of transportation (walking, cycling, driving, and public transportation) according to different travel periods (e.g., morning peak 7:00-9:00, evening peak 17:00-19:00, off-peak hours, and nighttime). For driving, based on historical traffic flow data or real-time traffic information, road segment congestion coefficients are established for different time periods; travel time is longer during congested periods and shorter during off-peak periods. For public transportation, the differences in departure frequency during different time periods are considered; higher departure frequency and shorter waiting times occur during peak hours, while lower departure frequency and longer waiting times occur during off-peak periods. For walking and cycling, although less affected by traffic congestion, the time-limited opening of facilities such as pedestrian overpasses and underpasses can be considered. Based on this dynamically adjusted time impedance model, the area reachable from the facility during a specific travel period is calculated, which serves as the dynamic theoretical service range of the facility during that period.

[0053] The dynamic time impedance model makes the calculation of theoretical service range more consistent with the time-varying characteristics of traffic conditions, avoiding the assessment bias caused by using static travel time. Differentiating between different travel periods reflects the differences in accessibility between peak and off-peak hours, providing a basis for time-based traffic management measures. Dynamic adjustments for different modes of transportation reflect the varying sensitivities of different modes to time-based changes, making the assessment more refined.

[0054] In some embodiments, multimodal transportation network data includes pedestrian networks, cycling networks, driving networks, and public transportation networks.

[0055] Specifically, both the pedestrian and cycling networks are built on the OpenStreetMap open-source map database. During construction, road labels in the OSM data are used for filtering: highways, two-lane roads without sidewalks, and road sections marked as prohibited or unsuitable for walking / cycling are excluded, ensuring the network only includes roads permitted for walking and cycling. The public transportation network includes infrastructure networks such as buses and subways, and is combined with the pedestrian network to create a complete travel chain with walking connections. This means a public transportation trip is modeled as a complete process of "walking to a bus / subway station, then taking public transportation, and then walking to the destination." The driving network, as a separate vehicular traffic network, is used for calculating the time of driving trips. The four sub-networks correspond to four modes of transportation: the pedestrian network for walking, the cycling network for cycling, the driving network for driving, and the public transportation network for public transportation. In trip time calculation, the corresponding sub-network is called for path planning and time calculation based on the actual travel mode for each trip record. The public transportation network is constructed as a complete travel chain with walking connections, restoring the true process of public transportation travel and avoiding the evaluation bias of the past, which only calculated travel time while ignoring walking time at both ends. The comprehensive coverage of four networks—walking, cycling, driving, and public transportation—enables accessibility assessments to be applicable to different travel groups and scenarios, resulting in more comprehensive assessments. The clear correspondence between each sub-network and mode of travel ensures the accuracy of travel time calculations.

[0056] This invention provides an accessibility assessment system based on travel intention, comprising: The data acquisition module is used to acquire facility data, multimodal transportation network data, and residents' travel intention data for the target area; the residents' travel intention data includes multiple travel records, and the travel records include the origin, purpose, and mode of travel. The association construction module is used to match the travel purpose with facility data, establish the correspondence between travel purpose and facility type, and identify the actual facility instance used by each travel record based on the destination location of the travel record, and construct an association dataset of travel intention and facility use; The calculation module is used to calculate the travel time from the origin of each travel record to its corresponding facility instance, matching the travel mode, based on the multi-modal transportation network data and the travel mode of each travel record; and to calculate the total number of actual trips served by each facility instance within a preset time threshold based on the travel time, and to calculate the theoretical service range of each facility instance based on the multi-modal transportation network within the preset time threshold. The evaluation module is used to generate accessibility evaluation indicators based on the comparison between the total number of trips actually served and the theoretical service range.

[0057] The present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements an accessibility assessment method based on travel intention.

[0058] This invention provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, when executing a program stored in memory, implements steps for a method of accessibility assessment based on travel intentions.

[0059] The above is a detailed description of the preferred embodiments of the present invention. However, the present invention is not limited to the embodiments described. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention. All such equivalent modifications or substitutions are included within the scope defined by the claims of this application.

Claims

1. A method for assessing accessibility based on travel intention, characterized in that, Includes the following steps: Acquire facility data, multimodal transportation network data, and residents' travel intention data for the target area; the residents' travel intention data includes multiple travel records, each including the origin, purpose, destination, and mode of travel. The travel purpose is matched with facility data to establish a correspondence between travel purpose and facility type. Based on the destination of each travel record, the actual facility instance used in the travel record is identified, and a dataset relating travel intention and facility use is constructed. Based on the associated dataset, the multimodal transportation network data, and the travel mode of each travel record, the travel time from the origin of each travel record to its corresponding facility instance, matching the travel mode, is calculated; based on the travel time, the total number of trips actually served by each facility instance within a preset time threshold is calculated, and the theoretical service range of each facility instance based on the multimodal transportation network within the preset time threshold is calculated. Based on the comparison between the total number of trips actually served and the theoretical service range, an accessibility assessment index is generated.

2. The accessibility assessment method based on travel intention as described in claim 1, characterized in that, The process of matching travel destinations with facility data includes the following steps: Perform semantic analysis on the stated travel purpose to extract destination keywords; Semantic analysis is performed on the facility names and facility categories in the facility data to extract facility keywords; Calculate the semantic similarity between the destination keyword and the facility keyword. When the similarity exceeds a preset threshold, establish a correspondence between the travel destination and the facility type.

3. The accessibility assessment method based on travel intention as described in claim 1, characterized in that, The process of identifying the actual facility instance used by each travel record based on the destination location includes the following steps: Spatial matching is performed between the destination coordinates of each travel record and the geographical coordinates of each facility in the facility data; When the distance between the destination coordinates and the coordinates of a facility is less than a preset distance threshold, it is determined that the travel record actually uses the facility as a facility instance.

4. The accessibility assessment method based on travel intention as described in claim 1, characterized in that, The calculation of the total number of trips actually served by each facility instance within a preset time threshold includes the following steps: Based on the travel time matching the travel mode for each travel record in the associated dataset, travel records with travel times less than a preset time threshold are filtered out. The filtered travel records are counted by facility instance to obtain the total number of trips actually served by each facility instance; The total number of trips is aggregated according to facility type, travel purpose, or travel mode to generate categorized total number of trips.

5. The accessibility assessment method based on travel intention as described in claim 1, characterized in that, The generation of accessibility assessment metrics includes the following steps: The analysis combines the origin of the actual total number of trips served with the theoretical service range. Identify a first group of people and a second group of people. The first group of people are those whose travel origin is outside the theoretical service area and who actually use the facility. The second group of people are those whose travel origin is within the theoretical service area and who have no travel records matching the facility in the associated dataset. Based on the travel records of the first group of people in the associated dataset, a statistical index of intention-driven travel proportion is calculated; based on the spatial distribution of the second group of people, a supply mismatch index is calculated.

6. The accessibility assessment method based on travel intention as described in claim 1, characterized in that, The theoretical service range is calculated based on the time impedance model of a multimodal transportation network. The time impedance model dynamically adjusts the travel time of various modes of transportation according to different travel periods.

7. The accessibility assessment method based on travel intention as described in claim 1, characterized in that, The multimodal transportation network data includes pedestrian networks, cycling networks, driving networks, and public transportation networks.

8. An accessibility assessment system based on travel intention, characterized in that, include: The data acquisition module is used to acquire facility data, multimodal transportation network data, and residents' travel intention data for the target area; The residents' travel intention data includes multiple travel records, which include the origin, purpose, and mode of travel. The association construction module is used to match the travel purpose with facility data, establish the correspondence between travel purpose and facility type, and identify the actual facility instance used by each travel record based on the destination location of the travel record, and construct an association dataset of travel intention and facility use; The calculation module is used to calculate the travel time from the origin of each travel record to its corresponding facility instance, matching the travel mode, based on the multi-modal transportation network data and the travel mode of each travel record; and to calculate the total number of actual trips served by each facility instance within a preset time threshold based on the travel time, and to calculate the theoretical service range of each facility instance based on the multi-modal transportation network within the preset time threshold. The evaluation module is used to generate accessibility evaluation indicators based on the comparison between the total number of trips actually served and the theoretical service range.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-7.

10. An electronic device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the steps of the method according to any one of claims 1-7.

Images