Traffic journey determination method and computing device cluster

Abstract

The invention provides a traffic itinerary determination method and a computing device cluster. The method comprises the steps that a traffic knowledge graph is acquired, the traffic knowledge graph is generated according to multiple entities, attribute information of the multiple entities and relation information among the multiple entities, and the multiple entities comprise multiple cities, multiple traffic stations and multiple traffic shifts; the traffic knowledge graph is inquired according to the travel information of the user, one or more transfer routes of the user are determined, and the transfer routes comprise one or more transfer cities. According to the method, the transit travel of the user is obtained by pre-constructing the traffic knowledge graph and querying the traffic knowledge graph, so that the query efficiency can be improved, and the user experience is improved.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method for determining traffic routes and a cluster of computing devices. Background Technology

[0002] Currently, some online ticketing platforms can provide users with ticketing services for one or more modes of transportation, such as airplanes, trains, and buses.

[0003] In related technologies, online ticketing platforms typically need to traverse the data of every transportation option in the resource database based on the user's travel information until a connecting itinerary matching the user's travel information is determined. When the data volume is large, this method of comparing each option one by one is inefficient and may result in users having to wait a long time for results, thus affecting the user experience. Summary of the Invention

[0004] This application provides a method for determining travel itineraries and a cluster of computing devices. By querying a pre-built traffic knowledge graph, the user's travel itinerary can be obtained, which can improve query efficiency.

[0005] Firstly, this application provides a method for determining a travel itinerary. The method includes: acquiring a traffic knowledge graph, which is generated based on multiple entities and their attribute information, as well as the relationship information between the multiple entities, including multiple cities, multiple transportation stations, and multiple transportation schedules; querying the traffic knowledge graph based on the user's travel information to determine one or more transit trips for the user, whereby the transit trips include one or more transit cities.

[0006] The transit itinerary includes a first transportation trip and a second transportation trip. The departure and arrival stations of the first transportation trip are located in the user's departure city and transit city, respectively. The departure and arrival stations of the second transportation trip are located in the transit city and the user's arrival city, respectively. The multiple cities include the departure city, transit city, and arrival city. The multiple transportation trips include the first and second transportation trips. The multiple transportation stations include the departure and arrival stations of the first transportation trip, as well as the departure and arrival stations of the second transportation trip.

[0007] In the above solution, the transportation knowledge graph is structured data generated based on cached resource data, which includes the relationship information between the entities mentioned above. When querying the transportation knowledge graph based on a user's travel information, the system can quickly retrieve the user's transit cities and transportation schedules based on the relationship information between entities, thus obtaining the user's transit itinerary. Compared to related technologies that traverse the data for each transportation schedule, this approach improves query efficiency and enhances the user experience because it does not require traversing all resource data.

[0008] In one possible implementation, before acquiring the traffic knowledge graph, the method further includes: acquiring resource data from the devices of one or more data providers according to a caching period; and performing knowledge extraction on the resource data to obtain information about multiple entities and their attributes, as well as information about the relationships between the multiple entities. The resource data may include traffic resource data and urban infrastructure data.

[0009] Normally, daily transportation schedules remain unchanged. In the above scheme, periodically caching data reduces data transmission volume, thereby reducing the consumption of communication resources.

[0010] In one possible implementation, the method further includes: determining feedback information from the user, the feedback information being determined based on the transit itinerary; and updating the traffic knowledge graph based on the feedback information.

[0011] In the above solution, since the resource data is periodically cached, updating the transportation knowledge graph based on user feedback can solve the problem of information delay caused by caching time differences, thus avoiding impacting user experience. For example, when a flight and / or train is canceled or delayed due to weather or other reasons, the transportation knowledge graph can be updated based on feedback from multiple users, thereby enabling more accurate transfer itineraries to be inferred for subsequent users.

[0012] In one possible implementation, the feedback information includes the actual departure and arrival times of a first transportation service from the user's departure city to a transit city in the transit itinerary, and / or the actual departure and arrival times of a second transportation service from the transit city in the transit itinerary to the user's arrival city. The plurality of transportation services includes the first transportation service and the second transportation service. Updating the transportation knowledge graph based on the feedback information includes updating the time information of the first transportation service and the time information of the second transportation service based on the feedback information. The attribute information of the transportation service includes the time information.

[0013] In the above solution, the departure and arrival times of transportation services may have been adjusted, but the time difference between the current time and the last cached data does not meet the caching period. In this case, the time information of transportation services can be updated based on feedback from different users regarding the same transportation service, thereby improving the user experience.

[0014] In one possible implementation, determining the transit itinerary includes: querying a transportation knowledge graph based on the user's departure city and arrival city to obtain multiple candidate transit itineraries; determining the transit itinerary from among the multiple candidate transit itineraries based on the target parameters corresponding to each candidate transit itinerary and their corresponding thresholds, and / or the user's historical data, wherein the target parameters include one or more of the following: distance between the transit city and the departure city, distance between the transit city and the arrival city, transit stay duration, and total travel time; and the historical data includes one or more of the following: historical travel time, historical arrival time, historical transportation schedules, and historical seat class.

[0015] In one possible implementation, travel information includes the number of travelers, and the attribute information of transportation routes includes the number of remainders. The process of querying the transportation knowledge graph based on the departure city and the arrival city to obtain multiple candidate transit itineraries includes: generating a query statement that matches the target data structure based on the departure city and the arrival city; querying the transportation knowledge graph based on the query statement to obtain multiple candidate transit itineraries, wherein the number of remainders of transportation routes in each candidate transit itinerary is equal to or greater than the number of travelers.

[0016] In one possible implementation, the city's attribute information includes latitude and longitude, and the method further includes: determining the distance between the transit city and the departure city, and the distance between the transit city and the arrival city, based on the latitude and longitude of the transit city, the departure city, and the arrival city.

[0017] In one possible implementation, before querying the traffic knowledge graph based on the departure city and arrival city to obtain multiple candidate transit routes, the method further includes: determining the query traffic knowledge graph to obtain multiple candidate transit routes based on the distance between the departure city and arrival city and its corresponding threshold, and / or the number of target transportation routes and its corresponding threshold, wherein the departure station and arrival station of the target transportation routes are located in the departure city and arrival city, respectively.

[0018] Secondly, this application also provides a traffic journey determination device. The device includes a determination module and a query module.

[0019] The determination module is used to obtain a traffic knowledge graph, which is generated based on multiple entities and their attribute information, as well as the relationship information between multiple entities. The multiple entities include multiple cities, multiple transportation stations, and multiple transportation schedules.

[0020] The query module is used to query the traffic knowledge graph based on the user's travel information to determine one or more transit trips for the user, which include one or more transit cities.

[0021] In one possible implementation, before acquiring the traffic knowledge graph, the determination module is further configured to: acquire resource data from the devices of one or more data providers according to a caching period; and perform knowledge extraction on the resource data to obtain information on multiple entities and their attributes, as well as information on the relationships between the multiple entities. The resource data may include traffic resource data and urban infrastructure data.

[0022] In one possible implementation, the determining module is further configured to: determine the user's feedback information, the feedback information being determined based on the transit itinerary; and update the traffic knowledge graph based on the feedback information.

[0023] In one possible implementation, the feedback information includes the actual departure and arrival times of a first transportation service from the user's departure city to a transit city in the transit itinerary, and / or the actual departure and arrival times of a second transportation service from the transit city to the user's arrival city, wherein the plurality of transportation services includes the first transportation service and the second transportation service. The determining module is further configured to: update the time information of the first transportation service and the time information of the second transportation service based on the feedback information, wherein the attribute information of the transportation service includes the time information.

[0024] In one possible implementation, the query module is used to: query the transportation knowledge graph based on the user's departure city and arrival city to obtain multiple candidate transit itineraries; and determine the transit itinerary from the multiple candidate transit itineraries based on the target parameters corresponding to each candidate transit itinerary and their corresponding thresholds, and / or the user's historical data. The target parameters include one or more of the following: the distance between the transit city and the departure city, the distance between the transit city and the arrival city, the transit stay duration, and the total travel time. The historical data includes one or more of the following: historical travel time, historical arrival time, historical transportation schedules, and historical seat class.

[0025] In one possible implementation, the travel information includes the number of travelers, the attribute information of the transportation schedules includes the number of remainders, and the query module is used to: generate a query statement that matches the target data structure based on the departure city and the arrival city; query the transportation knowledge graph based on the query statement to obtain multiple candidate transit itineraries, wherein the number of remainders of the transportation schedules in each candidate transit itinerary is equal to or greater than the number of travelers.

[0026] In one possible implementation, the city's attribute information includes latitude and longitude, and the query module is used to: determine the distance between the transit city and the departure city, and the distance between the transit city and the arrival city, based on the latitude and longitude of the transit city, the departure city, and the arrival city.

[0027] In one possible implementation, before querying the traffic knowledge graph based on the departure city and arrival city to obtain multiple candidate transit routes, the query module is used to: determine the traffic knowledge graph to query based on the distance between the departure city and arrival city and its corresponding threshold, and / or the number of target transportation routes and its corresponding threshold, to obtain multiple candidate transit routes, wherein the departure station and arrival station of the target transportation routes are located in the departure city and arrival city, respectively.

[0028] Thirdly, this application also provides a computing device. The computing device includes a processor and a memory, the processor being configured to execute instructions stored in the memory to cause the computing device to implement the method provided by the first aspect or any possible implementation thereof.

[0029] Fourthly, this application also provides a computing device cluster. This computing device cluster includes multiple computing devices as provided in the third aspect.

[0030] Fifthly, this application also provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the method provided by the first aspect or any possible implementation thereof.

[0031] Sixthly, this application also provides a computer program product containing instructions that, when run on a computer, cause the computer to perform the method provided by the first aspect or any possible implementation thereof.

[0032] Any of the devices, computer storage media, or computer program products provided above are used to execute the methods provided above. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects of the corresponding solutions in the corresponding methods provided above, and will not be repeated here. Attached Figure Description

[0033] Figure 1 This is a schematic diagram illustrating an application scenario of a traffic journey determination method provided in an embodiment of this application;

[0034] Figure 2 This is a flowchart of a traffic journey determination method provided in an embodiment of this application;

[0035] Figure 3 This is a flowchart illustrating the construction and updating of a traffic knowledge graph, as provided in an embodiment of this application.

[0036] Figure 4 This is a schematic diagram of a traffic knowledge graph provided in an embodiment of this application;

[0037] Figure 5This is a schematic diagram illustrating the screening of candidate transit routes provided in an embodiment of this application;

[0038] Figure 6 This is a schematic diagram of a user's transit itinerary provided in an embodiment of this application;

[0039] Figure 7 This is a schematic diagram of the structure of a traffic journey determination device provided in an embodiment of this application;

[0040] Figure 8 This is a schematic diagram of the structure of a computing device provided in an embodiment of this application;

[0041] Figure 9 This application provides a method based on... Figure 8 A schematic diagram of the computing device cluster shown;

[0042] Figure 10 This is one of the embodiments provided in this application. Figure 9 Deployed in the computing device cluster shown Figure 7 The diagram shows the structure of the device. Detailed Implementation

[0043] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions in the embodiments of this application will be described below with reference to the accompanying drawings.

[0044] In the description of the embodiments of this application, the words "exemplary," "for example," or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplary," "for example," or "for instance" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the words "exemplary," "for example," or "for instance" is intended to present the relevant concepts in a specific manner.

[0045] In the description of the embodiments in this application, the term "and / or" is merely a description of the association relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, B existing alone, and A and B existing simultaneously. Furthermore, unless otherwise stated, the term "multiple" means two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals.

[0046] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. The terms "comprising," "including," "having," and their variations all mean "including but not limited to," unless otherwise specifically emphasized.

[0047] Graph databases are a type of NoSQL database that stores, queries, and manages nodes and the relationships between them. Nodes represent entities, and edges represent relationships between entities. Graph databases use nodes and edges as the basic storage units. This storage structure allows graph databases to quickly respond to complex relational queries when processing data with complex relational structures, because the relationships between entities are pre-stored in the database. For example, Neo4j is a high-performance graph database that can store structured data on the network. The physical addresses of interconnected nodes in a Neo4j graph also point to each other in the database.

[0048] A knowledge graph is a structured semantic knowledge base used to describe concepts and relationships in the physical world in symbolic form. The basic unit of a knowledge graph can be an "entity-relationship-entity" triple, along with the entity's related attribute information. In a knowledge graph, entities are interconnected through relationships, forming a network-like knowledge structure. In some implementations, knowledge graphs can be stored using graph databases like Neo4j. Taking Neo4j as an example, the relationships between entities in a knowledge graph can be presented more intuitively, thereby improving the query efficiency for complex data structures.

[0049] Figure 1 This is a schematic diagram of a transportation scenario provided in an embodiment of this application. For example... Figure 1 As shown, this scenario includes a terminal device 101 and an online ticketing platform 102. Users can book transportation products through the terminal device 101 to the online ticketing platform 102. Transportation products may include direct trips and / or connecting trips. Direct trips and / or connecting trips may include trip information for one or more modes of transportation, such as airplanes, trains, long-distance buses, ships, etc.

[0050] Terminal device 101 may include user devices such as smartphones, tablets, laptops, desktop computers, and in-vehicle computers. In one embodiment, client software for an online ticketing platform 101 may be installed on terminal device 101. Users can run the client software on terminal device 101 and send reservation requests to the online ticketing platform 101 through the client software. The reservation request may include travel information such as the user's departure city, arrival city, and travel time.

[0051] Online ticketing platform 102 may include Figure 1 The illustration shows one or more storage devices 1021 and one or more computing devices 1022. For ease of illustration, Figure 1 Only one storage device 1021 and one computing device 1022 are shown. Of course, in other embodiments, the functions of storage device 1021 and computing device 1022 can also be integrated into a single device.

[0052] Storage device 1021 is used to store traffic resource data. The traffic resource data may include data on the schedules of one or more modes of transportation, such as airplane flights, train schedules, and long-distance bus schedules.

[0053] The computing device 1022 receives travel information from the terminal device 101 and queries traffic resource data in the storage device 1021 based on the travel information to obtain direct and / or connecting routes matching the travel information. If the computing device 1022 does not find a direct route matching the travel information in the traffic resource data, it means the user cannot travel directly. The computing device 1022 can then analyze the traffic resource data using certain technical means to obtain the user's connecting route.

[0054] Based on this, this application provides a method for determining travel itineraries. In the method provided in this application embodiment, a traffic knowledge graph is pre-constructed based on resource data, and the user's travel information is queried from the traffic knowledge graph to obtain the user's transit itinerary. Specifically, by constructing a traffic knowledge graph and then querying it to obtain the user's transit itinerary, query efficiency can be improved compared to directly querying resource data.

[0055] The following is combined Figure 2 The method for determining traffic routes provided in the embodiments of this application will be described in detail.

[0056] Figure 2 This is a flowchart of a method for determining a transportation transfer route provided in an embodiment of this application. Figure 2 As shown, this method can be derived from the above. Figure 1 The computing device 1022 in the middle is used for execution.

[0057] S201, computing device 1022 retrieves traffic knowledge graph from storage device 1021.

[0058] The computing device 1022 can pre-generate the traffic knowledge graph based on multiple entities and their attribute information, as well as the relationship information between the multiple entities, and then store it in the storage device 1021. Upon receiving a pre-defined request from a user, the computing device 1022 retrieves the traffic knowledge graph from the storage device 1021. In some embodiments, the traffic knowledge graph can also be stored in the computing device 1022.

[0059] The traffic knowledge graph contains multiple entities, including multiple cities, multiple transportation stations, and multiple transportation schedules. The relationship information between these entities includes the relationship between multiple cities and multiple transportation stations, as well as the relationship between multiple transportation stations and multiple transportation schedules.

[0060] Specifically, such as Figure 3 As shown, computing device 1022 can obtain traffic resource data for one or more modes of transportation from the resource cache library in storage device 1021, obtain basic urban data from the urban basic database in storage device 1021, and perform knowledge extraction on the traffic resource data and urban basic data. Specifically, computing device 1022 can extract knowledge from the traffic resource data to obtain information such as multiple transportation stations and their attributes, multiple transportation schedules and their attributes, and the relationship information between multiple transportation stations and multiple transportation schedules. Similarly, computing device 1022 can extract knowledge from the urban basic data to obtain information such as multiple cities and their attributes, multiple transportation stations and their attributes, and the relationship information between multiple cities and multiple transportation stations.

[0061] The city's attribute information may include its identity (ID), name, three-letter code, and latitude and longitude.

[0062] Taking railway stations and airports as examples, the attribute information of railway stations may include the railway station's ID, station name, latitude and longitude, etc.; the attribute information of airports may include the airport's ID, three-letter code, name, latitude and longitude, etc.

[0063] For example, train and flight information can be used to describe transportation options. Train information can include the train ID, train number, total travel time, departure information, stopover information, and arrival information. Departure information can include departure time, stopover information can include fare, available seats, stopover duration, arrival time, and departure time, and arrival information can include fare, available seats, and arrival time. Flight information can include the flight ID, flight number, departure time, arrival time, departure airport, fare and available seats for each class of service, departure terminal, check-in counter, and on-time performance.

[0064] In some embodiments, the data processed by the knowledge extraction described above may include structured data, unstructured data, and / or semi-structured data. For semi-structured and unstructured data, the computing device 1022 can process it using techniques such as entity recognition, entity classification, and relation extraction to obtain the entities, entity attributes, and relationships within it. Structured data is typically two-dimensional data represented and stored using relational data structures. For structured data, the computing device 1022 performs knowledge extraction using techniques such as schema fusion and entity alignment to obtain the entities, entity attributes, and relationships between entities.

[0065] In some embodiments, the data processed by the knowledge extraction described above can be provided by different vendors, i.e., multi-source heterogeneous data. For multi-source heterogeneous data, the extracted information may contain different attributes and / or different relationships of the same entity. Therefore, after knowledge extraction, such as... Figure 3 As shown, the computing device 1022 can fuse entities, entity attributes, and relationships between entities extracted from multi-source heterogeneous data, aligning different attributes and / or different relationships of the same entity to obtain the entity's attributes and relationships. Taking an airplane flight as an example, the computing device 1022 can align different attributes and / or different relationships of the same flight number extracted from multi-source heterogeneous data to obtain the airplane flight's attributes and relationships.

[0066] After determining the entities, their attributes, and relationship information, such as Figure 3 As shown, computing device 1022 can represent the knowledge in a language that a computer can understand, and then generate a traffic knowledge graph. For example, computing device 1022 can represent each entity, its attributes, and relationships as resource description framework (RDF) triples.

[0067] Taking the categories of transportation stations (airports and train stations) and transportation schedules (flights and train numbers) as examples, the relationship between cities and transportation stations can be represented as XX Airport located in city YY, and SS Station located in city NN, etc. Similarly, the relationship between transportation stations and transportation schedules can be represented as flight XX departing from airport YY and arriving at airport ZZ, and train XX departing from station YY, stopping at station WW, and arriving at station ZZ, etc.

[0068] The computing device 1022 generates a traffic knowledge graph based on these triples and stores the traffic knowledge graph. Figure 4 A portion of the transportation knowledge graph is shown in graphical form. The transportation knowledge graph clearly illustrates the relationships between cities and airports / train stations, as well as the relationships between airports and flights, and between train stations and train schedules.

[0069] Storage device 1021 can obtain the latest traffic resource data from the supplier at regular intervals and update the traffic resource data in the resource cache of storage device 1021. After a large influx of traffic resource data and updates to the resource cache, such as... Figure 4 As shown, the computing device 1022 can update the traffic knowledge graph. Typically, daily traffic schedules remain unchanged; periodically updating traffic resource data reduces the number of data transmissions, thus saving data transmission bandwidth.

[0070] Updates to a transportation knowledge graph primarily involve data layer updates, which can include adding or updating entities, entity attributes, and entity relationships. For example, if a city doesn't have an airport, but a neighboring city adds one, the relationships between that city's neighboring airports can be reflected in the transportation knowledge graph. Another example is the frequent changes in flight prices and availability slots in transportation resource data; these changes need to be reflected in the transportation knowledge graph's flight schedule attribute information in real time. Therefore, when flight prices or availability slots change, the price and availability slots in the knowledge graph's attribute information for that flight can be updated.

[0071] S202, based on the user's travel information, query the traffic knowledge graph to determine one or more transit trips for the user.

[0072] The computing device 1022 can extract the travel information from the user's booking request, and then infer one or more connecting trips matching the user's travel information based on a traffic knowledge graph. The travel information may include the departure city, arrival city, travel time, number of passengers, etc. Furthermore, in some embodiments, the computing device 1022 can also obtain direct trips matching the user's travel information based on the traffic knowledge graph.

[0073] Before inferring a user's transit itinerary, the computing device 1022 can determine whether transit conditions are met based on the user's travel information. Transit itinerary inference is then performed only if the transit conditions are met. For example, transit conditions may include a distance threshold between the departure city and the arrival city, and / or a number threshold for the number of direct routes between the departure city and the arrival city. Setting a distance threshold avoids planning transit itineraries for two closely spaced cities, saving computing resources. Setting a direct route number threshold allows for real-time inference of transit itineraries for the user, improving the user experience.

[0074] Next, taking city A1 as the departure city and city A2 as the arrival city as an example, we will introduce the specific process of reasoning about transit itineraries.

[0075] The computing device 1022 can generate a query statement based on the departure city A1 and the arrival city A2, and then query the transportation knowledge graph based on the query statement to obtain one or more candidate transit routes.

[0076] The query statements can include structured queries. The computing device 1022 can generate different query statements based on different numbers of transfers. Taking the traffic knowledge graph using the Neo4j graph database as an example, the query statements can include Cyper query statements.

[0077] Taking a single transfer as an example, the `cyper` query statement can be "match(q,n,p,s,k,m,t)". Here, `q` represents the departure city, `n` represents the departure station, `p` represents the first transportation number, `s` represents the transfer station, `k` represents the second transportation number, `m` represents the arrival station, and `t` represents the arrival city. The departure station is located in the departure city, and the arrival station is located in the arrival city.

[0078] Taking two transfers as an example, the Cyper query statement can be "match(q,n,p,s1,k,s2,j,m,t)". Here, s1 represents the first transfer station, s2 represents the second transfer station, and j represents the third transportation route.

[0079] By querying the traffic knowledge graph using the above Cyper query statement, the values ​​of each parameter in the query statement can be obtained.

[0080] Taking a single transfer between departure city A1 and arrival city A2 as an example, computing device 1022 can initiate a cyber query statement for flight combinations involving one transfer city to the transportation domain knowledge graph, obtaining one or more sets of values ​​for q, n, p, s, k, m, t. Based on these values, candidate transfer itineraries can be determined. These candidate itineraries include the departure city, transfer city, arrival city, and first itinerary information (from the departure city to the transfer city) and second itinerary information (from the transfer city to the arrival city). The first and second itinerary information can respectively include information such as flight schedules, seat information, time information, and price information.

[0081] Computing device 1022 can combine optimal path models, business rules, and user preference models, such as Figure 5 As shown, the user's transit itinerary is obtained from one or more candidate transit itineraries and output. Specifically, the computing device 1022 can calculate the set of transit cities T_geo between the user's departure city and arrival city according to the optimal route model. The intersection of the transit city set T_geo and the set T_kg composed of transit cities in the candidate transit itineraries is obtained to obtain the transit city set T_transfer. Then, the candidate transit itineraries that conform to the business rules and user preference model corresponding to each transit city in the transit city set T_transfer are output as the user's transit itinerary.

[0082] The optimal route model is used to select the optimal transit city. This model considers two key factors: distance and the number of direct transportation options between the two transit segments. The distances between the cities in the transit city set T_geo and the departure city A1 and the arrival city A2 satisfy the following conditions 1 to 3.

[0083] Condition 1 - Inside the circle: Cities located inside or on the circle with the straight-line distance between A1 and A2 as its diameter and the midpoint between A1 and A2 as its center can be added to the transit city set T_geo. If the number of cities in set T_geo is less than the number of target cities, condition 2 can be applied.

[0084] Condition 2 - Intersection of Two Circles: Cities located within the intersection area of ​​two circles with a radius equal to the straight-line distance between A1 and A2 and centers at A1 and A2 can be added to the city set T_geo. If the number of cities in set T_geo is less than the target number of cities, condition 3 can be applied.

[0085] Condition 3 - Center divergence: With A1 and A2 as centers respectively, gradually increase the radius. Cities within the region that do not intersect with conditions 1 and 2 can be added to the city set T_geo.

[0086] Business rules can include thresholds for target parameters such as transit stay duration, punctuality rate, seat class, and baggage allowance. The computing device can then filter candidate transit itineraries based on these thresholds.

[0087] The conditions for transit layover duration may include: the transit layover duration of two flights must be greater than the transit layover duration threshold of the same terminal at the same airport, or greater than the transit layover duration threshold of different terminals at the same airport, or greater than the transit layover duration threshold of different airports; the transit layover duration of two train services must be greater than the transit layover duration threshold of the same train station, or greater than the transit layover duration threshold of different train stations.

[0088] The on-time rate threshold can filter out transportation trips with an on-time rate below the threshold.

[0089] The seat class threshold can include the seat class specified by the user.

[0090] Among them, the baggage allowance threshold can be used for users to select transit trips where both segments of the trip have free baggage allowance, and the baggage allowance for the second segment is greater than or equal to the baggage allowance for the first segment.

[0091] The user preference model analyzes a user's historical booking behavior to obtain historical data and recommends connecting trips that match their preferences. This historical data can include historical departure and arrival times, airline numbers, seat class preferences, and flight preferences. The model can also score candidate connecting trips that meet business rules based on six dimensions: price, total travel time, layover length, same airline, user preference, and whether the trip spans multiple days. A connecting trip is then selected from the candidate trips based on the score.

[0092] In addition, the computing device 1022 can generate a query statement based on the transit city specified by the user, and obtain one or more candidate transit itineraries. Then, it is filtered according to business rules and / or user preference models.

[0093] The distance between departure city A1 and arrival city A2 can include, for example: Figure 6 The transit itinerary shown. Figure 6 In the list, cities A3 and A6 are transit cities. For example... Figure 6As shown, a user can take train D1 from train station B1 in city A1 to train station B3 in city A3, then take train D2 from train station B3 in city A3 to train station B2 in city A2, or take flight E3 from airport C3 in city A3 to airport C2 in city A2. Alternatively, a user can take flight E1 from airport C1 in city A1 to airport C6 in city A6, then take flight E2 from airport C6 in city A6 to airport C2 in city A2, or take train D3 from train station B6 in city A6 to train station B2 in city A2.

[0094] In this embodiment, the computing device 1022 can also receive feedback information from the user regarding transportation schedules during the transfer trip, and update the transportation knowledge graph based on this feedback information. This feedback information may indicate that a transportation schedule was canceled for some reason, or its actual arrival time, or delay duration. The computing device can update the attribute information and / or relationship information of that transportation schedule in the transportation knowledge graph based on the feedback information. This avoids affecting the subsequent reasoning results of users and improves the user experience.

[0095] The above Figure 2 In the method embodiment shown, a traffic knowledge graph is constructed based on resource data, and then the user's transfer itinerary is obtained by querying the traffic knowledge graph. Compared with directly querying resource data to obtain the transfer itinerary, the query efficiency can be improved, thereby enhancing the user experience.

[0096] based on Figure 2 The method embodiments shown in this application also provide a traffic journey determination device.

[0097] Figure 7 This is a schematic diagram of a traffic journey determination device 700 provided in an embodiment of this application. Wherein, as... Figure 7 As shown, the determining device 700 may include a determining module 701 and a query module 702.

[0098] The determination module 701 is used to obtain a traffic knowledge graph. The traffic knowledge graph is generated based on multiple entities and their attribute information, as well as the relationship information between the multiple entities. The multiple entities include multiple cities, multiple transportation stations, and multiple transportation schedules.

[0099] The query module 702 is used to query the traffic knowledge graph based on the user's travel information to determine one or more transit trips for the user, including one or more transit cities.

[0100] It should be noted that, Figure 7The traffic journey determination device 700 provided in the illustrated embodiment, when executing the traffic journey determination method, is only illustrated by the division of the above-described functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. Furthermore, the traffic journey determination device 700 provided in the above embodiment and... Figure 2 The illustrated methods for determining travel routes belong to the same concept, and their specific implementation process can be found in the method embodiments, which will not be repeated here.

[0101] Figure 8 This is a schematic diagram of the hardware structure of a computing device 800 provided in an embodiment of this application.

[0102] The computing device 800 can be the aforementioned computing device 1022. See also... Figure 8 The computing device 800 includes a processor 810, a memory 820, a communication interface 830, and a bus 840, which are interconnected via the bus 840. The processor 810, memory 820, and communication interface 830 may also be connected using other methods besides the bus 840.

[0103] The memory 820 can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), flash memory, optical storage, hard disk, etc.

[0104] The processor 810 may be a general-purpose processor, which can be a processor that performs specific steps and / or operations by reading and executing contents stored in memory (e.g., memory 820). For example, the general-purpose processor may be a central processing unit (CPU). The processor 810 may include at least one circuit to perform... Figure 2 The illustrated embodiment provides all or part of the steps of the traffic journey determination method.

[0105] The communication interface 830 includes input / output (I / O) interfaces, physical interfaces, and logical interfaces for interconnecting devices within the computing device 800, as well as interfaces for interconnecting the computing device 800 with other devices (such as other computing devices or user equipment). The physical interface can be an Ethernet interface, a fiber optic interface, an ATM interface, etc.

[0106] The bus 840 can be any type of communication bus used to interconnect the processor 810, memory 820 and communication interface 830, such as a system bus.

[0107] The aforementioned devices can be disposed on separate chips, or at least partially or entirely on the same chip. Whether to dispose of the devices independently on different chips or integrate them on one or more chips often depends on the needs of the product design. This application does not limit the specific implementation of the aforementioned devices.

[0108] Figure 8 The computing device 800 shown is merely an example. In the implementation process, the computing device 800 may also include other components, which will not be listed one by one in this article.

[0109] based on Figure 2 In addition to the method shown, this application also provides a computing device cluster.

[0110] Figure 9 This application provides a computing device cluster 900.

[0111] This computing device cluster 900 can be used to achieve Figure 1 The online ticketing platform shown is 100. (For example...) Figure 9 As shown, the computing device cluster includes at least one computing device 800. The memory 820 of one or more computing devices 800 in the computing device cluster may store the same memory for executing... Figure 2 The instructions for the method shown. Specifically, the traffic trip determination device 700 can be deployed on a single computing device 800 or distributed across multiple computing devices 800.

[0112] The computing device can be a server, such as a central server, an edge server, or a local server in a local data center. In some embodiments, the computing device can also be a terminal device such as a desktop computer, a laptop computer, or a smartphone.

[0113] In some possible implementations, the memory 820 of one or more computing devices 800 in the computing device cluster may also store memory for execution. Figure 2The instructions for the method shown are partial. In other words, a combination of one or more computing devices 800 can coexist for executing... Figure 2 The instructions for the method shown.

[0114] It should be noted that the memory 820 in different computing devices 800 within the computing device cluster can store different instructions, each for execution. Figure 7 The illustrated device performs some of its functions. Specifically, the instructions stored in the memory 820 of different computing devices 800 can implement... Figure 7 The function of one or more modules in the device shown.

[0115] In some possible implementations, one or more computing devices in a computing device cluster can be connected via a network. This network can be a wide area network (WAN) or a local area network (LAN), etc. Figure 10 One possible implementation is shown. For example... Figure 10 As shown, the two computing devices 800A and 800B are connected via a network. Specifically, they are connected to the network through the communication interfaces in each computing device. In this type of possible implementation, the memory 820 in computing device 800A and the memory 820 in computing device 800B respectively store instructions for implementing some functions of the traffic trip determination device 700. For example, the memory 820 in computing device 800A stores instructions for implementing the function of the determination module 701, and the memory 820 in computing device 800B stores instructions for implementing the function of the query module 702.

[0116] It should be understood that Figure 10 The functions of the computing device 800A shown can also be performed by multiple computing devices 800. Similarly, the functions of the computing device 800B can also be performed by multiple computing devices 800.

[0117] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0118] It is understood that the various numerical designations used in the embodiments of this application are merely for descriptive convenience and are not intended to limit the scope of the embodiments of this application. It should be understood that in the embodiments of this application, the order of the process numbers does not imply the order of execution; the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0119] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of this application. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, improvements, etc., made on the basis of the technical solution of this application should be included within the scope of protection of this application.

Claims

1. A method of determining a traffic trip, characterized by, The method comprises: obtaining a traffic knowledge graph, the traffic knowledge graph being generated according to a plurality of entities and attribute information thereof, and relationship information between the plurality of entities, the plurality of entities comprising a plurality of cities, a plurality of traffic stations and a plurality of traffic schedules; querying the traffic knowledge graph according to travel information of a user to determine one or more transfer itineraries of the user, the transfer itineraries comprising one or more transfer cities.

2. The method of claim 1, wherein, Before the obtaining of the traffic knowledge graph, the method further comprises: obtaining resource data from one or more devices of one or more data providers according to a cache period; performing knowledge extraction on the resource data to obtain the plurality of entities and attribute information thereof, and the relationship information between the plurality of entities.

3. The method of claim 2, wherein, The method further comprises: determining feedback information of the user, the feedback information being determined according to the transfer itineraries; updating the traffic knowledge graph according to the feedback information.

4. The method of claim 3, wherein, The feedback information comprises actual departure time and actual arrival time of a first traffic schedule from a departure city of the user to a transfer city in the transfer itineraries, and / or actual departure time and actual arrival time of a second traffic schedule from the transfer city in the transfer itineraries to an arrival city of the user, the plurality of traffic schedules comprising the first traffic schedule and the second traffic schedule, and updating the traffic knowledge graph according to the feedback information comprises: updating time information of the first traffic schedule and time information of the second traffic schedule according to the feedback information, the attribute information of the traffic schedule comprising the time information.

5. The method according to any one of claims 1 to 4, characterized in that, The determining of the transfer itineraries comprises: querying the traffic knowledge graph according to the departure city of the user and the arrival city of the user to obtain a plurality of candidate transfer itineraries; determining the transfer itineraries from the plurality of candidate transfer itineraries according to target parameters and corresponding threshold values thereof, and / or historical data of the user, wherein the target parameters comprise one or more of distance between a transfer city in each candidate transfer itinerary and the departure city, distance between the transfer city and the arrival city, transfer stay duration, and total travel time, and the historical data comprises one or more of historical travel time, historical arrival time, historical traffic schedule, and historical seat grade.

6. The method of claim 5, wherein, The travel information comprises a number of travelers, and the attribute information of the traffic schedule comprises a number of remaining seats, and the querying of the traffic knowledge graph according to the departure city and the arrival city to obtain a plurality of candidate transfer itineraries comprises: generating a query statement matching the target data structure according to the departure city and the arrival city; querying the traffic knowledge graph according to the query statement to obtain the plurality of candidate transfer itineraries, and the number of remaining seats of the traffic schedule in each candidate transfer itinerary being equal to or greater than the number of travelers.

7. The method of claim 5, wherein, The attribute information of the city comprises longitude and latitude, and the method further comprises: determining the distance between the transfer city and the departure city, and the distance between the transfer city and the arrival city according to the longitude and latitude of the transfer city, the longitude and latitude of the departure city and the longitude and latitude of the arrival city.

8. The method according to any one of claims 5-7, characterized in that, Before querying the traffic knowledge graph according to the departure city and the arrival city to obtain a plurality of candidate transfer itineraries, the method further includes: According to the distance between the departure city and the arrival city and the corresponding threshold value, and / or the number of target traffic classes and the corresponding threshold value, it is determined to query the traffic knowledge graph to obtain the plurality of candidate transfer itineraries, and the departure station and the arrival station of the target traffic class are located in the departure city and the arrival city, respectively.

9. A traffic trip determination apparatus characterized by comprising: The device includes: A determination module is configured to obtain a traffic knowledge graph, wherein the traffic knowledge graph is generated according to a plurality of entities and attribute information of the plurality of entities, and relationship information between the plurality of entities, the plurality of entities including a plurality of cities, a plurality of traffic stations and a plurality of traffic classes; A query module is configured to query the traffic knowledge graph according to travel information of a user to determine one or more transfer itineraries of the user, wherein the transfer itinerary includes one or more transfer cities.

10. A computing device, comprising: The computing device includes a processor and a memory, and the processor is configured to execute instructions stored in the memory to enable the computing device to implement the method of any one of claims 1 to 8.

11. A cluster of computing devices, characterized in that, A plurality of computing devices according to claim 10 are included.

12. A computer-readable storage medium, characterized in that, The instructions, when executed on a computer, cause the computer to implement the method of any one of claims 1 to 8.

13. A computer program product, characterised in that, The instructions, when executed on a computer, cause the computer to implement the method of any one of claims 1 to 8.

Images