Travel intention recognition method, travel strategy recommendation method and service platform

Abstract

The embodiments of the present application provide a travel intention recognition method, a travel strategy recommendation method, and a service platform. The travel intention recognition method includes: obtaining the current trip information and current passenger information of the current trip, as well as the historical travel information of the current passenger; extracting and combining features from the current trip information, current passenger information, and historical travel information to obtain the to-be-matched combined features corresponding to the current trip in multiple travel scenarios; matching the to-be-matched combined features of the current trip in each travel scenario with the feature requirements of each travel scenario respectively to determine the travel scenario matched by the current trip from multiple travel scenarios; wherein, the feature requirements of the travel scenario conform to the definition and characteristics of the travel scenario; and determining the travel intention of the current trip according to the travel scenario matched by the current trip. The embodiments of the present application can improve the recognition accuracy of travel intention and provide support for improving the accuracy of travel strategy recommendation.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of computer Internet, and particularly to a travel intention recognition method, a travel strategy recommendation method and a service platform. Background Art

[0002] A travel service platform is an online platform that provides travel services for users, such as an OTP (Online Travel Platform) or an OTA (Online Travel Agency) platform. The travel service platform aims to conveniently meet the travel needs of users. With the continuous development of intelligent technologies, the travel service platform not only provides ticketing services such as booking tickets, purchasing tickets, and ticket changes, but also involves diversified travel solutions such as hotel reservations, travel packages, and car rentals.

[0003] To improve the user travel experience, the travel service platform needs to accurately identify the travel intentions of users. Therefore, how to improve the accuracy of travel intention recognition has become a technical problem that needs to be solved urgently by those skilled in the art. Summary of the Invention

[0004] In view of this, the embodiments of the present application provide a travel intention recognition method, a travel strategy recommendation method and a service platform to improve the accuracy of travel intention recognition.

[0005] To achieve the above object, the embodiments of the present application provide the following technical solutions.

[0006] In a first aspect, the embodiments of the present application provide a travel intention recognition method, including:

[0007] Obtaining the current trip information and current passenger information of the current trip, as well as the historical travel information of the current passenger;

[0008] Extracting and combining features from the current trip information, the current passenger information and the historical travel information to obtain the to-be-matched combined features corresponding to the current trip in multiple travel scenarios respectively;

[0009] Matching the to-be-matched combined features of the current trip in each travel scenario with the feature requirements of each travel scenario respectively to determine the travel scenario matched by the current trip from the multiple travel scenarios; wherein, the feature requirements of the travel scenario conform to the definition and characteristics of the travel scenario;

[0010] Determining the travel intention of the current trip according to the travel scenario matched by the current trip.

[0011] In a second aspect, the embodiments of the present application provide a travel strategy recommendation method, including:

[0012] Obtain the travel intention of the current trip, where the travel intention of the current trip is determined based on the travel intention recognition method described in the first aspect above;

[0013] Determine the travel preference information of the current passenger;

[0014] Recommend the travel strategy of the current trip according to the travel intention of the current trip and the travel preference information of the current passenger.

[0015] In a third aspect, an embodiment of the present application provides a travel service platform, including: a travel intention recognition system;

[0016] The travel intention recognition system includes:

[0017] A preprocessing module, configured to extract and combine features from the current trip information, current passenger information of the current trip, and the historical travel information of the current passenger, so as to obtain the to-be-matched combined features corresponding to the current trip in multiple travel scenarios;

[0018] A travel intention recognition model, configured to match the to-be-matched combined features of the current trip in each travel scenario with the feature requirements of each travel scenario respectively, so as to determine the travel scenario matched by the current trip from multiple travel scenarios; wherein, the feature requirements of the travel scenario conform to the definition and characteristics of the travel scenario;

[0019] A postprocessing module, configured to determine the travel intention of the current trip according to the travel scenario matched by the current trip;

[0020] A travel scenario knowledge base, as the background knowledge base of the travel intention recognition model, records the background knowledge of multiple travel scenarios, and the background knowledge of the travel scenario at least includes the definition, characteristics, and feature requirements of the travel scenario.

[0021] In a fourth aspect, an embodiment of the present application provides a travel server, including a memory and a processor, the memory stores computer execution instructions, and the processor calls the computer execution instructions to execute the travel intention recognition method described in the first aspect above, or the travel strategy recommendation method described in the second aspect above.

[0022] In a fifth aspect, an embodiment of the present application provides a computer program product, including computer execution instructions, and when the computer execution instructions are executed, the travel intention recognition method described in the first aspect above, or the travel strategy recommendation method described in the second aspect above is implemented.

[0023] The travel intention recognition method provided by the embodiments of the present application synthesizes multi-dimensional information such as current trip information, current passenger information, and the historical travel information of the current passenger, and performs matching processing between the current trip and travel scenarios; specifically, features are extracted and combined from the current trip information, current passenger information, and historical travel information to form the to-be-matched combined features corresponding to the current trip in multiple travel scenarios, so that the to-be-matched combined features corresponding to the current trip in the travel scenarios can reflect various dimensional information and background of the current trip, avoid the possible deviation of the single-dimensional information of the current trip, and ensure that the background of the current trip can be fully considered when matching the travel scenario of the current trip; then, based on the feature requirements of the travel scenarios that conform to the definitions and characteristics of the travel scenarios, the to-be-matched combined features of the current trip in each travel scenario are respectively matched with the feature requirements of each travel scenario to determine the travel scenario matched by the current trip from multiple travel scenarios, so as to accurately determine the travel scenario matched by the current trip; that is to say, each travel scenario has clear feature requirements, which conform to the specific definitions and characteristics of the travel scenarios. By comparing and matching the to-be-matched combined features of the current trip in the travel scenarios with the feature requirements of the travel scenarios, it is possible to more accurately judge whether the current trip meets the requirements of the travel scenario, so as to accurately identify the travel scenario matched by the current trip from multiple travel scenarios; at the same time, the historical travel information of the current passenger is considered in the process of travel intention recognition. Since the historical travel information of the current passenger helps to understand the historical travel habits and preferences of the current passenger, the travel scenario matched by the current trip can be made more accurate; furthermore, according to the travel scenario matched by the current trip, the travel intention of the current trip is determined, and then the travel intention recognition of the current trip can be completed. In summary, the embodiments of the present application can improve the recognition accuracy of travel intention and provide support for improving the accuracy of travel strategy recommendation. Description of the Drawings

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings described below are only the embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0025] Figure 1 It is a flowchart of the travel intention recognition method provided by the embodiments of the present application.

[0026] Figure 2 It is an example diagram of some travel scenarios.

[0027] Figure 3 It is an example diagram of some feature types required for travel scenario matching.

[0028] Figure 4 An example diagram of partial feature requirements for partial travel scenarios.

[0029] Figure 5 An example diagram of the composition of a travel scenario knowledge base.

[0030] Figure 6 An example diagram of the architecture of a travel service platform provided by an embodiment of the present application.

[0031] Figure 7 An example diagram of the verification rules for partial travel scenarios recorded in the form of a verification list.

[0032] Figure 8 A flowchart of a travel strategy recommendation method provided by an embodiment of the present application.

[0033] Figure 9 Another example diagram of the architecture of a travel service platform provided by an embodiment of the present application. Detailed implementation manners

[0034] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0035] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or fully authorized by all parties. And the collection, use, and processing of relevant data need to comply with the relevant laws, regulations, and standards of relevant countries and regions, and corresponding operation entrances are provided for users to choose to authorize or refuse.

[0036] In the embodiments of the present application, the travel intention of a user refers to the motivation and reason for the user's travel, that is, the travel intention of the user can describe the reason for the user's travel. For example, the travel intention of the user describes why the user travels. Identifying the travel intention of the user is crucial for the travel service platform because the travel intention of the user can help the travel service platform better understand the travel needs of the user, and then provide targeted travel services for the user, such as providing targeted travel strategies for the user.

[0037] An itinerary strategy refers to an itinerary plan and / or additional travel services that are intelligently formulated and optimized based on information such as the user's travel needs and preferences. Specifically, formulating an itinerary strategy may include formulating an itinerary plan, such as formulating a travel route when the user books a ticket or makes a purchase, and recommending transportation schedules corresponding to the travel route (such as recommending train schedules for trains and flight schedules for airplanes); formulating an itinerary strategy may also not be limited to formulating an itinerary plan, but may also include recommending additional travel services, such as recommending hotel reservation services, car rental services, pick-up and drop-off services for departure and arrival, etc.

[0038] Once the user's travel intention is determined, the travel service platform can formulate an itinerary strategy around the user's travel intention to enhance the user's travel experience. For example, when the user books a ticket, if there are no remaining tickets for the travel plan the user expects (such as no remaining tickets for the train schedule or flight the user expects), the travel service platform can, based on the user's travel intention, provide an alternative travel plan that meets the user's needs (such as an alternative train schedule or an alternative flight); that is to say, when the travel plan the user expects cannot be satisfied, the travel service platform does not simply inform the user that tickets cannot be booked currently, nor does it provide simple transfer information for the itinerary, but instead, by identifying the travel intention, it intelligently recommends an alternative travel plan that meets the user's needs, thereby enhancing the user's travel experience.

[0039] Another example is that in addition to recommending an itinerary plan for the user when the user books or purchases a ticket, the travel service platform can also recommend other additional travel services that meet the user's needs based on the user's travel intention, such as car rental services, hotel reservation services, etc., thereby constructing a comprehensive travel solution and improving the user's travel experience and travel convenience.

[0040] For another example, the travel service platform can, based on the user's travel intention, through real-time notification and push services, help the user promptly understand ticket changes, departure time adjustments related to the user's travel, and even temporary weather, traffic and other factors affecting travel, ensuring the smooth progress of the user's travel plan.

[0041] It can be seen that identifying the user's travel intention is the basis for the travel service platform to provide accurate itinerary strategies for users, and it is of great significance for enhancing the user experience and reducing the user's decision-making cost. Therefore, optimizing the way of identifying travel intention and improving the accuracy of identifying travel intention have important technical significance.

[0042] As an optional implementation, Figure 1An optional flowchart of the travel intention recognition method provided by the embodiments of the present application is exemplarily shown. This travel intention recognition method can be applied to travel service platforms, such as OTP, OTA platforms, etc. In an optional implementation, the travel service platform (such as OTP, OTA platform) may include a server on the service side, referred to as a travel server (such as an OTP server, an OTA server). Thus, the travel intention recognition method provided by the embodiments of the present application can be specifically applied to the travel server. In an optional implementation, the travel service platform (such as OTP, OTA platform) can be regarded as an online service platform formed by a server cluster formed by travel servers through setting various software and hardware functional architectures.

[0043] Referring to Figure 1 , the travel intention recognition method provided by the embodiments of the present application may include the following steps.

[0044] Step S110: Obtain the current travel information and current passenger information of the current trip, as well as the historical travel information of the current passenger.

[0045] In an optional implementation, the current trip is a trip that is in progress or planned. For example, the user can log in to the travel service platform using the registered account of the travel service platform. Thus, the user can submit the current trip to the travel service platform through travel service requests such as ticket requests and travel strategy recommendation requests. Among them, a ticket request refers to any request initiated by the user during ticket-related operations, including but not limited to the ticket booking request when the user books a ticket, the ticket query request (such as the request to query train tickets, the request to query airplane tickets, etc.), the ticket change request (modifying the travel time or flight number of tickets such as train tickets and airplane tickets already purchased), etc. In a specific example, the trip submitted by the user through the ticket booking request can be the current trip. The travel strategy recommendation request is used for the user to request the travel service platform to recommend travel strategies, such as the user requesting the travel service platform to recommend the travel plan and / or travel additional services for the current trip.

[0046] The current travel information includes multiple characteristic information related to the current trip, such as the departure place of the current trip (such as the departure city, departure station), the destination (such as the destination city, destination station), the departure time (such as the departure date and departure time point), the arrival time (such as the arrival date and arrival time point), the travel duration, the type of transportation means (such as high-speed rail, bullet train, express train, airplane, etc.), the transportation schedule (such as the train number of the train, the flight number of the airplane, etc.), the ticket price, the seat type (such as the second-class seat, first-class seat, business class seat of the high-speed rail, etc.), the ticket booking time, the ticket type (such as student ticket, child ticket, adult ticket, etc.). In an optional implementation, the travel service platform can collect the current travel information of the current trip. For example, based on the ticket booking request or ticket query request submitted by the user, the information related to the trip in the ticket booking request or ticket query request is collected as the current travel information.

[0047] It should be noted that the user referred to in the embodiments of the present application is a user who registers and uses the travel service platform; the current passenger refers to the actual passenger of the current trip, such as the current rider. The current passenger may be the user himself or someone else who the user books tickets on behalf of; further, the current passenger may also be multiple people, including the user himself and someone else who the user books tickets on behalf of, or multiple other people who the user books tickets on behalf of.

[0048] The current passenger information includes multiple characteristic information related to the current passenger, such as the name, age, identity identifier (such as identity number), and the number of current passengers of the current passenger. In an optional implementation, the travel service platform may collect the current passenger information of the current trip, such as based on the ticket booking request or ticket query request submitted by the user, and collect the information related to the passenger in the ticket booking request or ticket query request as the current passenger information.

[0049] After determining the current passenger information, the embodiments of the present application may obtain the historical travel information of the current passenger based on the current passenger information; for example, based on the identity identifier of the current passenger in the current passenger information, obtain the historical travel information of the current passenger from the historical travel database, where the historical travel database records the historical travel information of multiple passengers, such as the travel information of the historical trips of multiple passengers and the corresponding passenger information, and the historical trip is a completed trip. In an optional implementation, the travel information and passenger information of the historical trip may be the travel information and passenger information of the completed historical ticket booking orders, and the historical travel database may record the travel information and passenger information of the completed historical ticket booking orders of multiple users (such as all users of the travel service platform).

[0050] In an optional implementation, the historical travel information of the current passenger may refer to the historical travel records of the current passenger, including the historical travel information corresponding to the historical trip of the current passenger and the travel frequency of the current passenger corresponding to the historical trip. Exemplarily, the historical travel information corresponding to the historical trip of the current passenger may include, but is not limited to, the departure place, destination, departure time, arrival time, travel duration, transportation tool type, transportation schedule, ticket price, seat type, ticket booking time, ticket type, etc. corresponding to the historical trip of the current passenger. Exemplarily, the travel frequency of the current passenger corresponding to the historical trip refers to the number of trips of the historical trips of the current passenger within a certain time range, including the travel frequency of the current passenger in the same historical trip. Further, it may also include the travel frequency of the current passenger in all historical trips; where the same historical trip refers to a historical trip with the same departure place and destination and the same travel route. By counting the number of trips of the current passenger in the same historical trip within a certain time range, the travel frequency of the current passenger in the same historical trip can be obtained.

[0051] Step S120: extract and combine features from the current trip information, the current passenger information and the historical travel information of the current passenger to obtain the to-be-matched combined features corresponding to the current trip in multiple travel scenarios.

[0052] In the embodiments of the present application, the travel scenario can represent the travel intention, which is used to describe the user's travel purpose or travel motivation. The travel scenario can be understood as a classification of the user's travel needs and behavior patterns, including the major category dimension of the travel scenario type, and the dimension of at least one subcategory subdivided under the travel scenario type. Among them, the travel scenario type is a major classification of travel scenarios, indicating the main categories of travel scenarios, such as commuting, business travel, tourism, etc.; the subcategories under the travel scenario type are further subcategories of the travel scenario type, in order to more accurately describe the user's travel needs under the travel scenario type, such as the commuting travel scenario type can be further subdivided into weekly commuting and daily commuting subcategories. The subcategories subdivided under the travel scenario type can be multi-level subcategories, such as the first-level subcategories and second-level subcategories under the travel scenario type.

[0053] For ease of understanding, Figure 2 The following is an example diagram showing some travel scenarios. Figure 2 Some of the travel scenario types and subcategories, as well as the relevant definitions and characteristics of the examples can be referred to.

[0054] In the embodiment of the present application, multiple travel scenario types can be pre-set, and sub-categories can be subdivided under some or all travel scenario types; taking sub-categories under some travel scenario types as an example, sub-categories exist under some travel scenario types, but not under other travel scenario types, for example, Figure 2 As shown, Figure 2 In the example, there are subcategories under the travel scenario types such as commuting, tourism, and returning home, but there are no subcategories under the business travel travel scenario type. For travel scenario types with subcategories, a subcategories under a travel scenario type corresponds to a travel scenario, indicating a travel intention, and has corresponding definitions and characteristics; for example, the subcategories of nearby tours under the travel scenario type of tourism correspond to a travel scenario, and have corresponding definitions and characteristics; the subcategories of long-distance tours under the travel scenario type of tourism correspond to a travel scenario, and have corresponding definitions and characteristics, and so on. For travel scenario types without subcategories, a travel scenario type corresponds to a travel scenario, indicating a travel intention, and has corresponding definitions and characteristics; for example, the travel scenario type of business travel corresponds to a travel scenario, and has corresponding definitions and characteristics.

[0055] That is to say, the travel scenario is a specific situation that describes the travel purpose and motivation, and is an expression of travel intention; the travel scenario type is the type classification of travel scenarios (such as commuting, traveling, etc.), and the subclasses under the travel scenario type further refine the specific needs or details of travel (such as weekly commuting under commuting, long-distance travel under traveling, etc.). Thus, through the travel scenario type, or the combination of the travel scenario type and subclasses, the travel scenario can be expressed. That is, the travel scenario can include the travel scenario type, or can further include the subclasses subdivided under the travel scenario type to accurately express travel needs.

[0056] The travel intention recognition method provided by the embodiments of this application is mainly used to recognize the travel intention of the current trip. Specifically, based on the current trip information, current passenger information, and the historical travel information of the current passenger, the travel scenario that matches the current trip is determined from multiple travel scenarios (multiple travel scenario types and subclasses), and thus the travel intention of the current trip is determined based on the travel scenario that matches the current trip. To determine the travel scenario that matches the current trip from multiple travel scenarios, the embodiments of this application can extract features and combine features from the current trip information, current passenger information, and the historical travel information of the current passenger to obtain the to-be-matched combined features corresponding to the current trip in multiple travel scenarios; the to-be-matched combined features corresponding to the current trip in one travel scenario are used for the matching process of the current trip with this travel scenario to determine whether the current trip matches this travel scenario. Thus, based on the to-be-matched combined features corresponding to the current trip in multiple travel scenarios, the embodiments of this application can match out the travel scenario that conforms to the travel intention of the current trip from multiple travel scenarios.

[0057] In an alternative implementation, the embodiments of this application can set the feature types required for the matching of each travel scenario, and thus extract features and perform feature combination from the current trip information, current passenger information, and the historical travel information of the current passenger according to the feature types required for the matching of each travel scenario, to obtain the to-be-matched combined features corresponding to the current trip in each travel scenario. That is to say, the matching process of each travel scenario requires specific feature types. Thus, according to the feature types required for the matching of each travel scenario, the specific features required for the matching of each travel scenario are extracted from the current trip information, current passenger information, and the historical travel information of the current passenger, and feature combination is performed, then the combined features to be matched by the current trip in each travel scenario can be formed for use in the matching process with each travel scenario.

[0058] As an alternative implementation, for any travel scenario, the types of features required for travel scenario matching can be preset based on the definition and characteristics of the travel scenario. That is, the definition and characteristics of the travel scenario determine the types of features that need to be extracted from the current trip information, current passenger information, and historical travel information, and can be preset. For multiple travel scenarios, some travel scenarios may need to extract and combine features from all of the current trip information, current passenger information, and historical travel information, while some travel scenarios may only need to extract and combine features from one or two of the current trip information, current passenger information, and historical travel information, depending on the specific definition and characteristics of the travel scenario.

[0059] In a further alternative implementation, the number of candidate combined features corresponding to the current trip in any travel scenario can be at least one. For example, the current trip may correspond to one or more candidate combined features in a travel scenario. Among them, one candidate combined feature is composed of at least two features and can be regarded as a composite feature. For example, a travel scenario related to the type of travel scenario of returning home may need to comprehensively consider features such as the identity identifier of the current passenger, the departure place, and the destination to analyze whether the current passenger is traveling back and forth to their hometown. Therefore, features such as the identity identifier of the current passenger, the departure place, and the destination can be combined to form a candidate combined feature. Another example is that a travel scenario related to the type of travel scenario of returning home may also need to comprehensively consider features such as the departure date and the arrival date to analyze whether the travel is during a holiday period. The number and specific form of the candidate combined features corresponding to the current trip in any travel scenario can be determined based on the matching requirements of the travel scenario, and the embodiments of the present application do not impose any limitations.

[0060] Of course, in other possible implementations, for any travel scenario, after the embodiments of the present application extract the specific features required for travel scenario matching from the current trip information, current passenger information, and historical travel information, they can also support combining the extracted features as a whole into a candidate combined feature, so as to obtain the candidate combined feature corresponding to the current trip in the travel scenario.

[0061] As an example, in combination with Figure 2As shown, for the weekly commuting sub-category under the commuting travel scenario type, based on the definition and characteristics of weekly commuting, the embodiments of the present application can preset the feature types required for matching the weekly commuting sub-category. Thus, according to the feature types required for matching the weekly commuting sub-category, features corresponding to the feature types are extracted from the current trip information, the current passenger information, and the historical travel information, and combined into one or more feature combinations to be matched. For example, features such as the departure location, destination, departure time, arrival time, trip duration, fare, ticket type, etc. are extracted from the current trip information, features such as the age of the current passenger and the number of current passengers are extracted from the current passenger information, and features such as the travel frequency of the historical trip information with the same trip route as the current trip and the identity identifier of the passenger are extracted from the historical travel information. Thus, based on the matching requirements of the weekly commuting sub-category, these extracted features are combined into one or more feature combinations to be matched, and the feature combinations to be matched for the current trip in the weekly commuting travel scenario are obtained, so as to analyze whether the content of the feature combinations to be matched for the current trip in the weekly commuting matches the weekly commuting travel scenario. For example, analyze whether the content of the feature combinations to be matched for the current trip in the weekly commuting conforms to the definition and characteristics of the weekly commuting. For example, it can be analyzed whether it is a regular round trip every week, whether the trip duration matches the duration corresponding to a longer trip duration, and whether the passenger is an adult, etc.

[0062] For another example, for the summer vacation homecoming sub-category under the homecoming travel scenario type, based on the definition and characteristics of the summer vacation homecoming, the embodiments of the present application can preset the feature types required for matching the summer vacation homecoming sub-category. Thus, according to the feature types required for matching the summer vacation homecoming sub-category, features are extracted from the current trip information and the current passenger information and combined into one or more feature combinations to be matched. For example, features such as the departure location, destination, departure time, fare, seat type, ticket type, etc. are extracted from the current trip information, and features such as the age of the current passenger and the identity identifier (such as the identity number) are extracted from the current passenger information. That is, at this time, no features are extracted from the historical travel information. Thus, based on the matching requirements of the summer vacation homecoming sub-category, these extracted features are combined into one or more feature combinations to be matched, and the feature combinations to be matched for the current trip in the summer vacation homecoming travel scenario are obtained, so as to analyze whether the content of the feature combinations to be matched for the current trip in the summer vacation homecoming matches the summer vacation homecoming travel scenario. For example, analyze whether the content of the feature combinations to be matched for the current trip in the summer vacation homecoming conforms to the definition and characteristics of the summer vacation homecoming. For example, it can be analyzed whether the travel time is during the summer vacation, whether the current passenger is a student (analyzed by the age of the current passenger or whether the ticket type is a student ticket, etc.), and whether the destination is the hometown of the current passenger, etc.

[0063] In an alternative implementation, the native place of the current passenger can be determined through the identity identifier of the current passenger (such as an identity number). For example, the identity number of the current passenger contains the geographical region code of the native place of the current passenger. Specifically, the identity number is encoded according to certain rules, and a specific number in the identity number (such as the first 6 digits) represents the geographical region code of the native place. Thus, by analyzing whether the destination matches the native place corresponding to the identity number of the current passenger, it can be analyzed whether the current passenger returns to their hometown.

[0064] For another example, for the type of surrounding wanderers in the travel trip scenario type, based on the definition and characteristics of surrounding travel, the embodiments of the present application can preset the feature types required for matching the type of surrounding wanderers. Thus, according to the feature types required for matching the type of surrounding wanderers, features are extracted from the current trip information and combined into one or more to-be-matched combined features. For example, features such as the departure place, destination, departure time, arrival time, trip duration, ticket price, seat type, ticket booking time, etc. are extracted from the current trip information. Thus, based on the matching requirements of the type of surrounding wanderers, these extracted features are combined into one or more to-be-matched combined features, and the to-be-matched combined features of the current trip in the surrounding travel trip scenario are obtained, so as to analyze whether the content of the to-be-matched combined features of the current trip in the surrounding travel matches the surrounding travel trip scenario. For example, it can be analyzed whether the content of the to-be-matched combined features of the current trip in the surrounding travel matches the definition and characteristics of the surrounding travel. By way of example, it can be analyzed whether the travel time is on weekends or small holidays, and whether the destination is a nearby city or a nearby scenic spot, etc.

[0065] In an alternative implementation, the embodiments of the present application can obtain the travel time by extracting the departure time and the arrival time from the current trip information. Thus, by comparing the travel time with a pre-set calendar list, it can be determined whether the current trip falls on weekends (non-working days) and holidays. Holidays refer to national statutory holidays, local holidays, etc.

[0066] It should be noted that for any travel scenario (such as for any travel scenario type and subclass), the feature types required for travel scenario matching can be preset based on the definition and characteristics of the travel scenario, so as to preset the feature types required for travel scenario matching. Among them, the feature types required by different travel scenario types and their subclasses may be different, and the feature types required for travel scenario matching can be flexibly set according to the definition and characteristics of the travel scenario; furthermore, based on the preset feature types required for travel scenario matching, the embodiments of the present application can extract the features corresponding to the feature types from the current trip information, current passenger information, and historical travel information, and perform feature combination based on the matching requirements of the travel scenario to obtain one or more to-be-matched combined features corresponding to the current trip in the travel scenario, so as to realize the conversion of the feature information in the current trip information, current passenger information, and historical travel information into the to-be-matched combined features corresponding to the current trip in the travel scenario, so as to provide support for matching the travel scenario that conforms to the travel intention of the current trip from multiple travel scenarios.

[0067] For ease of understanding, Figure 3 An exemplary diagram showing some of the feature types required for travel scenario matching is provided for reference.

[0068] Step S130: Match the to-be-matched combined features of the current trip in each travel scenario with the feature requirements of each travel scenario respectively, so as to determine the travel scenario that the current trip matches from multiple travel scenarios; among them, the feature requirements of the travel scenario conform to the definition and characteristics of the travel scenario.

[0069] In the embodiments of the present application, each travel scenario has specific feature requirements, and the feature requirements of the travel scenario conform to the definition and characteristics of the travel scenario; the feature requirements of the travel scenario can be understood as a detailed description of the features of the travel scenario, reflecting the definition and characteristics of the travel scenario. That is to say, the feature requirements of the travel scenario are specific descriptions of the feature attributes of the travel scenario, including the feature matching criteria and the range of feature thresholds of the travel scenario, etc., and are the criteria for judging whether the current trip matches the travel scenario.

[0070] For ease of understanding, Figure 4 An exemplary diagram showing some of the feature requirements of some travel scenarios is provided for reference. It should be noted that Figure 4 The illustration is only for example, and the feature requirements of each travel scenario can be set based on the definition and characteristics of the travel scenario. The embodiments of the present application do not limit the specific form and content of the feature requirements of the travel scenario, as long as the feature requirements of the travel scenario conform to the definition and characteristics of the travel scenario and can be used as the matching criteria for the travel scenario.

[0071] For any travel scenario, the embodiments of the present application can match the to-be-matched combined features of the current trip in the travel scenario with the feature requirements of the travel scenario, so as to determine whether the current trip matches the travel scenario, that is, whether the current trip belongs to the travel scenario; furthermore, by respectively matching the to-be-matched combined features of the current trip in each travel scenario with the feature requirements of each travel scenario, the travel scenario that the current trip matches in multiple travel scenarios can be determined, that is, the travel scenario that the current trip belongs to among multiple travel scenarios.

[0072] In an alternative implementation, for any travel scenario, the embodiments of the present application can compare the to-be-matched combined features of the current trip in the travel scenario with the feature requirements of the travel scenario. If the to-be-matched combined features of the current trip in the travel scenario meet the feature requirements of the travel scenario, for example, the to-be-matched combined features of the current trip in the travel scenario are consistent with the feature requirements of the travel scenario or within the feature threshold range of the feature requirements, then the current trip matches the travel scenario, that is, the current trip belongs to the travel scenario; if the to-be-matched combined features of the current trip in the travel scenario do not meet the feature requirements of the travel scenario, for example, the to-be-matched combined features of the current trip in the travel scenario are inconsistent with the feature requirements of the travel scenario or not within the feature threshold range of the feature requirements, then the current trip does not match the travel scenario, that is, the current trip does not belong to the travel scenario.

[0073] In a further alternative implementation, the embodiments of the present application can set up a travel scenario knowledge base and train a travel intention recognition model, so as to use the travel intention recognition model and the travel scenario knowledge base to respectively match the to-be-matched combined features of the current trip in each travel scenario with the feature requirements of each travel scenario, and obtain the travel scenario that the current trip matches in multiple travel scenarios. For example, the to-be-matched combined features of the current trip in each travel scenario are respectively input into the travel intention recognition model, so that the travel intention recognition model, based on the travel scenario knowledge base, respectively matches the to-be-matched combined features of the current trip in each travel scenario with the feature requirements of each travel scenario, and thus the embodiments of the present application can obtain the travel scenario that the current trip matches output by the travel intention recognition model.

[0074] In the embodiments of the present application, the travel intention recognition model is a model for recognizing travel intentions, and the model form includes but is not limited to large models (such as natural language processing models), rule models, etc. The travel scenario knowledge base can be regarded as the background knowledge base of the travel intention recognition model, which records the background knowledge of multiple travel scenarios. Among them, the background knowledge of a travel scenario includes but is not limited to the definition and characteristics of the travel scenario, and the feature requirements of the travel scenario; for the sake of understanding, Figure 5An exemplary composition example diagram of the travel scenario knowledge base is shown for reference. The travel scenario knowledge base can be used to assist the travel intention recognition model in understanding the definitions, characteristics, and feature requirements of each travel scenario; furthermore, by inputting the to-be-matched combined features of the current trip in each travel scenario into the travel intention recognition model, the travel intention recognition model can determine the travel scenario that the current trip matches from multiple travel scenarios based on the records in the travel scenario knowledge base.

[0075] As an optional implementation, taking the travel intention recognition model as a large model for recognizing travel intentions as an example, a large model refers to a model that can process a large amount of data and perform automatic feature learning and prediction. The large model can adopt a natural language processing model or other deep learning models. In the embodiments of the present application, the travel intention recognition model can be regarded as an inference engine or knowledge inference system for travel intentions. By providing the travel scenario knowledge base to the travel intention recognition model, the travel intention recognition model can understand the background knowledge related to travel scenarios, including but not limited to understanding the definitions, characteristics, feature requirements, etc. of each travel scenario (such as each travel scenario type and subclass). Further, the travel scenario knowledge base can be continuously improved and updated according to the actual situation, such as by expert input, historical data analysis, etc. to improve and update the background knowledge of the travel scenarios recorded in the travel scenario knowledge base.

[0076] In an optional implementation, the travel intention recognition model in the form of a large model can understand the background knowledge of the travel scenarios recorded in the travel scenario knowledge base through pattern learning or inference algorithms, enabling the travel intention recognition model to have the reasoning ability to match travel scenarios for the current trip. Furthermore, by inputting the to-be-matched combined features of the current trip in each travel scenario into the travel intention recognition model in the form of a large model, the travel intention recognition model can perform matching processing on the to-be-matched combined features of the current trip in the travel scenario and the feature requirements of the travel scenario according to the background knowledge of the travel scenarios recorded in the travel scenario knowledge base; if the travel intention recognition model determines that the to-be-matched combined features of the current trip in a certain travel scenario match the feature requirements of that travel scenario, the travel intention recognition model can determine that travel scenario as the travel scenario matched by the current trip, and thus output the matched travel scenario.

[0077] As an alternative implementation, taking the travel intention recognition model as an example of the rule model for identifying travel intentions, the rule model relies on explicit rule sets for matching processing. Specifically, the rule model is composed of matching rules for each travel scenario. Among them, the matching rules for travel scenarios are formed based on the background knowledge of travel scenarios recorded in the travel scenario knowledge base, that is, the matching rules for travel scenarios correspond to the background knowledge of travel scenarios. For ease of understanding, as an example, taking the background knowledge of travel scenarios including the feature requirements of travel scenarios as an example, the rule model may include the following simplified matching rules for daily commuting: If the travel time is during the morning rush hour and the frequency is every working day, then it matches daily commuting.

[0078] As an alternative implementation, after constructing the travel scenario knowledge base, the embodiments of the present application can construct matching rules for each travel scenario (one or more matching rules for a travel scenario) based on the background knowledge of each travel scenario in the travel scenario knowledge base, and form a travel intention recognition model in the form of a rule model. Furthermore, the rule model checks whether the to-be-matched combined features of the current trip in the travel scenario match the feature requirements of the travel scenario through the matching rules of the travel scenario, so as to confirm the travel scenario matched by the current trip. For example, the matching rule can be a rule structure of conditions and conclusions. Thus, taking the to-be-matched combined features of the current trip in the travel scenario as the input and the feature requirements of the travel scenario as the conditions, when the input meets the conditions, the travel intention recognition model in the form of a rule model can draw the conclusion that the current trip matches the travel scenario.

[0079] Of course, the large model and the rule model are only alternative model forms of the travel intention recognition model. The embodiments of the present application can also support travel intention recognition models in other model forms, and are not limited to the large model and the rule model.

[0080] Step S140: Determine the travel intention of the current trip according to the travel scenario matched by the current trip.

[0081] As an alternative implementation, the travel scenario(s) matched by the current trip may be one or more. For example, the current trip matches one or more travel scenarios. Specifically, there may be intersections or overlaps in the definitions and characteristics of some travel scenarios (for example, travel scenarios related to returning home and traveling may both occur during holidays). Thus, multiple features of the current trip (such as departure time, departure place, destination, etc.) may simultaneously meet different travel scenarios, so it is possible for the current trip to match more than one travel scenario.

[0082] For example, taking the current itinerary where the user goes home to visit relatives during holidays and their hometown is a tourist city as an example, there are similarities between the to-be-matched combined features of the current itinerary in the travel scenarios related to returning home and those in the travel scenarios related to tourism. Therefore, when the travel intention recognition model determines the travel scenario matched by the current itinerary, the current itinerary may match both the travel scenarios related to returning home and those related to tourism.

[0083] That is to say, the intersection of the definitions and characteristics of travel scenarios makes it possible for the current itinerary to have multiple matches in more than one travel scenario, which conforms to the matching logic of actual travel scenarios.

[0084] In an alternative implementation, if the travel scenario matched by the current itinerary is one, the travel scenario matched by the current itinerary can be directly used as the travel intention of the current itinerary.

[0085] In an alternative implementation, if the travel scenarios matched by the current itinerary are multiple, the embodiments of the present application can determine the travel scenario with the highest priority among the travel scenarios matched by the current itinerary according to the priorities of the respective travel scenarios matched by the current itinerary as the travel intention of the current itinerary.

[0086] As an alternative implementation, the priority of a travel scenario can be determined based on the matched proportion of the travel scenario. The matched proportion of a travel scenario represents the proportion of the number of times the travel scenario has been matched to the total number of matches of multiple travel scenarios. Thus, the travel scenario with the highest matched proportion among the travel scenarios matched by the current itinerary is the travel scenario with the highest priority. That is to say, the matched proportion of a travel scenario refers to the proportion of the number of times the travel scenario has been matched among all travel scenarios. For example, if the total number of matches of all travel scenarios is 100 times, that is, the travel service platform has performed travel intention recognition on multiple itineraries and the travel scenarios matched by the multiple itineraries as a whole are 100 times. Further, assuming that the number of times the travel scenario of daily commuting has been matched is 50 times, that is, the travel service platform has performed travel intention recognition on multiple itineraries and the travel scenario of daily commuting has been matched 50 times, then the matched proportion of the travel scenario of daily commuting is 50 / 100 = 50%. By calculating the proportion of the number of times a travel scenario has been matched to the total number of matches of all travel scenarios, the relative priority of the travel scenario can be determined. Thus, when the current itinerary matches more than one travel scenario, the travel scenario with the highest priority among the travel scenarios matched by the current itinerary is used as the travel intention of the current itinerary, that is, the travel scenario with the highest matched proportion among the travel scenarios matched by the current itinerary is the travel intention of the current itinerary.

[0087] The travel intention recognition method provided by the embodiments of the present application comprehensively considers multi-dimensional information such as current trip information, current passenger information, and the historical travel information of the current passenger, and performs matching processing between the current trip and travel scenarios. Specifically, features are extracted and combined from the current trip information, current passenger information, and historical travel information to form a to-be-matched combined feature corresponding to the current trip in multiple travel scenarios, so that the to-be-matched combined feature corresponding to the current trip in the travel scenario can reflect the information and background of each dimension of the current trip, avoid the deviation that may exist in the single-dimensional information of the current trip, and ensure that the background of the current trip is fully considered when matching the travel scenario of the current trip. Then, based on the feature requirements of the travel scenario that conform to the definition and characteristics of the travel scenario, the to-be-matched combined features of the current trip in each travel scenario are respectively matched with the feature requirements of each travel scenario to determine the travel scenario matched by the current trip from multiple travel scenarios, so as to accurately determine the travel scenario matched by the current trip. That is to say, each travel scenario has clear feature requirements that conform to the specific definition and characteristics of the travel scenario. By comparing and matching the to-be-matched combined feature of the current trip in the travel scenario with the feature requirements of the travel scenario, it can be more accurately judged whether the current trip meets the requirements of the travel scenario, so as to accurately identify the travel scenario matched by the current trip from multiple travel scenarios. At the same time, the historical travel information of the current passenger is considered in the process of travel intention recognition. Since the historical travel information of the current passenger helps to understand the historical travel habits and preferences of the current passenger, the travel scenario matched by the current trip can be made more accurate. Furthermore, according to the travel scenario matched by the current trip, the travel intention of the current trip is determined, and then the travel intention recognition of the current trip can be completed. In summary, the embodiments of the present application can improve the recognition accuracy of travel intention and provide support for improving the accuracy of travel strategy recommendation.

[0088] As an implementation example, Figure 6 An exemplary architecture diagram of the travel service platform provided by the embodiments of the present application is shown, as Figure 6 shown, the travel service platform may include: a ticketing system 610, a historical travel database 620, and a travel intention recognition system 630.

[0089] A ticketing system 610 is used to provide ticketing services such as booking tickets and querying tickets for users; the ticketing system 610 can transmit the current itinerary information and current passenger information of the current itinerary in the user's ticket request to the travel intention recognition system 630. In an alternative implementation example, when the user books a ticket through the ticketing system 610, if there are no remaining tickets for the travel plan expected by the user (for example, there are no remaining tickets for the train or flight expected by the user), the ticketing system 610 can transmit the current itinerary information and current passenger information of the current itinerary in the ticket booking request to the travel intention recognition system 630, so that the travel intention recognition system 630 can recognize the travel intention of the current itinerary and provide support for recommending alternative travel plans for the user.

[0090] The historical travel database 620 records the historical travel information of multiple passengers; after the travel intention recognition system 630 obtains the current itinerary information and current passenger information transmitted by the ticketing system 610, it can retrieve the historical travel information of the current passenger from the historical travel database 620 based on the current passenger information; thus, the travel intention recognition system 630 can obtain the current itinerary information, current passenger information, and historical travel information of the current passenger to perform travel intention recognition of the current itinerary.

[0091] The travel intention recognition system 630 may include: a preprocessing module 631, a travel intention recognition model 632, a postprocessing module 633, and a travel scenario knowledge base 634.

[0092] Among them, the preprocessing module 631 is used to extract and combine features from the current itinerary information, current passenger information, and historical travel information to obtain the to-be-matched combined features corresponding to the current itinerary in multiple travel scenarios;

[0093] The travel intention recognition model 632 is used to match the to-be-matched combined features of the current itinerary in each travel scenario with the feature requirements of each travel scenario respectively, so as to determine the travel scenario that the current itinerary matches from multiple travel scenarios; among them, the feature requirements of the travel scenario conform to the definition and characteristics of the travel scenario;

[0094] The postprocessing module 633 is used to determine the travel intention of the current itinerary according to the travel scenario that the current itinerary matches;

[0095] The travel scenario knowledge base 634, as the background knowledge base of the travel intention recognition model, records the background knowledge of multiple travel scenarios, and the background knowledge of the travel scenario at least includes the definition, characteristics, and feature requirements of the travel scenario.

[0096] The relevant content of the preprocessing module, travel intention recognition model, postprocessing module, and travel scenario knowledge base in the travel intention recognition system 630 can be referred to the corresponding description in the previous text and will not be elaborated here. In an alternative implementation, the travel intention recognition model can be a large model or a rule model. The relevant content of the travel intention recognition model in the form of a large model or a rule model can be referred to the corresponding description in the previous text and will not be elaborated here.

[0097] Further, in combination with Figure 6 As shown, the travel service platform may further include: a proportion data recording module 640 for recording the matched proportion of each travel scenario. Thus, when the travel scenarios matched by the current trip determined by the travel intention recognition model 632 are more than one, the postprocessing module 633 may, based on the matched proportion of each travel scenario recorded by the proportion data recording module, determine the travel scenario with the highest matched proportion among the travel scenarios matched by the current trip as the travel intention of the current trip. In other alternative implementations, if the travel scenario matched by the current trip determined by the travel intention recognition model 632 is one, the postprocessing module 633 may directly determine the travel scenario matched by the current trip as the travel intention of the current trip.

[0098] In a further alternative implementation, the proportion data recording module can be regarded as part of the overall proportion data system of the travel service platform. The overall proportion data system is a large-scale analysis system of the travel service platform based on global data, aiming to identify group characteristics and travel trends by statistically analyzing the behavior patterns of all users. That is to say, the overall proportion data system is a macroscopic analysis tool that provides reference data at the overall level. For example, it collects the ticket booking data of all users and extracts characteristic information such as the departure place, destination, travel time, and seat type, so as to analyze the overall travel trends (such as popular routes, ticket demands at different time periods, etc.). Further, the overall proportion data system can also collect and analyze the user data of all users (such as age groups, occupation distributions, regional preferences) and group characteristics related to travel. Through the macroscopic analysis of the full-scale data by the overall proportion data system, the travel rules of specific times, specific regions, and specific populations can be determined. In the embodiments of the present application, the matched proportion of each travel scenario, as a type of data collected and analyzed by the overall proportion data system, can be recorded in the proportion data recording module in the overall proportion data system.

[0099] Further, in combination with Figure 6As shown in the figure, the travel service platform may further include a travel intention storage module 650. As the travel intention storage layer of the travel service platform, the travel intention storage module 650 can be used to store the travel intention data of each trip. In an alternative implementation, the travel intention data of a trip may at least include the travel intention of the trip, and may further include the OD (Origin / Destination) pair corresponding to the trip. For example, for multiple trips submitted by multiple users to the travel service platform, the travel service platform can use the travel intention recognition method provided in the embodiments of the present application to determine the travel intention of each trip, so that the travel intention of each trip, as well as the departure place and destination (i.e., the OD pair) corresponding to each trip, form the travel intention data of each trip and are stored in the travel intention storage module.

[0100] In a further alternative implementation, the travel intention data of the trips stored in the travel intention storage module may expire over time, that is, the travel intention data of the trips may lose timeliness over time. For example, the travel intention related to returning home during holidays may expire after the holidays, so the expired travel intention data in the travel intention storage module needs to be cleared regularly to maintain the efficient operation of the travel intention storage module. Further, when the deviation between the travel intention and the actual travel behavior of the user is large, the determined travel intention may become invalid. For example, if the user originally planned to return home but finally changed the ticket to a non-hometown location, there is a deviation between the travel intention and the actual travel behavior of the user, and the travel intention becomes invalid; the travel intention data corresponding to the invalid travel intention can be marked as invalid data.

[0101] Further, in combination with Figure 6 As shown in the figure, the travel service platform may further include: a verification module 660, which is used to verify whether the travel scenario matched by the current trip output by the travel intention recognition model 632 conforms to the corresponding verification rules of the travel scenario according to the verification list; if not, a warning prompt message is triggered. Through the verification module 660, the output result (the travel scenario matched by the current trip) of the travel intention recognition model 632 can be verified, and then the travel intention recognition model can be optimized based on the verification result, which can improve the reliability and accuracy of travel intention recognition. As an example, the verification module can set the verification rules corresponding to each travel scenario through the verification list to verify the output result of the travel intention recognition model, and the verification rules of the travel scenario may be partially similar to the rules when the travel intention recognition model matches the travel scenario for the current trip.

[0102] For example, for any travel scenario, the verification list can specifically record the verification items corresponding to the travel scenario in the current trip information, the current passenger information, and the historical travel information. Figure 7An exemplary diagram showing an example of the verification rules for some travel scenarios recorded in a verification list can be referred to.

[0103] Furthermore, in addition to the definition, characteristics, and feature requirements of travel scenarios, the background knowledge of travel scenarios recorded in the travel scenario knowledge base may also include: extended knowledge points and logical rules for matching travel scenarios to help the travel intention recognition model more accurately determine the travel scenario matching the current trip in specific tasks. Exemplarily, the knowledge points and logical rules that the travel scenario knowledge base can extend for matching travel scenarios include, but are not limited to:

[0104] Identity number rule, used to analyze the identity number of the current passenger to determine the hometown origin; for example, the travel scenario knowledge base can extend the knowledge points and logical rules of the geographical locations corresponding to geographical area codes, where the identity number contains the geographical area code of the place of origin; the identity number rule is used when judging whether the travel intention of the current trip is a travel scenario related to returning to one's hometown.

[0105] Tourist city rule, used to identify whether the destination is a tourist city to assist in judging the travel intention, such as determining whether the travel intention is for tourism; thus, the travel scenario knowledge base can extend knowledge points and logical rules such as the list of tourist cities and their corresponding scenic spot information; the tourist city rule is used when judging whether the travel intention of the current trip is a travel scenario related to tourism. If the destination of the current trip is in the list of tourist cities, or the destination is associated with the scenic spots corresponding to the tourist city, it can be judged that the travel intention of the current trip conforms to the travel scenario related to tourism; further, in combination with holiday data, it can be determined whether the travel scenario related to tourism is a holiday tourism.

[0106] It should be noted that the extended knowledge points and logical rules of the travel scenario knowledge base can be determined according to the actual situation. The above is only an example; for example, based on the definition, characteristics, and matching requirements of specific travel scenarios, the knowledge points and logical rules required by the travel scenario knowledge base in specific travel scenarios can be extended. The embodiments of the present application do not limit this.

[0107] In a further optional implementation, after the travel service platform determines the travel intention of the current trip, it can recommend travel strategies based on the travel intention of the current trip. As an optional implementation, Figure 8 An exemplary optional flowchart of the travel strategy recommendation method provided by the embodiments of the present application is shown. This travel strategy recommendation method can be applied to a travel service platform, such as specifically applied to a travel server.

[0108] Refer to Figure 8 , the travel strategy recommendation method provided by the embodiments of the present application may include the following steps.

[0109] Step S810: Obtain the travel intention of the current trip.

[0110] In an alternative implementation, the current trip can be submitted to the travel service platform through travel service requests such as ticket requests and travel strategy recommendation requests. Thereby, the travel service platform can use the travel intention recognition method provided in the embodiments of the present application to determine the travel intention of the current trip. The relevant content for recognizing the travel intention of the current trip can be referred to the previous description and will not be elaborated here.

[0111] In an alternative implementation, the embodiments of the present application can directly determine the travel intention of the current trip after obtaining the travel service request. For example, if the travel service request is a travel strategy recommendation request directly requesting a travel strategy, the travel intention of the current trip can be directly determined. Also, for example, the embodiments of the present application can determine the travel intention of the current trip without restricting the type and specific form of the travel service request.

[0112] In other alternative implementations, the embodiments of the present application can determine the travel intention of the current trip after obtaining the travel service request and when the preset travel intention recognition conditions are met. For example, when the travel service request is a ticket request, the embodiments of the present application can determine the travel intention of the current trip when the ticket status corresponding to the ticket request meets the preset travel intention recognition conditions.

[0113] Exemplarily, taking the ticket booking request in the ticket request as the travel service request as an example, the ticket booking request is used to book tickets for the expected travel plan of the current trip (such as the expected train number or expected flight). If there are no remaining tickets for the expected travel plan of the current trip, it is considered that the preset travel intention recognition conditions are met, and the embodiments of the present application can determine the travel intention of the current trip.

[0114] Step S820: Determine the travel preference information of the current passenger.

[0115] The travel preference information of the current passenger refers to the habits and tendencies of the current passenger during travel. In an alternative implementation, the travel preference information of the current passenger can be the personal travel preference information of the current passenger or the population travel preference information of the group to which the current passenger belongs. That is to say, the embodiments of the present application can use the personal travel preference information of the current passenger as the travel preference information of the current passenger; or use the population travel preference information of the group to which the current passenger belongs as the travel preference information of the current passenger.

[0116] The personal travel preference information of the current passenger can be determined based on the historical travel information of the current passenger, and / or personalized settings, and / or the operation records of the current passenger on the travel service platform, and is regarded as the personalized travel preference of the current passenger; for example, the personal travel preference information of the current passenger is determined based on the historical travel records of the current passenger, the active selection of the current passenger (such as the preference settings filled in by the current passenger on the travel service platform), the behavior operations of the current passenger on the travel service platform (such as frequently querying a certain type of transportation tool), etc.

[0117] In an alternative implementation, the travel service platform can record the personal travel preference information of each passenger through a personal travel preference database, including the passenger information of each passenger and the corresponding personal travel preference information; thus, the embodiments of the present application can obtain the personal travel preference information of the current passenger from the personal travel preference database based on the identity identifier of the current passenger. In an alternative implementation example, the personal travel preference information can be regarded as a part of the personal portrait.

[0118] The population travel preference information of the population to which the current passenger belongs refers to the general travel preference information of the population to which the current passenger belongs, that is, the population travel preference information is the general travel preference characteristics of a specific group, rather than the personalized characteristics of a single individual. The population travel preference information, as a group preference, does not change with the short-term behavior of an individual; in an alternative implementation, the embodiments of the present application can determine the population travel preference information of each population based on the massive group data related to travel accumulated by the travel service platform.

[0119] In an alternative implementation, the travel service platform can record the population travel preference information of each population through a population travel preference database, including the population characteristics of each population and the corresponding population travel preference information; thus, the embodiments of the present application can determine the population characteristics corresponding to the passenger information of the current passenger based on the passenger information of the current passenger, and thus determine the population corresponding to the population characteristics as the population to which the current passenger belongs. For example, the population can be classified according to dimensions such as age, occupation, and region, so as to divide different populations; furthermore, obtain the population travel preference information of the population to which the current passenger belongs from the population travel preference database.

[0120] For example, the travel preference information of the current passenger (not limited to the personal travel preference information or the population travel preference information of the current passenger) may include at least one of the following:

[0121] Travel time preference, such as departure time preference, arrival time preference, etc.;

[0122] Arrival time overflow sensitivity, such as the sensitivity of the user to the overtime of the transportation tool arriving at the destination station in the case that the transportation tool does not arrive at the destination station on time;

[0123] Departure time overflow sensitivity, such as the degree of sensitivity of a user to the overtime of a transportation vehicle departing from the departure station when the transportation vehicle fails to depart from the departure station on time;

[0124] Fare preference, such as the degree of sensitivity of a user to fare overflow;

[0125] Comfort preference, that is, the comfort requirements of a user for a transportation vehicle, such as transportation vehicle preference, seat preference, etc.;

[0126] Trip duration overflow sensitivity, such as the degree of sensitivity of a user to trip overtime;

[0127] Departure anxiety level, that is, whether a user is prone to anxiety about departure. With a high anxiety level, the user tends to arrive at the departure station well in advance, while with a low anxiety level, the user tends to arrive at the departure station near the departure time.

[0128] Of course, the above travel preference information is only for illustrative purposes. The embodiments of the present application do not limit the specific form of travel preference information, as long as it can express the habits and tendencies of passengers during travel.

[0129] Step S830: Recommend a travel strategy for the current trip according to the travel intention of the current trip and the travel preference information of the current passenger.

[0130] After determining the travel intention of the current trip and the travel preference information of the current passenger, the embodiments of the present application can combine the travel intention of the current trip (such as returning home, business travel, tourism, etc.) and the travel preference information to recommend a travel strategy. For example, under the travel intention of the current trip, a travel plan and / or travel additional services that meet the travel preferences of the current passenger are recommended.

[0131] Exemplarily, when the travel intention of the current trip is a commuting-related travel scenario, the embodiments of the present application can combine the travel preference information of the current passenger to recommend a travel plan that meets the commuting needs from multiple aspects such as transportation vehicles, time arrangements, transfer plans, seat types, etc.; further, additional services such as shuttle services for commuting-related travel scenarios and commuting preferential plans (such as high-speed rail monthly passes, subway monthly passes, etc.) can also be provided to enhance the commuting experience and convenience.

[0132] Exemplarily, when the travel intention of the current trip is a travel scenario of returning home during major holidays (such as returning home during the Spring Festival), the embodiments of the present application can combine the travel preference information of the current passenger to recommend a travel plan that meets the needs of returning home during major holidays (such as returning home during the Spring Festival) from multiple aspects such as transportation vehicles, travel time, ticket priority, etc.; further, additional services such as transfer guidance and itinerary reminders can also be provided to ensure that passengers can return home smoothly and improve travel convenience and comfort.

[0133] Exemplarily, in the travel scenario where the travel intention of the current trip is for business travel, the embodiments of the present application can, in combination with the travel preference information of the current passenger, recommend travel plans that meet the business travel needs from multiple aspects such as transportation means with priority on efficiency, flexible time arrangements, and seat selections with higher comfort; further, additional services such as itinerary planning, fast security check, and transportation connection can also be provided to improve the travel efficiency and experience of business travelers.

[0134] Exemplarily, in the travel scenario where the travel intention of the current trip is related to tourism, the embodiments of the present application can, in combination with the travel preference information of the current passenger, recommend travel plans that meet the tourism needs from multiple aspects such as transportation means suitable for leisure and flexible ticket selections; further, additional services such as scenic spot information introduction, hotel reservation, and transportation connection can also be provided to help passengers optimize itinerary arrangements and enhance the overall tourism experience.

[0135] As an implementation example, Figure 9 Exemplarily, another architecture example diagram of the travel service platform provided by the embodiments of the present application is shown, in combination with Figure 6 and Figure 9 as shown, on the basis of the Figure 6 example, the travel service platform shown in Figure 9 may further include: a travel strategy recommendation system 910.

[0136] The travel strategy recommendation system 910 is used to obtain the travel intention of the current trip and determine the travel preference information of the current passenger; according to the travel intention of the current trip and the travel preference information of the current passenger, recommend the travel strategy of the current trip.

[0137] In an optional implementation, the travel intention of the current trip can be stored in the travel intention storage module 650, and the travel strategy recommendation system 910 can obtain the travel intention of the current trip from the travel intention storage module 650.

[0138] In a further optional implementation, the travel service platform may further include: a travel preference database 920 that records travel preference information; the travel preference database 920 can be a personal travel preference database that records the personal travel preference information of each passenger, or a population travel preference database that records the population travel preference information of each population. The embodiments of the present application can detect the travel preference information of the current passenger from the travel preference database 920, such as detecting the population travel preference information of the population to which the current passenger belongs, so as to input the detected travel preference information of the current passenger into the travel strategy recommendation system 910, so that the travel strategy recommendation system 910 combines the travel intention of the current trip and the travel preference information of the current passenger to recommend the travel strategy of the current trip.

[0139] In a further optional implementation, the travel strategy recommendation system 910 may include a strategy management component for managing recommendation rules (such as recommendation algorithms), trigger conditions, etc. of travel strategies.

[0140] In a further optional implementation, taking the recommendation of travel plans as an example, the recommendation rules (such as recommendation algorithms) of the travel strategy recommendation system may be implemented based on a recall strategy and a scoring strategy. The recall strategy and the scoring strategy are respectively responsible for two key stages in the travel strategy recommendation process: the preliminary screening stage (recall stage) and the precise ranking stage (scoring stage). That is, the recall strategy and the scoring strategy are important components of the recommendation algorithm (for recommending travel strategies), and the purpose is to recommend efficient and accurate travel plans for passengers.

[0141] As an optional implementation, the purpose of the recall strategy is to quickly screen out a candidate set related to travel needs to reduce subsequent computational workload and improve recommendation efficiency. Among them, the candidate set may include multiple candidate travel plans. The recall strategy has the following characteristics: large scope, a relatively large candidate set will be screened out during recall (for example, selecting train trips that match the destination from all train trip information); quick screening, mainly filtering out travel plans that obviously do not meet travel needs; coarse-grained screening, not particularly finely sorting candidate travel plans, only ensuring that these candidate travel plans are related to travel needs. For example, in the travel scenario of returning home during the Spring Festival, the recall strategy can screen out train trips that match the destination of the itinerary from all train ticket information during the travel time related to returning home during the Spring Festival.

[0142] In a more specific optional implementation, the recall strategy may include at least one of the following sub-strategies:

[0143] Rejection sub-strategy, eliminating travel plans that do not meet passenger preferences; for example, if the passenger preference is to only accept high-speed train trips, regular-speed train trips will be directly eliminated. If the passenger preference is not to accept evening trips, trips departing in the evening will be eliminated;

[0144] Inter-city transfer sub-strategy, recommending travel plans that require inter-city transfers;

[0145] Time limit sub-strategy, recalling travel plans within a specified time period;

[0146] Price limit sub-strategy, eliminating travel plans that exceed the passenger's budget.

[0147] That is to say, in the case of recommending travel plans, the core purpose of the recall strategy is to quickly find candidate travel plans that may meet travel needs (travel needs can be determined by combining travel intentions and travel preferences), and provide input for the subsequent scoring strategy stage.

[0148] As an alternative implementation, the scoring strategy is to perform precise scoring and ranking based on multiple dimensions on the candidate set generated by the recall strategy, so as to select the recommended travel plan. The scoring strategy has the following characteristics: small scope, only targeting the candidate set provided by the recall strategy; precise calculation, detailed evaluation and ranking of the candidate travel plans in the candidate set; fine-grained ranking, determining the priority in combination with the specific travel preference information of the passenger (such as time, price, comfort).

[0149] As an example, the scoring dimensions of the recall strategy may include at least one of the following:

[0150] Departure time, giving priority to recommending trains that meet the passenger's time preference;

[0151] Price, according to the passenger's fare preference, giving priority to recommending trains that meet the budget;

[0152] Travel time, recommending travel plans with shorter total travel time;

[0153] Booking success rate, in the booking scenario, giving priority to recommending trains with a higher booking success rate.

[0154] That is to say, in the case of recommending a travel plan, the core purpose of the scoring strategy is to select the recommended travel plan from the candidate set of the recall strategy to ensure the accuracy of the recommended travel plan.

[0155] In a further alternative implementation, the travel service platform may further include a test component 930, which is used to test the impact of different versions of the travel strategy on user behavior by using a controlled experiment test method (such as the AB test method), such as the impact of different versions of the travel strategy on user click-through rate and order conversion rate, so as to optimize the recommendation logic of the travel strategy. In the alternative implementation, the test component may adopt a test method of controlled experiments such as the AB test to test the impact of different versions of the travel strategy on user behavior; specifically, the AB test is a test method of controlled experiments used to compare the differences between two or more versions of the travel strategy, so as to evaluate the impact of different versions of the travel strategy on user behavior or system goals (such as click-through rate, order conversion rate, etc.), so as to optimize the recommendation logic of the travel strategy.

[0156] In the alternative implementation, different versions of the travel strategy may include the travel strategy of the first version and the travel strategy of the second version. In the embodiments of the present application, the travel strategy of the second version is determined based on travel intent and travel preference information, and the travel strategy of the first version is the original version of the travel strategy.

[0157] For example, the travel strategy of the first version can be regarded as the travel strategy of version A in the A / B test, that is, the original travel strategy, and the original travel strategy is not determined by using the technical solution provided in the embodiments of the present application; the travel strategy of the second version can be regarded as the travel strategy of version B in the A / B test, that is, the new travel strategy, and the new travel strategy is determined by using the technical solution provided in the embodiments of the present application, that is, the travel strategy of the second version is determined by combining travel intentions and travel preferences.

[0158] During the testing process, the embodiments of the present application can define the key metrics of the test, such as the key metrics being to increase the user click-through rate, improve the order conversion rate, optimize the user retention rate, etc.; furthermore, users are randomly divided into two groups, for example, users are randomly divided into group A and group B, group A experiences version A, and group B experiences version B, and it is ensured that the distribution of the two groups of users is random and uniform; the testing component compares the performance of group A and group B in terms of the key metrics by collecting the behavior data of users corresponding to version A and version B, such as how many times the user clicks on the recommended content, how many orders the user has completed, etc., to determine the version with better performance in the key metrics, so as to optimize the recommendation logic.

[0159] In a further optional implementation, the travel service platform may further include a data logging and analysis system 940, which is used to collect and analyze user behavior data through data logging to optimize the performance of the travel strategy recommendation system and the travel strategies recommended by the travel strategy recommendation system.

[0160] Specifically, data logging refers to presetting data collection points in the key processes or user behaviors of the system, and recording the behaviors, operations, and feedback of users through logging.

[0161] In an optional implementation, the dimensions of data logging can be test dimensions and population dimensions.

[0162] The data logging for the test dimension is used to evaluate the effects of different versions of travel strategies (such as the travel strategies of version A and version B in the A / B test); the logged content can be recall data and link data; among them, the recall data can include coverage rate, indicating whether the recalled candidate solutions can meet the user's needs, for example, whether the recalled candidate solutions contain the user's expected destination or departure time; the link data can include the seat occupancy success rate and the ticket issuance rate, etc. The seat occupancy success rate is used to count the success rate of users preempting the required seats in scenarios such as booking tickets during holidays (such as the Spring Festival travel rush), and the ticket issuance rate is used to count the proportion of users who actually complete ticket issuance.

[0163] Data logging at the population dimension is used to analyze whether the recommended travel strategies meet the needs of different populations according to their preferences, so as to evaluate the recommendation effect; the logged content can be attribution data, such as the final decision data of users, including factors that affect user decisions (such as time, price, comfort, etc.).

[0164] Collecting user behavior data through data logging enables data analysis and processing. The specific metrics for data analysis can include, but are not limited to:

[0165] Reach rate, whether the recommended travel strategies are seen or noticed by users;

[0166] Callback rate, whether users have taken further actions on the recommended travel strategies (such as click operations, view details operations, etc.);

[0167] Acceptance rate, whether users have accepted the recommended travel strategies;

[0168] Ticket issuance rate, the proportion of users who actually complete ticket issuance.

[0169] In a further optional implementation, to measure whether the recommendation causes interference to users, the data logging and analysis system can collect and analyze disturbance data to measure whether the travel strategy recommendation system causes recommendation interference to users; among them, disturbance data refers to the data that disturbs the normal operations or decisions of users due to the recommendation or intervention behavior of the travel strategy recommendation system, reflecting the negative feedback or unexpected behaviors of users caused by irrelevant or inappropriate recommendations. That is to say, disturbance data includes the behavior data generated by users being disturbed by the recommended content.

[0170] As an optional implementation, the relevant factors of disturbance data include, but are not limited to, the behavior of closing the recommendation and the rejection rate. Among them, the behavior of closing the recommendation is the behavior of users actively closing the recommended content, and the rejection rate is the proportion of users clearly rejecting the recommended content. That is to say, the behavior of closing the recommendation is a negative reaction behavior of users to the recommended content, manifested as the operation of users actively closing the recommended content; the rejection rate is the proportion of the number of times users clearly reject the recommended content to the number of times the recommendation is displayed. Furthermore, the embodiments of the present application can determine the disturbance rate corresponding to the disturbance data based on the behavior of closing the recommendation and the rejection rate. Among them, the disturbance rate is an index calculated from the disturbance data, used to measure the proportion of the recommended content that causes interference to users; for example, the disturbance rate is determined by the number of times of closing the recommendation and the number of times of rejecting the recommendation. Among them, the number of times of rejecting the recommendation can be determined based on the rejection rate. For example, the disturbance rate = (the number of times of closing the recommendation + the number of times of rejecting the recommendation) / the number of times the recommended content is displayed; if the disturbance rate is relatively high, it indicates that the recommended content causes relatively large interference to users and the recommendation logic needs to be optimized.

[0171] In a further alternative implementation, an embodiment of the present application further provides a travel server, which is regarded as a server or a server cluster set in a travel service platform; in an alternative implementation, the travel server may include a memory and a processor, the memory stores computer-executable instructions, and the processor calls the computer-executable instructions stored in the memory to execute the travel intention recognition method provided by the embodiment of the present application, or the travel strategy recommendation method provided by the embodiment of the present application.

[0172] In a further alternative implementation, an embodiment of the present application further provides a storage medium that stores computer-executable instructions. When the computer-executable instructions are executed (for example, when the computer-executable instructions are executed by a processor), the travel intention recognition method provided by the embodiment of the present application, or the travel strategy recommendation method provided by the embodiment of the present application is implemented.

[0173] In a further alternative implementation, an embodiment of the present application further provides a computer program product, including computer-executable instructions. When the computer-executable instructions are executed (for example, when the computer-executable instructions are executed by a processor), the travel intention recognition method provided by the embodiment of the present application, or the travel strategy recommendation method provided by the embodiment of the present application is implemented.

[0174] The above describes multiple embodiment solutions provided by the embodiments of the present application. The various alternative methods described in each embodiment solution can be combined and cross-referenced with each other without conflict, so as to extend a variety of possible embodiment solutions, all of which can be considered as the embodiment solutions disclosed and made public by the embodiments of the present application.

[0175] Although the embodiments of the present application are disclosed as above, the present application is not limited thereto. Any person skilled in the art can make various changes and modifications without departing from the spirit and scope of the present application. Therefore, the protection scope of the present application should be subject to the scope defined by the claims.

Claims

1. A travel intention recognition method, characterized in that Including: Obtain the current trip information and current passenger information of the current trip, as well as the historical travel information of the current passenger; Extract and combine features from the current trip information, the current passenger information, and the historical travel information to obtain the to-be-matched combined features corresponding to the current trip in multiple travel scenarios; Match the to-be-matched combined features of the current trip in each travel scenario with the feature requirements of each travel scenario respectively, so as to determine the travel scenario that the current trip matches from the multiple travel scenarios; wherein, the feature requirements of the travel scenario conform to the definition and characteristics of the travel scenario; Determine the travel intention of the current trip according to the travel scenario that the current trip matches; Among them, there are intersections or overlaps in the definitions and characteristics of some travel scenarios, and there is a possibility that the current trip matches more than one travel scenario. If the travel scenarios that the current trip matches are multiple, determine the travel scenario with the highest matching priority among the travel scenarios that the current trip matches as the travel intention of the current trip. The priority of the travel scenario is determined based on the matched ratio of the travel scenario. The matched ratio of a travel scenario represents the proportion of the number of times the travel scenario has been matched to the total number of matches of the multiple travel scenarios. The matched ratios of each travel scenario are recorded in the overall proportion data system of the travel service platform. The overall proportion data system aims to identify group characteristics and travel trends by statistically analyzing the behavior patterns of all users. Moreover, the travel intention data of the trip loses timeliness over time.

2. The method according to claim 1, characterized in that, The step of matching the to-be-matched combined features of the current trip in each travel scenario with the feature requirements of each travel scenario respectively to determine the travel scenario that the current trip matches from the multiple travel scenarios includes: Input the to-be-matched combined features of the current trip in each travel scenario into the travel intention recognition model respectively, so that the travel intention recognition model, based on the travel scenario knowledge base, matches the to-be-matched combined features of the current trip in each travel scenario with the feature requirements of each travel scenario respectively; Obtain the travel scenario that the current trip matches output by the travel intention recognition model; Among them, the travel scenario knowledge base is the background knowledge base of the travel intention recognition model, and records the background knowledge of the multiple travel scenarios. The background knowledge of the travel scenario at least includes the definition, characteristics, and feature requirements of the travel scenario.

3. The method according to claim 2, wherein The travel intention recognition model is a large model. The large model understands the background knowledge of the multiple travel scenarios recorded in the travel scenario knowledge base through pattern learning or inference algorithms, so as to have the inference ability to match travel scenarios for the current trip; Or, The travel intention recognition model is a rule model, including the matching rules of each travel scenario; the matching rules of the travel scenario are formed based on the background knowledge of the travel scenario recorded in the travel scenario knowledge base, and are used to check whether the to-be-matched combined features of the current trip in the travel scenario match the feature requirements of the travel scenario.

4. The method according to any one of claims 1 to 3, characterized in that, Extracting features from the current trip information, the current passenger information, and the historical travel information and combining them to obtain the to-be-matched combined features corresponding to the current trip in multiple travel scenarios includes: For any travel scenario, extracting features from the current trip information, the current passenger information, and the historical travel information based on the feature types required for matching the travel scenario; For any travel scenario, combining the extracted features into at least one to-be-matched combined feature corresponding to the current trip in the travel scenario, or combining the extracted features as a whole into a to-be-matched combined feature corresponding to the current trip in the travel scenario based on the matching requirements of the travel scenario.

5. The method according to any one of claims 1 to 3, characterized in that, Determining the travel intention of the current trip according to the travel scenario matched by the current trip includes: If the travel scenario matched by the current trip is one, using the travel scenario matched by the current trip as the travel intention of the current trip; If the travel scenarios matched by the current trip are multiple, determining the travel scenario with the highest priority among the travel scenarios matched by the current trip as the travel intention of the current trip according to the priorities of the respective travel scenarios matched by the current trip; Among them, the travel scenario with the highest matched proportion among the travel scenarios matched by the current trip is the travel scenario with the highest priority.

6. The method according to any one of claims 2-3, characterized in that, The method further includes: Verifying, according to the verification list, whether the travel scenario matched by the current trip output by the travel intention recognition model conforms to the corresponding verification rules of the travel scenario; if not, triggering a warning prompt message; Among them, for any travel scenario, the verification list records the verification items corresponding to the travel scenario in the current trip information, the current passenger information, and the historical travel information respectively; The multiple travel scenarios include multiple travel scenario types and subclasses under the travel scenario types; among them, some of the multiple travel scenario types have subclasses; for a travel scenario type with subclasses, one subclass under a travel scenario type corresponds to one travel scenario; for a travel scenario type without subclasses, one travel scenario type corresponds to one travel scenario; The background knowledge of the travel scenario further includes: extended knowledge points and logical rules for matching the travel scenario.

7. A travel strategy recommendation method, characterized in that, Including: Obtaining the travel intention of the current trip, where the travel intention of the current trip is determined based on the travel intention recognition method according to any one of claims 1-6; Determining the travel preference information of the current passenger; Recommending the travel strategy of the current trip according to the travel intention of the current trip and the travel preference information of the current passenger.

8. The travel strategy recommendation method according to claim 7, wherein Before performing the step of obtaining the travel intention of the current trip, the method further includes: Obtaining a travel service request, where the travel service request is used to request a travel service for the current trip; the travel service request includes a ticket request or a travel strategy recommendation request, and when the ticket status corresponding to the ticket request meets the preset travel intention recognition conditions, entering the step of obtaining the travel intention of the current trip; The method further includes: Using the control experiment test method, test the impact of different versions of travel strategies on user behavior to optimize the recommendation logic of travel strategies; among them, different versions of travel strategies include the travel strategy of the first version and the travel strategy of the second version; the travel strategy of the second version is determined based on travel intent and travel preference information, and the travel strategy of the first version is the original version of the travel strategy.

9. A travel service platform, characterized in that, Including: Travel intent recognition system; The travel intent recognition system includes: A preprocessing module for extracting and combining features from the current trip information, current passenger information, and historical travel information of the current passenger of the current trip to obtain the to-be-matched combined features corresponding to the current trip in multiple travel scenarios; A travel intent recognition model for matching the to-be-matched combined features of the current trip in each travel scenario with the feature requirements of each travel scenario respectively to determine the travel scenario matched by the current trip from multiple travel scenarios; among them, the feature requirements of the travel scenario conform to the definition and characteristics of the travel scenario; A post-processing module for determining the travel intent of the current trip according to the travel scenario matched by the current trip; A travel scenario knowledge base, as the background knowledge base of the travel intent recognition model, records the background knowledge of multiple travel scenarios, and the background knowledge of the travel scenario at least includes the definition, characteristics, and feature requirements of the travel scenario; Among them, there are intersections or overlaps in the definitions and characteristics of some travel scenarios, and there is a possibility that the current trip matches more than one travel scenario. If the travel scenarios matched by the current trip are multiple, the travel scenario with the highest matching priority among the travel scenarios matched by the current trip is determined as the travel intent of the current trip. The priority of the travel scenario is determined based on the matched ratio of the travel scenario. The matched ratio of a travel scenario represents the proportion of the number of times the travel scenario has been matched to the total number of matches of the multiple travel scenarios. The matched ratios of each travel scenario are recorded in the overall proportion data system of the travel service platform. The overall proportion data system aims to identify group characteristics and travel trends by statistically analyzing the behavior patterns of all users. And the travel intent data of the trip loses timeliness over time.

10. The travel service platform according to claim 9, wherein, Also including: A travel strategy recommendation system for obtaining the travel intent of the current trip and determining the travel preference information of the current passenger; Recommend the travel strategy of the current trip according to the travel intent of the current trip and the travel preference information of the current passenger; A travel preference database that records travel preference information; The travel preference database includes a personal travel preference database that records the personal travel preference information of each passenger, or a population travel preference database that records the population travel preference information of each population; A test component for using the control experiment test method to test the impact of different versions of travel strategies on user behavior to optimize the recommendation logic of travel strategies; among them, different versions of travel strategies include the travel strategy of the first version and the travel strategy of the second version; The travel strategy of the second version is determined based on travel intent and travel preference information, and the travel strategy of the first version is the original version of the travel strategy; A data logging and analysis system is used to collect user behavior data through data logging and perform analysis to optimize the performance of the travel strategy recommendation system and the travel strategies recommended by the travel strategy recommendation system.

11. A travel server, characterized in that, It includes a memory and a processor. The memory stores computer-executable instructions, and the processor calls the computer-executable instructions to execute the travel intention recognition method according to any one of claims 1-6, or the travel strategy recommendation method according to any one of claims 7-8.

12. A computer program product, characterized in that, It includes computer-executable instructions. When the computer-executable instructions are executed, the travel intention recognition method according to any one of claims 1-6, or the travel strategy recommendation method according to any one of claims 7-8 is implemented.

Images