Multi-destination travel route planning method, system, equipment, medium and product

Abstract

The invention discloses a multi-destination travel route planning method, system and device, a medium and a product. The planning method comprises the following steps: generating a destination combination pool according to holiday product data and user high-frequency request data; determining a multi-destination route based on the target destination combination pool; acquiring a plurality of corresponding atomic routes from a set single-destination atomic route library according to the multi-destination route; splicing the plurality of atomic routes according to a destination sequence to generate an original multi-destination route; and performing a second rationality test on the original multi-destination line to obtain a target multi-destination line. According to the method, the destination combination pool is obtained based on the user high-frequency request data and the holiday product data, and the first rationality test is performed, so that the line data rationality is ensured from the perspective of the real travel demand of the user; and performing second rationality inspection on the original multi-destination line to ensure the availability of the generated line so as to improve the expectation degree of the target multi-destination line user.

Description

Technical Field

[0001] The present invention relates to the technical field of route planning, and in particular to a planning method, system, equipment, medium and product for a multi-destination tourist route. Background Art

[0002] In recent years, as the online travel industry has recovered, online travel platforms have been working hard to develop content marketing. For longer travel plans, users hope to obtain high-quality multi-destination travel routes from OTA platforms (Ordered Target Area, online travel agencies).

[0003] At present, OTA platforms often use manual customization, vehicle routing problem (VRP), route planning algorithms and LLM large models to plan travel routes. Although the quality of manually operated routes is high, the production speed is slow and it is difficult to quickly cover most of the destination combinations in the world; directly using a single algorithm to produce multi-destination routes makes the actual routes impossible to implement. The conditions that meet the user's travel needs are difficult to abstract into variables or constraints, the model effect cannot meet expectations, the results of the LLM large model are uncontrollable, and training and running the LLM large model requires a lot of computing resources, which is costly and not suitable for mass production. Summary of the invention

[0004] The technical problem to be solved by the present invention is to overcome the defects of the prior art that multi-destination route planning cannot meet the user's expected standards, is time-consuming and has poor rationality, and to provide a multi-destination tourist route planning method, system, equipment, medium and product.

[0005] The present invention solves the above technical problems through the following technical solutions:

[0006] In a first aspect, the present invention provides a method for planning a multi-destination tourist route, the planning method comprising:

[0007] Generate a destination combination pool based on vacation product data and user high-frequency request data;

[0008] Performing a first rationality check on the destination combination pool to obtain a target destination combination pool; the first rationality check is used to represent a check on the destination combination profile;

[0009] Determine a multi-destination route based on the target destination combination pool; the multi-destination route is used to represent a route with a determined destination sequence and corresponding days;

[0010] Obtain a corresponding number of atomic routes from the set single-destination atomic route library according to the multi-destination route; the set single-destination atomic route library is used to represent a route database with different style identifiers or type identifiers, single destinations, and corresponding days configured in advance;

[0011] Splice a number of the atomic routes in the order of the destinations to generate an original multi-destination route;

[0012] Conduct a second rationality check on the original multi-destination route to obtain a target multi-destination route; the second rationality check is used to represent the check of the overview of the spliced route.

[0013] Preferably, the step of determining the multi-destination route based on the target destination combination pool includes:

[0014] Determine the first destination corresponding to each destination combination in the target destination combination pool;

[0015] Use the TSP path planning algorithm to calculate the shortest transfer path corresponding to the first destination;

[0016] Calculate the allocated days of each destination corresponding to the shortest transfer path according to the recommended days of each set destination to generate the multi-destination route.

[0017] Preferably, the first rationality check includes at least one of days rationality, cross-country rationality of destination combinations, destination type rationality, destination subordination relationship rationality, and destination popularity difference;

[0018] And / or, the second rationality check includes at least one of days detour rationality check, cross-city day time-consuming rationality check, and scenic spot relationship rationality check.

[0019] Preferably, the step of generating the destination combination pool according to the vacation product data and the user high-frequency request data includes:

[0020] Screen out a first feasible route alternative pool greater than the set confidence level according to the original vacation products, product quantities, and order quantities of the vacation product data;

[0021] Screen out a second feasible route alternative pool greater than the set frequency according to the user search destination combinations, search times, and search days of the user high-frequency request data;

[0022] Generate the destination combination pool based on the first feasible route alternative pool and the second feasible route alternative pool.

[0023] Preferably, the planning method further includes:

[0024] When the original multi-destination route does not meet the second rationality test, obtain the corresponding new atomic route from the set of single-destination atomic routes;

[0025] Splice a number of new atomic routes in the order of the destinations to generate a new original multi-destination route.

[0026] Preferably, the planning method further includes:

[0027] When all the new original multi-destination routes generated by replacing all the atomic routes do not meet the second rationality test, perform a fallback correction operation; the fallback correction operation is used to represent the operation of removing unnecessary destinations in the original multi-destination route.

[0028] In a second aspect, the present invention provides a multi-destination travel route planning system, the planning system includes:

[0029] A first generation module, configured to generate a destination combination pool according to vacation product data and user high-frequency request data;

[0030] A first inspection module, configured to perform a first rationality test on the destination combination pool to obtain a target destination combination pool; the first rationality test is used to represent the inspection of the destination combination state;

[0031] A determination module, configured to determine a multi-destination route based on the target destination combination pool; the multi-destination route is used to represent a route with a determined destination order and corresponding number of days;

[0032] A first acquisition module, configured to obtain a number of corresponding atomic routes from a set of single-destination atomic routes according to the multi-destination route; the set of single-destination atomic routes is used to represent a route database of single destinations with different style identifiers or type identifiers and corresponding number of days configured in advance;

[0033] A second generation module, configured to splice a number of the atomic routes in the order of the destinations to generate an original multi-destination route;

[0034] A first inspection module, configured to perform a second rationality test on the original multi-destination route to obtain a target multi-destination route; the second rationality test is used to represent the inspection of the overview of the spliced route.

[0035] In a third aspect, the present invention provides an electronic device, including a processor, a memory, and a computer program stored on the memory and executable on the processor, and when the computer program is executed by the processor, it implements the multi-destination travel route planning method as described in the first aspect.

[0036] Fourthly, the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the planning method of the multi-destination travel route as described in the first aspect is implemented.

[0037] Fifthly, the present invention provides a computer program product, including a computer program. When the computer program is executed by a processor, the planning method of the multi-destination travel route as described in the first aspect is implemented.

[0038] The positive and progressive effects of the present invention are as follows: A planning method, system, device, medium and product for a multi-destination travel route are provided. A destination combination pool is obtained based on user high-frequency request data and vacation product data and a first rationality test is performed. This method starts from the perspective of users' real travel needs to ensure the rationality of route data. According to the multi-destination route, atomic routes are obtained from the set single-destination atomic route library and spliced to generate an original multi-destination route, and a second rationality test is performed to ensure the availability of the generated route, so as to improve the expectation degree of users for the target multi-destination route. Description of the Drawings

[0039] Figure 1 It is the first flowchart of the planning method of the multi-destination travel route in Embodiment 1 of the present invention.

[0040] Figure 2 It is the second flowchart of the planning method of the multi-destination travel route in Embodiment 1 of the present invention.

[0041] Figure 3 It is the third flowchart of the planning method of the multi-destination travel route in Embodiment 1 of the present invention.

[0042] Figure 4 It is the fourth flowchart of the planning method of the multi-destination travel route in Embodiment 1 of the present invention.

[0043] Figure 5 It is the first module schematic diagram of the planning system of the multi-destination travel route in Embodiment 2 of the present invention.

[0044] Figure 6 It is the second module schematic diagram of the planning system of the multi-destination travel route in Embodiment 2 of the present invention.

[0045] Figure 7 It is the hardware structure schematic diagram of the electronic device in Embodiment 3 of the present invention. Detailed Embodiments

[0046] The present invention will be further described below by way of embodiments, but the present invention is not limited to the scope of the described embodiments.

[0047] Embodiment 1

[0048] This embodiment provides a method for planning a multi-destination travel route, as Figure 1 shown, the planning method includes:

[0049] S11. Generate a destination combination pool according to vacation product data and user high-frequency request data;

[0050] S12. Conduct a first rationality test on the destination combination pool to obtain a target destination combination pool; the first rationality test is used to represent the test of the destination combination overview;

[0051] S13. Determine a multi-destination route based on the target destination combination pool; the multi-destination route is used to represent the route with the determined destination order and corresponding number of days;

[0052] S14. Obtain a corresponding number of atomic routes from the set single-destination atomic route library according to the multi-destination route; the set single-destination atomic route library is used to represent a route database of single destinations with different style identifiers or type identifiers and corresponding number of days pre-configured;

[0053] S15. Concatenate the several atomic routes in the destination order to generate an original multi-destination route;

[0054] S16. Conduct a second rationality test on the original multi-destination route to obtain a target multi-destination route; the second rationality test is used to represent the test of the concatenated route overview.

[0055] Among them, the first rationality test includes at least one of the number of days rationality, cross-country rationality of the destination combination, destination type rationality, destination subordination relationship rationality, and destination popularity difference;

[0056] And / or, the second rationality test includes at least one of the number of days detour rationality test, cross-city day time-consuming rationality test, and scenic spot relationship rationality test.

[0057] For the above steps S11 - S13, a first rationality test is performed on the destination combination pool from aspects such as the number of days, cross - border destination combinations, destination types, destination subordination relationships, and destination popularity. All destination combination pools that pass the first rationality test are used as the target destination combination pool. Based on the target destination combination pool, multi - destination routes are determined from two aspects: reasonable number of days allocation and reasonable destination transfer order. This method ensures the reasonable configuration of multi - destination combination selection, number of days allocation, and order, enhancing the rationality of subsequent generation of original multi - destination routes. Exemplarily, when determining the rationality of cross - border destination combinations, since the generated routes are for the PGC (Professional Generated Content) scenario, considering issues such as visas and transportation, classic cross - border travel combinations such as Singapore - Malaysia - Thailand and the Schengen Area in Europe are preferentially retained, and other cross - border situations are excluded. When determining the rationality of destination types, considering that the subsequent route generation depends on the recommended routes of multi - destinations spliced from individual destinations, destinations with too large a scope, for example, countries and provinces, can be regarded as the results of multi - destination combinations and excluded. When determining the rationality of destination subordination relationships, due to the administrative hierarchical subordination relationships between destinations, for destinations with superior - subordinate relationships in the combination, priority is given to merging or splitting them according to popularity and user perception. When determining the difference in destination popularity, due to the referenceability of the routes, when referring to the destination popularity scores of the OTA platform, parts with extremely large differences in destination popularity are excluded. When judging the rationality of the number of days, ensure that the number of days corresponding to the destination combination satisfies the following formula: where D represents the number of days, n represents the number of destinations in the destination combination, and dmaxi represents the maximum recommended number of days for a single destination.

[0058]

[0059] For the above steps S14 - S16, an atomic splicing framework is adopted to construct a single - destination atomic route library, making the generation of multi - destination routes more flexible, so as to increase the fault - tolerance rate of route planning. From the perspective of user travel, a second rationality check is carried out on the spliced original multi - destination route to ensure the rationality of the multi - destination travel route planning result. When checking the rationality of detours in terms of days, the core is to check whether there is a detour in the daily travel route. Since the spliced atomic multi - destination routes may lead to detours between days. For example, on the first day, it is arranged to visit Scenic Area A, and on the third day, it is arranged to visit Scenic Area B, but there is no continuous play in the two scenic areas, which does not meet the rationality check of detours in terms of days. When checking the rationality of the time consumption on the cross - city day, since cross - city transfers usually require a long time for major transportation such as airplanes and trains, if there are many scenic spots to visit on the day of major transportation transfer, that day will be extremely tired, then the original multi - destination route is obviously unreasonable. When checking the rationality of the time consumption between cross - city days, multiple assumptions need to be made to judge whether it is reasonable to add major transportation between the two cross - city days. The first step: Call the transportation interface to obtain the best major transportation method and transportation duration between the two destinations, and waiting durations will be reserved for airplane and train methods. The second step: Define the total acceptable time consumption within a day as: the shortest duration , the longest duration , and this interval basically meets the user's needs. The third step: Make assumptions about the arrangement position of the major transportation: Assume that the major transportation is arranged on the previous day, then calculate whether the sum of the minimum play duration on the first day, the small transportation duration on the previous day, and the major transportation duration is within . If the condition is met, then arrange the major transportation on the day before the cross - city in this route. If the condition is not met, assume that the major transportation is arranged on the last day, then calculate whether the sum of the minimum play duration on the next day, the small transportation duration on the previous day, and the major transportation duration is within , and calculate whether the sum of the longest play duration on the next day, the small transportation duration on the previous day, and the major transportation duration is within . At the same time, check whether the remaining time can meet the opening and closing times of the scenic spots to be visited on the day after the major transportation arrives at the next city. When checking the rationality of the relationship between scenic spots, the core is to check whether there is a phenomenon of duplicate scenic spots in the spliced original multi - destination route, or whether there is an inclusion relationship between scenic spots.

[0060] In an embodiment, as Figure 2 shown, step S13 specifically includes:

[0061] S131. Determine the first destination corresponding to each destination combination in the target destination combination pool;

[0062] S132. Use the TSP path planning algorithm to determine the shortest transfer path corresponding to the first destination;

[0063] S133. Calculate the allocated days for each destination corresponding to the shortest transfer path according to the recommended days set for each destination, so as to generate a multi-destination itinerary.

[0064] For the above steps S131 - S133, for multi-destination travel, users usually prefer to arrive at and visit destinations with greater fame and attractiveness first, or destinations where it is more convenient to travel by major transportation means such as airplanes and trains first. When determining the first destination, it is usually comprehensively determined by the destination popularity score in the OTA platform and the transportation convenience of having direct flights or trains to the destination. The shortest path calculation uses the TSP (Traveling Salesman Problem) path planning algorithm, and the distance between two destinations is obtained by calculating the spherical distance from their longitudes and latitudes. After determining the first destination, the TSP path planning algorithm can be used to calculate a non-loop shortest transfer path. Calculate the days allocation ratio using the recommended play days for each destination, and then calculate the allocated days for each destination. If it is less than one day, it is calculated as one day.

[0065] In one embodiment, as Figure 3 shown, step S11 specifically includes:

[0066] S111. Screen out the first feasible route alternative pool with a confidence level greater than the set value according to the original vacation products, product quantities, and order quantities in the vacation product data;

[0067] S112. Screen out the second feasible route alternative pool with a frequency greater than the set value according to the user search destination combinations, search times, and search days in the user high-frequency request data;

[0068] S113. Generate a destination combination pool based on the first feasible route alternative pool and the second feasible route alternative pool.

[0069] For the above steps S111 - S113, screen out a feasible route alternative pool with high confidence according to the original vacation products, product quantities, and order quantities, and check each destination combination in the feasible route alternative pool for abnormal points one by one. After removing the destination combinations with abnormal points, the first feasible route alternative pool is obtained. When a certain destination is far from other destinations while the distances between other destinations are relatively close, determine that destination combination as an abnormal point. Screen out the destination combinations and corresponding days with a high set frequency according to the user search destination combinations, search times, and search days as the second feasible route alternative pool. Obtain a destination combination pool including a recommended days range according to the maximum and minimum recommended days of each destination in the first feasible route alternative pool and the second feasible route alternative pool. For example, if Shanghai is recommended for 2 - 4 days and Suzhou is recommended for 1 - 2 days, then the recommended days range is 3 - 6 days.

[0070] In one embodiment, as Figure 4 shown, this planning method includes:

[0071] S17. If the original multi-destination route does not meet the second rationality test, obtain the corresponding new atomic route from the set single-destination atomic route library;

[0072] S181. Splice several new atomic routes in the order of destinations to generate a new original multi-destination route, and continue to execute step S16.

[0073] S182. If all the new original multi-destination routes generated by replacing all the atomic routes do not meet the second rationality test, perform a fallback correction operation; the fallback correction operation is used to represent the operation of removing non-essential destinations in the original multi-destination route.

[0074] For the above steps S17 - S182, obtain the corresponding new atomic route from the set single-destination atomic route library, and check whether the new original multi-destination route meets the second rationality test. If not, continue to obtain the corresponding next new atomic route from the set single-destination atomic route library, and loop to execute the second rationality test. If all the atomic routes are replaced and still cannot meet the second rationality test, execute the fallback correction logic. In this fallback correction logic, when the daily play duration is within the set range, at least one destination corresponding to a less popular non-essential scenic spot is preferentially deleted to ensure the comfort of the original multi-destination route.

[0075] In this embodiment, a method for planning a multi-destination travel route is provided. A destination combination pool is obtained based on user high-frequency request data and vacation product data and subjected to the first rationality test. This method starts from the perspective of users' real travel needs to ensure the rationality of route data; according to the multi-destination route, atomic routes are obtained from the set single-destination atomic route library and spliced to generate the original multi-destination route and subjected to the second rationality test to ensure the availability of the generated route, so as to improve the expectation of users for the target multi-destination route.

[0076] Embodiment 2

[0077] The multi-destination travel route planning system of this embodiment is as Figure 5 shown. This planning system includes:

[0078] The first generation module 210 is used to generate a destination combination pool according to vacation product data and user high-frequency request data;

[0079] The first test module 220 is used to perform the first rationality test on the destination combination pool to obtain the target destination combination pool; the first rationality test is used to represent the test of the destination combination state;

[0080] A determination module 230, configured to determine a multi-destination route based on a target destination combination pool; the multi-destination route is used to represent a route for which the destination order and corresponding number of days have been determined;

[0081] A first acquisition module 240, configured to acquire a corresponding number of atomic routes from a set of single-destination atomic route libraries according to the multi-destination route; the set of single-destination atomic route libraries is used to represent a route database that is pre-configured with single destinations having different style identifiers or type identifiers and the corresponding number of days;

[0082] A second generation module 250, configured to splice a plurality of atomic routes in the destination order to generate an original multi-destination route;

[0083] A second verification module 260, configured to perform a second rationality verification on the original multi-destination route to obtain a target multi-destination route; the second rationality verification is used to represent the verification of the overview of the spliced route.

[0084] Wherein, the first rationality verification includes at least one of the rationality of the number of days, the rationality of cross-country destination combination, the rationality of destination type, the rationality of destination subordination relationship, and the difference in destination popularity;

[0085] And / or, the second rationality verification includes at least one of the rationality verification of the number of days of detour, the rationality verification of the time-consuming across cities per day, and the rationality verification of the scenic spot relationship.

[0086] The first verification module 220 conducts a first rationality verification on the destination combination pool from aspects such as the combination of days and destinations across countries, destination types, destination subordination relationships, and destination popularity. All destination combination pools that meet the first rationality verification are used as the target destination combination pool. The determination module 230 determines a multi-destination route based on the target destination combination pool from two aspects: reasonable days allocation and reasonable destination transfer order. This method ensures the rational configuration of multi-destination combination selection, days allocation, and order, and enhances the rationality of subsequent generation of the original multi-destination route. Exemplarily, when determining the rationality of cross-border destination combinations, since the generated routes are for the PGC (Professional Generated Content) scenario, considering issues such as visas and transportation, classic cross-border travel combinations such as the combination of Singapore, Malaysia, and Thailand, and the Schengen area in Europe are preferentially retained, and other cross-border situations are excluded. When determining the rationality of destination types, considering that the subsequent route generation depends on the recommended routes of multi-destinations spliced from individual destinations, destinations with too large a scope, for example, countries and provinces, can be regarded as the results of multi-destination combinations and excluded. When determining the rationality of destination subordination relationships, since there is an administrative hierarchical subordination relationship between destinations, for destinations with a superior-subordinate relationship in the combination, priority is given to merging or splitting according to popularity and user perception. When determining the difference in destination popularity, due to the referenceability of the route, when referring to the destination popularity scores on the OTA platform, parts with extremely large differences in destination popularity are excluded. When judging the rationality of days, it is ensured that the days corresponding to the destination combination satisfy the following formula: where D represents the number of days, n represents the number of destinations in the destination combination, and dmaxi represents the maximum recommended number of days for a single destination.

[0087]

[0088] Adopt an atomic splicing framework to construct a single-destination atomic route library, making the generation of multi-destination routes more flexible to increase the fault tolerance rate of route planning. The second inspection module 260 starts from the perspective of user travel and conducts a second rationality inspection on the spliced original multi-destination route to ensure the rationality of the multi-destination travel route planning result. When conducting the rationality inspection of day detours, the core is to check whether there is a detour in the travel route of each day. Since the spliced atomic multi-destination route may cause detours between days. For example, on the first day, it is arranged at Scenic Spot A, and on the third day, it is arranged at Scenic Spot B, but there is no continuous play arrangement between the two scenic spots, which does not meet the rationality inspection of day detours. When conducting the rationality inspection of the time consumption on the cross-city day, since cross-city transfers usually require a long time for major transportation such as airplanes and trains, if there are many scenic spots to visit on the day of major transportation transfer, that day will be extremely tired, then this original multi-destination route is obviously unreasonable. When conducting the rationality inspection of the time consumption between cross-city days, multiple assumptions need to be made to judge whether it is reasonable to add major transportation between the two cross-city days. The first step is to call the traffic interface to obtain the best major transportation method and traffic duration between the two destinations, and the waiting time will be reserved for the airplane and train methods accordingly. The second step is to define the acceptable total time consumption within a day as: the shortest time , the longest time , and this interval basically meets the user's needs. The third step is to make an assumption about the arrangement position of the major transportation: assume that the major transportation is arranged on the previous day, then calculate whether the sum of the minimum play duration on the first day, the small transportation duration on the previous day, and the major transportation duration is within . If the condition is met, then arrange the major transportation on the day before the cross-city in this route. If the condition is not met, then assume that the major transportation is arranged on the last day, then calculate whether the sum of the minimum play duration on the next day, the small transportation duration on the previous day, and the major transportation duration is within , and calculate whether the sum of the longest play duration on the next day, the small transportation duration on the previous day, and the major transportation duration is within . At the same time, check whether the remaining time can meet the opening and closing times of the scenic spots to be visited on the day after the major transportation arrives at the next city on the second day. When conducting the rationality inspection of scenic spot relationships, the core is to check whether there is a phenomenon of repeated scenic spots in the spliced original multi-destination route, or whether there is an inclusion relationship between scenic spots.

[0089] In one embodiment, as Figure 6 shown, the determination module 230 includes:

[0090] A determination unit 231 for determining the first destination corresponding to each destination combination in the target destination combination pool;

[0091] A calculation unit 232 for calculating the shortest transfer path corresponding to the first destination by using the TSP path planning algorithm;

[0092] A route generation unit 233 is configured to calculate the allocated days of each destination corresponding to the shortest transfer route according to the recommended days set for each destination, so as to generate a multi-destination route.

[0093] For multi-destination trips, users usually prefer to first arrive at destinations with greater fame and attractiveness for sightseeing, or first arrive at destinations where it is more convenient to travel by major transportation means such as airplanes and trains. When the determination unit 231 determines the first destination, it is usually determined comprehensively by the destination popularity score in the OTA platform and the transportation convenience degree of the destination having direct flights or trains. In the calculation unit 232, the shortest path calculation adopts the TSP (Traveling Salesman Problem) path planning algorithm, and the distance between two destinations is obtained by calculating the spherical distance from their longitudes and latitudes. After the first destination is determined, a non-loop shortest transfer path can be calculated using the TSP path planning algorithm. The route generation unit 233 calculates the days allocation ratio using the recommended play days of each destination, and then calculates the allocated days of each destination. Less than one day is calculated as one day.

[0094] In one embodiment, as Figure 6 shown, the first generation module 210 includes:

[0095] A first screening unit 211 is configured to screen out a first pool of alternative feasible routes greater than a set confidence level according to the original vacation products, product quantities, and order quantities of vacation product data;

[0096] A second screening unit 212 is configured to screen out a second pool of alternative feasible routes greater than a set frequency according to the user search destination combinations, search times, and search days of user high-frequency request data;

[0097] A first generation unit 213 is configured to generate a destination combination pool based on the first pool of alternative feasible routes and the second pool of alternative feasible routes.

[0098] The first screening unit 211 screens out a pool of alternative feasible routes with high confidence according to the original vacation products, product quantities, and order quantities, and checks each destination combination in the pool of alternative feasible routes for the existence of abnormal points. After removing the destination combinations with abnormal points, the first pool of alternative feasible routes is obtained. When a certain destination is far from other destinations, while the distances between other destinations are relatively close, the destination combination is determined as an abnormal point. The second screening unit 212 screens out the destination combinations and corresponding days with a high set frequency according to the destination combinations, search times, and search days searched by the user as the second pool of alternative feasible routes. The first generation unit 213 obtains a destination combination pool including a recommended days interval according to the maximum and minimum recommended days of each destination in the first pool of alternative feasible routes and the second pool of alternative feasible routes. For example, if Shanghai is recommended for 2 - 4 days and Suzhou is recommended for 1 - 2 days, then the recommended days interval is 3 - 6 days.

[0099] In one embodiment, as Figure 6 shown, the planning method further includes:

[0100] A second acquisition module 270, configured to obtain corresponding new atomic routes from a set single-destination atomic route library when the original multi-destination route does not satisfy the second rationality test;

[0101] A splicing module 281, configured to splice a plurality of new atomic routes in the order of destinations to generate a new original multi-destination route.

[0102] An execution module 282, configured to perform a fallback correction operation when all the new original multi-destination routes generated by replacing the corresponding atomic routes do not satisfy the second rationality test; the fallback correction operation is used to represent the operation of removing unnecessary destinations in the original multi-destination route.

[0103] The second acquisition module 270 obtains corresponding new atomic routes from the set single-destination atomic route library, checks whether the new original multi-destination route spliced by the splicing module 281 meets the second rationality test. If not, continue to obtain the corresponding next new atomic route from the set single-destination atomic route library, and loop to perform the second rationality test. When all the atomic routes are replaced and still cannot meet the second rationality test, the execution module 282 executes the fallback correction logic. In this fallback correction logic, when the daily play duration is within the set interval, at least one destination corresponding to a less popular non-essential scenic spot is preferentially deleted to ensure the comfort of the original multi-destination route.

[0104] In this embodiment, a planning system for a multi-destination travel route is provided. The first generation module obtains a destination combination pool based on user high-frequency request data and vacation product data and performs a first rationality test. This method starts from the perspective of users' real travel needs to ensure the rationality of route data; the first acquisition module, the second generation module, and the second test module obtain atomic routes from a set single-destination atomic route library according to the multi-destination route, splice them to generate an original multi-destination route, and perform a second rationality test to ensure the availability of the generated route, so as to improve the expectation of users of the target multi-destination route.

[0105] Embodiment 3

[0106] Figure 7 It is a schematic hardware structure diagram of an electronic device provided in this embodiment. The electronic folding book includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the planning method for the multi-destination travel route in Embodiment 1. Figure 7 The displayed electronic device 60 is only an example and should not bring any limitations to the functions and usage ranges of the embodiments of the present invention.

[0107] The electronic device 60 may be presented in the form of a general-purpose computing device. For example, it may be a server device. The components of the electronic device 60 may include, but are not limited to: the at least one processor 61 described above, the at least one memory 62 described above, and a bus 63 that connects different system components (including the memory 62 and the processor 61).

[0108] The bus 63 includes a data bus, an address bus, and a control bus.

[0109] The memory 62 may include volatile memory, such as a random access memory (RAM) 621 and / or a cache memory 622, and may further include a read-only memory (ROM) 623.

[0110] The memory 62 may further include a program / utility 625 having a set (at least one) of program modules 624. Such program modules 624 include, but are not limited to: an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include the implementation of a network environment.

[0111] The processor 61 executes various functional applications and data processing by running computer programs stored in the memory 62, such as the method for planning a multi-destination travel route in Embodiment 1 of the present invention.

[0112] The electronic device 60 may also communicate with one or more external devices 64 (such as a keyboard, a pointing device, etc.). Such communication may be carried out through an input / output (I / O) interface 65. And the electronic device 60 for model generation may also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 66. As shown in the figure, the network adapter 66 communicates with other modules of the electronic device 60 for model generation through the bus 63. It should be understood that although Figure 7 not shown in the figure, other hardware and / or software modules may be used in combination with the electronic device 60 for model generation, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (Redundant Array of Independent Disks) systems, tape drives, and data backup storage systems, etc.

[0113] It should be noted that although several units / modules or sub-units / modules of the electronic device are mentioned in the above detailed description, such a division is merely exemplary and not mandatory. In fact, according to the embodiments of the present invention, the features and functions of two or more units / modules described above may be embodied in one unit / module. Conversely, the features and functions of one unit / module described above may be further divided and embodied by multiple units / modules.

[0114] Example 4

[0115] This embodiment provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the steps of the method for planning a multi-destination travel route in Embodiment 1 are implemented.

[0116] Among them, more specifically, the readable storage medium can include but is not limited to: portable disk, hard disk, random access memory, read-only memory, erasable programmable read-only memory, optical storage device, magnetic storage device, or any suitable combination of the above.

[0117] In a possible implementation manner, the present invention can also be implemented in the form of a program product, which includes program code. When the program product runs on a terminal device, the program code is used to cause the terminal device to execute the steps of the method for planning a multi-destination travel route in Embodiment 1.

[0118] Among them, the program code for executing the present invention can be written in any combination of one or more programming languages. The program code can be executed completely on the user device, partially on the user device, executed as an independent software package, partially on the user device and partially on a remote device, or completely on a remote device.

[0119] Example 5

[0120] This embodiment further provides a computer program product, including a computer program. When the computer program is executed by a processor, the method for planning a multi-destination travel route described in any one of the above is implemented.

[0121] Among them, the program code for executing the computer program product of the present disclosure can be written in any combination of one or more programming languages. The program code can be executed completely on the user device, partially on the user device, executed as an independent software package, partially on the user device and partially on a remote device, or completely on a remote device.

[0122] Although the specific implementation manners of the present invention are described above, those skilled in the art should understand that this is only an example. The protection scope of the present invention is defined by the appended claims. Without departing from the principles and essence of the present invention, those skilled in the art can make various changes or modifications to these implementation manners, but these changes and modifications all fall within the protection scope of the present invention.

Claims

1. A method for planning a multi-destination travel route, characterized in that, The planning method includes: Generating a destination combination pool based on vacation product data and user high-frequency request data; Performing a first rationality test on the destination combination pool to obtain a target destination combination pool; the first rationality test is used to characterize the test of the destination combination overview; Determining a multi-destination route based on the target destination combination pool; the multi-destination route is used to characterize a route with a determined destination order and corresponding number of days; Obtaining a corresponding number of atomic routes from a set single-destination atomic route library according to the multi-destination route; the set single-destination atomic route library is used to characterize a route database of single destinations with different style identifiers or type identifiers and corresponding numbers of days configured in advance; Splicing a plurality of the atomic routes in the destination order to generate an original multi-destination route; Performing a second rationality test on the original multi-destination route to obtain a target multi-destination route; the second rationality test is used to characterize the test of the spliced route overview.

2. The planning method of the multi-destination travel route according to claim 1, characterized in that The step of determining a multi-destination route based on the target destination combination pool includes: Determining the first destination corresponding to each destination combination in the target destination combination pool; Calculating the shortest transfer path corresponding to the first destination using the TSP path planning algorithm; Calculating the allocated number of days for each destination corresponding to the shortest transfer path according to the recommended number of days for each set destination to generate the multi-destination route.

3. The planning method of the multi-destination travel route according to claim 1, characterized in that, The first rationality test includes at least one of the rationality of the number of days, the cross-country rationality of the destination combination, the rationality of the destination type, the rationality of the destination subordination relationship, and the difference in destination popularity; And / or, the second rationality test includes at least one of the rationality test of the number of days for detouring, the rationality test of the cross-city day travel time, and the rationality test of the scenic spot relationship.

4. The planning method of the multi-destination travel route according to claim 1, characterized in that, The step of generating a destination combination pool according to the vacation product data and the user high-frequency request data includes: Screening out a first feasible route alternative pool with a confidence level greater than a set value according to the original vacation products, the number of products, and the number of orders in the vacation product data; Screening out a second feasible route alternative pool with a frequency greater than a set value according to the user search destination combination, the number of searches, and the number of search days in the user high-frequency request data; Generating the destination combination pool based on the first feasible route alternative pool and the second feasible route alternative pool.

5. The planning method of the multi-destination travel route according to claim 1, characterized in that The planning method further includes: When the original multi-destination route does not meet the second rationality test, obtaining corresponding new atomic routes from the set single-destination atomic route library; Splicing a plurality of the new atomic routes in the destination order to generate a new original multi-destination route.

6. The method for planning a multi-destination travel route according to claim 5, wherein, The planning method further includes: When all the atomic routes replaced to generate a new original multi-destination route do not meet the second rationality test, performing a fallback correction operation; the fallback correction operation is used to characterize the operation of removing unnecessary destinations in the original multi-destination route.

7. A planning system for a multi-destination travel route, characterized in that, The planning system includes: A first generation module for generating a destination combination pool according to vacation product data and user high-frequency request data; The first verification module is used to perform a first rationality verification on the destination combination pool to obtain a target destination combination pool; the first rationality verification is used to represent the verification of the destination combination state. The determination module is used to determine a multi-destination route based on the target destination combination pool; the multi-destination route is used to represent a route with a determined destination order and corresponding number of days. The first acquisition module is used to obtain a corresponding number of atomic routes from a set single-destination atomic route library according to the multi-destination route; the set single-destination atomic route library is used to represent a route database of single destinations with different style identifiers or type identifiers and corresponding number of days pre-configured. The second generation module is used to splice a plurality of the atomic routes in the destination order to generate an original multi-destination route. The second verification module is used to perform a second rationality verification on the original multi-destination route to obtain a target multi-destination route; the second rationality verification is used to represent the verification of the spliced route overview.

8. An electronic device, characterized in that, It includes a processor, a memory, and a computer program stored on the memory and executable on the processor. When the computer program is executed by the processor, it implements the multi-destination travel route planning method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium. When the computer program is executed by the processor, it implements the multi-destination travel route planning method according to any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the multi-destination travel route planning method according to any one of claims 1-6.

Images