Travel recommendation method and system based on smart city

Abstract

The invention discloses a travel recommendation method and system based on a smart city, and the method comprises the steps: generating a travel recommendation scheme of a travel destination for a user based on the travel destination information inputted by the user; according to the travel recommendation method and device, the travel recommendation scheme which is most suitable for the user is obtained through real-time analysis according to the own travel feeling of the user, and compared with a common recommendation scheme, the travel recommendation method and device better meet the requirements of the user, and the user experience is improved. Efficient journey allocation is realized in the journey process among different scenic spots in a smart city, the humanization degree of a journey recommendation scheme is increased, and more choices are provided for remaining journey arrangement of a user in each time period; meanwhile, on roads from hotels to scenic spots, travel peak hours are avoided according to individual requirements of users, and the possibility of road congestion in route areas is reduced to the maximum extent. The system has the characteristics of high humanization degree and strong journey planning capability.

Description

Technical Field

[0001] The present invention relates to the technical field of travel recommendation, and particularly to a travel recommendation method and system based on a smart city. Background Art

[0002] With the rapid development of network information technology and the fast development of the Internet industry, the information technology of the Internet and the tourism service industry are carrying out collaborative cooperation and rapid integration, thus generating more creative industrial forms and exploring a development path of information transformation and intelligent upgrading. The smart city travel recommendation system utilizes technologies such as cloud computing, Internet of Things, next-generation communication network, high-performance information processing, intelligent mining, big data management, etc., and timely grasps the needs of the main body, object media, and carrier of tourism through the Internet, mobile Internet or information processing terminal, and actively senses various factors such as tourism resources, tourism economy, tourism activities, tourists, etc. By extracting and analyzing data information, the relationship between each main body is continuously optimized, so that it can be presented efficiently, conveniently and sustainably in a systematic and intensive manner.

[0003] However, the existing smart tourism recommendation systems still have difficulty in meeting user needs. In the prior art, the location recommendation methods in smart cities are single, and it is difficult for users to obtain highly matched recommended resources during the process of playing or daily consumption. The matching degree between the recommended location and the actual needs of users is poor, resulting in a low utilization rate of the recommendation scheme. Especially when users are unable to complete the journey plan due to various factors, they are prone to have an anxious mood, which makes the journey recommendation scheme obtained by normal retrieval often difficult to be accepted by users due to the inherent route plan. At the same time, the system will not make corresponding judgments on the implicit choices of users, thus affecting the quality of the system's recommendation to users and even affecting the user experience. Therefore, it is necessary to design a travel recommendation method and system based on a smart city with a high degree of humanization and strong journey planning ability. Summary of the Invention

[0004] The purpose of the present invention is to provide a travel recommendation method and system based on a smart city to solve the problems raised in the above background art.

[0005] To solve the above technical problems, the present invention provides the following technical solutions: A travel recommendation method and system based on a smart city, including:

[0006] Receiving travel destination information input by a user, and generating multiple travel recommendation schemes for the travel destination based on the travel destination information;

[0007] Collecting journey information of the user during the user's journey, analyzing ranking indicators based on the journey information, and ranking the multiple travel recommendation schemes according to the ranking indicators;

[0008] After the user completes a journey, analyze the calibration rate of the next trip based on the ranking results. The calibration rate is used to judge the willingness ratio of whether the user hopes to go to the scenic spots expected by the user. During the user's journey, the calibration rate is adjusted in real time, and the most suitable travel recommendation plan is output to the user based on the ranking results after calibration.

[0009] According to the above technical solution, generating multiple travel recommendation plans for the travel destination for the user based on the travel destination information input by the user, including:

[0010] Retrieve the travel destination data in the database. The travel destination data includes the location information of multiple hotels, the location information of multiple scenic spots, the location information of various means of transportation, and the itinerary route information between the above three locations after the user arrives at the travel destination by means of transportation;

[0011] Based on the travel destination location data, monitor the itinerary route, obtain the monitoring information of the journey information, compare the daily average traffic flow information stored in the monitoring information with the preset reference daily average traffic flow, and add the travel recommendation plan of the day to the travel plan of the day. When the daily average traffic flow of the day is higher than 10% of the reference daily average traffic flow, it is preset as the first travel recommendation plan; otherwise, it is preset as the second travel recommendation plan;

[0012] Based on the travel destination scenic spot data, obtain the average time required to visit the travel destination scenic spot. If the average time required to visit is higher than the remaining time t, it is preset as the third travel recommendation plan; otherwise, it is preset as the fourth travel recommendation plan;

[0013] Calibrate the multiple travel recommendation plans corresponding to the scenic spots that can be retrieved near the travel destination in turn according to the first travel recommendation plan, the second travel recommendation plan, the third travel recommendation plan, and the fourth travel recommendation plan;

[0014] According to the above technical solution, collecting the journey information of the user during the user's journey and ranking the multiple travel recommendation plans, including:

[0015] Rank the multiple travel recommendation plans corresponding to the scenic spots that can be retrieved near the travel destination according to the ranking indicators. Among them, the indicators for ranking the multiple travel recommendation plans include: the possible enjoyment degree of the user's actual journey, the parameter matching degree between the user's actual journey and the travel destination information input by the user in the smart city APP, and the displacement distance expected by the user from the start to the end of the journey;

[0016] Among them,

[0017] The possible enjoyment degree of the user's actual journey is related to the later journey situation of the user's daily journey in the smart city;

[0018] The matching degree between the user's actual journey and the parameters of the tourist destination information input by the user in the smart city APP is based on matching the corresponding location information at the corresponding time node;

[0019] The displacement distance that the user expects from the start to the end of the journey, including the total value of the itinerary route information, and the displacement distance can affect the possible enjoyment degree of the journey.

[0020] According to the above technical solution, the analysis result obtained based on the ranking includes:

[0021] Based on the current user journey situation, when it is monitored that 30% of the users do not perform any operations at the time of the next itinerary route information, the user journey is predicted and adjusted, including: based on the user's current location, at intervals of the next itinerary route information, retrieve the preset arrival time range of the second itinerary route information, calculate the longest time to reach the preset arrival time range at the current time, and sort the scenic spots that can be reached from the user's current location within the longest time range according to the arrival time.

[0022] According to the above technical solution, the output of the most suitable travel recommendation plan to the user based on the ranking includes:

[0023] For the scenic spots sorted in sequence, increase the calibration rate of the next journey based on the proportion of the arrival time to the maximum time, and increase the calibration rate of the next journey

[0024] Increase the calibration rate of the next journey according to the displacement distance, obtain the final calibration rate, and based on the final calibration rate, output the obtained scenic spot recommendation plan to the user through the smart city APP.

[0025] According to the above technical solution, the increase of the calibration rate of the next journey according to the displacement distance includes:

[0026] Divide the displacement distance into effective displacement distance and ineffective displacement distance;

[0027] The effective displacement distance is obtained from the expected displacement distance A in the user's journey, and the range of the effective displacement distance is [0, (1 + η%) × the expected displacement distance A in the user's journey], where η is the additional effective displacement distance coefficient, and the additional effective displacement distance coefficient is directly proportional to the parameter matching degree;

[0028] The invalid displacement distance is obtained from the difference A between the actual displacement distance B in the user journey and the expected displacement distance. The range of the invalid displacement distance is [the expected displacement distance B in the user journey - (1 + η%) the expected displacement distance A in the user journey, the actual displacement distance B in the user journey];

[0029] Based on the proportion values of the effective displacement distance and the invalid displacement distance in the displacement distance respectively, obtain the possible enjoyment degree of the user journey When it is monitored that the possible enjoyment degree W of the user journey is lower than the preset threshold value, increase the calibration rate of the next journey by 20%, and the increased calibration rate is not higher than 90%.

[0030] According to the above technical solution, a travel recommendation system based on a smart city includes:

[0031] A collection module, which is used to receive the travel destination information input by the user and generate multiple travel recommendation plans for the travel destination based on the travel destination information;

[0032] An analysis module, which is used to collect the journey information of the user during the user journey, analyze the ranking indicators based on the journey information, and rank the multiple travel recommendation plans according to the ranking indicators;

[0033] An output module, which is used to analyze the calibration rate of the next travel based on the ranking result when the user completes a journey. The calibration rate is used to judge the willingness ratio of the user to go to the scenic area expected by the user, adjust the calibration rate in real time during the user's travel, and output the most suitable travel recommendation plan to the user based on the calibrated ranking result.

[0034] According to the above technical solution, the collection module includes:

[0035] A travel destination information collection module, which is used to retrieve the travel destination data in the database. The travel destination data includes the location information of multiple hotels, the location information of multiple scenic areas, the location information of various means of transportation, and the itinerary information between the above three locations after the user arrives at the travel destination by means of transportation;

[0036] A travel recommendation plan generation module, which is used to monitor the itinerary based on the travel destination location data, obtain the monitoring information of the journey information, compare the daily average traffic flow information stored in the monitoring information with the preset reference daily average traffic flow, and add the travel recommendation plan of the day to the travel plan of the day. When the daily average traffic flow of the day is higher than 10% of the reference daily average traffic flow, it is preset as the first travel recommendation plan; otherwise, it is preset as the second travel recommendation plan; based on the scenic spot data of the travel destination, obtain the average time required to visit the scenic spots of the travel destination. If the required average time is higher than the remaining time t, it is preset as the third travel recommendation plan; otherwise, it is preset as the fourth travel recommendation plan; according to the first travel recommendation plan, the second travel recommendation plan, the third travel recommendation plan and the fourth travel recommendation plan, the corresponding multiple travel recommendation plans of the scenic spots that can be retrieved near the travel destination are calibrated in turn.

[0037] According to the above technical solution, the analysis module includes:

[0038] A plan ranking module, which is used to rank the multiple travel recommendation plans corresponding to the scenic spots that can be retrieved near the travel destination according to the ranking indicators. The indicators for ranking the multiple travel recommendation plans include: the possible enjoyment degree of the user's actual journey, the parameter matching degree between the user's actual journey and the travel destination information input by the user in the smart city APP, and the displacement distance expected by the user from the start to the end of the journey; the possible enjoyment degree of the user's actual journey is related to the later journey situation of the user's daily journey in the smart city; the parameter matching degree between the user's actual journey and the travel destination information input by the user in the smart city APP is based on matching the corresponding location information at the corresponding time node; the displacement distance expected by the user from the start to the end of the journey includes the total sum value of the itinerary information, and the displacement distance can affect the possible enjoyment degree of the journey.

[0039] A ranking indicator analysis module, which is used to predict and adjust the user's journey based on the current user journey situation when 30% of the users do not perform any operations when monitoring the next itinerary information time, including: based on the user's current location, at intervals of the next itinerary information, retrieve the preset arrival time range of the second itinerary information, calculate the longest time to reach the preset arrival time range at the current time, and sort the scenic spots that can be reached from the user's current location within the longest time range according to the arrival time.

[0040] According to the above technical solution, the output module includes:

[0041] Recommended solution output module, which is used to sequentially rank the scenic spots that have been ranked, increase the calibration rate of the next journey based on the proportion of the arrival time to the maximum time, and increase the calibration rate of the next journey Increase the calibration rate of the next journey according to the displacement distance, obtain the final calibration rate, and output the corresponding scenic spot recommendation solution to the user through the Smart City APP based on the final calibration rate.

[0042] Calibration rate allocation module, which is used to divide the displacement distance into effective displacement distance and ineffective displacement distance; the effective displacement distance is obtained from the expected displacement distance A in the user's journey, and the effective displacement distance range is [0, (1 + η%) expected displacement distance A in the user's journey], where η is the additional effective displacement distance coefficient, and the additional effective displacement distance coefficient is directly proportional to the parameter matching degree; the ineffective displacement distance is obtained from the difference A between the actual displacement distance B and the expected displacement distance in the user's journey, and the ineffective displacement distance range is [expected displacement distance B in the user's journey - (1 + η%) expected displacement distance A in the user's journey, actual displacement distance B in the user's journey]; respectively, based on the proportion values of the effective displacement distance and the ineffective displacement distance to the displacement distance, obtain the possible enjoyment degree of the user's journey If it is monitored that the possible enjoyment degree W of the user's journey is lower than the preset threshold value, increase the calibration rate of the next journey by 20%, and the increased calibration rate is not higher than 90%.

[0043] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: In the present invention, by collecting the user's journey information during the user's journey, generating a travel recommendation solution for the user's journey, ranking the recommendation solutions according to the ranking indicators, and analyzing in real time according to the user's own journey feelings to obtain the most suitable journey solution for the user, it is more in line with the user's needs compared with ordinary recommendation solutions. At the same time, efficient journey allocation is realized during the journey between scenic spots at different locations in the smart city, increasing the humanization degree of the travel recommendation solution and providing more choices for the remaining journey arrangements of the user at each time period; at the same time, on the road from the hotel to the scenic spot, avoid the travel peak period according to the user's personalized needs, and reduce the possibility of road congestion in the route area to the greatest extent. Brief Description of the Drawings

[0044] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention, and do not constitute a limitation to the present invention. In the drawings:

[0045] Figure 1 It is a flowchart of a travel recommendation method based on a smart city provided by an embodiment of the present invention;

[0046] Figure 2 It is a schematic diagram of the module composition of a travel recommendation system based on a smart city provided by an embodiment of the present invention. Specific implementation manners

[0047] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0048] Please refer to Figure 1 , which is a flowchart of a travel recommendation method based on a smart city provided by an embodiment of the present invention. As Figure 1 can be seen, the travel recommendation method based on a smart city includes:

[0049] Step S1: Receive the travel destination information input by the user, and generate multiple travel recommendation plans for the travel destination based on the travel destination information;

[0050] Step S2: Collect the user's journey information during the user's travel, analyze the ranking indicators based on the journey information, and rank the multiple travel recommendation plans according to the ranking indicators;

[0051] Step S3: When the user completes a journey, analyze the calibration rate of the next journey based on the ranking result. The calibration rate is used to judge the willingness ratio of the user to go to the scenic spots expected by the user. During the user's travel, the calibration rate is adjusted in real time, and the most suitable travel recommendation plan is output to the user based on the calibrated ranking result.

[0052] In the embodiment of the present invention, by collecting the user's journey information during the user's journey, generating travel recommendation plans for the user's journey, ranking the recommendation plans according to the ranking indicators, and analyzing in real time the most suitable journey plan for the user according to the user's own journey feelings, it is more in line with the user's needs compared with ordinary recommendation plans. At the same time, efficient journey allocation is realized during the journey between scenic spots at different locations in the smart city, increasing the humanization degree of the travel recommendation plan and providing more choices for the remaining journey arrangements of the user at each time period; at the same time, on the road from the hotel to the scenic spot, avoid the travel peak period according to the user's personalized needs, and minimize the possibility of road congestion in the route area.

[0053] In some preferred embodiments, based on the travel destination information input by the user, a plurality of travel recommendation plans for the travel destination are generated for the user, including:

[0054] Step S11: Retrieve the travel destination data in the database. The travel destination data includes, after the user arrives at the travel destination by means of transportation, the location information of multiple hotels, the location information of multiple scenic spots, the location information of multiple means of transportation, and the itinerary information between the above three locations;

[0055] Step S12: Based on the travel destination location data, monitor the itinerary, obtain the monitoring information of the journey information, compare the daily average traffic flow information stored in the monitoring information with a preset reference daily average traffic flow, and add the current day's travel recommendation plan to the current day's travel plan. When the current day's average traffic flow is higher than 10% of the reference daily average traffic flow, it is preset as the first travel recommendation plan; otherwise, it is preset as the second travel recommendation plan;

[0056] Step S13: Based on the travel destination scenic spot data, obtain the average time required to visit the travel destination scenic spots. If the average time required is higher than the remaining time t, it is preset as the third travel recommendation plan; otherwise, it is preset as the fourth travel recommendation plan;

[0057] Step S14: Mark the corresponding multiple travel recommendation plans for the scenic spots that can be retrieved near the travel destination in sequence according to the first travel recommendation plan, the second travel recommendation plan, the third travel recommendation plan, and the fourth travel recommendation plan.

[0058] In a preferred embodiment, obtaining the daily average traffic flow information stored in the monitoring information includes: analyzing the travel destination data according to the travel guide in the database, matching the corresponding location information at the corresponding time node. The location information includes the location information of multiple travel locations, the location information of multiple scenic spots, and the location information of multiple means of transportation. When reaching the corresponding time node, count the number of people whose location information changes, compare the counted number of people whose location information changes with the possible interval of the number of people corresponding to the traffic flow. The possible interval of the number of people corresponding to the traffic flow is related to the number of people that the vehicle can carry and the number of people on the vehicle. Among them, record the maximum value of the number of people that the vehicle can carry and the number of people on the vehicle according to the vehicle model recorded in the monitoring information, randomly select a value within the maximum value of the number of people on the vehicle as the possible value of the number of people on the vehicle, and output the average value of the possible values of the number of people on the vehicle corresponding to the traffic flow;

[0059] In some preferred embodiments, collecting the journey information of the user during the user journey and ranking the multiple travel recommendation plans includes:

[0060] Step S211: Ranking the multiple travel recommendation plans corresponding to the scenic spots that can be retrieved near the travel destination according to the ranking indicators. The indicators for ranking the multiple travel recommendation plans include: the possible enjoyment degree of the user's actual journey, the parameter matching degree between the user's actual journey and the travel destination information input by the user in the smart city APP, and the displacement distance expected by the user from the start to the end of the journey.

[0061] Among them,

[0062] The possible enjoyment degree of the user's actual journey is related to the later journey situation of the user's daily journey in the smart city.

[0063] In the early stage of the daily journey, it may be affected by: the fatigue degree of the previous day's journey arrangement, the user's own compactness of the journey arrangement, the time required to complete a single scenic spot, etc. Therefore, the analysis of the early stage of the daily journey is uncontrollable. However, when the user reaches the later stage of the daily journey, fatigue will normally occur.

[0064] The parameter matching degree between the user's actual journey and the travel destination information input by the user in the smart city APP is based on matching the corresponding location information at the corresponding time node.

[0065] The parameter matching degree is divided into two aspects. On the one hand, when the user has not yet started the journey, analyze whether the user can complete the journey feasibility. On the other hand, when the user has completed the journey, analyze the deviation between the user and the expected journey.

[0066] The more the corresponding location information is matched at the corresponding time node, the higher the parameter matching degree between the journey and the journey input by the user; conversely, the less the corresponding location information is matched at the corresponding time node, the lower the parameter matching degree between the journey and the journey input by the user.

[0067] The displacement distance expected by the user from the start to the end of the journey includes the total value of the itinerary route information, and the displacement distance can affect the possible enjoyment degree of the journey.

[0068] In some preferred embodiments, the analysis results obtained based on the ranking include:

[0069] Step S221: Based on the current user journey, when it is monitored that the user has not performed any operation for 30% of the time of the next itinerary route information, the user journey is predicted and adjusted, including: based on the user's current location, the next itinerary route information is separated, the preset arrival time range of the second itinerary route information is retrieved, the longest time from the current time to the preset arrival time range is calculated, and the scenic spots that can be reached from the user's current location within the longest time range are sorted according to the arrival time.

[0070] Through the analysis process of the tourist destination, after the user enters the destination, the user arrives at the tourist destination and recommends the itinerary plan to help the user complete a more accurate plan during the journey;

[0071] However, during the actual travel process, users may shelve or be unable to efficiently complete their travel plans due to their own or external reasons, resulting in a decline in their travel experience. In actual situations, whether the user's travel experience meets expectations is not only due to the quality of the scenic spot itself, but also the proportion of the user's completion of the preset journey plan. If the optimal solution for the remaining journey can be recommended at any time, the adjustability of the travel plan will be too small. A method is needed to maximize the real-time variability of the journey while controlling the journey to complete the user's expected plan within the preset time, rather than changing the journey after the time node has been missed, which will waste a lot of daily travel time. If the user fails to complete the journey due to his own reasons, he should be able to predict the next journey to a certain extent and find the optimal solution for the journey plan.

[0072] In some preferred embodiments, outputting the most suitable travel recommendation plan to the user based on the ranking includes:

[0073] Step S31: For the sorted scenic spots, the calibration rate of the next journey is increased based on the ratio of the arrival time to the maximum time, and the calibration rate of the next journey is increased.

[0074] Step S32: The calibration rate of the next journey is increased according to the displacement distance to obtain a final calibration rate, and based on the final calibration rate, the corresponding scenic spot recommendation plan is output to the user through the smart city APP.

[0075] Compared with the prior art, the current travel recommendation system in a smart city will, after the user inputs a travel destination, generate the most suitable travel plan for the user based on the user's personal preferences and historical records, as well as the online guides for tourist attractions; at the same time, combining the road condition data of the travel destination, it will adjust the travel in a timely manner during the user's travel; however, what the user hopes to obtain is a brand-new travel experience. Such a system lacks personalized recommendations. The recommended results are for all users. Regardless of the type of user or the approximate recommended result the user wants, the system only makes a general recommendation without classifying the users and then making targeted recommendations according to the user's needs.

[0076] Since the user's hotel location has been fixed during the journey or within the available time period of living at the hotel location, the distance between the user and the scenic spot is determined. At the same time, how to allocate the time to go to the scenic spot within the available time period, the level of the calibration rate of the next journey determines whether it is necessary to go to the scenic spot expected by the user. If the calibration rate of the next journey is high, only the scenic spot expected by the user is recommended, but considering the travel time, the factor of time arrangement decreases; if the calibration rate of the next journey is low, multiple scenic spots can be recommended, comprehensively considering the travel time and the factor of time arrangement.

[0077] In some preferred embodiments, improving the calibration rate of the next journey according to the displacement distance includes:

[0078] Step S321: Divide the displacement distance into an effective displacement distance and an ineffective displacement distance;

[0079] Step S322: The effective displacement distance is obtained from the expected displacement distance A in the user's journey. The range of the effective displacement distance is [0, (1 + η%) × the expected displacement distance A in the user's journey], where η is the additional effective displacement distance coefficient, and the additional effective displacement distance coefficient is directly proportional to the parameter matching degree;

[0080] Step S323: The ineffective displacement distance is obtained from the difference between the actual displacement distance B and the expected displacement distance A in the user's journey. The range of the ineffective displacement distance is [the expected displacement distance B in the user's journey - (1 + η%) × the expected displacement distance A in the user's journey, the actual displacement distance B in the user's journey];

[0081] Step S323: Based on the proportion values of the effective displacement distance and the ineffective displacement distance in the displacement distance respectively, obtain the possible enjoyment degree of the user's journey If it is monitored that the possible enjoyment degree W of the user's journey is lower than the preset threshold value, the calibration rate of the next journey is increased by 20%, and the increased calibration rate is not higher than 90%.

[0082] Please refer toFigure 2 , based on the same concept as the above embodiments, an embodiment of the present invention further provides a travel recommendation system based on a smart city, including:

[0083] A collection module, which is used to receive travel destination information input by a user, and based on the travel destination information, generate multiple travel recommendation plans for the travel destination;

[0084] An analysis module, which is used to collect the journey information of the user during the user's travel, analyze the ranking indicators based on the journey information, and rank the multiple travel recommendation plans according to the ranking indicators;

[0085] An output module, which is used to analyze the calibration rate of the next travel based on the ranking result when the user completes a journey. The calibration rate is used to judge the willingness ratio of the user to go to the scenic area expected by the user. During the user's travel, the calibration rate is adjusted in real time, and the most suitable travel recommendation plan is output to the user based on the calibrated ranking result.

[0086] In this embodiment, the collection module includes:

[0087] A travel destination information collection module, which is used to retrieve the travel destination data in the database. The travel destination data includes the location information of multiple hotels, the location information of multiple scenic areas, the location information of various means of transportation, and the itinerary route information between the above three locations after the user arrives at the travel destination by means of transportation;

[0088] A travel recommendation plan generation module, which is used to monitor the itinerary route based on the travel destination location data, obtain the monitoring information of the journey information, compare the daily average traffic flow information stored in the monitoring information with the preset reference daily average traffic flow, and add the travel recommendation plan of the day to the travel plan of the day. When the daily average traffic flow of the day is higher than 10% of the reference daily average traffic flow, it is preset as the first travel recommendation plan; otherwise, it is preset as the second travel recommendation plan; based on the travel destination scenic area data, obtain the average time required to play in the travel destination scenic area. If the required average time is higher than the remaining time t, it is preset as the third travel recommendation plan; otherwise, it is preset as the fourth travel recommendation plan; according to the first travel recommendation plan, the second travel recommendation plan, the third travel recommendation plan, and the fourth travel recommendation plan, the multiple travel recommendation plans corresponding to the scenic areas that can be retrieved near the travel destination are calibrated in sequence.

[0089] In this embodiment, the analysis module includes:

[0090] A solution ranking module, which is used to rank the multiple travel recommendation solutions corresponding to the scenic spots that can be retrieved near the calibrated travel destination according to ranking indicators. The indicators for ranking the multiple travel recommendation solutions include: the possible enjoyment degree of the user's actual journey, the parameter matching degree between the user's actual journey and the travel destination information input by the user in the Smart City APP, and the displacement distance that the user expects from the start to the end of the journey; the possible enjoyment degree of the user's actual journey is related to the later journey situation of the user's daily journey in the Smart City; the parameter matching degree between the user's actual journey and the travel destination information input by the user in the Smart City APP is based on matching the corresponding location information at the corresponding time node; the displacement distance that the user expects from the start to the end of the journey includes the total value of the itinerary route information, and the displacement distance can affect the possible enjoyment degree of the journey.

[0091] A ranking indicator analysis module, which is used to predict and adjust the user's journey based on the current user journey situation when it is monitored that 30% of the users do not perform any operations at the time of the next itinerary route information. The prediction and adjustment include: based on the user's current location, at intervals of the next itinerary route information, retrieve the preset arrival time range of the second itinerary route information, calculate the longest time to reach the preset arrival time range at the current time, and sort the scenic spots that can be reached from the user's current location within the longest time range according to the arrival time.

[0092] In this embodiment, the output module includes:

[0093] A recommended solution output module, which is used to sequentially improve the calibration rate of the next journey based on the proportion of the arrival time to the maximum time for the ranked scenic spots, and the calibration rate of the next journey Improve the calibration rate of the next journey according to the displacement distance, obtain the final calibration rate, and output the corresponding scenic spot recommendation solution to the user through the Smart City APP based on the final calibration rate.

[0094] Calibration rate adjustment module, which is used to divide the displacement distance into effective displacement distance and ineffective displacement distance; the effective displacement distance is obtained from the expected displacement distance A in the user journey, and the range of the effective displacement distance is [0, (1 + η%) × the expected displacement distance A in the user journey], where η is the additional effective displacement distance coefficient, and the additional effective displacement distance coefficient is directly proportional to the parameter matching degree; the ineffective displacement distance is obtained from the difference between the actual displacement distance B and the expected displacement distance A in the user journey, and the range of the ineffective displacement distance is [the expected displacement distance B in the user journey - (1 + η%) × the expected displacement distance A in the user journey, the actual displacement distance B in the user journey]; respectively, based on the proportion values of the effective displacement distance and the ineffective displacement distance in the displacement distance, obtain the possible enjoyment degree of the user journey If it is monitored that the possible enjoyment degree W of the user journey is lower than the preset boundary value, the calibration rate of the next journey will be increased by 20%, and the increased calibration rate shall not be higher than 90%.

[0095] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device.

[0096] Finally, it should be noted that the above are only the preferred embodiments of the present invention and are not used to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A travel recommendation method based on smart city, characterized by: include: receiving travel destination information input by a user, and generating a plurality of travel recommendation plans for the travel destination based on the travel destination information; Collecting the user's journey information during the user's travel, analyzing the ranking index based on the journey information, and ranking the multiple travel recommendation plans according to the ranking index; When the user completes a journey, the calibration rate of the next journey is analyzed based on the ranking results. The calibration rate is used to determine whether the user is willing to go to the scenic spot they desire. The calibration rate is adjusted in real time during the user's journey, and the most suitable travel recommendation plan is output to the user based on the ranking results calibrated with the calibration rate.

2. A travel recommendation method based on smart city according to claim 1, characterized in that: The receiving of the travel destination information input by the user and generating a plurality of travel recommendation plans for the travel destination based on the travel destination information includes: Retrieving the tourist destination data in a database, the tourist destination data including location information of multiple hotels, location information of multiple scenic spots, location information of multiple means of transportation, and itinerary route information between the above three locations after the user arrives at the tourist destination by means of transportation; According to the daily average traffic flow information, the preset reference daily average traffic flow is compared, and the travel recommendation plan for the day is added to the travel plan for the day. When the average traffic flow for the day is higher than 10% of the reference daily average traffic flow, it is preset as the first travel recommendation plan; otherwise, it is preset as the second travel recommendation plan; Based on the tourist destination scenic spot data, the average time required to visit the tourist destination scenic spot is obtained, and if the average time required to visit is greater than the remaining time t, the third travel recommendation plan is preset; otherwise, the fourth travel recommendation plan is preset; According to the first travel recommendation plan, the second travel recommendation plan, the third travel recommendation plan and the fourth travel recommendation plan, the multiple travel recommendation plans corresponding to the scenic spots that can be retrieved near the travel destination are marked in sequence.

3. A travel recommendation method based on smart city according to claim 2, characterized in that: The collecting of the user's journey information during the user's travel, and analyzing the ranking index based on the journey information, includes: The plurality of travel recommendation plans corresponding to the scenic spots that can be retrieved near the travel destination are ranked according to ranking indicators, wherein the indicators for ranking the plurality of travel recommendation plans include: the possible enjoyment of the user's actual journey, the matching degree of the parameters of the user's actual journey and the travel destination information input by the user in the smart city APP, and the displacement distance expected by the user from the start to the end of the journey; in, The possible enjoyment of the user's actual journey is related to the later journey conditions of the user's daily journey in the smart city; The degree of matching between the parameters of the user's actual journey and the tourist destination information input by the user in the smart city APP is based on matching the corresponding location information at the corresponding time node; The user expects the displacement distance from the start to the end of the trip, including the total value of the itinerary route information, and the displacement distance can affect the possible enjoyment of the journey.

4. A travel recommendation method based on smart city according to claim 3, characterized in that: The step of ranking the plurality of travel recommendation solutions according to the ranking index comprises: Based on the current user journey situation, when it is monitored that the user has not performed any operation for 30% of the time of the next itinerary route information, the user journey is predicted and adjusted, including: based on the user's current location, the next itinerary route information is separated, the preset arrival time range of the second itinerary route information is retrieved, the longest time from the current time to the preset arrival time range is calculated, and the scenic spots that can be reached from the user's current location within the longest time range are sorted according to the arrival time.

5. A travel recommendation method based on smart city according to claim 2, characterized in that: When the user completes a journey, the calibration rate of the next journey is analyzed based on the ranking result, and the most suitable travel recommendation plan is output to the user based on the ranking result after calibration of the calibration rate, including: For the sorted scenic spots, the calibration rate of the next journey is increased based on the ratio of the arrival time to the maximum time, and the calibration rate of the next journey is increased. Where T is the time to monitor the next trip route information; The calibration rate of the next journey is improved according to the displacement distance to obtain a final calibration rate, and based on the final calibration rate, the corresponding scenic spot recommendation plan is output to the user through the smart city APP.

6. A travel recommendation method based on smart city according to claim 5, characterized in that: The real-time adjustment of the calibration rate during the user's travel process includes: Dividing the displacement distance into effective displacement distance and invalid displacement distance; The effective displacement distance is obtained by the expected displacement distance A in the user journey, and the effective displacement distance range is [0, (1+η%) the expected displacement distance A in the user journey], where η is an additional effective displacement distance coefficient, and the additional effective displacement distance coefficient is proportional to the parameter matching degree; The invalid displacement distance is obtained by the difference A between the actual displacement distance B and the expected displacement distance in the user journey, and the invalid displacement distance range is [the expected displacement distance B in the user journey - (1 + η%) the expected displacement distance A in the user journey, the actual displacement distance B in the user journey]; Based on the ratio of the effective displacement distance and the invalid displacement distance to the displacement distance, the possible enjoyment of the user's journey is obtained. If it is monitored that the possible enjoyment W of the user's journey is lower than the preset limit value, the calibration rate of the next journey is increased by 20%, and the calibration rate after the increase is not higher than 90%.

7. A travel recommendation system based on smart city, characterized by: include: A collection module, the collection module is used to receive travel destination information input by a user, and generate a plurality of travel recommendation plans for the travel destination based on the travel destination information; An analysis module, the analysis module is used to collect the user's journey information during the user's travel, analyze the ranking index based on the journey information, and rank the multiple travel recommendation plans according to the ranking index; An output module is used to analyze the calibration rate of the next trip based on the ranking results after the user completes a trip. The calibration rate is used to judge whether the user wants to go to the user's desired scenic spot. The calibration rate is adjusted in real time during the user's trip, and the most suitable travel recommendation plan is output to the user based on the ranking result after calibration of the calibration rate.

8. A travel recommendation system based on smart city according to claim 7, characterized in that: The acquisition module comprises: A travel destination information collection module is used to Retrieving the tourist destination data in a database, the tourist destination data including location information of multiple hotels, location information of multiple scenic spots, location information of multiple means of transportation, and itinerary route information between the above three locations after the user arrives at the tourist destination by means of transportation; Based on the tourist destination scenic spot data, the average time required to visit the tourist destination scenic spot is obtained, and if the average time required to visit is greater than the remaining time t, the third travel recommendation plan is preset; otherwise, the fourth travel recommendation plan is preset; According to the first travel recommendation plan, the second travel recommendation plan, the third travel recommendation plan and the fourth travel recommendation plan, the multiple travel recommendation plans corresponding to the scenic spots that can be retrieved near the travel destination are marked in sequence. The travel destination data is retrieved in a database, and the travel destination data includes the location information of multiple hotels, the location information of multiple scenic spots, the location information of multiple transportation tools, and the itinerary route information between the above three locations after the user arrives at the travel destination by transportation; A travel recommendation plan generation module, the travel recommendation plan generation module is used to monitor the itinerary route based on the tourist destination location data, obtain the monitoring information of the journey information, compare the daily average traffic flow information stored in the monitoring information with the preset reference daily average traffic flow, and add the travel recommendation plan of the day to the tourism plan of the day. When the average traffic flow of the day is higher than 10% of the reference daily average traffic flow, it is preset as the first travel recommendation plan; otherwise, it is preset as the second travel recommendation plan; based on the tourist destination scenic spot data, the average time required to visit the tourist destination scenic spot is obtained. If the average time required to visit is higher than the remaining time t, it is preset as the third travel recommendation plan; otherwise, it is preset as the fourth travel recommendation plan; according to the first travel recommendation plan, the second travel recommendation plan, the third travel recommendation plan and the fourth travel recommendation plan, the multiple travel recommendation plans corresponding to the scenic spots that can be retrieved near the travel destination are marked in turn.

9. A travel recommendation system based on smart city according to claim 8, characterized in that: The analysis module comprises: A scheme ranking module, the scheme ranking module is used to rank the multiple travel recommendation schemes corresponding to the scenic spots that can be retrieved near the travel destination according to the ranking indicators, and the indicators for ranking the multiple travel recommendation schemes include: the possible enjoyment of the user's actual journey, the parameter matching degree of the user's actual journey and the tourist destination information input by the user in the smart city APP, and the displacement distance expected by the user from the beginning to the end of the journey; the possible enjoyment of the user's actual journey is based on the later journey situation of the user's daily journey in the smart city; the parameter matching degree of the user's actual journey and the tourist destination information input by the user in the smart city APP is based on the matching of the corresponding location information at the corresponding time node; the displacement distance expected by the user from the beginning to the end of the journey includes the sum of the itinerary route information, and the displacement distance can affect the possible enjoyment of the journey; A ranking indicator analysis module is used to predict and adjust the user journey based on the current user journey situation when it is monitored that the user has not performed any operation for 30% of the time of the next journey route information, including: based on the user's current location, the next journey route information is separated, the preset arrival time range of the second journey route information is retrieved, the longest time from the current time to the preset arrival time range is calculated, and the scenic spots that can be reached from the user's current location within the longest time range are sorted according to the arrival time.

10. A travel recommendation system based on smart city according to claim 9, characterized in that: The output module comprises: A recommendation output module is used to sequentially sort the scenic spots, increase the calibration rate of the next journey based on the proportion of the arrival time to the maximum time, and increase the calibration rate of the next journey The calibration rate of the next journey is improved according to the displacement distance to obtain a final calibration rate, and based on the final calibration rate, the corresponding scenic spot recommendation plan is output to the user through the smart city APP. A calibration rate adjustment module, the calibration rate adjustment module is used to divide the displacement distance into an effective displacement distance and an invalid displacement distance; the effective displacement distance is obtained by the expected displacement distance A in the user journey, and the effective displacement distance range is [0, (1+η%) the expected displacement distance A in the user journey], wherein η is an additional effective displacement distance coefficient, and the additional effective displacement distance coefficient is proportional to the parameter matching degree; the invalid displacement distance is obtained by the difference A between the actual displacement distance B in the user journey and the expected displacement distance, and the invalid displacement distance range is [the expected displacement distance B in the user journey-(1+η%) the expected displacement distance A in the user journey, the actual displacement distance B in the user journey]; based on the ratio of the effective displacement distance and the invalid displacement distance to the displacement distance, the possible enjoyment of the user journey is obtained. If it is monitored that the possible enjoyment W of the user's journey is lower than the preset limit value, the calibration rate of the next journey is increased by 20%, and the calibration rate after the increase is not higher than 90%.

Images