WO2022134478A1 - 路线推荐方法、装置、电子设备和存储介质 - Google Patents

路线推荐方法、装置、电子设备和存储介质 Download PDF

Info

Publication number
WO2022134478A1
WO2022134478A1 PCT/CN2021/097901 CN2021097901W WO2022134478A1 WO 2022134478 A1 WO2022134478 A1 WO 2022134478A1 CN 2021097901 W CN2021097901 W CN 2021097901W WO 2022134478 A1 WO2022134478 A1 WO 2022134478A1
Authority
WO
WIPO (PCT)
Prior art keywords
route
theme
information
poi
routes
Prior art date
Application number
PCT/CN2021/097901
Other languages
English (en)
French (fr)
Inventor
陈浩
赵润美
Original Assignee
北京百度网讯科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京百度网讯科技有限公司 filed Critical 北京百度网讯科技有限公司
Priority to US17/640,816 priority Critical patent/US11976935B2/en
Priority to KR1020227004987A priority patent/KR20220026602A/ko
Priority to EP21814666.0A priority patent/EP4047447A4/en
Priority to JP2022505517A priority patent/JP2023511799A/ja
Publication of WO2022134478A1 publication Critical patent/WO2022134478A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries

Definitions

  • the present disclosure relates to the field of data processing, and in particular, to the field of intelligent recommendation.
  • the present disclosure provides a route recommendation method, apparatus, electronic device and storage medium.
  • a method for recommending a route including:
  • the route recommendation request includes travel label information of N dimensions; N is a positive integer;
  • M theme routes are selected from the theme route library, including:
  • At least one theme route is selected from the theme route database; wherein, i is a positive integer less than or equal to N.
  • a route recommendation device comprising:
  • a receiving module configured to receive a route recommendation request, wherein the route recommendation request includes travel label information of N dimensions; N is a positive integer;
  • the route selection module is used to select M theme routes from the theme route library according to the itinerary label information of N dimensions; wherein, M is a positive integer;
  • the route determination module is used to determine the recommended route from the M theme routes
  • the route selection module selects at least one theme route from the theme route library according to the itinerary label information of the ith dimension in the N dimensions and the theme information of each theme route in the theme route library; wherein, i is a positive value less than or equal to N Integer.
  • an electronic device comprising:
  • the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method in any of the embodiments of the present disclosure.
  • a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method in any of the embodiments of the present disclosure.
  • a computer program product comprising a computer program that, when executed by a processor, implements the method in any of the embodiments of the present disclosure.
  • subject routes are respectively selected according to the itinerary label information of different dimensions in the route recommendation request, and then the recommended route is determined from the selected theme routes. Therefore, the personalized requirements corresponding to the route recommendation request can be met. , which automatically and efficiently recommends highly themed routes.
  • FIG. 1 is a schematic diagram of a route recommendation method provided according to an embodiment of the present disclosure
  • FIG. 2 is a schematic diagram of a route recommendation method provided according to another embodiment of the present disclosure.
  • FIG. 3 is a schematic diagram of an application example of the route recommendation method according to the present disclosure.
  • FIG. 4 is a schematic diagram of a route recommendation device provided according to an embodiment of the present disclosure.
  • FIG. 5 is a schematic diagram of a route recommendation device provided according to another embodiment of the present disclosure.
  • FIG. 6 is a block diagram of an electronic device used to implement the route recommendation method of an embodiment of the present disclosure.
  • FIG. 1 shows a schematic diagram of a route recommendation method provided by an embodiment of the present disclosure. As shown in Figure 1, the method includes:
  • Step S11 receiving a route recommendation request, wherein the route recommendation request includes travel label information of N dimensions; N is a positive integer;
  • Step S12 according to the itinerary label information of N dimensions, select M theme routes from the theme route library; wherein, M is a positive integer;
  • Step S13 determining a recommended route from the M theme routes
  • step S11 according to the itinerary label information of N dimensions, M theme routes are selected from the theme route library, including:
  • At least one theme route is selected from the theme route database; wherein, i is a positive integer less than or equal to N.
  • the route recommendation request may be triggered based on a user operation. For example, when the user inputs information such as travel destination, travel time, etc., the electronic device receives the corresponding route recommendation request.
  • the above N dimensions may include user positioning information, map area location information, user type, travel scene, travel mode, new heat index, and the like.
  • the user positioning information may refer to the positioning information when the user inputs the itinerary information, such as the user positioning city.
  • the itinerary label information in the dimension of user positioning information is, for example, Beijing, Shanghai, or Guangzhou.
  • the location information of the map area can be the geographic map area that the user frequently browses. For example, the user often browses a certain city or a certain scenic spot on the electronic map, and the itinerary label information corresponding to the dimension of the map area location information can be the city or the scenic spot.
  • the user type may include the user's geographic type, status type, age type, and the like.
  • the itinerary label information of the user type dimension includes local users, remote users, single users, family users, elderly users, and student users.
  • the itinerary scene may include the season in which the itinerary is located, and the itinerary label information corresponding to the itinerary scene dimension includes spring, summer, autumn, winter or early winter, late winter, etc.
  • the travel mode may refer to the user's preferred mode of transportation or the user-specified mode of transportation.
  • the itinerary label information of the travel mode dimension is, for example, cycling, walking, self-driving, or using public transportation.
  • the new heat index is used to characterize the newness or popularity of POIs (Point of Interest) passing through the itinerary or route.
  • the itinerary label information of the new hot index dimension may be a specific numerical value, and may be determined based on the user's preference for new hot spots.
  • M theme routes are first selected from the theme route library. For example, if a student user who prefers cycling initiates a route recommendation request for a winter tour, the route recommendation request includes travel label information in multiple dimensions, such as travel mode, user type, and travel scenario. These trip label information are cycling, student users, and winter. Then, the theme information is selected from the theme route library as the theme route of cycling, student exclusive, and winter tour. Among them, the number of various theme routes is not limited.
  • the itinerary corresponding to the route recommendation request and the relevant information of the user can be comprehensively considered, and the most suitable route can be selected from the M theme routes as the recommended route.
  • the relevant information of the itinerary includes, for example, the weather information of the itinerary period, the planning time of the itinerary, the number of days of the itinerary, the itinerary scene, etc.
  • the relevant information of the user includes the user portrait such as gender, age and other information, and user interests such as food consumption price preference, accommodation preference, etc. , user behavior such as browsing behavior on travel apps, etc.
  • the recommended route may be determined from the M topic routes based on preset rules, models, or user selection.
  • the route recommendation method provided by the embodiment of the present disclosure first selects theme routes according to the itinerary label information of different dimensions in the route recommendation request, and then determines the recommended route from the selected theme routes, the route recommendation request can correspond to the route recommendation request. automatically and efficiently recommend highly themed routes.
  • At least one theme route is selected from the theme route library according to the itinerary label information of the ith dimension in the N dimensions and the theme information of each theme route in the theme route library, include:
  • At least one theme route is selected from the theme route library.
  • the itinerary label information in the dimension of user positioning information is Beijing, that is, the similarity between the theme information of Beijing surrounding tour and the Forbidden City tour and the itinerary label information is high, and the similarity between the theme information Guangzhou surrounding tour and the itinerary label information is low. Therefore,
  • the theme information is selected as the theme route of Beijing Surrounding Tour, Forbidden City Tour, etc., and the theme information is not selected as the theme route of Guangzhou Surrounding Tour.
  • selecting at least one theme route from the theme route database includes: selecting at least one theme route from the theme route database with a similarity greater than a preset threshold.
  • the similarity may be determined based on the similarity calculation model or the characteristic distance between the itinerary label information and the topic information.
  • the subject route matching the itinerary tag information can be accurately selected.
  • the recommended route is determined from the M theme routes, including:
  • a preset model is used to obtain the score of each theme route in the M theme routes;
  • a recommended route is determined from the M theme routes.
  • the preset model may include a rank model or a classification model obtained based on supervised training.
  • DCN Deep&Cross Network, deep cross network
  • the user information corresponding to the above route recommendation request may include user portraits, user interests, user behaviors, and the like.
  • user portraits include gender, age, etc.
  • user interests include food consumption price preferences, accommodation preferences, etc.
  • user behaviors include browsing behaviors, retrieval behaviors, map poke behaviors, etc. on travel apps or electronic map apps, for example.
  • the subject information, itinerary label information and user information of the subject route can be input into the preset model, and the score of the subject route output by the preset model can be obtained.
  • the determination of the score can refer to the following formula:
  • Score f(user_profile, user_interest, user_action, scene, theme_info)
  • user_profile represents user profile
  • user_interest represents user preference
  • user_action represents user behavior
  • scene represents scene information in itinerary tag information
  • theme_info represents theme information of theme route.
  • f(*) represents the function corresponding to the preset model.
  • FIG. 2 shows a route recommendation method provided by another embodiment of the present disclosure, and the method may include:
  • Step S21 clustering at least one POI according to the label information of at least one POI in the target dimension to obtain at least one POI set;
  • Step S22 based on at least one POI set, obtain at least one theme route corresponding to the target dimension, and based on the label information of each POI in each POI set in the at least one POI set, obtain at least one theme route in each theme route. subject information;
  • Step S23 adding at least one theme route to the theme route library.
  • the target dimension may include the location of the POI, the recommended user type, the recommended play time, the recommended travel mode, feature information, new popularity index, and the like.
  • the label information of the recommended user type dimension of the POI may be a local user or a remote user.
  • the recommended play time of POI may include the recommended play season, month, and time period (such as morning, noon, and evening).
  • time period such as morning, noon, and evening.
  • the tag information of the recommended play time of POI can be determined, such as spring or summer, Monday or weekend, etc.
  • the label information of the recommended travel mode dimension of POI can be cycling, walking, self-driving, or using public transportation.
  • the navigation data of the electronic map App can be used to collect statistics on the distribution information of the navigation modes of the users going to and from the POI, so as to obtain the recommended travel mode of the POI.
  • the label information of the feature information dimension of POI can be based on keywords extracted and mined from user comments and third-party open data, such as red leaves, northwest, grassland, parent-child, and online celebrity punch cards.
  • the label information of the new heat index of POI is the specific new heat index value. Based on the statistical information of the electronic map App and third-party open data, the new heat index of POI can be mined. For example, the Palace Museum, which is open for a limited time and is in the 600-year exhibition, has a high new heat index, and has no popular activities and has been open for many years. Wangshan's new heat index is low. The new heat index can be updated regularly.
  • the POIs are clustered according to the label information of the POIs in a certain dimension, so that at least one POI set can be obtained.
  • the label information corresponding to different POI sets is quite different, and the labels of each POI in the same POI set The information difference is small.
  • Based on the POIs in each POI set in the at least one POI set a topic route containing the POIs can be derived.
  • the subject information of the subject route is the same or similar to the tag information of each POI in the target dimension.
  • clustering based on the recommended play time of POIs can make POIs suitable for spring play into one category, and POIs suitable for summer play into another category; if a theme route is obtained based on POIs of the same category, you can get a group of POIs suitable for spring play. Themed routes and routes suitable for summer play.
  • multiple themed routes located in different location areas or cities can be obtained, such as themed routes around the Forbidden City or the theme routes of must-visit attractions in Beijing.
  • Clustering based on travel mode can obtain self-driving tour theme routes, cycling theme routes, etc.
  • Clustering based on the characteristic information can obtain the theme route of red leaf tour, parent-child tour theme route, etc.
  • Clustering based on new hot information can obtain, for example, the exhibition theme routes that cannot be missed in October.
  • a theme route with strong theme and fun theme can be mined for specific user needs, which is beneficial to recommend a route that meets their individual needs for users.
  • the theme route is automatically generated, the user does not need to spend time and energy designing the theme route, which can reduce the pressure of manual content generation and efficiently perform route recommendation.
  • the above route recommendation method may further include:
  • At least one of the tour sequence, tour time and travel mode of each POI is determined.
  • itinerary-related information such as user departure time, itinerary compactness, etc.
  • user preference information such as travel mode preference (airplane/train/self-driving/bus, etc.), travel distance preference (short-haul/long-distance, etc.) and each POI
  • the location information, estimated duration of stay, etc. automatically generate the play route and specific time arrangement.
  • self-driving routes can be recommended for car owners, and public transportation routes can be recommended for non-car owners
  • time schedules with different degrees of compactness can be recommended for college students and users with children at home, such as 2 days for college students and 2 days for home users. Users with young children are scheduled for 3 days.
  • the play itinerary of each POI in the recommended route can be automatically planned, the pressure of manual planning is reduced, and the user experience is improved.
  • the above route recommendation method may further include:
  • the electronic map displays the recommended route and the board and lodging advice information within the preset range of each POI in the recommended route.
  • the food and lodging suggestion information may include recommended food information and recommended hotel information.
  • the electronic map may be a map in an electronic map App. Based on the existing surrounding location recommendation capabilities of the electronic map, combined with user interests (such as food consumption prices, hotel preferences, etc.), the recommended food information and recommended hotel information can be obtained. Based on the recommended route, the planning and arrangement of each POI in the recommended route And recommended food information, recommended hotel information, get a more complete travel guide.
  • the suggested information on board and lodging can be determined according to the tour time of each POI. For example, it is lunch time after a certain scenic spot in the itinerary, the intelligent recommends surrounding food for the user, and displays the surrounding food in the display area of the scenic spot on the electronic map; another example, displays the surrounding hotels in the display area of the last scenic spot on a certain day.
  • FIG. 3 shows a schematic diagram of an application example of the route recommendation method provided by the embodiment of the present disclosure.
  • the overall route recommendation method can be divided into two parts: offline strategy mining and online strategy validation.
  • the offline strategy mining part obtains POIs, user behavior information and third-party open data within a preset range, and understands the content of these contents to generate a theme route and obtain a theme route library, in which the theme route will be used as a candidate route.
  • the effective part of the online strategy includes a recall module, a sorting module, an automatic route calculation module and a surrounding recommendation module.
  • the recall module selects at least one theme route from the theme route library according to the current scene information and user information.
  • the sorting module sorts the at least one theme route according to the preset model to obtain a recommended route.
  • the automatic route calculation module plans the specific arrangement information of each POI in the recommended route based on the recommended route, that is, the user information, and the surrounding recommendation module recommends food and lodging advice information for the user. In this way, you can get a complete travel guide that combines the travel route and the recommendations for accommodation and meals.
  • subject routes are respectively selected for the itinerary label information of different dimensions in the route recommendation request, and then the recommended route is determined from the selected theme routes. automatically and efficiently recommend highly themed routes.
  • the present disclosure also provides a route recommendation device.
  • the device includes:
  • a receiving module 410 configured to receive a route recommendation request, wherein the route recommendation request includes travel label information of N dimensions; N is a positive integer;
  • the route selection module 420 is used to select M theme routes from the theme route library according to the itinerary label information of N dimensions; wherein, M is a positive integer;
  • a route determination module 430 configured to determine a recommended route from the M theme routes
  • the route selection module selects at least one theme route from the theme route library according to the itinerary label information of the ith dimension in the N dimensions and the theme information of each theme route in the theme route library; wherein, i is a positive value less than or equal to N Integer.
  • the route selection module 420 includes:
  • the selecting unit 422 selects at least one theme route from the theme route library according to the similarity.
  • the route determination module 430 includes:
  • the scoring unit 431 is used to obtain the score of each theme route in the M theme routes by using a preset model based on the user information corresponding to the M theme routes and the route recommendation request;
  • the determining unit 432 is configured to determine a recommended route from the M theme routes according to the score.
  • the device further includes:
  • the clustering module 510 is configured to perform clustering on at least one POI according to the label information of at least one POI in the target dimension to obtain at least one POI set;
  • the route generation module 520 is used to obtain at least one theme route corresponding to the target dimension based on at least one POI set, and obtain each POI in the at least one theme route based on the label information of each POI in each POI set in the at least one POI set. theme information for each theme route;
  • the route adding module 530 is used for adding at least one theme route to the theme route library.
  • the device further includes:
  • the route planning module 540 is configured to determine at least one of the tour sequence, tour time and travel mode of each POI according to the user preference information corresponding to the route recommendation request and the POI information in the recommended route.
  • the device further includes:
  • the information display module 550 is configured to display the recommended route and the board and lodging advice information within the preset range of each POI in the recommended route in the electronic map.
  • the apparatuses provided by the embodiments of the present disclosure have technical effects corresponding to the methods provided by the embodiments of the present disclosure.
  • the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.
  • FIG. 6 shows a schematic block diagram of an example electronic device 600 that may be used to implement embodiments of the present disclosure.
  • Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers.
  • Electronic devices may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smart phones, wearable devices, and other similar computing devices.
  • the components shown herein, their connections and relationships, and their functions are by way of example only, and are not intended to limit implementations of the disclosure described and/or claimed herein.
  • the device 600 includes a computing unit 601 that can be executed according to a computer program stored in a read only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603 Various appropriate actions and handling. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored.
  • the computing unit 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604.
  • An input/output (I/O) interface 605 is also connected to bus 604 .
  • Various components in the device 600 are connected to the I/O interface 605, including: an input unit 606, such as a keyboard, mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a magnetic disk, an optical disk, etc. ; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, and the like.
  • the communication unit 609 allows the device 600 to exchange information/data with other devices through a computer network such as the Internet and/or various telecommunication networks.
  • Computing unit 601 may be various general-purpose and/or special-purpose processing components with processing and computing capabilities. Some examples of computing units 601 include, but are not limited to, central processing units (CPUs), graphics processing units (GPUs), various specialized artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, digital signal processing processor (DSP), and any suitable processor, controller, microcontroller, etc.
  • the computing unit 601 executes the various methods and processes described above, such as a route recommendation method.
  • the route recommendation method may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 608 .
  • part or all of the computer program may be loaded and/or installed on device 600 via ROM 602 and/or communication unit 609 .
  • the computer program When the computer program is loaded into RAM 603 and executed by computing unit 601, one or more steps of the route recommendation method described above may be performed.
  • the computing unit 601 may be configured to perform the route recommendation method by any other suitable means (eg, by means of firmware).
  • Various implementations of the systems and techniques described herein above may be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips system (SOC), load programmable logic device (CPLD), computer hardware, firmware, software, and/or combinations thereof.
  • FPGAs field programmable gate arrays
  • ASICs application specific integrated circuits
  • ASSPs application specific standard products
  • SOC systems on chips system
  • CPLD load programmable logic device
  • computer hardware firmware, software, and/or combinations thereof.
  • These various embodiments may include being implemented in one or more computer programs executable and/or interpretable on a programmable system including at least one programmable processor that
  • the processor which may be a special purpose or general-purpose programmable processor, may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device an output device.
  • Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer or other programmable data processing apparatus, such that the program code, when executed by the processor or controller, performs the functions/functions specified in the flowcharts and/or block diagrams. Action is implemented.
  • the program code may execute entirely on the machine, partly on the machine, partly on the machine and partly on a remote machine as a stand-alone software package or entirely on the remote machine or server.
  • a machine-readable medium may be a tangible medium that may contain or store a program for use by or in connection with the instruction execution system, apparatus or device.
  • the machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
  • Machine-readable media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or devices, or any suitable combination of the foregoing.
  • machine-readable storage media would include one or more wire-based electrical connections, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), fiber optics, compact disk read only memory (CD-ROM), optical storage, magnetic storage, or any suitable combination of the foregoing.
  • RAM random access memory
  • ROM read only memory
  • EPROM or flash memory erasable programmable read only memory
  • CD-ROM compact disk read only memory
  • magnetic storage or any suitable combination of the foregoing.
  • the systems and techniques described herein may be implemented on a computer having a display device (eg, a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user ); and a keyboard and pointing device (eg, a mouse or trackball) through which a user can provide input to the computer.
  • a display device eg, a CRT (cathode ray tube) or LCD (liquid crystal display) monitor
  • a keyboard and pointing device eg, a mouse or trackball
  • Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (eg, visual feedback, auditory feedback, or tactile feedback); and can be in any form (including acoustic input, voice input, or tactile input) to receive input from the user.
  • the systems and techniques described herein may be implemented on a computing system that includes back-end components (eg, as a data server), or a computing system that includes middleware components (eg, an application server), or a computing system that includes front-end components (eg, a user's computer having a graphical user interface or web browser through which a user may interact with implementations of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system.
  • the components of the system may be interconnected by any form or medium of digital data communication (eg, a communication network). Examples of communication networks include: Local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
  • a computer system can include clients and servers.
  • Clients and servers are generally remote from each other and usually interact through a communication network.
  • the relationship of client and server arises by computer programs running on the respective computers and having a client-server relationship to each other.

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Navigation (AREA)

Abstract

一种路线推荐方法、装置、电子设备和存储介质，涉及数据处理领域，尤其涉及智能推荐领域。所述方法包括：接收路线推荐请求，其中，路线推荐请求包括N个维度的行程标签信息（S11）；根据N个维度的行程标签信息，从主题路线库中选取M个主题路线（S12）；从M个主题路线中确定出推荐路线（S13）；其中，根据N个维度的行程标签信息，从主题路线库中选取M个主题路线，包括：根据N个维度中第i个维度的行程标签信息与主题路线库中各主题路线的主题信息，从主题路线库中选取至少一个主题路线。所述方法能够针对用户的个性化需求，自动、高效地推荐主题性强的路线。

Description

路线推荐方法、装置、电子设备和存储介质 技术领域
本公开涉及数据处理领域，尤其涉及智能推荐领域。
背景技术
随着经济和生活水平的提高，人们旅游外出的需求日益繁盛。虽然旅行社会为用户提供旅游产品，但这些旅游产品并非针对用户定制的。
随着互联网的兴起，越来越多的用户选择自由行，以满足自身的个性化需求。由于目的地一般是用户不熟悉的地域，因此，用户会在旅游App(Application，应用程序)上搜索其他用户分享的旅游路线。但是这些旅游路线内容纷繁复杂且针对的用户群体千差万别，因此，用户一般通过查看用户分享的旅游路线才能决策出符合自身需求的路线。
发明内容
本公开提供了一种路线推荐方法、装置、电子设备和存储介质。
根据本公开的一方面，提供了一种路线推荐方法，包括：
接收路线推荐请求，其中，路线推荐请求包括N个维度的行程标签信息；N为正整数；
根据N个维度的行程标签信息，从主题路线库中选取M个主题路线；其中，M为正整数；
从M个主题路线中确定出推荐路线；
其中，根据N个维度的行程标签信息，从主题路线库中选取M个主题路线，包括：
根据N个维度中第i个维度的行程标签信息与主题路线库中各主题路线的主题信息，从主题路线库中选取至少一个主题路线；其中，i为小于等于N的正整数。
根据本公开的另一方面，提供了一种路线推荐装置，包括：
接收模块，用于接收路线推荐请求，其中，路线推荐请求包括N个维度的行程标签信息；N为正整数；
路线选取模块，用于根据N个维度的行程标签信息，从主题路线库中选取M个主题路线；其中，M为正整数；
路线确定模块，用于从M个主题路线中确定出推荐路线；
其中，路线选取模块根据N个维度中第i个维度的行程标签信息与主题路线库中各主题路线的主题信息，从主题路线库中选取至少一个主题路线；其中，i为小于等于N的正整数。
根据本公开的另一方面，提供了一种电子设备，包括：
至少一个处理器；以及
与该至少一个处理器通信连接的存储器；其中，
该存储器存储有可被该至少一个处理器执行的指令，该指令被该至少一个处理器执行，以使该至少一个处理器能够执行本公开任一实施例中的方法。
根据本公开的另一方面，提供了一种存储有计算机指令的非瞬时计算机可读存储介质，该计算机指令用于使计算机执行本公开任一实施例中的方法。
根据本公开的另一方面，提供了一种计算机程序产品，包括计算机程序，该计算机程序被处理器执行时实现本公开任一实施例中的方法。
由于本公开的技术方案，先针对路线推荐请求中不同维度的行程标签信息，分别选取主题路线，再从选取的主题路线中确定出推荐路线，因此，能够针对路线推荐请求所对应的个性化需求，自动、高效地推荐主题性强的路线。
应当理解，本部分所描述的内容并非旨在标识本公开的实施例的关键或重要特征，也不用于限制本公开的范围。本公开的其它特征将通过以下的说明书而变得容易理解。
附图说明
附图用于更好地理解本方案，不构成对本公开的限定。其中：
图1是根据本公开一个实施例提供的路线推荐方法的示意图；
图2是根据本公开另一个实施例提供的路线推荐方法的示意图；
图3是根据本公开的路线推荐方法的一个应用示例的示意图；
图4是根据本公开一个实施例提供的路线推荐装置的示意图；
图5是根据本公开另一个实施例提供的路线推荐装置的示意图；
图6是用来实现本公开实施例的路线推荐方法的电子设备的框图。
具体实施方式
以下结合附图对本公开的示范性实施例做出说明，其中包括本公开实施例的各种细节以助于理解，应当将它们认为仅仅是示范性的。因此，本领域普通技术人员应当认识到，可以对这里描述的实施例做出各种改变和修改，而不会背离本公开的范围和精神。同样，为了清楚和简明，以下的描述中省略了对公知功能和结构的描述。
图1示出了本公开一个实施例提供的路线推荐方法的示意图。如图1所示，该方法包括：
步骤S11，接收路线推荐请求，其中，路线推荐请求包括N个维度的行程标签信息；N为正整数；
步骤S12，根据N个维度的行程标签信息，从主题路线库中选取M个主题路线；其中，M为正整数；
步骤S13，从M个主题路线中确定出推荐路线；
其中，在步骤S11中，根据N个维度的行程标签信息，从主题路线库中选取M个主题路线，包括：
根据N个维度中第i个维度的行程标签信息与主题路线库中各主题路线的主题信息，从主题路线库中选取至少一个主题路线；其中，i为小于等于N的正整数。
示例性地，路线推荐请求可以基于用户操作触发，例如当用户输入行程目的地、行程时间等信息时，电子设备接收到对应的路线推荐请求。
上述N个维度可以包括用户定位信息、图区位置信息、用户类型、行程场景、出行方式、新热指数等。
其中，用户定位信息可以指用户输入行程信息时的定位信息，例如用户定位城市。用户定位信息维度的行程标签信息例如是北京、上海或广州等。
图区位置信息可以是用户经常浏览的地域图区，例如用户在电子地图上经常浏览某个城市或某个景区，图区位置信息维度对应的行程标签信息可以是该城市或该景区。
用户类型可以包括用户的地域类型、状态类型、年龄类型等。用户类型维度的行程标签信息包括本地用户、异地用户、单身用户、家庭用户、老年用户、学生用户等。
行程场景可以包括行程所在的季节，行程场景维度对应的行程标签信息包括春、夏、秋、冬或早冬、晚冬等。
出行方式可以指用户偏好的交通方式或用户指定的交通方式。出游方式维度的行程标签信息例如是骑行、步行、自驾车或使用公共交通等。
新热指数用于表征行程或路线中经过的POI(Point of Interest，兴趣点)的新热程度或者说热门程度。新热指数维度的行程标签信息可以是具体的数值，可以基于用户对新热景点的偏好程度确定。
本公开实施例中，根据N个维度中每个维度的行程标签信息，先从主题路线库中选取M个主题路线。例如，偏好骑行的学生用户发起了冬日游的路线推荐请求，则路线推荐请求中包括出行方式、用户类型、行程场景等多个维度的行程标签信息。这些行程标签信息分别是骑行、学生用户、冬天。则从主题路线库中选取主题信息为骑行、学生专属、冬日游的主题路线。其中，各类主题路线的数量不限。
在选取了M个主题路线后，可以综合考虑路线推荐请求所对应的行程和用户的相关信息，从M个主题路线中选取最合适的路线作为推荐路线。其中，行程的相关信息包括例如行程时段的天气信息、行程计划用时、行程天数、行程场景等，用户的相关信息包括用户画像例如性别、年龄等信息，用户兴趣例如美食消费价格偏好、住宿偏好等，用户行为例如在旅游App上的浏览行为等。举例而言，在选取了骑行主题路线和冬日游主题路 线后，综合考虑场景和行程时段的天气信息，从骑行主题路线和冬日游主题路线中选取冬日游主题路线作为推荐路线。示例性地，可以基于预设则、模型或用户的选择从M个主题路线中确定出推荐路线。
由于本公开实施例提供的路线推荐方法，先针对路线推荐请求中不同维度的行程标签信息，分别选取主题路线，再从选取的主题路线中确定出推荐路线，因此，能够针对路线推荐请求所对应的个性化需求，自动、高效地推荐主题性强的路线。
在一种示例性实施方式中，上述步骤S12中，根据N个维度中第i个维度的行程标签信息与主题路线库中各主题路线的主题信息，从主题路线库中选取至少一个主题路线，包括：
确定第i个维度的行程标签信息与主题路线库中各主题路线的主题信息之间的相似度；
根据相似度，从主题路线库中选取至少一个主题路线。
例如，用户定位信息维度的行程标签信息为北京，即主题信息北京周边游、故宫游等与行程标签信息的相似度较高，主题信息广州周边游与行程标签信息的相似度较低，因此，选取主题信息为北京周边游、故宫游等的主题路线，不选取主题信息为广州周边游的主题路线。
示例性地，根据相似度，从主题路线库中选取至少一个主题路线，包括：从主题路线库中选取相似度大于预设阈值的至少一个主题路线。
其中，相似度可以基于相似度计算模型或行程标签信息和主题信息之间的特征距离确定。
根据上述示例性实施方式，采用相似度量化行程标签信息和主题信息之间的匹配程度，可以准确选取与行程标签信息匹配的主题路线。
在一种示例性的实施方式中，上述步骤S13，从M个主题路线中确定出推荐路线，包括：
基于M个主题路线和路线推荐请求所对应的用户信息，利用预设模型得到M个主题路线中每个主题路线的分数；
根据分数，从M个主题路线中确定出推荐路线。
示例性地，预设模型可以包括基于有监督训练得到的排序(rank)模型或分类模型。实际应用中，可以选择DCN(Deep&Cross Network，深度交叉网络)等实现。
上述路线推荐请求所对应的用户信息可以包括用户画像、用户兴趣、用户行为等。其中，用户画像包括例如性别、年龄等，用户兴趣包括例如美食消费价格偏好、住宿偏好等，用户行为包括例如在旅游App或电子地图App上的浏览行为、检索行为、地图戳点行为等。
示例性地，可以将主题路线的主题信息、行程标签信息和用户信息输入预设模型，得到预设模型输出的主题路线的分数。该分数Score的确定可参考如下公式：
Score＝f(user_profile,user_interest,user_action,scene,theme_info)
其中，user_profile表示用户画像，user_interest表示用户偏好，user_action表示用户行为，scene表示行程标签信息中的场景信息，theme_info表示主题路线的主题信息。f(*)表示预设模型对应的函数。
本公开实施例还提供上述主题路线的生成方式。具体的，图2示出了本公开另一实施例提供的路线推荐方法，该方法可以包括：
步骤S21，根据至少一个兴趣点POI在目标维度的标签信息，对至少一个POI进行聚类，得到至少一个POI集合；
步骤S22，基于至少一个POI集合，得到与目标维度对应的至少一个主题路线，并基于至少一个POI集合中每个POI集合中的各POI的标签信息，得到至少一个主题路线中每个主题路线的主题信息；
步骤S23，将至少一个主题路线添加到主题路线库中。
示例性地，目标维度可以包括POI的位置、推荐用户类型、推荐游玩时间、推荐出行方式、特色信息、新热指数等。
其中，POI的推荐用户类型维度的标签信息可以是本地用户或异地用户。利用电子地图App用户在地图中对某个POI的交互行为例如点击或导航行为，结合各用户的常住地信息，可以统计得到本地用户和异地用户对该POI的交互次数比例。例如北京百望山的本异地用户交互比例可能是本地：异地＝99:1，因此百望山在推荐用户类型维度上的标签信息为本地用户。
POI的推荐游玩时间，可以包括推荐游玩季节、月份、时段(如早中晚)。通过电子地图App的轨迹数据，可以统计得到POI在不同时间的人流数量，基于人流数量和营业时间，可以确定POI的推荐游玩时间的标签信息例如是春天或夏天、周一或周末等。
POI的推荐出行方式维度的标签信息可以是骑行、步行、自驾车或采用公共交通等。可以利用电子地图App的导航数据，统计来往该POI的用户的导航方式分布信息，得到POI的推荐出行方式。
POI的特色信息维度的标签信息可以是根据从用户评论和第三方开放数据中抽取和挖掘的关键词，例如，红叶、西北、草原、亲子、网红打卡等。
POI的新热指数的标签信息为具体的新热指数数值。可以基于电子地图App的统计信息和第三方开放数据，挖掘出POI的新热指数，例如限时开放且正处于600年大展中的故宫博物院的新热指数高，无热门活动且开放多年的百望山的新热指数低。新热指数可以定时统计更新。
本公开实施例中，根据POI在某种维度的标签信息，对POI进行聚类，从而可以得到至少一个POI集合，不同的POI集合对应的标签信息差别较大，同一POI集合中各POI的标签信息差别较小。基于至少一个POI集合中的每个POI集合中的各POI，可以得到包含各POI的主题路线。其中，该主题路线的主题信息与各POI在目标维度上的标签信息相同或相近。
例如，基于POI的推荐游玩时间进行聚类，可以使适合春天游玩的POI聚成一类，适合夏天游玩的POI聚成另一类；基于同一类的POI得到一个主题路线，则可以得到适合春天游玩的主题路线和适合夏天游玩的路线。
类似地，基于位置进行聚类，可以得到位于不同位置区域或者城市的多个主题路线，例如故宫周边游主题路线或北京必游景点主题路线等。
基于出行方式进行聚类，可以得到自驾游主题路线、骑行主题路线等。
基于特色信息进行聚类，可以得到红叶游主题路线、亲子游主题路线等。
基于新热信息进行聚类，可以得到例如10月不能错过的展览主题路线等。
可见，根据上述实施方式，可以挖掘到针对特定用户需求的主题性强富有主题乐趣的主题路线，有利于为用户推荐满足其个性化需求的路线。并且，由于自动生成了主题路线，不需要用户花费时间和精力设计主题路线，可以减少人工内容生成的压力，高效地进行路线推荐。
示例性地，上述路线推荐方法还可以包括：
根据路线推荐请求所对应的用户偏好信息和推荐路线中的各POI信息，确定各POI的游览顺序、游览时间及出行方式中至少之一。
实际应用中，可以结合行程相关信息例如用户出发时间、行程紧凑程度等，以及用户偏好信息例如出游方式偏好(飞机/火车/自驾/公交等)，出游距离偏好(短途/长途等)以及各POI的位置信息、预计停留时长等，自动化生成游玩线路、具体的时间安排。例如可以为车主用户推荐自驾线路，为非车主用户推荐公共交通线路；又如，为大学生用户和为家有小孩的用户推荐紧凑程度不同的时间安排，比如为大学生用户安排为2天，为家有小孩的用户安排为3天。
根据上述实施方式，可以自动规划推荐路线中各POI的游玩行程，减少人工规划的压力，提高用户体验度。
示例性地，上述路线推荐方法还可以包括：
在电子地图中显示推荐路线以及推荐路线中各POI的预设范围内的食宿建议信息。
其中，食宿建议信息可以包括推荐美食信息和推荐酒店信息。
示例性地，该电子地图可以是电子地图App中的地图。基于电子地图已有的周边地点推荐能力，结合用户兴趣(比如美食消费价格、住酒店偏好等)等，可以获得推荐美食信息和推荐酒店信息，基于推荐路线、对推荐路线中各POI的规划安排以及推荐美食信息、推荐酒店信息，得到较为完善的出游指南。
实际应用中，可以根据各POI的游览时间确定食宿建议信息。例如行程中某景点结束后是午饭时间，则智能为用户推荐周边美食，在电子地图上该景点的显示区域显示周边美食；又如，在某天的最后一个景点的显示 区域显示周边酒店等。
图3示出了本公开实施例提供的路线推荐方法的一个应用示例的示意图。如图3所示，路线推荐方法整体可分为离线策略挖掘、在线策略生效两个部分实现。其中离线策略挖掘部分通过获取预设范围内的POI、用户行为信息和第三方开放数据，对这些内容进行内容理解，可以生成主题路线，得到主题路线库，其中的主题路线将作为候选路线。在线策略生效部分包括召回模块、排序模块、自动算路模块和周边推荐模块。其中，召回模块根据当前场景信息和用户信息，从主题路线库中选取至少一个主题路线。排序模块根据预设模型对至少一个主题路线进行排序，得到推荐路线。自动算路模块基于推荐路线即用户信息规划推荐路线中各POI的具体安排信息，周边推荐模块为用户推荐食宿建议信息。如此，可以得到结合游玩路线和食宿建议的完善的出游指南。
可见，根据本公开实施例提供的方法，先针对路线推荐请求中不同维度的行程标签信息，分别选取主题路线，再从选取的主题路线中确定出推荐路线，因此，能够针对路线推荐请求所对应的个性化需求，自动、高效地推荐主题性强的路线。
作为上述各方法的实现，本公开还提供一种路线推荐装置。如图4所示，该装置包括：
接收模块410，用于接收路线推荐请求，其中，路线推荐请求包括N个维度的行程标签信息；N为正整数；
路线选取模块420，用于根据N个维度的行程标签信息，从主题路线库中选取M个主题路线；其中，M为正整数；
路线确定模块430，用于从M个主题路线中确定出推荐路线；
其中，路线选取模块根据N个维度中第i个维度的行程标签信息与主题路线库中各主题路线的主题信息，从主题路线库中选取至少一个主题路线；其中，i为小于等于N的正整数。
示例性地，如图5所示，路线选取模块420包括：
相似度确定单元421，用于确定第i个维度的行程标签信息与主题路线库中各主题路线的主题信息之间的相似度；
选取单元422，同于根据相似度，从主题路线库中选取至少一个主题路线。
示例性地，如图5所示，路线确定模块430包括：
评分单元431，用于基于M个主题路线和路线推荐请求所对应的用户信息，利用预设模型得到M个主题路线中每个主题路线的分数；
确定单元432，用于根据分数，从M个主题路线中确定出推荐路线。
示例性地，如图5所示，该装置还包括：
聚类模块510，用于根据至少一个POI在目标维度的标签信息，对至少一个POI进行聚类，得到至少一个POI集合；
路线生成模块520，用于基于至少一个POI集合，得到与目标维度对应的至少一个主题路线，并基于至少一个POI集合中每个POI集合中的各POI的标签信息，得到至少一个主题路线中每个主题路线的主题信息；
路线添加模块530，用于将至少一个主题路线添加到主题路线库中。
示例性地，如图5所示，该装置还包括：
路线规划模块540，用于根据路线推荐请求所对应的用户偏好信息和推荐路线中的各POI信息，确定各POI的游览顺序、游览时间及出行方式中至少之一。
示例性地，如图5所示，该装置还包括：
信息显示模块550，用于在电子地图中显示推荐路线以及推荐路线中各POI的预设范围内的食宿建议信息。
本公开实施例提供的装置，具有与本公开实施例提供的方法相应的技术效果。
根据本公开的实施例，本公开还提供了一种电子设备、一种可读存储介质和一种计算机程序产品。
图6示出了可以用来实施本公开的实施例的示例电子设备600的示意性框图。电子设备旨在表示各种形式的数字计算机，诸如，膝上型计算机、台式计算机、工作台、个人数字助理、服务器、刀片式服务器、大型计算机、和其它适合的计算机。电子设备还可以表示各种形式的移动装置，诸如，个人数字处理、蜂窝电话、智能电话、可穿戴设备和其它类似的计算装置。本文所示的部件、它们的连接和关系、以及它们的功能仅仅作为示例，并且不意在限制本文中描述的和/或者要求的本公开的实现。
如图6所示，设备600包括计算单元601，其可以根据存储在只读存储器(ROM)602中的计算机程序或者从存储单元608加载到随机访问存储器(RAM)603中的计算机程序，来执行各种适当的动作和处理。在RAM 603中，还可存储设备600操作所需的各种程序和数据。计算单元601、ROM 602以及RAM 603通过总线604彼此相连。输入/输出(I/O)接口605也连接至总线604。
设备600中的多个部件连接至I/O接口605，包括：输入单元606，例如键盘、鼠标等；输出单元607，例如各种类型的显示器、扬声器等；存储单元608，例如磁盘、光盘等；以及通信单元609，例如网卡、调制解调器、无线通信收发机等。通信单元609允许设备600通过诸如因特网的计算机网络和/或各种电信网络与其他设备交换信息/数据。
计算单元601可以是各种具有处理和计算能力的通用和/或专用处理组件。计算单元601的一些示例包括但不限于中央处理单元(CPU)、图形处理单元(GPU)、各种专用的人工智能(AI)计算芯片、各种运行机器学习模型算法的计算单元、数字信号处理器(DSP)、以及任何适当的处理器、控制器、微控制器等。计算单元601执行上文所描述的各个方法和处理， 例如路线推荐方法。例如，在一些实施例中，路线推荐方法可被实现为计算机软件程序，其被有形地包含于机器可读介质，例如存储单元608。在一些实施例中，计算机程序的部分或者全部可以经由ROM 602和/或通信单元609而被载入和/或安装到设备600上。当计算机程序加载到RAM 603并由计算单元601执行时，可以执行上文描述的路线推荐方法的一个或多个步骤。备选地，在其他实施例中，计算单元601可以通过其他任何适当的方式(例如，借助于固件)而被配置为执行路线推荐方法。
本文中以上描述的系统和技术的各种实施方式可以在数字电子电路系统、集成电路系统、场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准产品(ASSP)、芯片上系统的系统(SOC)、负载可编程逻辑设备(CPLD)、计算机硬件、固件、软件、和/或它们的组合中实现。这些各种实施方式可以包括：实施在一个或者多个计算机程序中，该一个或者多个计算机程序可在包括至少一个可编程处理器的可编程系统上执行和/或解释，该可编程处理器可以是专用或者通用可编程处理器，可以从存储系统、至少一个输入装置、和至少一个输出装置接收数据和指令，并且将数据和指令传输至该存储系统、该至少一个输入装置、和该至少一个输出装置。
用于实施本公开的方法的程序代码可以采用一个或多个编程语言的任何组合来编写。这些程序代码可以提供给通用计算机、专用计算机或其他可编程数据处理装置的处理器或控制器，使得程序代码当由处理器或控制器执行时使流程图和/或框图中所规定的功能/操作被实施。程序代码可以完全在机器上执行、部分地在机器上执行，作为独立软件包部分地在机器上执行且部分地在远程机器上执行或完全在远程机器或服务器上执行。
在本公开的上下文中，机器可读介质可以是有形的介质，其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的程序。机器可读介质可以是机器可读信号介质或机器可读储存介质。机器可读介质可以包括但不限于电子的、磁性的、光学的、电磁的、红外的、或半导体系统、装置或设备，或者上述内容的任何合适组合。机器可读存储介质的更具体示例会包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦除可编程只读存储器(EPROM或快闪存储器)、光纤、便捷式紧凑盘只读存储器(CD-ROM)、光学储存设备、磁储存设备、或上述内容的任何合适组合。
为了提供与用户的交互，可以在计算机上实施此处描述的系统和技术，该计算机具有：用于向用户显示信息的显示装置(例如，CRT(阴极射线管)或者LCD(液晶显示器)监视器)；以及键盘和指向装置(例如，鼠标或者轨迹球)，用户可以通过该键盘和该指向装置来将输入提供给计算机。其它种类的装置还可以用于提供与用户的交互；例如，提供给用户的反馈可以是任何形式的传感反馈(例如，视觉反馈、听觉反馈、或者触觉反馈)；并 且可以用任何形式(包括声输入、语音输入或者、触觉输入)来接收来自用户的输入。
可以将此处描述的系统和技术实施在包括后台部件的计算系统(例如，作为数据服务器)、或者包括中间件部件的计算系统(例如，应用服务器)、或者包括前端部件的计算系统(例如，具有图形用户界面或者网络浏览器的用户计算机，用户可以通过该图形用户界面或者该网络浏览器来与此处描述的系统和技术的实施方式交互)、或者包括这种后台部件、中间件部件、或者前端部件的任何组合的计算系统中。可以通过任何形式或者介质的数字数据通信(例如，通信网络)来将系统的部件相互连接。通信网络的示例包括：局域网(LAN)、广域网(WAN)和互联网。
计算机系统可以包括客户端和服务器。客户端和服务器一般远离彼此并且通常通过通信网络进行交互。通过在相应的计算机上运行并且彼此具有客户端-服务器关系的计算机程序来产生客户端和服务器的关系。
应该理解，可以使用上面所示的各种形式的流程，重新排序、增加或删除步骤。例如，本发公开中记载的各步骤可以并行地执行也可以顺序地执行也可以不同的次序执行，只要能够实现本公开公开的技术方案所期望的结果，本文在此不进行限制。
上述具体实施方式，并不构成对本公开保护范围的限制。本领域技术人员应该明白的是，根据设计要求和其他因素，可以进行各种修改、组合、子组合和替代。任何在本公开的精神和原则之内所作的修改、等同替换和改进等，均应包含在本公开保护范围之内。

Claims (15)

  1. 一种路线推荐方法，包括：
    接收路线推荐请求，其中，所述路线推荐请求包括N个维度的行程标签信息；N为正整数；
    根据所述N个维度的行程标签信息，从主题路线库中选取M个主题路线；其中，M为正整数；
    从所述M个主题路线中确定出推荐路线；
    其中，所述根据所述N个维度的行程标签信息，从主题路线库中选取M个主题路线，包括：
    根据所述N个维度中第i个维度的行程标签信息与所述主题路线库中各主题路线的主题信息，从所述主题路线库中选取至少一个主题路线；其中，i为小于等于N的正整数。
  2. 根据权利要求1所述的方法，其中，所述根据所述N个维度中第i个维度的行程标签信息与所述主题路线库中各主题路线的主题信息，从所述主题路线库中选取至少一个主题路线，包括：
    确定所述第i个维度的行程标签信息与所述主题路线库中各主题路线的主题信息之间的相似度；
    根据所述相似度，从所述主题路线库中选取至少一个主题路线。
  3. 根据权利要求1所述的方法，其中，所述从所述M个主题路线中确定出推荐路线，包括：
    基于所述M个主题路线和所述路线推荐请求所对应的用户信息，利用预设模型得到所述M个主题路线中每个主题路线的分数；
    根据所述分数，从所述M个主题路线中确定出推荐路线。
  4. 根据权利要求1-3中任一项所述的方法，还包括：
    根据至少一个兴趣点POI在目标维度的标签信息，对所述至少一个POI进行聚类，得到至少一个POI集合；
    基于所述至少一个POI集合，得到与所述目标维度对应的至少一个主题路线，并基于所述至少一个POI集合中每个POI集合中的各POI的所述标签信息，得到所述至少一个主题路线中每个主题路线的主题信息；
    将所述至少一个主题路线添加到所述主题路线库中。
  5. 根据权利要求1-3中任一项所述的方法，还包括：
    根据所述路线推荐请求所对应的用户偏好信息和所述推荐路线中的各POI信息，确定所述各POI的游览顺序、游览时间及出行方式中至少之一。
  6. 根据权利要求1-3中任一项所述的方法，还包括：
    在电子地图中显示所述推荐路线以及所述推荐路线中各POI的预设范围内的食宿建议信息。
  7. 一种路线推荐装置，包括：
    接收模块，用于接收路线推荐请求，其中，所述路线推荐请求包括N个维度的行程标签信息；N为正整数；
    路线选取模块，用于根据所述N个维度的行程标签信息，从主题路线库中选取M个主题路线；其中，M为正整数；
    路线确定模块，用于从所述M个主题路线中确定出推荐路线；
    其中，所述路线选取模块根据所述N个维度中第i个维度的行程标签信息与所述主题路线库中各主题路线的主题信息，从所述主题路线库中选取至少一个主题路线；其中，i为小于等于N的正整数。
  8. 根据权利要求7所述的装置，其中，所述路线选取模块包括：
    相似度确定单元，用于确定所述第i个维度的行程标签信息与所述主题路线库中各主题路线的主题信息之间的相似度；
    选取单元，同于根据所述相似度，从所述主题路线库中选取至少一个主题路线。
  9. 根据权利要求7所述的装置，其中，所述路线确定模块包括：
    评分单元，用于基于所述M个主题路线和所述路线推荐请求所对应的用户信息，利用预设模型得到所述M个主题路线中每个主题路线的分数；
    确定单元，用于根据所述分数，从所述M个主题路线中确定出推荐路线。
  10. 根据权利要求7-9中任一项所述的装置，还包括：
    聚类模块，用于根据至少一个POI在目标维度的标签信息，对所述至少一个POI进行聚类，得到至少一个POI集合；
    路线生成模块，用于基于所述至少一个POI集合，得到与所述目标维度对应的至少一个主题路线，并基于所述至少一个POI集合中每个POI集合中的各POI的所述标签信息，得到所述至少一个主题路线中每个主题路线的主题信息；
    路线添加模块，用于将所述至少一个主题路线添加到所述主题路线库中。
  11. 根据权利要求7-9中任一项所述的装置，还包括：
    路线规划模块，用于根据所述路线推荐请求所对应的用户偏好信息和所述推荐路线中的各POI信息，确定所述各POI的游览顺序、游览时间及出行方式中至少之一。
  12. 根据权利要求7-9中任一项所述的装置，还包括：
    信息显示模块，用于在电子地图中显示所述推荐路线以及所述推荐路线中各POI的预设范围内的食宿建议信息。
  13. 一种电子设备，包括：
    至少一个处理器；以及
    与所述至少一个处理器通信连接的存储器；其中，
    所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被 所述至少一个处理器执行，以使所述至少一个处理器能够执行权利要求1-6中任一项所述的方法。
  14. 一种存储有计算机指令的非瞬时计算机可读存储介质，其中，所述计算机指令用于使计算机执行根据权利要求1-6中任一项所述的方法。
  15. 一种计算机程序产品，包括计算机程序，所述计算机程序在被处理器执行时实现根据权利要求1-6中任一项所述的方法。
PCT/CN2021/097901 2020-12-24 2021-06-02 路线推荐方法、装置、电子设备和存储介质 WO2022134478A1 (zh)

Priority Applications (4)

Application Number Priority Date Filing Date Title
US17/640,816 US11976935B2 (en) 2020-12-24 2021-06-02 Route recommendation method, electronic device, and storage medium
KR1020227004987A KR20220026602A (ko) 2020-12-24 2021-06-02 노선 추천방법, 장치, 전자기기, 저장매체 및 컴퓨터 프로그램
EP21814666.0A EP4047447A4 (en) 2020-12-24 2021-06-02 ROUTE RECOMMENDATION METHOD AND DEVICE, ELECTRONIC DEVICE AND STORAGE MEDIA
JP2022505517A JP2023511799A (ja) 2020-12-24 2021-06-02 経路推奨方法、装置、電子デバイス、記憶媒体、及びプログラム

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011546162.7 2020-12-24
CN202011546162.7A CN112632379A (zh) 2020-12-24 2020-12-24 路线推荐方法、装置、电子设备和存储介质

Publications (1)

Publication Number Publication Date
WO2022134478A1 true WO2022134478A1 (zh) 2022-06-30

Family

ID=75324166

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/097901 WO2022134478A1 (zh) 2020-12-24 2021-06-02 路线推荐方法、装置、电子设备和存储介质

Country Status (2)

Country Link
CN (1) CN112632379A (zh)
WO (1) WO2022134478A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117648497A (zh) * 2024-01-29 2024-03-05 贵州大学 一种基于大数据实现用户信息智能采集方法及系统

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112632379A (zh) * 2020-12-24 2021-04-09 北京百度网讯科技有限公司 路线推荐方法、装置、电子设备和存储介质
JP2023511799A (ja) 2020-12-24 2023-03-23 ベイジン バイドゥ ネットコム サイエンス テクノロジー カンパニー リミテッド 経路推奨方法、装置、電子デバイス、記憶媒体、及びプログラム
CN113239269A (zh) * 2021-04-30 2021-08-10 河海大学 一种基于改进推荐算法的旅游路线定制方法
CN113704625A (zh) * 2021-09-03 2021-11-26 北狐数字科技(上海)有限公司 一种基于时间和地理位置的兴趣点推荐方法

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180188053A1 (en) * 2017-01-04 2018-07-05 International Business Machines Corporation Route generation based on aggregated path data
CN110096645A (zh) * 2019-05-07 2019-08-06 北京百度网讯科技有限公司 信息推荐方法、装置、设备和介质
CN110765361A (zh) * 2019-12-30 2020-02-07 恒大智慧科技有限公司 一种基于用户信息的景点推荐方法、装置及存储介质
CN111143680A (zh) * 2019-12-27 2020-05-12 上海携程商务有限公司 路线的推荐方法、系统、电子设备及计算机存储介质
CN111966929A (zh) * 2020-08-17 2020-11-20 携程旅游信息技术（上海）有限公司 基于标签的旅游路线推送方法、系统、设备及存储介质
CN112632379A (zh) * 2020-12-24 2021-04-09 北京百度网讯科技有限公司 路线推荐方法、装置、电子设备和存储介质

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105468679B (zh) * 2015-11-13 2019-04-12 中国人民解放军国防科学技术大学 一种旅游信息处理与方案提供方法
CN109918573A (zh) * 2019-03-28 2019-06-21 黑龙江大学 一种基于位置社交网络的个性化线路推荐系统和方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180188053A1 (en) * 2017-01-04 2018-07-05 International Business Machines Corporation Route generation based on aggregated path data
CN110096645A (zh) * 2019-05-07 2019-08-06 北京百度网讯科技有限公司 信息推荐方法、装置、设备和介质
CN111143680A (zh) * 2019-12-27 2020-05-12 上海携程商务有限公司 路线的推荐方法、系统、电子设备及计算机存储介质
CN110765361A (zh) * 2019-12-30 2020-02-07 恒大智慧科技有限公司 一种基于用户信息的景点推荐方法、装置及存储介质
CN111966929A (zh) * 2020-08-17 2020-11-20 携程旅游信息技术（上海）有限公司 基于标签的旅游路线推送方法、系统、设备及存储介质
CN112632379A (zh) * 2020-12-24 2021-04-09 北京百度网讯科技有限公司 路线推荐方法、装置、电子设备和存储介质

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117648497A (zh) * 2024-01-29 2024-03-05 贵州大学 一种基于大数据实现用户信息智能采集方法及系统
CN117648497B (zh) * 2024-01-29 2024-04-30 贵州大学 一种基于大数据实现用户信息智能采集方法及系统

Also Published As

Publication number Publication date
CN112632379A (zh) 2021-04-09

Similar Documents

Publication Publication Date Title
WO2022134478A1 (zh) 路线推荐方法、装置、电子设备和存储介质
Jin et al. Using user-generated content to explore the temporal heterogeneity in tourist mobility
Cui et al. Personalized travel route recommendation using collaborative filtering based on GPS trajectories
US9767800B2 (en) Communication system
Padhi et al. Quantifying potential tourist behavior in choice of destination using Google Trends
CN107679661B (zh) 一种基于知识图谱的个性化旅游路线规划方法
US10281289B2 (en) Search along the route
JP7159405B2 (ja) 地図情報表示方法、装置、電子デバイス及び記憶媒体
CN111143680A (zh) 路线的推荐方法、系统、电子设备及计算机存储介质
CN112612957A (zh) 兴趣点的推荐方法、兴趣点推荐模型的训练方法、装置
TWI525460B (zh) 電子計算裝置、其個人化資訊推薦方法及其電腦程式產品
Bi et al. How built environment impacts online car-hailing ridership
Zhou et al. Familiarity-dependent computational modelling of indoor landmark selection for route communication: a ranking approach
KR20210065773A (ko) 빅데이터 기반의 감성정보 분석평가 시스템 및 그 구동방법
Huang et al. Quantifying the environmental characteristics influencing the attractiveness of commercial agglomerations with big geo-data
Luo et al. Exploring destination image through online reviews: an augmented mining model using latent Dirichlet allocation combined with probabilistic hesitant fuzzy algorithm
Ding et al. Route planning in a new tourist recommender system: A fireworks algorithm based approach
Zhang et al. Automatic latent street type discovery from web open data
US11976935B2 (en) Route recommendation method, electronic device, and storage medium
Gao et al. Mining tourist preferences and decision support via tourism-oriented knowledge graph
Guo et al. Fine-grained dynamic price prediction in ride-on-demand services: Models and evaluations
Zhou et al. Evaluating the nonlinear impacts of built environment on online car-hailing: Focus on the whole day
Xiang et al. Camer: a context-aware mobile service recommendation system
Ruan et al. Exploring emotion differences in tourist attractions based on online travel notes: a case study in Nanjing, China
CN115017200B (zh) 搜索结果的排序方法、装置、电子设备和存储介质

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 2021814666

Country of ref document: EP

Effective date: 20211206

ENP Entry into the national phase

Ref document number: 2022505517

Country of ref document: JP

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 20227004987

Country of ref document: KR

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE