Tourist route recommendation method and system, electronic equipment and storage medium

Abstract

The invention discloses a tourist route recommendation method and system, electronic equipment and a storage medium, and the method comprises the steps: constructing a tourist route structural body according to preset configuration; collecting scenic spot strategy data; associating the scenic spot strategy data with scenic spots in a preset scenic spot library to obtain a travel strategy library; obtaining a user demand; and according to the user demand, the travel strategy library and the travel route structural body, utilizing a pre-training recommendation model to generate a plurality of recommended routes. According to the invention, the technical problems of high cost, low efficiency and uneven quality of a tourist route recommendation method in the prior art are solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of data recommendation, and in particular, relates to a method, system, electronic device and storage medium for recommending a travel route. Background Art

[0002] As the global tourism market continues to expand, the demand for travel planning services is growing, especially the desire for personalized, high-quality travel routes. Currently, the generation of travel routes mainly relies on manual editing or a single automated model. Although manual editing can provide customized services, its inherent problems of high cost, low efficiency, and high quality fluctuations are becoming increasingly prominent, becoming a major bottleneck in the tourism industry. Specifically:

[0003] High cost: Manual editing requires a lot of time and human resources, which is a considerable cost for travel platforms that seek to respond quickly to market changes and provide large-scale services.

[0004] Inefficiency: The manual editing process is cumbersome and difficult to achieve rapid iteration and adapt to dynamic changes in user needs.

[0005] Uneven quality: Individually edited lines may have unstable line quality due to differences in the editor’s experience and knowledge, affecting the user experience.

[0006] On the other hand, although existing automated models, such as generative models, have shown some potential in improving efficiency, they have obvious limitations in terms of the rationality of generated routes, information accuracy, and personalized services. The algorithmic characteristics of generative models may make them lack consideration of actual conditions when generating text, resulting in logical errors or "hallucinations" and generating some routes that are actually not feasible. In addition, due to the limitations of the data foundation, these models often find it difficult to ensure the integrity and timeliness of route information, especially when generating comprehensive routes involving multiple tourist attractions.

[0007] In view of the above background, the present invention aims to develop a new travel route generation method by integrating multi-model technology, combining structured data and natural language processing capabilities, so as to overcome the limitations of the existing technology, provide more efficient, more accurate and more personalized travel route services, and meet the growing needs of the tourism market and users. Summary of the invention

[0008] The embodiments of the present invention provide a travel route recommendation method, system, electronic device and storage medium to at least solve the technical problems of high cost, low efficiency and uneven quality of travel route recommendation methods in related technologies.

[0009] According to a first aspect of an embodiment of the present invention, a method for recommending a tourist route is provided, comprising: constructing a tourist route structure according to a preset configuration; collecting scenic spot strategy data; associating the scenic spot strategy data with scenic spots in a preset scenic spot library to obtain a tourist strategy library; obtaining user needs; and using a pre-trained recommendation model to generate a recommended route according to user needs, the tourist strategy library and the tourist route structure, wherein the recommended route includes multiple scenic spots.

[0010] In one implementation of the present application, the tourist route structure includes at least: scenic spot data, play method data, price, transportation method, and play time.

[0011] In one implementation of the present application, the preset scenic spot library includes: scenic spot name, scenic spot address, scenic spot price, scenic spot characteristics, and scenic spot business hours.

[0012] In one implementation of the present application, scenic spot strategy data is associated with scenic spots in a preset scenic spot library to obtain a travel strategy library, including: formatting the scenic spot strategy data to obtain a gameplay library; using a preset entity model to perform entity extraction on the scenic spot strategy data to obtain an entity extraction result; based on the entity extraction result, using a preset association model to associate the entity extraction result with the scenic spots in the preset scenic spot library to obtain an association result; and determining the travel strategy library based on the association result and the gameplay library.

[0013] In one embodiment of the present application, the pre-trained recommendation model includes a quality inspection model and a recommendation optimization model. The quality inspection model is used to perform quality inspection on the output initial recommended route to obtain a quality inspection result, and the recommendation optimization model is used to optimize the quality inspection result to obtain a recommended route.

[0014] In one implementation of the present application, it also includes: collecting user feedback by obtaining online surveys, user reviews or social media analysis; identifying changes in user demand and market trends using preset strategies based on user feedback; optimizing the travel route structure and pre-trained recommendation model according to preset optimization strategies based on changes in user demand and market trends.

[0015] One aspect of the present application provides a travel route recommendation system, including: a construction module, used to construct a travel route structure according to a preset configuration; a collection module, used to collect scenic spot guide data; an association module, used to associate the scenic spot guide data with scenic spots in a preset scenic spot library to obtain a travel guide library; an acquisition module, used to obtain user needs; a recommendation module, used to generate a recommended route based on user needs, the travel guide library and the travel route structure, using a pre-trained recommendation model, wherein the recommended route includes multiple scenic spots.

[0016] In one implementation of the present application, the tourist route structure constructed by the construction module includes at least: scenic spot data, play method data, price, transportation method, and play time.

[0017] In one implementation of the present application, the preset scenic spot library in the association module includes: scenic spot name, scenic spot address, scenic spot price, scenic spot characteristics, and scenic spot business hours.

[0018] In one embodiment of the present application, the association module is also used to: format the scenic spot strategy data to obtain a gameplay library; use a preset entity model to perform entity extraction on the scenic spot strategy data to obtain an entity extraction result; based on the entity extraction result, use a preset association model to associate the entity extraction result with the scenic spot in the preset scenic spot library to obtain an association result; and determine the travel strategy library based on the association result and the gameplay library.

[0019] In one embodiment of the present application, the pre-trained recommendation model in the recommendation module includes a quality inspection model and a recommendation optimization model. The quality inspection model is used to perform quality inspection on the output initial recommended route to obtain a quality inspection result, and the recommendation optimization model is used to optimize the quality inspection result to obtain a recommended route.

[0020] In one embodiment of the present application, the travel route recommendation system also includes an optimization module, which is connected to the recommendation module and is used to: collect user feedback by obtaining online surveys, user reviews or social media analysis; identify changes in user demand and market trends using preset strategies based on user feedback; and optimize the travel route structure and pre-trained recommendation model according to preset optimization strategies based on changes in user demand and market trends.

[0021] In one embodiment of the present application, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor is configured to run the computer program to execute the above-mentioned travel route recommendation method.

[0022] In one implementation of the present application, a computer program is stored in a non-volatile storage medium, and the computer program is configured to execute the above-mentioned travel route recommendation method when running on a computer or a processor.

[0023] In one embodiment of the present application, the computer program product includes a computer program, and the computer program implements the above-mentioned travel route recommendation method when executed by a processor.

[0024] The embodiment of the present invention discloses that a tourist route structure is constructed according to a preset configuration; scenic spot strategy data is collected; the scenic spot strategy data is associated with the scenic spots in the preset scenic spot library to obtain a tourist strategy library; user needs are obtained; a pre-trained recommendation model is used to generate a recommended route according to user needs, a tourist strategy library and a tourist route structure, wherein the recommended route includes multiple scenic spots. Through the tourist route recommendation method of the present application, it is possible to intelligently generate tourist routes that meet user interests and budgets according to the personalized needs of users, combined with rich scenic spot strategy data and pre-trained recommendation models. This method not only improves the accuracy and diversity of tourist route recommendations, but also can adjust and optimize recommendation strategies in real time to adapt to changes in user needs and market trends. In practical applications, this method significantly improves user satisfaction, increases user stickiness and market competitiveness of tourism platforms, and provides strong support for the digital transformation of the tourism industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0026] Figure 1 is a flow chart of a method for recommending a travel route according to one embodiment of the present invention;

[0027] Figure 2 is a flow chart of a method for recommending a travel route according to one embodiment of the present invention;

[0028] Figure 3 4 is a structural block diagram of a travel route recommendation system according to one embodiment of the present invention. DETAILED DESCRIPTION

[0029] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0030] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0031] According to an embodiment of the present invention, an embodiment of a method for recommending a travel route is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system comprising at least one set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0032] The method embodiment can also be executed in an electronic device including a memory and a processor, a similar control device or a cloud. Taking an electronic device as an example, the electronic device may include one or more processors and a memory for storing data. Optionally, the electronic device may also include a communication device and a display device for communication functions. It can be understood by those of ordinary skill in the art that the above structural description is only illustrative and does not limit the structure of the above electronic device. For example, the electronic device may also include more or fewer components than the above structural description, or have a configuration different from the above structural description.

[0033] The processor may include one or more processing units. For example, the processor may include a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processing (DSP) chip, a microcontroller unit (MCU), a field-programmable gate array (FPGA), a neural network processor (NPU), a tensor processing unit (TPU), an artificial intelligence (AI) type processor, and the like. Among them, different processing units may be independent components or integrated into one or more processors. In some instances, the electronic device may also include one or more processors.

[0034] The memory can be used to store computer programs, such as storing the computer program corresponding to the tourist route recommendation method in the embodiment of the present invention, and the processor implements the above-mentioned tourist route recommendation method by running the computer program stored in the memory. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory may further include a memory remotely arranged relative to the processor, and these remote memories can be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0035] The communication device is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the communication device includes a network adapter (network interface controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the communication device can be a radio frequency (radio frequency, RF) module, which is used to communicate with the Internet wirelessly. In some embodiments of the present solution, the communication device is used to connect to mobile devices such as mobile phones and tablets, and instructions can be sent to electronic devices through the mobile device.

[0036] The display device may be a touch screen type liquid crystal display (LCD) and a touch display (also referred to as a "touch screen" or "touch display screen"). The liquid crystal display may enable a user to interact with a user interface of the electronic device. In some embodiments, the electronic device has a graphical user interface (GUI), and a user may interact with the GUI by touching a finger release and / or gestures on a touch-sensitive surface, and executable instructions for executing the above-mentioned human-computer interaction functions are configured / stored in a computer program product or a readable storage medium executable by one or more processors.

[0037] Figure 1 is a flow chart of a method for recommending a travel route according to one embodiment of the present invention, taking the method executed in an electronic device with a display module as an example. Figure 1 As shown, the method comprises the following steps:

[0038] Step S101, constructing a travel route structure according to a preset configuration.

[0039] Specifically, according to the components of the structure configured according to the preset configuration, the tourist route structure includes various types of information that a tourist route must include.

[0040] Illustratively, in one embodiment of the present application, the tourist route structure includes at least: scenic spot data, gameplay data, price, transportation method, and tour time.

[0041] Step S102, collecting scenic spot guide data.

[0042] Specifically, scenic spot guide data can be collected and extracted from travel guides posted by users on different platforms.

[0043] Step S103, associating the scenic spot guide data with the scenic spots in the preset scenic spot library to obtain a travel guide library.

[0044] Specifically, the scenic spot guide data collected in step S102 is associated with the pre-built scenic spot library to supplement the scenic spot information in the scenic spot library.

[0045] Optionally, in one implementation of the present application, the preset scenic spot library includes: scenic spot name, scenic spot address, scenic spot price, scenic spot characteristics, and scenic spot business hours.

[0046] Exemplarily, the pre-built scenic spot library includes information such as the scenic spot name, location, and business hours of scenic spot A. When making an association, the guide to scenic spot A is found from the collected scenic spot guide data, and the information of scenic spot A in the preset scenic spot library is supplemented, such as the recommended visit time, recommended visit route, etc.

[0047] Step S104, obtaining user needs.

[0048] Specifically, in the recommendation process, user needs need to be obtained first. For example, the obtained user needs are a three-day tour in Chengdu.

[0049] Step S105, using the pre-trained recommendation model, generating a recommended route according to user needs, the travel guide library and the travel route structure, wherein the recommended route includes multiple scenic spots.

[0050] Specifically, after obtaining user needs, the user needs are input into a pre-trained recommendation model. The pre-trained model can generate a recommended route for the user based on the user needs, the travel guide library, and the travel route structure.

[0051] Exemplarily, the recommended route includes multiple scenic spots, and for each scenic spot, it also includes a specific travel guide for the scenic spot in the travel guide library.

[0052] The embodiment of the present invention discloses that a tourist route structure is constructed according to a preset configuration; scenic spot strategy data is collected; the scenic spot strategy data is associated with the scenic spots in the preset scenic spot library to obtain a tourist strategy library; user needs are obtained; a pre-trained recommendation model is used to generate a recommended route according to user needs, a tourist strategy library and a tourist route structure, wherein the recommended route includes multiple scenic spots. Through the tourist route recommendation method of the present application, it is possible to intelligently generate tourist routes that meet user interests and budgets according to the personalized needs of users, combined with rich scenic spot strategy data and pre-trained recommendation models. This method not only improves the accuracy and diversity of tourist route recommendations, but also can adjust and optimize recommendation strategies in real time to adapt to changes in user needs and market trends. In practical applications, this method significantly improves user satisfaction, increases user stickiness and market competitiveness of tourism platforms, and provides strong support for the digital transformation of the tourism industry.

[0053] Optionally, in one implementation of the present application, in step S103, the scenic spot guide data is associated with the scenic spots in the preset scenic spot library to obtain a travel guide library, including the following steps:

[0054] Step S1031, formatting the scenic spot guide data to obtain a gameplay library.

[0055] Specifically, the scenic spot strategy data is formatted to obtain a gameplay library covering the scenic spot's popular gameplay, visiting time, precautions, characteristics of different time periods, and themes.

[0056] Step S1032, using a preset entity model to perform entity extraction on the scenic spot guide data to obtain an entity extraction result;

[0057] Step S1033: According to the entity extraction result, the entity extraction result is associated with the scenic spots in the preset scenic spot library using a preset association model to obtain an association result.

[0058] Specifically, the TENER (preset entity model) model is used to extract entities from the posts, and the extracted entities are associated with the scenic spots in the scenic spot library through the preset association model.

[0059] Step S1034, determining a travel strategy library based on the association result and the gameplay library.

[0060] Specifically, after obtaining the association result and the gameplay library, the scenic spot information in the preset scenic spot library can be associated and supplemented through the gameplay library to improve the basic information of the scenic spot.

[0061] Optionally, in one embodiment of the present application, the pre-trained recommendation model includes a quality inspection model and a recommendation optimization model, the quality inspection model is used to perform quality inspection on the output initial recommended route to obtain a quality inspection result, and the recommendation optimization model is used to optimize the quality inspection result to obtain a recommended route.

[0062] Specifically, the quality inspection model included in the preset recommendation model performs a quality inspection on the playability and playable form of the initial recommended route initially generated by the model, and the quality inspection result is input into the recommendation optimization model to adjust and optimize the sequence of route attractions, and the recommended route is output after optimization.

[0063] Optionally, in one implementation of the present application, the following further includes:

[0064] Step S106, collecting user feedback by obtaining online surveys, user reviews, or social media analysis;

[0065] Step S107, identifying changes in user demand and market trends using preset strategies based on user feedback;

[0066] Step S108, optimizing the travel route structure and the pre-trained recommendation model according to the preset optimization strategy based on the changes in user demand and market trends.

[0067] Specifically, user feedback is collected through online surveys, user reviews or analysis of social media arguments. After user feedback is collected, changes in user demand and market trends are identified based on user feedback according to preset strategies. Furthermore, according to changes in user demand and market trends, the distance and travel time of scenic spot itineraries are optimized according to preset optimization strategies. The travel time of each scenic spot is saved in the scenic spot database. If the journey time + travel time exceeds J hours, a certain scenic spot will be automatically eliminated through the large model comprehensive popularity and scenic spot. If a certain scenic spot is more than K kilometers away from other scenic spots. It is considered that there may be recognition errors or other problems with the scenic spot and it is eliminated. K and J are thresholds set based on different cities according to changes in user demand and duration trends.

[0068] Specifically, refer to Figure 2 This embodiment describes a travel route generation method based on multi-model fusion, which aims to automatically generate high-quality structured travel routes in batches. The specific steps are as follows:

[0069] Structured route structure design: First, a travel route structure is defined, including but not limited to fields such as scenic spot information, transportation methods, food recommendations, price, and travel time. Each field is designed to store structured data. For example, the scenic spot information field may contain subfields such as scenic spot name, address, business hours, and ticket price.

[0070] Data infrastructure construction: Using existing data resources, including information on domestic and foreign scenic spots, a popular scenic spot database was built. Each scenic spot has a detailed description, such as address, business hours, ticket price, rating, etc. These data will serve as the basis for model training and route generation.

[0071] Construction of a gameplay library: We collected a large amount of user-generated content, including travel posts, guides, user reviews, etc. By analyzing these contents, we built a gameplay library that contains information such as popular gameplay, visit time, precautions, features and themes of each scenic spot.

[0072] It should be noted that the above steps are a pre-construction process for recommending travel routes, which is not shown in the figure.

[0073] Post preprocessing: The collected travel posts are preprocessed using the TENER named entity recognition model to identify key entities, such as scenic spot names, transportation methods, and food recommendations. Subsequently, these entities are attached to the corresponding scenic spots in the popular scenic spot database through an entity attachment model (such as all-distilroberta-v1) to improve the scenic spot information.

[0074] Information supplement and improvement: For the missing travel information in the pre-processed posts, use the gameplay library to supplement it to ensure that the relevant information of each attraction is complete.

[0075] Structured route mining: The processed information is input into a system that integrates the generative model and the rule model. The system can perform in-depth mining and generate preliminary structured travel routes based on the content of travel posts and the information of the scenic spot library and the gameplay library.

[0076] Quality inspection: The generated travel routes are evaluated for logic and feasibility through quality inspection models to ensure the rationality of the routes and avoid logical errors or information omissions.

[0077] Intelligent generation: For problematic routes discovered by the quality inspection model, the GPT model is used to adjust and optimize them, including but not limited to the sequence of attractions, transportation suggestions, food recommendations, etc., to generate the final structured travel route.

[0078] User feedback loop: After the system goes online, user feedback will be collected, including satisfaction with travel routes, improvement suggestions, etc. These feedbacks will be used to further optimize the model and update the gameplay library to adapt to market changes and user needs.

[0079] In this embodiment, the application process of the entity affiliation model is described in detail. The specific steps are as follows:

[0080] Entity Recognition: Use the TENER model to perform entity recognition on the original travel posts and extract all the mentioned scenic spot names.

[0081] Candidate entity generation: For each identified scenic spot name, a candidate entity list is generated from the popular scenic spot library and preliminary screening is performed based on the similarity of the names.

[0082] Context analysis: Analyze the contextual information around the scenic spot name, including descriptions, travel suggestions, etc., to further narrow the scope of candidate entities.

[0083] Similarity calculation: The all-distilroberta-v1 model is used to calculate the similarity between each candidate entity and the actual scenic spot name, including semantic similarity, entity attribute matching, etc.

[0084] Ambiguity resolution: Based on the similarity calculation results, the most matching candidate entity is selected as the actual scenic spot affiliation result. If the similarity is low, manual intervention may be required for confirmation.

[0085] Result confirmation: For the final registration result, the system provides a confirmation process, allowing manual review of the accuracy of the registration. Once confirmed, the registration result will be used to improve the generation of structured travel routes.

[0086] It can be understood that, based on the description of the above embodiments, the present invention has the following beneficial effects:

[0087] The need for manual editing is greatly reduced through automated processes, which significantly improves the efficiency of travel route generation. Automated processing reduces the interference of human factors and makes route generation faster and more scalable.

[0088] By reducing the reliance on manual editing, the method can significantly reduce labor costs when generating travel routes, while reducing additional costs caused by manual errors.

[0089] The design of structured route structure ensures the completeness and accuracy of travel route information. Through entity extraction and scenic spot affiliation model, the method can accurately identify and supplement key information, avoiding information omission or error.

[0090] The application of the quality inspection model ensures that the generated travel routes are logically coherent and meet actual travel needs, which improves user satisfaction with the travel routes.

[0091] This method can adjust and optimize routes according to users' personalized needs and feedback, provide customized travel experiences, and meet the specific preferences of different users.

[0092] The method is designed with good flexibility and scalability, can adapt to changing market demands and user behaviors, and facilitate the addition and upgrading of future functions.

[0093] Using big data analysis and machine learning techniques, the method is able to learn from user feedback and behavior patterns to provide data-driven decision support for route generation.

[0094] Through intelligent generation and user feedback loops, the method encourages users to participate in the generation of travel routes, while providing a variety of convenient interactive forms when using routes, thereby improving user participation and satisfaction.

[0095] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), including a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0096] In this embodiment, a travel route recommendation system is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" is a combination of software and / or hardware that can implement a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0097] Figure 3 is a structural block diagram of a travel route recommendation system 200 according to one embodiment of the present invention. Figure 3 As shown, a travel route recommendation system 200 is used as an example, including: a construction module 201, which is used to construct a travel route structure according to a preset configuration; a collection module 202, which is used to collect scenic spot guide data; an association module 203, which is used to associate the scenic spot guide data with the scenic spots in a preset scenic spot library to obtain a travel guide library; an acquisition module 204, which is used to obtain user needs; a recommendation module 205, which is used to generate a recommended route based on user needs, the travel guide library and the travel route structure using a pre-trained recommendation model, wherein the recommended route includes multiple scenic spots.

[0098] In one implementation of the present application, the tourist route structure constructed by the construction module 201 includes at least: scenic spot data, play method data, price, transportation method, and play time.

[0099] In one implementation of the present application, the preset scenic spot library in the association module 203 includes: scenic spot name, scenic spot address, scenic spot price, scenic spot characteristics, and scenic spot business hours.

[0100] In one embodiment of the present application, the association module 203 is also used to: format the scenic spot guide data to obtain a gameplay library; use a preset entity model to perform entity extraction on the scenic spot guide data to obtain an entity extraction result; based on the entity extraction result, use a preset association model to associate the entity extraction result with the scenic spot in the preset scenic spot library to obtain an association result; and determine the travel guide library based on the association result and the gameplay library.

[0101] In one embodiment of the present application, the pre-trained recommendation model in the recommendation module 205 includes a quality inspection model and a recommendation optimization model. The quality inspection model is used to perform quality inspection on the output initial recommended route to obtain a quality inspection result, and the recommendation optimization model is used to optimize the quality inspection result to obtain a recommended route.

[0102] In one embodiment of the present application, the travel route recommendation system also includes an optimization module, which is connected to the recommendation module 205 and is used to: collect user feedback by obtaining online surveys, user reviews or social media analysis; identify changes in user demand and market trends using preset strategies based on user feedback; and optimize the travel route structure and pre-trained recommendation model according to preset optimization strategies based on changes in user demand and market trends.

[0103] An embodiment of the present invention further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the travel route recommendation method described in any of the above embodiments.

[0104] Optionally, in this embodiment, the processor in the above electronic device may be configured to run a computer program to perform the following steps:

[0105] Step S101, constructing a travel route structure according to a preset configuration.

[0106] Step S102, collecting scenic spot guide data.

[0107] Step S103, associating the scenic spot guide data with the scenic spots in the preset scenic spot library to obtain a travel guide library.

[0108] Step S104, obtaining user needs.

[0109] Step S105, using the pre-trained recommendation model, generating a recommended route according to user needs, the travel guide library and the travel route structure, wherein the recommended route includes multiple scenic spots.

[0110] Optionally, in one embodiment of the present application, the tourist route structure includes at least: scenic spot data, gameplay data, price, transportation method, and travel time.

[0111] Optionally, in one implementation of the present application, the preset scenic spot library includes: scenic spot name, scenic spot address, scenic spot price, scenic spot characteristics, and scenic spot business hours.

[0112] Optionally, in one embodiment of the present application, scenic spot strategy data is associated with scenic spots in a preset scenic spot library to obtain a travel strategy library, including: formatting the scenic spot strategy data to obtain a gameplay library; using a preset entity model to perform entity extraction on the scenic spot strategy data to obtain an entity extraction result; based on the entity extraction result, using a preset association model to associate the entity extraction result with the scenic spots in the preset scenic spot library to obtain an association result; and determining the travel strategy library based on the association result and the gameplay library.

[0113] Optionally, in one embodiment of the present application, the pre-trained recommendation model includes a quality inspection model and a recommendation optimization model, the quality inspection model is used to perform quality inspection on the output initial recommended route to obtain a quality inspection result, and the recommendation optimization model is used to optimize the quality inspection result to obtain a recommended route.

[0114] Optionally, in one implementation of the present application, it also includes: collecting user feedback by obtaining online surveys, user reviews or social media analysis; identifying changes in user demand and market trends using preset strategies based on user feedback; optimizing the travel route structure and pre-trained recommendation model according to preset optimization strategies based on changes in user demand and market trends.

[0115] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.

[0116] An embodiment of the present invention further provides a non-volatile storage medium, in which a computer program is stored, wherein the computer program is configured to execute the travel route recommendation method described in any of the above embodiments when running on a computer or a processor.

[0117] Optionally, in this embodiment, the above-mentioned computer program may be configured to store a computer program for performing the following steps:

[0118] Step S101, obtaining business data.

[0119] Step S102, determining step S101, constructing a travel route structure according to a preset configuration.

[0120] Step S102, collecting scenic spot guide data.

[0121] Step S103, associating the scenic spot guide data with the scenic spots in the preset scenic spot library to obtain a travel guide library.

[0122] Step S104, obtaining user needs.

[0123] Step S105, using the pre-trained recommendation model, generating a recommended route according to user needs, the travel guide library and the travel route structure, wherein the recommended route includes multiple scenic spots.

[0124] Optionally, in one embodiment of the present application, the tourist route structure includes at least: scenic spot data, gameplay data, price, transportation method, and travel time.

[0125] Optionally, in one implementation of the present application, the preset scenic spot library includes: scenic spot name, scenic spot address, scenic spot price, scenic spot characteristics, and scenic spot business hours.

[0126] Optionally, in one embodiment of the present application, scenic spot strategy data is associated with scenic spots in a preset scenic spot library to obtain a travel strategy library, including: formatting the scenic spot strategy data to obtain a gameplay library; using a preset entity model to perform entity extraction on the scenic spot strategy data to obtain an entity extraction result; based on the entity extraction result, using a preset association model to associate the entity extraction result with the scenic spots in the preset scenic spot library to obtain an association result; and determining the travel strategy library based on the association result and the gameplay library.

[0127] Optionally, in one embodiment of the present application, the pre-trained recommendation model includes a quality inspection model and a recommendation optimization model, the quality inspection model is used to perform quality inspection on the output initial recommended route to obtain a quality inspection result, and the recommendation optimization model is used to optimize the quality inspection result to obtain a recommended route.

[0128] Optionally, in one implementation of the present application, it also includes: collecting user feedback by obtaining online surveys, user reviews or social media analysis; identifying changes in user demand and market trends using preset strategies based on user feedback; optimizing the travel route structure and pre-trained recommendation model according to preset optimization strategies based on changes in user demand and market trends.

[0129] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.

[0130] An embodiment of the present invention further provides a computer program product, including a computer program, which implements the travel route recommendation method described in any of the above embodiments when executed by a processor.

[0131] Optionally, in this embodiment, the above computer program implements the following steps when executed by a processor:

[0132] Step S101, constructing a travel route structure according to a preset configuration.

[0133] Step S102, collecting scenic spot guide data.

[0134] Step S103, associating the scenic spot guide data with the scenic spots in the preset scenic spot library to obtain a travel guide library.

[0135] Step S104, obtaining user needs.

[0136] Step S105, using the pre-trained recommendation model, generating a recommended route according to user needs, the travel guide library and the travel route structure, wherein the recommended route includes multiple scenic spots.

[0137] Optionally, in one embodiment of the present application, the tourist route structure includes at least: scenic spot data, gameplay data, price, transportation method, and travel time.

[0138] Optionally, in one implementation of the present application, the preset scenic spot library includes: scenic spot name, scenic spot address, scenic spot price, scenic spot characteristics, and scenic spot business hours.

[0139] Optionally, in one embodiment of the present application, scenic spot strategy data is associated with scenic spots in a preset scenic spot library to obtain a travel strategy library, including: formatting the scenic spot strategy data to obtain a gameplay library; using a preset entity model to perform entity extraction on the scenic spot strategy data to obtain an entity extraction result; based on the entity extraction result, using a preset association model to associate the entity extraction result with the scenic spots in the preset scenic spot library to obtain an association result; and determining the travel strategy library based on the association result and the gameplay library.

[0140] Optionally, in one embodiment of the present application, the pre-trained recommendation model includes a quality inspection model and a recommendation optimization model, the quality inspection model is used to perform quality inspection on the output initial recommended route to obtain a quality inspection result, and the recommendation optimization model is used to optimize the quality inspection result to obtain a recommended route.

[0141] Optionally, in one implementation of the present application, it also includes: collecting user feedback by obtaining online surveys, user reviews or social media analysis; identifying changes in user demand and market trends using preset strategies based on user feedback; optimizing the travel route structure and pre-trained recommendation model according to preset optimization strategies based on changes in user demand and market trends.

[0142] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0143] In some embodiments provided in the present application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the modules can be a logical function division. There may be other division methods in actual implementation. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, modules or indirect coupling or communication connection of modules, which can be electrical or other forms.

[0144] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment.

[0145] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of software functional modules.

[0146] If the integrated module is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0147] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for recommending tourist routes, characterized in that: include: Construct a tourist route structure according to the preset configuration; Collect scenic spot guide data; Associating the scenic spot guide data with the scenic spots in a preset scenic spot library to obtain a travel guide library; Obtain user needs; According to the user demand, the travel guide library and the travel route structure, a recommended route is generated using a pre-trained recommendation model, wherein the recommended route includes multiple routes.

2. The method for recommending a tourist route according to claim 1, characterized in that: The tourist route structure includes at least: scenic spot data, playing method data, price, transportation method, and playing time.

3. The method for recommending a tourist route according to claim 1, characterized in that: The preset scenic spot library includes: scenic spot name, scenic spot address, scenic spot price, scenic spot characteristics, and scenic spot business hours.

4. The method for recommending a tourist route according to claim 1, characterized in that: The step of associating the scenic spot guide data with the scenic spots in the preset scenic spot library to obtain a travel guide library includes: Formatting the scenic spot strategy data to obtain a gameplay library; Using a preset entity model to perform entity extraction on the scenic spot guide data to obtain an entity extraction result; According to the entity extraction result, the entity extraction result is associated with the scenic spots in the preset scenic spot library using a preset association model to obtain an association result; The travel strategy library is determined according to the association result and the gameplay library.

5. The method for recommending a tourist route according to claim 1, characterized in that: The pre-trained recommendation model includes a quality inspection model and a recommendation optimization model. The quality inspection model is used to perform quality inspection on the output initial recommended route to obtain a quality inspection result, and the recommendation optimization model is used to optimize the quality inspection result to obtain the recommended route.

6. The method for recommending a tourist route according to claim 1, characterized in that: Also includes: Gather user feedback by obtaining online surveys, user reviews, or social media analysis; Based on the user feedback, using preset strategies to identify changes in user demand and market trends; According to the changes in user demand and the duration trend, the travel route structure and the pre-trained recommendation model are optimized according to a preset optimization strategy.

7. A tourist route recommendation system, characterized in that: include: A construction module, used to construct a travel route structure according to a preset configuration; Collection module, used to collect scenic spot guide data; An association module, used to associate the scenic spot guide data with scenic spots in a preset scenic spot library to obtain a travel guide library; Acquisition module, used to obtain user needs; The recommendation module is used to generate a recommended route based on the user needs, the travel guide library and the travel route structure using a pre-trained recommendation model, wherein the recommended route includes multiple routes.

8. An electronic device, comprising a memory and a processor, characterized in that: The memory stores a computer program, and the processor is configured to run the computer program to execute the travel route recommendation method described in any one of claims 1 to 6.

9. A non-volatile storage medium, characterized in that: The non-volatile storage medium stores a computer program, wherein the computer program is configured to execute the travel route recommendation method described in any one of claims 1 to 6 when running on a computer or a processor.

10. A computer program product, characterized in that It comprises a computer program, which, when executed by a processor, implements the method for recommending a tourist route according to any one of claims 1 to 6.

Images