An intelligent interactive guide device based on preference matching and a guide method thereof

Abstract

The present application relates to the technical field of wisdom travel, and more particularly to an intelligent interactive guide device based on preference matching and a guide method thereof, which proposes a light and portable device integrating a GNSS positioning module, a storage module, a preference analysis module, a matching trigger module, an interactive response module and a gesture recognition module to solve the problems of complicated interaction, lack of non-sensory triggering and insufficient personalization in existing city roaming tours.The method comprises the following steps: constructing a tourism resource database with preference tags; acquiring the position of tourists in real time and recording the historical trajectory; analyzing and generating a set of tourist preference tags; automatically triggering a reminder when the distance between the position and the scenic spot is less than a threshold value and the tag matching degree exceeds a threshold value; and confirming whether to enter by double-clicking or shaking the gesture. If refused, the search radius is expanded by 50 meters and the matching degree threshold is reduced by 5% for stepwise adaptive re-search. The present application realizes non-sensory and personalized intelligent guide, and improves the immersive tour experience.

Description

Technical Field

[0001] This invention relates to the field of smart cultural tourism technology, and more specifically, to a smart interactive tour guide device and tour guide method based on preference matching. Background Technology

[0002] Currently, the development of smart tourism is receiving increasing attention. Various systems and methods related to tourism guidance have been disclosed in existing technologies. For example, Yang Yungang et al. (2019) disclosed a method and system for sharing intelligent equipment in the tourism industry, which improves information processing speed and service diversity through message queue processors and SaaS servers; Xu Dayi et al. (2020) disclosed an interactive experience system that enhances tourists' interactive experience and knowledge acquisition by combining a dynamic tracking projector with a display screen; Ou Jiangping et al. (2020) disclosed a method and system for obtaining tour information based on geolocation, which uses latitude and longitude information to determine the area where tourists are located, improving the flexibility of regional information push; Qu Lei et al. (2024) disclosed a method and system for planning tourist routes based on artificial intelligence, which performs project matching and route planning based on user characteristics.

[0003] In summary, existing technologies mainly focus on the following four models: 1) service resource sharing based on cloud computing and SaaS; 2) immersive interactive experiences utilizing hardware sensors and multimedia devices; 3) regionalized information services based on GPS / BeiDou and other positioning technologies; and 4) personalized trip planning based on artificial intelligence algorithms.

[0004] However, the aforementioned existing technologies still have significant shortcomings and deficiencies in practical applications. First, most solutions are primarily applicable to enclosed spaces such as museums, fixed scenic areas, or small historical sites, lacking adaptability to city-wide, open, and non-fixed-route "citywalk" urban exploration scenarios. Second, existing interactive devices (such as QR codes, RFID, and NFC) require users to actively approach or scan them, which is cumbersome and disrupts the immersive experience, lacking a seamless triggering mechanism. Third, large-scale light and shadow or motion-sensing interactive devices are bulky and costly, making it difficult to achieve personalized, lightweight, and portable use. Finally, existing solutions generally lack in-depth analysis of tourists' long-term historical behavioral patterns and dynamic preference modeling, making it difficult to achieve truly personalized, non-active recommendations.

[0005] Therefore, how to realize a lightweight, seamless, personalized, and long-term learning-capable intelligent tour guide device in urban roaming scenarios remains an urgent problem to be solved in the current technology field. Summary of the Invention

[0006] The purpose of this invention is to provide an intelligent interactive tour guide based on preference matching and a tour guide method thereof, so as to solve the above-mentioned technical problems.

[0007] To achieve the above objectives, the embodiments of this application provide the following technical solutions: On one hand, this application provides an intelligent interactive tour guide device based on preference matching. The device includes: a GNSS positioning module for acquiring tourists' geographical location information in real time; a storage module for storing a city tourism resource database, the database containing the geographical coordinates of multiple tourist spots and their corresponding preference tags; a preference analysis module for analyzing and generating a set of tourist preference tags based on the tourist's historical travel trajectory; a matching trigger module connected to the GNSS positioning module, storage module, and preference analysis module, for generating a trigger signal when the distance between the current location acquired by the GNSS positioning module and any tourist spot is less than a preset threshold, and the matching degree between the tourist spot's preference tag and the tourist's preference tag set exceeds a preset matching threshold; an interaction response module for responding to the trigger signal by reminding tourists through one or more of the following methods: vibration, sound, display, or APP pop-up; and a gesture recognition module for recognizing tourists' non-contact gesture operations on the device and determining whether tourists have entered recommended tourist spots based on the gesture operations.

[0008] Optionally, the preference labels are generated as follows: Tourism content data is crawled from online platforms, then word frequency analysis is performed on the tourism content data to generate an initial tag set, and the tags are prioritized according to the word frequency analysis results; The preset threshold in the matching trigger module is 40-80 meters, and the preset matching threshold is 65%-75%.

[0009] Optionally, the interactive response module further includes: when a tourist chooses not to enter a recommended tourist spot, the matching trigger module gradually expands the search radius in 50-meter increments and gradually decreases the matching threshold in 5% increments until a new recommended tourist spot is matched; The gesture recognition module includes an accelerometer and / or a gyroscope for recognizing double-tap or shaking gestures from tourists; wherein, a double-tap gesture indicates selecting to enter a recommended tourist spot, and a shaking gesture indicates not entering a recommended tourist spot.

[0010] Optionally, the storage module is further configured to: Store tourists' historical tour trajectory data, and initialize the tourist's preference tag set when the number of historical trajectories is less than or equal to 5; When the number of historical trajectories is greater than 5 and less than or equal to 10, iteratively optimize the preference label set; When the number of historical trajectories exceeds 10, a stable set of personalized preference tags is formed.

[0011] On the other hand, this embodiment provides a tour guide method applicable to the aforementioned preference-matching-based intelligent interactive tour guide device, the method comprising: Collect the geographic coordinates of urban tourist attractions and label them with preference tags to build a tourism resource database; Real-time acquisition of tourists' GNSS location information and recording of their historical tour routes; Generate or update visitor preference tag sets based on historical travel patterns; A trigger signal is generated when the distance between a tourist's current location and any tourist spot is less than a preset threshold, and the match between the tourist spot's tag and the tourist's preferred tag set exceeds a preset matching threshold. In response to the trigger signal, the visitor will be alerted via vibration, sound, display, or pop-up window. By recognizing tourists' hand gestures, the system determines whether they have entered recommended tourist spots and updates their historical trajectory data accordingly. If a tourist chooses not to enter the currently recommended tourist spot, the search radius will be gradually expanded in 50-meter increments, and the matching threshold will be gradually reduced in 5% increments until a new recommended tourist spot is matched.

[0012] Optionally, the method for generating and updating the preference tag set includes: Tourism content data is crawled from mainstream online platforms, word frequency analysis is performed on the crawled data, an initial tag set is generated, and tag priority is determined; For attractions that have not been visited, multiple preference tags for the attraction are automatically generated using a machine learning model based on the initial tag set; Based on the tags of the attractions visited in the tourist's historical travel trajectory and their frequency of occurrence, a weighted statistical method is used to generate a set of tourist preference tags, where the weight of each tag is positively correlated with the cumulative number of times that tag appears in the historical trajectory; Once the number of historical tracks exceeds 10, the main structure of the tourist's preference tag set is locked, and only the boundary tags with a matching degree between 60% and 80% are fine-tuned and updated.

[0013] Optionally, the gesture recognition steps include: The device collects the gesture data of tourists through its built-in accelerometer and / or gyroscope. When the device detects two consecutive changes in acceleration peak within 2 seconds, it is interpreted as a "double-tap to confirm" gesture, indicating that the tourist has selected to enter the currently recommended visit point; When the device is detected to swing continuously three times in the left and right directions within 2 seconds and the swing amplitude exceeds the preset angle threshold, it is judged as a "shake to refuse" gesture, indicating that the tourist chooses not to enter the currently recommended tourist spot; If no valid gesture is detected within 30 seconds of the trigger signal being issued, it will be considered a rejection by default, and the alert will be automatically turned off.

[0014] Optionally, if tourists choose not to enter the currently recommended attractions, the search radius will be expanded in 50-meter increments, and the matching threshold will be reduced in 5% increments, including: Set the initial search radius Meters, initial matching threshold Maximum search radius Meters, minimum matching threshold radius step size Meters, threshold step size ; In the k-th level search, the search radius Matching threshold ; In the current search radius Search within for all items that have not been rejected and are within a certain distance. And matching degree Tourist attractions; If there are multiple candidate points, they are recommended in order of priority from high to low matching degree and from near to far distance; If no recommended point is matched within 3 consecutive ladder levels, a cooldown mechanism is activated, pausing recommendations for 10 minutes, after which the search parameters are reset to their initial values.

[0015] Thirdly, embodiments of this application provide an intelligent interactive tour guide device based on preference matching, the device including a memory and a processor.

[0016] The memory is used to store the computer program; the processor is used to implement the steps of the above-described intelligent interactive guide method based on preference matching when executing the computer program.

[0017] Fourthly, embodiments of this application provide a medium on which a computer program is stored, which, when executed by a processor, implements the steps of the above-described intelligent interactive guide method based on preference matching.

[0018] The beneficial effects of this invention are as follows: This invention utilizes GNSS meter-level precise positioning and multimodal sensor fusion to automatically complete location matching and preference comparison in the background without requiring users to take out their phones, scan codes, or get close to the device. When a tourist approaches a scenic spot with a matching degree exceeding a threshold, an automatic reminder is triggered, completely eliminating the cumbersome steps of "taking out a phone - opening the APP - scanning a code - waiting for loading" in traditional tour guides. This achieves a natural emergence of services and greatly enhances the immersiveness and continuity of the tour.

[0019] Secondly, this invention employs a dual judgment mechanism of "location distance threshold + tag matching degree threshold" (e.g., 50-meter distance + 70% matching degree), combined with dynamic preference analysis of tourists' historical trajectories, effectively avoiding frequent interruptions from irrelevant attractions. Simultaneously, when tourists decline recommendations, the system gradually expands the search range and lowers the matching requirements in a tiered manner, achieving an adaptive balance between coverage and accuracy.

[0020] This invention's device is independent of mobile phones, compact, cost-effective, and can be designed in various forms (such as pendants, bracelets, etc.). More importantly, the device has a built-in preference analysis module that can continuously learn during tourist use—initializing a profile when there are 5 or fewer historical trajectories, iteratively optimizing when there are 5 to 10, and forming a stable preference after more than 10, achieving true "the more you use it, the better it understands you," which has long-term value for frequent travelers. Through multimodal reminders via vibration motors, speakers, displays, or APP pop-ups, combined with non-contact interaction such as gesture recognition (double-tap to confirm, shake to refuse), this invention ensures that tourists can make decisions without shifting their attention during their travels, enhancing immersion and increasing the fun and storytelling of the tour. This device eliminates the need to deploy a large number of beacons, QR codes, or large interactive devices within scenic areas, significantly reducing maintenance costs for attraction operators. Simultaneously, the device itself can be sold as a cultural tourism IP derivative product, providing new revenue growth points for cultural tourism cities and promoting the in-depth development of the cultural tourism industry.

[0021] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing embodiments of the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings. Attached Figure Description

[0022] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a schematic diagram of the structure of an intelligent interactive tour guide device based on preference matching, as described in an embodiment of the present invention. Figure 2 This is a schematic diagram of a smart interactive tour guide method based on preference matching as described in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an intelligent interactive tour guide electronic device based on preference matching, as described in an embodiment of the present invention. Figure 4 This is a schematic diagram illustrating an application scenario of an intelligent interactive tour guide device based on preference matching, as described in an embodiment of the present invention. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0025] It should be noted that similar reference numerals or letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this invention, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0026] Example 1:

[0027] like Figure 1 As shown, this embodiment provides an intelligent interactive tour guide device based on preference matching. The device includes: The GNSS positioning module is used to obtain tourists' geographical location information in real time. It adopts a Beidou and GPS dual-mode positioning chip to obtain tourists' geographical coordinates in real time, with positioning accuracy reaching the meter level. A storage module is used to store a database of urban tourism resources. This database contains the geographic coordinates of multiple tourist attractions and their corresponding preference tags. Specifically, it includes non-volatile flash memory for storing the urban tourism resource database and tourists' historical travel trajectory data. The database includes the name, geographic coordinates, preference tags (such as "historical culture," "food exploration," "popular spots," "natural scenery," etc.), and tag weights for each tourist attraction. The storage module is also used to: store tourists' historical travel trajectory data; initialize the tourists' preference tag set when the number of historical trajectories is less than or equal to 5; iteratively optimize the preference tag set when the number of historical trajectories is greater than 5 but less than or equal to 10; and form a stable personalized preference tag set when the number of historical trajectories is greater than 10.

[0028] The preference analysis module uses an embedded microprocessor (MCU) to run a lightweight machine learning algorithm to analyze, generate, or update tourists' preference tag sets and corresponding weights based on their historical travel trajectories. The preference tags are generated in the following way: Tourism content data is crawled from online platforms, then word frequency analysis is performed on the tourism content data to generate an initial tag set, and the tags are prioritized according to the word frequency analysis results; The preset threshold in the matching trigger module is 40-80 meters, and the preset matching threshold is 65%-75%.

[0029] The matching trigger module is connected to the GNSS positioning module, the storage module and the preference analysis module respectively. It is used to generate a trigger signal when the distance between the current position obtained by the GNSS positioning module and any tourist point is less than a preset threshold, and the matching degree between the preference tag of the tourist point and the tourist's preference tag set exceeds a preset matching threshold. An interactive response module is used to respond to the trigger signal and remind tourists through one or more of the following methods: vibration, sound, display or APP pop-up; the interactive response module also includes: when a tourist chooses not to enter the recommended tourist spot, the matching trigger module gradually expands the search radius in 50-meter increments and gradually decreases the matching degree threshold in 5% increments until a new recommended tourist spot is matched. The gesture recognition module includes an accelerometer and / or a gyroscope for recognizing double-tap or shaking gestures from tourists; wherein, a double-tap gesture indicates selecting to enter a recommended tourist spot, and a shaking gesture indicates not entering a recommended tourist spot.

[0030] The gesture recognition module is used to recognize tourists' non-contact gesture operations on the device and determine whether tourists have entered recommended tourist spots based on the gesture operations.

[0031] This invention utilizes GNSS meter-level precise positioning and multimodal sensor fusion to automatically complete location matching and preference comparison in the background without requiring users to take out their phones, scan codes, or get close to the device. When a tourist approaches a scenic spot with a matching degree exceeding a threshold, an automatic reminder is triggered, completely eliminating the cumbersome steps of "taking out a phone - opening the APP - scanning a code - waiting for loading" in traditional tour guides. This achieves a natural emergence of services and greatly enhances the immersiveness and continuity of the tour.

[0032] Secondly, this invention employs a dual judgment mechanism of "location distance threshold + tag matching degree threshold" (e.g., 50-meter distance + 70% matching degree), combined with dynamic preference analysis of tourists' historical trajectories, effectively avoiding frequent interruptions from irrelevant attractions. Simultaneously, when tourists decline recommendations, the system gradually expands the search range and lowers the matching requirements in a tiered manner, achieving an adaptive balance between coverage and accuracy.

[0033] This invention's device is independent of mobile phones, compact, cost-effective, and can be designed in various forms (such as pendants, bracelets, etc.). More importantly, the device has a built-in preference analysis module that can continuously learn during tourist use—initializing a profile when there are 5 or fewer historical trajectories, iteratively optimizing when there are 5 to 10, and forming a stable preference after more than 10, achieving true "the more you use it, the better it understands you," which has long-term value for frequent travelers. Through multimodal reminders via vibration motors, speakers, displays, or APP pop-ups, combined with non-contact interaction such as gesture recognition (double-tap to confirm, shake to refuse), this invention ensures that tourists can make decisions without shifting their attention during their travels, enhancing immersion and increasing the fun and storytelling of the tour. This device eliminates the need to deploy a large number of beacons, QR codes, or large interactive devices within scenic areas, significantly reducing maintenance costs for attraction operators. Simultaneously, the device itself can be sold as a cultural tourism IP derivative product, providing new revenue growth points for cultural tourism cities and promoting the in-depth development of the cultural tourism industry.

[0034] Example 2:

[0035] like Figure 2 As shown, this embodiment, based on Embodiment 1, provides a tour guide method suitable for the aforementioned preference-matching-based intelligent interactive tour guide device. The method includes: Step S1: Collect the geographic coordinates of urban tourist attractions and label them with preference tags to build a tourism resource database; Step S2: Obtain the GNSS location information of tourists in real time and record their historical tour routes; Step S3: Generate or update the tourist preference tag set based on historical tour trajectory analysis; The method for generating and updating the preference label set is as follows: Step S31: Crawl tourism content data from mainstream online platforms, perform word frequency analysis on the crawled data, generate an initial tag set, and determine tag priority; Step S32: For attractions that have not been visited, use a machine learning model to automatically generate multiple preference tags for the attraction based on the initial tag set; Step S33: Based on the tags of the attractions visited in the tourist's historical travel trajectory and their frequency of occurrence, a weighted statistical method is used to generate a set of tourist preference tags, wherein the weight of each tag is positively correlated with the cumulative number of times the tag appears in the historical trajectory; Step S34: When the number of historical trajectories exceeds 10, lock the main structure of the tourist's preference tag set, and only fine-tune and update the boundary tags with a matching degree between 60% and 80%. Step S4: When the distance between the tourist's current location and any tourist spot is less than a preset threshold, and the matching degree between the tourist spot's tag and the tourist's preferred tag set exceeds a preset matching threshold, a trigger signal is generated. Step S5: In response to the trigger signal, remind the visitor through vibration, sound, display or pop-up window; Step S6: By recognizing the tourist's gestures, determine whether they have entered the recommended tourist spot and update the historical trajectory data accordingly; The gesture recognition steps include: Step S61: Collect the tourist's hand gesture data through the device's built-in accelerometer and / or gyroscope; Step S62: When the device detects two consecutive changes in acceleration peak within 2 seconds, it is determined as a "double-click confirmation" gesture, indicating that the tourist has selected to enter the currently recommended visit point; Step S63: When the device is detected to swing continuously in the left and right directions three times within 2 seconds and the swing amplitude exceeds the preset angle threshold, it is judged as a "shaking rejection" gesture, indicating that the tourist chooses not to enter the currently recommended tourist spot; Step S64: If no valid gesture is detected within 30 seconds after the trigger signal is issued, it will be considered a rejection by default, and the reminder will be automatically turned off.

[0036] Step S7: If the tourist chooses not to enter the currently recommended tourist spot, the search radius is gradually expanded in 50-meter increments, and the matching threshold is gradually decreased in 5% increments until a new recommended tourist spot is matched. Specifically, this can be done as follows: Step S71: If the tourist chooses not to enter the currently recommended tourist spot, the search radius is gradually expanded in 50-meter increments, and the matching threshold is gradually decreased in 5% increments, including: Step S72: Set the initial search radius Meters, initial matching threshold Maximum search radius Meters, minimum matching threshold radius step size Meters, threshold step size ; Step S73: In the k-th level search, the search radius... Matching threshold ; Step S74: Within the current search radius Search within for all items that have not been rejected and are within a certain distance. And matching degree Tourist attractions; Step S75: If there are multiple candidate points, they are recommended in order of priority from high to low matching degree and from near to far distance. Step S76: If no recommended point is matched within 3 consecutive steps, the cooling mechanism is activated, the recommendation is paused for 10 minutes, and then the search parameters are reset to the initial value.

[0037] Example 3: This embodiment is based on Embodiment 2 and is used to provide two coherent and specific typical application scenarios. Combining the two typical application scenarios, the implementation process of the method of the present invention is explained in detail.

[0038] Scenario 1: First-time users of the device (with ≤ 5 historical tracks).

[0039] A tourist used the device for the first time in city A, and the number of his / her historical tracks was 0.

[0040] Step A1 (Data Collection and Database Construction): The system pre-collects the geographical coordinates of all tourist attractions in City A. Simultaneously, it crawls tourism content data of City A from mainstream travel platforms (such as Xiaohongshu, Mafengwo, Ctrip, etc.), performs word frequency analysis, generates an initial set of preference tags (such as "coffee shops," "historical buildings," "art galleries," etc.), and sorts them by word frequency. Tourist attractions are then associated with the tags and stored in the database.

[0041] Step A2 (Initial Positioning and Track Recording): The tourist turns on the device, and the GNSS module begins recording their 24-hour travel trajectory in City A. When the tourist enters within 50 meters of a scenic spot, the system determines that they have "passed by".

[0042] Step A3 (Portrait Initialization): Since there are ≤5 historical tracks, the device initially determines that the tourist prefers "art" type attractions based on the tags of the attractions the tourist entered in the first few times (for example, the tourist entered "XX Art Museum" and "XX Sculpture Park" in succession, both of which are tagged "art"). The preferred tag set is initialized as {"art": 0.8, "default": 0.2}.

[0043] Step A4 (Recommendation and Learning): When a visitor wanders within 50 meters of a "creative park" (tagged "art," "trendy," "coffee"), the matching degree is calculated to be 80% (above 70%). The device vibrates and announces: "There is an art park ahead, recommended to visit." If the visitor double-clicks to confirm, the point is recorded; if they shake to refuse, it is not recorded, and the system automatically expands the search range.

[0044] Scenario 2: Experienced users (historical activity records > 10) This tourist has used the device to visit multiple cities, with more than 10 historical tracks. Their preference tag set has stabilized at {"Historical Sites": 0.9, "Folklore": 0.7, "Food": 0.6}.

[0045] Step B1 (Arrival in a New City): The tourist arrives in City D carrying the device. The device automatically matches the City D database and, based on the tourist's preference tag set, proactively announces: "Based on your preferences, we recommend that you first visit the ancient city wall ruins of City D."

[0046] Step B2 (Unnoticed Triggering During Roaming): After finishing their tour of the ancient city wall, the tourist begins free roaming. When the tourist walks to an old street (48 meters away, the street is tagged with "folk customs", "handicrafts" and "food", and the matching degree is calculated as (0.7+0.6) / 2 = 65%, which is less than 70%), the device is not triggered.

[0047] Step B3 (Adaptive Expanding Matching): The tourist continues forward and does not enter any other triggering areas. The system automatically expands the matching radius to 100 meters, and the matching threshold drops to 65%. At this point, the matching degree of the aforementioned old street reaches the new threshold of 65%, and the device triggers a prompt: "There is a folk-style old street nearby, would you like to go?" Step B4 (Interaction and Feedback): The visitor double-clicks to confirm entry. The device records the visit point in its historical track and slightly increases the weight of the "Folklore" and "Food" tags to further refine the visitor profile. Throughout the process, the visitor does not need to take out their phone or perform any active operations, achieving a completely seamless smart tour guide experience.

[0048] In summary, the tour guide method of the intelligent interactive tour guide device based on preference matching described in this embodiment effectively solves the problems of cumbersome interaction, lack of personalization, and high false trigger rate in urban roaming scenarios of existing technologies by combining lightweight portable devices, GNSS positioning, multimodal gesture recognition, dynamic preference analysis and step-by-step adaptive matching algorithm, and significantly improves the immersive experience of tourists and the level of intelligence of cultural and tourism services.

[0049] Example 4: Corresponding to the above method embodiments, this disclosure also provides a preference-matching-based intelligent interactive tour guide device. The preference-matching-based intelligent interactive tour guide device described below and the preference-matching-based intelligent interactive tour guide method described above can be referred to in correspondence.

[0050] Figure 3 This is a block diagram illustrating a preference-matching-based intelligent interactive tour guide electronic device according to an exemplary embodiment. Figure 3 As shown, the electronic device 800 may include a processor 801 and a memory 802. The electronic device 800 may also include one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0051] The processor 801 controls the overall operation of the electronic device 800 to complete all or part of the steps in the preference-matching-based intelligent interactive guide method described above. The memory 802 stores various types of data to support the operation of the electronic device 800. This data may include, for example, instructions for any application or method operating on the electronic device 800, and application-related data such as contact data, sent and received messages, pictures, audio, video, etc. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. Multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touchscreen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in memory 802 or transmitted via communication component 805. The audio component also includes at least one speaker for outputting audio signals. I / O interface 804 provides an interface between processor 801 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual or physical buttons. Communication component 805 is used for wired or wireless communication between the electronic device 800 and other devices. Wireless communication may include Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination of these. Therefore, the corresponding communication component 805 may include a Wi-Fi module, a Bluetooth module, or an NFC module.

[0052] In an exemplary embodiment, the electronic device 800 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-described preference-matching-based intelligent interactive guide method.

[0053] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the preference-matching-based intelligent interactive guide method described above. For example, the computer-readable storage medium may be the memory 802 including the program instructions described above, which may be executed by the processor 801 of the electronic device 800 to complete the preference-matching-based intelligent interactive guide method described above.

[0054] Example 5: Corresponding to the above method embodiments, this disclosure also provides a readable storage medium. The readable storage medium described below corresponds to and can be referred to in relation to the above-described intelligent interactive guide method based on preference matching.

[0055] A readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the preference-matching-based intelligent interactive guide method described in the above method embodiments.

[0056] Specifically, the readable storage medium can be a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, or any other readable storage medium capable of storing program code.

[0057] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A smart interactive tour guide device based on preference matching, characterized in that, The device includes: GNSS positioning module, used to obtain tourists' geographical location information in real time; The storage module is used to store a database of urban tourism resources, which contains the geographical coordinates of multiple tourist attractions and their corresponding preference tags. The preference analysis module is used to analyze and generate a set of preference tags for tourists based on their historical travel patterns. The matching trigger module is connected to the GNSS positioning module, the storage module and the preference analysis module respectively. It is used to generate a trigger signal when the distance between the current position obtained by the GNSS positioning module and any tourist point is less than a preset threshold, and the matching degree between the preference tag of the tourist point and the tourist's preference tag set exceeds a preset matching threshold. An interactive response module is used to respond to the trigger signal and remind tourists through one or more of the following methods: vibration, sound, display, or APP pop-up. The gesture recognition module is used to recognize tourists' non-contact gesture operations on the device and determine whether tourists have entered recommended tourist spots based on the gesture operations.

2. The intelligent interactive tour guide device based on preference matching according to claim 1, characterized in that, The preference tags are generated in the following way: Tourism content data is crawled from online platforms, then word frequency analysis is performed on the tourism content data to generate an initial tag set, and the tags are prioritized according to the word frequency analysis results; The preset threshold in the matching trigger module is 40-80 meters, and the preset matching threshold is 65%-75%.

3. The intelligent interactive tour guide device based on preference matching according to claim 2, characterized in that, The interactive response module also includes: when a tourist chooses not to enter a recommended tourist spot, the matching trigger module gradually expands the search radius in 50-meter increments and gradually decreases the matching degree threshold in 5% increments until a new recommended tourist spot is matched. The gesture recognition module includes an accelerometer and / or a gyroscope for recognizing double-tap or shaking gestures from tourists; wherein, a double-tap gesture indicates selecting to enter a recommended tourist spot, and a shaking gesture indicates not entering a recommended tourist spot.

4. The intelligent interactive tour guide device based on preference matching according to claim 3, characterized in that, The storage module is also used for: Store tourists' historical tour trajectory data, and initialize the tourist's preference tag set when the number of historical trajectories is less than or equal to 5; When the number of historical trajectories is greater than 5 and less than or equal to 10, iteratively optimize the preference label set; When the number of historical trajectories exceeds 10, a stable set of personalized preference tags is formed.

5. A tour guide method based on a preference-matching intelligent interactive tour guide device according to any one of claims 1-4, the method comprising: Collect the geographic coordinates of urban tourist attractions and label them with preference tags to build a tourism resource database; Real-time acquisition of tourists' GNSS location information and recording of their historical tour routes; Generate or update visitor preference tag sets based on historical travel patterns; A trigger signal is generated when the distance between a tourist's current location and any tourist spot is less than a preset threshold, and the match between the tourist spot's tag and the tourist's preferred tag set exceeds a preset matching threshold. In response to the trigger signal, the visitor will be alerted via vibration, sound, display, or pop-up window. By recognizing tourists' hand gestures, the system determines whether they have entered recommended tourist spots and updates their historical trajectory data accordingly. If a tourist chooses not to enter the currently recommended tourist spot, the search radius will be gradually expanded in 50-meter increments, and the matching threshold will be gradually reduced in 5% increments until a new recommended tourist spot is matched.

6. The tour guide method according to claim 5, characterized in that, The method for generating and updating the preference tag set includes: Tourism content data is crawled from mainstream online platforms, word frequency analysis is performed on the crawled data, an initial tag set is generated, and tag priority is determined; For attractions that have not been visited, multiple preference tags for the attraction are automatically generated using a machine learning model based on the initial tag set; Based on the tags of the attractions visited in the tourist's historical travel trajectory and their frequency of occurrence, a weighted statistical method is used to generate a set of tourist preference tags, where the weight of each tag is positively correlated with the cumulative number of times that tag appears in the historical trajectory; Once the number of historical tracks exceeds 10, the main structure of the tourist's preference tag set is locked, and only the boundary tags with a matching degree between 60% and 80% are fine-tuned and updated.

7. The tour guide method according to claim 6, characterized in that, Gesture recognition steps include: The device collects the gesture data of tourists through its built-in accelerometer and / or gyroscope. When the device detects two consecutive changes in acceleration peak within 2 seconds, it is interpreted as a "double-tap to confirm" gesture, indicating that the tourist has selected to enter the currently recommended visit point; When the device is detected to swing continuously three times in the left and right directions within 2 seconds and the swing amplitude exceeds the preset angle threshold, it is judged as a "shake to refuse" gesture, indicating that the tourist chooses not to enter the currently recommended tourist spot; If no valid gesture is detected within 30 seconds of the trigger signal being issued, it will be considered a rejection by default, and the alert will be automatically turned off.

8. The tour guide method according to claim 7, characterized in that, If a tourist chooses not to enter the currently recommended tourist spot, the search radius will be gradually expanded in 50-meter increments, and the matching threshold will be gradually reduced in 5% increments, including: Set the initial search radius Meters, initial matching threshold Maximum search radius Meters, minimum matching threshold radius step size Meters, threshold step size ; In the k-th level search, the search radius Matching threshold ; In the current search radius Search within for all results that have not been rejected and are within a certain distance. And matching degree Tourist attractions; If there are multiple candidate points, they are recommended in order of priority from high to low matching degree and from near to far distance; If no recommended point is matched within 3 consecutive ladder levels, a cooldown mechanism is activated, pausing recommendations for 10 minutes, after which the search parameters are reset to their initial values.

Images