Personalized intelligent travel route recommendation system and method based on MR technology

Abstract

The invention discloses a personalized intelligent travel route recommendation system and method based on an MR technology, and belongs to the technical field of intelligent recommendation. Acquiring heart rate data and step number data of the user and staying time of the user at the scenic spot; uniformly dividing the staying time into a plurality of staying time periods; calculating a fatigue degree evaluation value of the user in a single stay time period; calculating the preference degree of a user for a single scenic spot based on the fatigue degree evaluation value; presetting a fatigue degree evaluation mean value threshold value and a preference degree threshold value, and analyzing and dynamically adjusting the route of the user; and calculating the preference similarity between the users, presetting a preference similarity threshold value, and analyzing and carrying out intelligent route recommendation. Through fatigue calculation and preference evaluation, dynamic personalized adjustment and an intelligent recommendation mechanism, the recommendation system can adapt to the state and interest of the user in real time, the tourism comfort and personalized experience are improved, the limitation of a traditional static recommendation system is effectively broken through, and higher-quality tourism service is provided.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent recommendation, and specifically provides a personalized intelligent recommendation system and method for cultural and tourism routes based on MR technology. Background Art

[0002] In recent years, with the deep integration of the culture and tourism industries, the cultural and tourism market has shown a development trend of diversification, personalization, and intelligence. Traditional tourism route planning methods usually rely on historical data, user ratings, and expert recommendations, but lack comprehensive consideration of individual users' physiological states, interest preferences, and real-time feedback. To enhance the immersive experience of tourists, mixed reality (MR) technology has gradually been applied to the cultural and tourism field. However, existing MR technologies mainly focus on information display and interaction levels and have not fully combined users' physiological feedback data for personalized recommendations. In addition, most existing personalized tourism recommendation systems are based on users' historical behavior data and interest tags, ignoring users' physiological states and fatigue levels during actual tours and making it difficult to achieve dynamic adjustment and accurate recommendation.

[0003] Existing traditional tourism recommendation algorithms usually rely on collaborative filtering, content recommendation, or path optimization, mainly depending on static data and lacking dynamic perception of users' physiological states (such as heart rate, steps, fatigue level, etc.), resulting in difficult adaptation of recommendation results to users' real-time needs. Secondly, although some intelligent recommendation systems consider users' real-time behavior data (such as the time spent at scenic spots), they fail to deeply analyze their physiological feedback, which may recommend tour routes beyond users' tolerance and affect the tourism experience. Thirdly, existing cultural and tourism intelligent recommendation solutions often ignore social factors, that is, the preference similarity among tourists is not fully utilized, and optimized recommendation based on group behavior cannot be achieved. Summary of the Invention

[0004] The purpose of the present invention is to provide a personalized intelligent recommendation system and method for cultural and tourism routes based on MR technology to solve the problems raised in the above background art.

[0005] To solve the above technical problems, the present invention provides the following technical solutions:

[0006] A personalized intelligent recommendation method for cultural and tourism routes based on MR technology, which includes the following steps: Step S1: After obtaining user authorization, obtain the user's heart rate data and step count data; obtain the user's stay time at the scenic spot; Step S2: Uniformly divide the stay time into multiple stay time periods; Step S3: Based on the heart rate data and step count data, calculate the fatigue degree evaluation value of the user within a single stay time period; based on the fatigue degree evaluation value, calculate the user's preference degree for a single scenic spot; Step S4: Preset the average fatigue degree evaluation threshold and preference degree threshold, analyze and dynamically adjust the user's route; calculate the preference similarity between users, preset the preference similarity threshold, analyze and perform intelligent route recommendation.

[0007] As a preferred solution of the personalized intelligent recommendation method for cultural and tourism routes based on MR technology of the present invention, after obtaining user authorization, a bracelet-type MR device is worn on the user's wrist. The bracelet-type MR device is internally provided with an optical heart rate sensor, an acceleration sensor, and a gyroscope; the optical heart rate sensor is used to monitor the user's heart rate data, and the acceleration sensor and the gyroscope are used to monitor the user's step count data.

[0008] A Bluetooth signal base station is built in the scenic spots of the cultural and tourism route. The signal coverage range of the Bluetooth signal base station is the area range of the scenic spot; the bracelet-type MR device obtains the user's stay time at the scenic spot by establishing a signal connection with the Bluetooth signal base station; the stay time is obtained by subtracting the time when the bracelet-type MR device establishes a signal connection with the Bluetooth signal base station from the time when the bracelet-type MR device disconnects the signal connection with the Bluetooth signal base station.

[0009] As a preferred solution of the personalized intelligent recommendation method for cultural and tourism routes based on MR technology of the present invention, the time when the bracelet-type MR device establishes a signal connection with the Bluetooth signal base station built in the i-th scenic spot is denoted as ESC i ,the time when the bracelet-type MR device disconnects the signal connection with the Bluetooth signal base station built in the i-th scenic spot is denoted as DSC i ; based on the connection time ESC i and the disconnection time DSC i , the stay time of the j-th user at the i-th scenic spot is denoted as ΔT j,i = DSC j,i - ESC j,i .

[0010] Divide the stay time ΔT j,i of the j-th user at the i-th scenic spot into N stay time periods evenly, obtain the user's heart rate data and step count data within the a-th stay time period, and denote the heart rate data and the step count data as HR j.i,a and SNj,i,a 。

[0011] As a preferred solution of the personalized intelligent recommendation method for cultural and tourism routes based on MR technology described in the present invention, based on the heart rate data HR j,i,a and step count data SN j,i,a of the j-th user in the a-th stay period, calculate the fatigue degree evaluation value of the user in the a-th stay period, and the calculation formula is as follows:

[0012]

[0013] where FLA j,i,a represents the fatigue degree evaluation value of the j-th user in the a-th stay period, α and β respectively represent the influence factors of the preset heart rate data and step count data, HR base represents the preset basic heart rate data, HR max represents the preset maximum heart rate data (generally obtained by subtracting the age from 220 to get the maximum heart rate data), SN max represents the preset maximum step count data (generally set by comprehensively considering factors such as personal age, physical condition, exercise foundation, and exercise purpose).

[0014] It should be noted that the first half of the formula evaluates the fatigue degree based on the heart rate data, calculates the ratio of the current heart rate to the range of the basic heart rate and the maximum heart rate, reflecting the degree of change of the heart rate. Generally speaking, the closer the heart rate is to the maximum heart rate, the higher the fatigue degree of the human body. Multiplying by α (the influence factor of the heart rate data) is to adjust the weight of the heart rate in the fatigue assessment according to the actual situation; the second half of the formula evaluates the fatigue degree based on the step count data, calculates the ratio of the current step count to the preset maximum step count. The more steps, usually the more energy the body consumes, and the higher the fatigue degree may be. Multiplying by β (the influence factor of the step count data) is used to adjust the weight of the step count in the fatigue assessment; adding the two parts together comprehensively considers the influence of the heart rate and the step count on the fatigue degree, and more comprehensively evaluates the fatigue state of the user in a specific period; generally speaking, this formula takes into account both the heart rate and the step count, two factors closely related to human fatigue. The heart rate reflects the immediate physiological load of the body, and the step count reflects the accumulation of activity volume. The combination of the two can measure the fatigue degree more comprehensively and is more accurate than evaluating based on a single factor.

[0015] Obtain the fatigue degree evaluation value of the j-th user in all stay periods, and combine the stay time ΔT j,i , calculate the preference degree of the j-th user for the i-th scenic spot, and the calculation formula is as follows:

[0016]

[0017] Among them, PD j,i represents the preference degree of the j-th user for the i-th scenic spot, γ and δ represent the influence factors of the preset stay time and fatigue degree evaluation value, and PΔT j,i represents the planned stay time of the j-th user at the i-th scenic spot, represents the average fatigue degree evaluation of the j-th user during all stay time periods.

[0018] It should be noted that this formula comprehensively considers the user's stay behavior and physical state at the scenic spot. The stay time directly reflects the user's interest in the scenic spot, while the fatigue degree corrects the possible deviation brought by the stay time; for example, if a user stays at a certain scenic spot for a long time but is in a highly fatigued state, then their true preference for this scenic spot may not be as high as judged solely from the stay time, and the formula makes a reasonable adjustment through the fatigue degree; specifically, the first half of the formula considers the proportional relationship between the actual stay time and the planned stay time of the user at the scenic spot; if the actual stay time is relatively long compared to the planned stay time, it usually means that the user has a high interest in this scenic spot, and multiply by (the influence factor of the stay time) to adjust its weight in the preference degree calculation; the second half of the formula considers the overall fatigue degree of the user during the stay at the scenic spot, is the average fatigue degree evaluation during all stay time periods, and the higher the fatigue degree, the smaller the value, which means that in a highly fatigued state, even if the stay time is long, the preference degree for the scenic spot will be affected; by adding the two parts together, the preference degree of the user for the scenic spot can be accurately calculated, providing a key basis for the personalized adjustment and intelligent recommendation of the cultural and tourism route.

[0019] As a preferred solution of the personalized intelligent recommendation method for cultural and tourism routes based on MR technology described in the present invention, a preset average fatigue degree evaluation threshold and a preference degree threshold of the j-th user for the i-th scenic spot are set.

[0020] If the average fatigue degree evaluation of the j-th user during all stay time periods is greater than or equal to the average fatigue degree evaluation threshold, and, the preference degree PD of the j-th user for the i-th scenic spot j,i is less than or equal to the preference degree threshold, it is determined that the j-th user is fatigued and not preferred for the i-th scenic spot, and then reduce the scenic spots similar to the i-th scenic spot in the subsequent route and add rest areas.

[0021] If the average fatigue degree evaluation of the j-th user during all stay time periods Less than the average fatigue level assessment threshold, and the preference degree PD of the j-th user for the i-th scenic spot j,i is greater than the preference degree threshold, then it is determined that the j-th user is not fatigued and has a preference for the i-th scenic spot, and similar scenic spots to the i-th scenic spot are added to the subsequent route.

[0022] After the route dynamic adjustment of the j-th user is completed, obtain the route of the j-th user, and calculate the preference similarity between the j-th user and the k-th user. The calculation formula is as follows:

[0023]

[0024] where S j,k represents the preference similarity between the j-th user and the k-th user, PD k,i represents the preference degree of the k-th user for the i-th scenic spot, represents the average fatigue level assessment value of the k-th user during all stay time periods.

[0025] Preset a preference similarity threshold. If the preference similarity S between the j-th user and the k-th user j,k is greater than the preference similarity threshold, then it is determined that the j-th user and the k-th user have similar preferences, and the route of the j-th user is intelligently recommended to the k-th user.

[0026] A personalized intelligent recommendation system for cultural and tourism routes based on MR technology. This system includes: a data acquisition module, a time period division module, a fatigue level assessment value and preference degree calculation module, and a preference similarity calculation and intelligent recommendation module.

[0027] The data acquisition module: After obtaining user authorization, obtain the user's heart rate data and step count data; obtain the user's stay time at the scenic spot.

[0028] The time period division module: evenly divide the stay time into multiple stay time periods.

[0029] The fatigue level assessment value and preference degree calculation module: Based on the heart rate data and step count data, calculate the fatigue level assessment value of the user during a single stay time period; based on the fatigue level assessment value, calculate the preference degree of the user for a single scenic spot.

[0030] The preference similarity calculation and intelligent recommendation module: Preset an average fatigue level assessment threshold and a preference degree threshold, analyze and dynamically adjust the user's route; calculate the preference similarity between users, preset a preference similarity threshold, analyze and perform intelligent route recommendation.

[0031] Further, the data acquisition module includes a data acquisition unit.

[0032] The data acquisition unit: After obtaining user authorization, a bracelet-type MR device is worn on the user's wrist. The bracelet-type MR device is built-in with an optical heart rate sensor, an acceleration sensor, and a gyroscope. The optical heart rate sensor is used to monitor the user's heart rate data, and the acceleration sensor and gyroscope are used to monitor the user's step data. Bluetooth signal base stations are built-in in the scenic spots of the cultural and tourism route, and the signal coverage range of the Bluetooth signal base stations is the area range of each scenic spot. The bracelet-type MR device obtains the user's stay time at the scenic spot by establishing a signal connection with the Bluetooth signal base station. The stay time is obtained by subtracting the time when the bracelet-type MR device disconnects the signal connection from the time when the bracelet-type MR device establishes a signal connection with the Bluetooth signal base station.

[0033] Further, the time period division module includes a time period division unit.

[0034] The time period division unit: evenly divides the user's stay time in the scenic spot into multiple stay time periods, and obtains the user's heart rate data and step data within a single stay time period.

[0035] Further, the fatigue degree evaluation value and preference calculation module includes a fatigue degree evaluation value calculation unit and a preference calculation unit.

[0036] The fatigue degree evaluation value calculation unit: calculates the fatigue degree evaluation value of the user within a single stay time period based on the user's heart rate data and step data within a single stay time period.

[0037] The preference calculation unit: obtains the fatigue degree evaluation values of the user within all stay time periods, and combines the stay time to calculate the user's preference for a single scenic spot.

[0038] Further, the preference similarity calculation and intelligent recommendation module includes a preference similarity calculation unit and an intelligent recommendation unit.

[0039] The preference similarity calculation unit: preset a fatigue degree evaluation mean threshold and a preference threshold; if the average value of the fatigue degree evaluation of the user within all stay time periods is greater than or equal to the fatigue degree evaluation mean threshold, and the user's preference for a single scenic spot is less than or equal to the preference threshold, it is determined that the user is fatigued and not fond of the scenic spot, and then reduce the scenic spots similar to this scenic spot in the subsequent route and add rest areas; if the average value of the fatigue degree evaluation of the user within all stay time periods is less than the fatigue degree evaluation mean threshold, and the user's preference for the scenic spot is greater than the preference threshold, it is determined that the user is not fatigued and is fond of the scenic spot, and then increase the scenic spots similar to this scenic spot in the subsequent route; after the dynamic adjustment of the user's route is completed, obtain the user's route and calculate the preference similarity between different users.

[0040] The intelligent recommendation unit: preset a preference similarity threshold. If the preference similarity between different users is greater than the preference similarity threshold, it is determined that the preferences of the users are similar, and then the route of this user is intelligently recommended to another user.

[0041] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: In a personalized intelligent recommendation system and method for cultural and tourism routes based on MR technology provided by the present invention, by authorizing users to wear bracelet-type MR devices, the optical heart rate sensor, acceleration sensor, and gyroscope are used to collect the heart rate and step data of users in real time, and the Bluetooth signal base stations in scenic spots are combined to accurately record the stay time of users, realizing the non-intrusive monitoring of the physiological state and motion state of users; Subsequently, the stay time of users in scenic spots is divided into multiple time periods, and the heart rate and step data are collected, so as to calculate the fatigue degree of users in a fine-grained manner, and the preference degree of users for scenic spots is evaluated in combination with the stay time; Based on the fatigue degree and preference degree of users, the recommended route is dynamically adjusted. For example, the arrangement of high-intensity scenic spots for high-fatigue users is reduced, and more similar scenic spots are recommended to high-preference users to optimize the travel experience; In addition, the preference similarity between users is calculated, enabling users with similar interests to share itinerary recommendations and improving the intelligence and socialization level of recommendations; Through accurate data collection, scientific fatigue calculation and preference evaluation, dynamic personalized adjustment, and intelligent recommendation mechanism, the present invention enables the recommendation system to adapt to the state and interests of users in real time, improves the tourism comfort and personalized experience, effectively breaks through the limitations of traditional static recommendation systems, and provides better tourism services. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention, and do not constitute a limitation to the present invention.

[0043] Figure 1 It is a schematic diagram of the steps of a personalized intelligent recommendation method for cultural and tourism routes based on MR technology of the present invention;

[0044] Figure 2 It is a schematic diagram of the structure of a personalized intelligent recommendation system for cultural and tourism routes based on MR technology of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0045] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0046] See also Figure 1 In the first embodiment, a personalized intelligent recommendation method for cultural and tourism routes based on MR technology is provided, and the method includes the following steps:

[0047] Step S1: After authorization by the user, obtain the user's heart rate data and step data; obtain the user's stay time at the scenic spot.

[0048] Specifically, after the user's authorization, a bracelet-type MR device is worn on the user's wrist, and the bracelet-type MR device has a built-in optical heart rate sensor, an acceleration sensor and a gyroscope; the optical heart rate sensor is used to monitor the user's heart rate data, and the acceleration sensor and gyroscope are used to monitor the user's step data.

[0049] Furthermore, a Bluetooth signal base station is built into the scenic spot along the cultural and tourism route, and the signal coverage range of the Bluetooth signal base station is the area range of the scenic spot; the wristband-type MR device obtains the user's stay time at the scenic spot by establishing a signal connection with the Bluetooth signal base station; the stay time is obtained by subtracting the time when the wristband-type MR device disconnects the signal connection with the Bluetooth signal base station from the time when the wristband-type MR device establishes a signal connection with the Bluetooth signal base station.

[0050] In the present invention, existing cultural and tourism route recommendations often lack accurate perception of users' real-time status and behavior, and this step solves the problem of how to obtain relevant data of users in cultural and tourism scenarios in real time and accurately, providing a rich and accurate data basis for subsequent personalized recommendations; for example, traditional recommendation systems may only make recommendations based on users' historical evaluations or simple scenic spot browsing records, but cannot know the user's actual experience in the scenic spot (such as fatigue level, etc.). This step can better measure the user's experience status by obtaining heart rate and step count data.

[0051] Step S2: evenly divide the residence time into a plurality of residence time periods.

[0052] Specifically, the time for the wristband MR device to establish a signal connection with the built-in Bluetooth signal base station of the i-th scenic spot is recorded as DSC i The time when the wristband MR device disconnects from the Bluetooth signal base station built into the i-th scenic spot is recorded as DSC i ; Based on the time to establish signal connection ESC i and disconnect signal time DSC i , the time the jth user spends at the i-th scenic spot is recorded as ΔT j,i =DSC j,i -DSC j,i .

[0053] The residence time ΔT of the j-th user in the i-th scenic spot j,i is evenly divided into N residence time periods, and the heart rate data and step count data of the user in the a-th residence time period are obtained, and the heart rate data and step count data are respectively denoted as HR j.i,a and SN j,i,a .

[0054] Step S3: Based on the heart rate data and step count data, calculate the fatigue degree evaluation value of the user in a single residence time period; based on the fatigue degree evaluation value, calculate the preference degree of the user for a single scenic spot.

[0055] Specifically, based on the heart rate data HR j,i,a and step count data SN j,i,a of the j-th user in the a-th residence time period, calculate the fatigue degree evaluation value of the user in the a-th residence time period, and the calculation formula is as follows:

[0056]

[0057] where FLA j,i,a represents the fatigue degree evaluation value of the j-th user in the a-th residence time period, α and β respectively represent the influence factors of the preset heart rate data and step count data, HR base represents the preset basic heart rate data, HR max represents the preset maximum heart rate data (generally obtained by subtracting the age from 220 to obtain the maximum heart rate data), SN max represents the preset maximum step count data (generally set by comprehensively considering factors such as personal age, physical condition, exercise foundation, and exercise purpose).

[0058] Furthermore, obtain the fatigue degree evaluation values of the j-th user in all residence time periods, and combine the residence time ΔT j,i , calculate the preference degree of the j-th user for the i-th scenic spot, and the calculation formula is as follows:

[0059]

[0060] where PD j,i represents the preference degree of the j-th user for the i-th scenic spot, γ and δ represent the influence factors of the preset residence time and fatigue degree evaluation value, PΔT j,i represents the planned residence time of the j-th user for the i-th scenic spot, represents the average value of the fatigue degree evaluation of the j-th user in all residence time periods.

[0061] In the present invention, when evaluating the user's preference for scenic spots in the prior art, the influence of the user's physical state during the tour on the preference is often ignored; by introducing the fatigue degree evaluation in this step, the true preference of the user for the scenic spots can be more accurately reflected. For example, if a user stays at a certain scenic spot for a long time, but the heart rate and the number of steps show that the user is in a highly fatigued state, then the traditional method may overestimate the user's preference for this scenic spot. However, the present invention can correct this deviation through the fatigue degree evaluation, making the preference calculation more accurate.

[0062] It should be noted that this formula comprehensively considers the user's stay behavior and physical state at the scenic spot. The stay time directly reflects the user's interest in the scenic spot, while the fatigue degree corrects the possible deviation brought by the stay time. For example, if a user stays at a certain scenic spot for a long time but is in a highly fatigued state, then the user's true preference for this scenic spot may not be as high as judged simply from the stay time. The formula makes a reasonable adjustment through the fatigue degree. Specifically, the first half of the formula considers the proportional relationship between the actual stay time of the user at the scenic spot and the planned stay time; if the actual stay time is relatively long compared to the planned stay time, it usually means that the user has a higher interest in this scenic spot, and it is multiplied by (the influence factor of the stay time) to adjust its weight in the preference calculation. The second half of the formula considers the overall fatigue degree of the user during the stay at the scenic spot, which is the average value of the fatigue degree evaluation during all stay time periods. The higher the fatigue degree, the smaller the value, which means that in a highly fatigued state, even if the stay time is long, the preference for the scenic spot will be affected. By adding the two parts together, the preference of the user for the scenic spot can be accurately calculated, providing a key basis for the personalized adjustment and intelligent recommendation of the cultural and tourism route.

[0063] Step S4: Preset the average threshold of the fatigue degree evaluation and the preference threshold, analyze and dynamically adjust the user's route; calculate the preference similarity between users, preset the preference similarity threshold, analyze and conduct intelligent route recommendation.

[0064] Specifically, preset the average threshold of the fatigue degree evaluation and the preference threshold of the j-th user for the i-th scenic spot.

[0065] Furthermore, if the average value of the fatigue degree evaluation of the j-th user during all stay time periods is greater than or equal to the average threshold of the fatigue degree evaluation, and the preference PD of the j-th user for the i-th scenic spot j,i is less than or equal to the preference threshold, it is determined that the j-th user is fatigued and not preferred for the i-th scenic spot. Then, reduce the scenic spots similar to the i-th scenic spot in the subsequent route and add a rest area.

[0066] If the average fatigue degree evaluation of the j-th user during the entire stay period is less than the fatigue degree evaluation mean threshold, and the preference degree PD of the j-th user for the i-th scenic spot j,i is greater than the preference degree threshold, it is determined that the j-th user is not fatigued and has a preference for the i-th scenic spot, and then a scenic spot similar to the i-th scenic spot is added to the subsequent route.

[0067] Furthermore, after the route dynamic adjustment of the j-th user is completed, obtain the route of the j-th user, and calculate the preference similarity between the j-th user and the k-th user. The calculation formula is as follows:

[0068]

[0069] where S j,k represents the preference similarity between the j-th user and the k-th user, PD k,i represents the preference degree of the k-th user for the i-th scenic spot, represents the average fatigue degree evaluation of the k-th user during the entire stay period.

[0070] Preset a preference similarity threshold. If the preference similarity S between the j-th user and the k-th user j,k is greater than the preference similarity threshold, it is determined that the j-th user and the k-th user have similar preferences, and then the route of the j-th user is intelligently recommended to the k-th user.

[0071] In the present invention, traditional cultural and tourism route recommendations are usually fixed and general, and cannot be dynamically adjusted according to the real-time status and preferences of users; this step solves the problem of how to optimize the route in real time according to user individual differences, and at the same time realizes intelligent recommendation based on user group characteristics through preference similarity calculation; for example, when a user is fatigued and has no preference for a certain scenic spot, the system can timely adjust the subsequent route, reduce similar scenic spots and increase rest areas to improve the user's cultural and tourism experience; when it is found that users have similar preferences, personalized routes are recommended, which can provide more users with route options that meet their needs.

[0072] It should be noted that this formula compares the proportional relationship between the preference degree PD j,i of the j-th user and the k-th user for the i-th scenic spot and PD k,i , and their average fatigue degree evaluation at this scenic spot and The proportional relationship is used to calculate the preference similarity. The preference degree reflects the user's preference for scenic spots, and the average value of fatigue degree evaluation reflects the user's physical state experience at the scenic spots. The combination of the two can more comprehensively measure the similarity between users in terms of their feelings and preferences for specific scenic spots. Specifically, by calculating the preference similarity between different users for specific scenic spots, it provides a basis for intelligent route recommendation based on user group characteristics. When it is found that the preference similarity between users is relatively high, the personalized route of one user can be recommended to another user to improve the accuracy and effectiveness of the recommendation.

[0073] Please refer to Figure 2 In the second embodiment: A personalized intelligent recommendation system for cultural and tourism routes based on MR technology is provided. The system includes: a data acquisition module, a time period division module, a fatigue degree evaluation value and preference degree calculation module, and a preference similarity calculation and intelligent recommendation module.

[0074] The data acquisition module: After obtaining user authorization, it acquires the user's heart rate data and step count data; and acquires the stay time of the user at the scenic spot.

[0075] The time period division module: evenly divides the stay time into multiple stay time periods.

[0076] The fatigue degree evaluation value and preference degree calculation module: Based on the heart rate data and step count data, calculates the fatigue degree evaluation value of the user within a single stay time period; and based on the fatigue degree evaluation value, calculates the preference degree of the user for a single scenic spot.

[0077] The preference similarity calculation and intelligent recommendation module: Presets the average fatigue degree evaluation threshold and preference degree threshold, analyzes and dynamically adjusts the user's route; calculates the preference similarity between users, presets the preference similarity threshold, analyzes and conducts intelligent route recommendation.

[0078] Further, the data acquisition module includes a data acquisition unit.

[0079] The data acquisition unit: After obtaining user authorization, wears a bracelet-type MR device on the user's wrist. The bracelet-type MR device is built-in with an optical heart rate sensor, an acceleration sensor, and a gyroscope; the optical heart rate sensor is used to monitor the user's heart rate data, and the acceleration sensor and gyroscope are used to monitor the user's step count data; a Bluetooth signal base station is built-in in the scenic spots of the cultural and tourism route, and the signal coverage range of the Bluetooth signal base station is the area range of the scenic spot; the bracelet-type MR device obtains the stay time of the user at the scenic spot by connecting with the Bluetooth signal base station; the stay time is obtained by subtracting the time when the bracelet-type MR device disconnects the signal connection with the Bluetooth signal base station from the time when the bracelet-type MR device establishes the signal connection with the Bluetooth signal base station.

[0080] Furthermore, the time period division module includes a time period division unit.

[0081] The time period division unit: evenly divides the user's stay time in the scenic spot into multiple stay time periods, and obtains the user's heart rate data and step count data within a single stay time period.

[0082] Furthermore, the fatigue degree evaluation value and preference calculation module includes a fatigue degree evaluation value calculation unit and a preference calculation unit.

[0083] The fatigue degree evaluation value calculation unit: calculates the fatigue degree evaluation value of the user within a single stay time period based on the user's heart rate data and step count data within a single stay time period.

[0084] The preference calculation unit: obtains the fatigue degree evaluation values of the user within all stay time periods, and combines the stay time to calculate the user's preference for a single scenic spot.

[0085] Furthermore, the preference similarity calculation and intelligent recommendation module includes a preference similarity calculation unit and an intelligent recommendation unit.

[0086] The preference similarity calculation unit: presets a fatigue degree evaluation mean threshold and a preference degree threshold; if the average value of the fatigue degree evaluation of the user within all stay time periods is greater than or equal to the fatigue degree evaluation mean threshold, and the user's preference for a single scenic spot is less than or equal to the preference degree threshold, it is determined that the user is fatigued and not fond of this scenic spot, then reduce the scenic spots similar to this scenic spot in the subsequent route and add a rest area; if the average value of the fatigue degree evaluation of the user within all stay time periods is less than the fatigue degree evaluation mean threshold, and the user's preference for this scenic spot is greater than the preference degree threshold, it is determined that the user is not fatigued and is fond of this scenic spot, then increase the scenic spots similar to this scenic spot in the subsequent route; after the dynamic adjustment of this user's route is completed, obtain the user's route and calculate the preference similarity between different users.

[0087] The intelligent recommendation unit: presets a preference similarity threshold, if the preference similarity between different users is greater than the preference similarity threshold, it is determined that the preferences of the users are similar, then intelligently recommends this user's route to another user.

[0088] It should be noted that, in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device.

[0089] Finally, it should be noted that the above are only preferred embodiments of the present invention and are not used to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A personalized intelligent recommendation method for cultural and tourism routes based on MR technology, characterized in that: The method comprises the following steps: Step S1: After authorization by the user, obtain the user's heart rate data and step data; obtain the user's stay time at the scenic spot; Step S2: evenly divide the residence time into a plurality of residence time periods; Step S3: Calculate the user's fatigue level evaluation value in a single stay period based on the heart rate data and the step count data; Calculate the user's preference for a single scenic spot based on the fatigue level evaluation value; Step S4: preset fatigue level assessment mean threshold and preference threshold, analyze and dynamically adjust the user's route; calculate preference similarity between users, preset preference similarity threshold, analyze and make intelligent route recommendations.

2. According to claim 1, a personalized intelligent recommendation method for cultural and tourism routes based on MR technology is characterized in that: The specific implementation process of step S1 includes: After authorization by the user, the user wears a wristband-type MR device on his wrist, wherein the wristband-type MR device has an optical heart rate sensor, an acceleration sensor and a gyroscope built in; the optical heart rate sensor is used to monitor the user's heart rate data, and the acceleration sensor and the gyroscope are used to monitor the user's step data; A Bluetooth signal base station is built into the scenic spot along the cultural and tourism route, and the signal coverage range of the Bluetooth signal base station is the area range of the scenic spot; the bracelet-type MR device obtains the user's stay time at the scenic spot by establishing a signal connection with the Bluetooth signal base station; the stay time is obtained by subtracting the time when the bracelet-type MR device disconnects the signal connection with the Bluetooth signal base station from the time when the bracelet-type MR device establishes a signal connection with the Bluetooth signal base station.

3. According to claim 2, a personalized intelligent recommendation method for cultural and tourism routes based on MR technology is characterized in that: The specific implementation process of step S2 includes: The time for the wristband MR device to establish a signal connection with the built-in Bluetooth signal base station of the i-th scenic spot is recorded as ESC i The time when the wristband MR device disconnects from the Bluetooth signal base station built into the i-th scenic spot is recorded as DSC i ; Based on the time to establish signal connection ESC i and disconnect signal time DSC i , the time the jth user spends at the i-th scenic spot is recorded as ΔT j,i =DSC j,i -ESC j,i ; The stay time ΔT of the jth user in the i-th scenic spot j,i The user's heart rate data and step count data in the ath stay time period are obtained, and the heart rate data and step count data are recorded as HR j.i,a and SN j,i,a .

4. According to claim 3, a personalized intelligent recommendation method for cultural and tourism routes based on MR technology is characterized in that: The specific implementation process of step S3 includes: Based on the heart rate data HR of the jth user in the ath stay time period j,i,a and step count data SN j,i,a , calculate the user's fatigue level evaluation value in the a-th stay time period, the calculation formula is as follows: Among them, FLA j,i,a represents the fatigue level evaluation value of the jth user in the ath stay time period, α and β represent the influencing factors of the preset heart rate data and step data, respectively. base Indicates the preset basic heart rate data, HR max Indicates the preset maximum heart rate data, SN max Indicates the preset maximum number of steps data; Get the fatigue level evaluation value of the jth user during the entire stay period, combined with the stay time ΔT j,i , calculate the preference of the jth user for the i-th scenic spot, the calculation formula is as follows: Among them, PD j,i represents the preference of the jth user for the ith scenic spot, γ and δ represent the influencing factors of the preset stay time and fatigue evaluation value, PΔT j,i represents the planned stay time of the jth user at the i-th scenic spot, It represents the mean fatigue evaluation value of the jth user during the entire stay period.

5. According to claim 4, a personalized intelligent recommendation method for cultural and tourism routes based on MR technology is characterized in that: The specific implementation process of step S4 includes: Preset the fatigue level assessment mean threshold and the preference threshold of the j-th user for the i-th scenic spot; If the jth user's fatigue level evaluation mean value during all the stay time periods is is greater than or equal to the fatigue level evaluation mean threshold, and the jth user's preference for the i-th scenic spot PD j,i If the jth user is less than or equal to the preference threshold, it is determined that the jth user is tired and has no preference for the ith scenic spot, and then the scenic spots similar to the ith scenic spot are reduced in the subsequent route, and a rest area is added; If the jth user's fatigue level evaluation mean value during all the stay time periods is is less than the fatigue level evaluation mean threshold, and the jth user's preference for the i-th scenic spot PD j,i If the jth user is not tired and has a preference for the ith scenic spot, then a scenic spot similar to the ith scenic spot is added to the subsequent route; When the jth user's route is dynamically adjusted, the jth user's route is obtained, and the preference similarity between the jth user and the kth user is calculated. The calculation formula is as follows: Among them, S j,k represents the preference similarity between the jth user and the kth user, PD j,i represents the preference of the kth user for the i-th scenic spot, represents the mean fatigue evaluation value of the kth user during the entire stay period; Preset preference similarity threshold, if the preference similarity S between the jth user and the kth user j,k If the preference similarity is greater than the preference similarity threshold, it is determined that the j-th user has similar preferences to the k-th user, and the route of the j-th user is intelligently recommended to the k-th user.

6. A personalized intelligent recommendation system for cultural and tourism routes based on MR technology, which executes a personalized intelligent recommendation method for cultural and tourism routes based on MR technology as described in any one of claims 1 to 5, characterized in that: The system comprises: a data acquisition module, a time period division module, a fatigue degree evaluation value and preference calculation module, and a preference similarity calculation and intelligent recommendation module; The data acquisition module: after authorization by the user, acquires the user's heart rate data and step data; acquires the user's stay time at the scenic spot; The time period division module is used to evenly divide the residence time into a plurality of residence time periods; The fatigue evaluation value and preference calculation module: calculates the fatigue evaluation value of the user in a single stay period based on the heart rate data and the step count data; calculates the user's preference for a single scenic spot based on the fatigue evaluation value; The preference similarity calculation and intelligent recommendation module: presets the fatigue level assessment mean threshold and preference threshold, analyzes and dynamically adjusts the user's route; calculates the preference similarity between users, presets the preference similarity threshold, analyzes and performs intelligent route recommendation.

7. The personalized intelligent recommendation system for cultural and tourism routes based on MR technology according to claim 6 is characterized by: The data acquisition module includes a data acquisition unit; The data acquisition unit: after authorization by the user, a bracelet-type MR device is worn on the user's wrist, and the bracelet-type MR device is equipped with an optical heart rate sensor, an acceleration sensor and a gyroscope; the optical heart rate sensor is used to monitor the user's heart rate data, and the acceleration sensor and the gyroscope are used to monitor the user's step data; a Bluetooth signal base station is built in the scenic spot on the cultural and tourism route, and the signal coverage range of the Bluetooth signal base station is the area range of the scenic spot; the bracelet-type MR device obtains the user's stay time at the scenic spot by establishing a signal connection with the Bluetooth signal base station; the stay time is obtained by subtracting the time when the bracelet-type MR device disconnects the signal connection with the Bluetooth signal base station from the time when the bracelet-type MR device establishes a signal connection with the Bluetooth signal base station.

8. The personalized intelligent recommendation system for cultural and tourism routes based on MR technology according to claim 7 is characterized by: The time period division module includes a time period division unit; The time period division unit is used to evenly divide the user's stay time in the scenic spot into a plurality of stay time periods, and obtain the user's heart rate data and step count data in a single stay time period.

9. The personalized intelligent recommendation system for cultural and tourism routes based on MR technology according to claim 8, characterized in that: The fatigue level evaluation value and preference calculation module includes a fatigue level evaluation value calculation unit and a preference calculation unit; The fatigue level evaluation value calculation unit calculates the fatigue level evaluation value of the user in a single stay time period based on the user's heart rate data and step count data in a single stay time period; The preference calculation unit is used to obtain the fatigue evaluation value of the user in the entire stay time period, and calculate the user's preference for a single scenic spot in combination with the stay time.

10. The personalized intelligent recommendation system for cultural and tourism routes based on MR technology according to claim 9, characterized in that: The preference similarity calculation and intelligent recommendation module includes a preference similarity calculation unit and an intelligent recommendation unit; The preference similarity calculation unit: presets a fatigue level evaluation mean threshold and a preference threshold; If the user's fatigue level evaluation mean value in all the stay time periods is greater than or equal to the fatigue level evaluation mean value threshold, and the user's preference for a single scenic spot is less than or equal to the preference value threshold, it is determined that the user is fatigued and does not prefer the scenic spot, and scenic spots similar to the scenic spot are reduced in the subsequent route, and a rest area is added; if the user's fatigue level evaluation mean value in all the stay time periods is less than the fatigue level evaluation mean value threshold, and the user's preference for the scenic spot is greater than the preference value threshold, it is determined that the user is not fatigued and prefers the scenic spot, and scenic spots similar to the scenic spot are added in the subsequent route; after the dynamic adjustment of the user's route is completed, the user's route is obtained, and the preference similarity between different users is calculated; The intelligent recommendation unit: presets a preference similarity threshold, and if the preference similarity between different users is greater than the preference similarity threshold, it is determined that the preferences between the users are similar, and the route of the user is intelligently recommended to another user.

Images