A sightseeing recommendation method and device based on human light scene perception

Abstract

The present application belongs to the technical field of computer, and provides a tour recommendation method based on human light scene perception, comprising: acquiring a predicted time period corresponding to a target tour time and a light climate prediction type, and acquiring a travel distance representation between scenic spots in a scenic area; acquiring light scene experience evaluation of the scenic spots under the predicted time period and the light climate prediction type from a light scene experience relationship table; combining the light scene experience evaluation of the scenic spots and the travel distance representation between the scenic spots, determining an optimal tour route for the target tour time, the optimal tour route passing through different scenic spots and taking a scenic area entrance as a starting point and a scenic area exit as an ending point; and recommending the optimal tour route to a tourist; the present application further provides a tour recommendation device based on human light scene perception; the optimal tour route can be guided by human perception of light scenes, can improve recommendation accuracy, and further improve experience satisfaction of tourists.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and in particular to a method and apparatus for recommending tours based on human perception of light and scenery. Background Technology

[0002] To enhance the tourist experience, existing metaverse virtual tourism systems use physiological triggering devices to stimulate senses in real time and receive feedback data, creating various virtual tourism scenarios and experiences. Existing cultural tourism big data platforms centrally manage and process data through a central management module, while simultaneously connecting with a power monitoring module to simultaneously detect and display multiple data points. These existing tourism systems primarily focus on creating rich, multi-layered tourism experiences by collecting user experience data to manage the digital universe optimization process and monitor scenic area conditions in real time, thus scheduling scenic area information. In terms of experience, they tend to focus on the user's personal, general tour experience, prioritizing subjective (blind) experiences and lacking a focus on human perception. Specifically, they lack tourism experiences guided by human perception of light and scenery (visual perception), resulting in insufficient tourist satisfaction and failing to develop targeted management methods for scenic areas based on the tourist population.

[0003] Among them, "light and scenery" refers to a landscape composed of light sources, objects, light and shadow, and their changes, or a landscape that evokes a strong visual impression through light sources, light and shadow, and their changes. In the triangular relationship between people, environment, and space, "light and scenery" emphasizes people's perception under different lighting conditions. Summary of the Invention

[0004] The present invention aims to solve the technical problem that existing tour recommendation methods lack guidance based on human perception of light and scenery, resulting in insufficient tourist satisfaction. The invention provides a tour recommendation method and device based on human perception of light and scenery.

[0005] To achieve the above-mentioned objectives of the present invention, according to a first aspect of the present invention, the present invention provides a tour recommendation method based on human perception of light and scenery, comprising: obtaining a predicted time period and a light and climate prediction type corresponding to a target tour time; obtaining a representation of the travel distance between attractions within a scenic area; obtaining a light and scenery experience evaluation of attractions under the predicted time period and light and climate prediction type from a light and scenery experience relationship table; combining the light and scenery experience evaluation of attractions and the representation of the travel distance between attractions to determine the optimal tour route under the target tour time, wherein the optimal tour route passes through different attractions and starts at the scenic area entrance and ends at the scenic area exit; and recommending the optimal tour route to tourists.

[0006] To achieve the above-mentioned objectives of the present invention, according to a second aspect of the present invention, the present invention provides a tour recommendation device based on human light and scenery perception, used to implement the tour recommendation method based on human light and scenery perception described in the first aspect of the present invention, comprising: a data acquisition module, for acquiring a predicted time period and a light and climate prediction type corresponding to a target tour time, and acquiring a representation of the travel distance between attractions within a scenic area; a query module, for acquiring light and scenery experience evaluations of attractions under the predicted time period and light and climate prediction type from a light and scenery experience relationship table; an optimal tour route determination module, for determining the optimal tour route under the target tour time by combining the light and scenery experience evaluations of attractions and the representation of the travel distance between attractions, wherein the optimal tour route passes through different attractions and starts at the scenic area entrance and ends at the scenic area exit; and a recommendation module, for recommending the optimal tour route to tourists.

[0007] The beneficial technical effects of this invention are as follows: First, this invention obtains the predicted time period and light climate prediction type corresponding to the target visit time. Then, based on the pre-constructed light and scenery experience relationship table, it queries the light and scenery experience evaluation under the predicted time period and light climate prediction type. Based on the queried light and scenery experience evaluation and the distance representation between attractions within the scenic area, it determines the optimal visit route that can balance the light and scenery experience evaluation and the travel distance representation under the target visit time. The obtained optimal visit route can be guided by people's perception of light and scenery (light and scenery experience evaluation), rather than the traditional method of simply recommending visit routes based on extensive user subjective experience satisfaction data analysis. This invention can improve the recommendation accuracy, thereby improving tourists' experience satisfaction and facilitating targeted management of scenic area operations. Attached Figure Description

[0008] Figure 1 This is a flowchart illustrating a preferred embodiment of the tour recommendation method based on human perception of light and scenery according to the present invention.

[0009] Figure 2 This is a flowchart illustrating the implementation of a tour recommendation method based on human light and scenery perception in one application scenario of the present invention.

[0010] Figure 3 This is a schematic diagram illustrating the principle of measuring indoor illuminance information at scenic spots in a preferred embodiment of the present invention.

[0011] Figure 4 This is a schematic diagram illustrating the principle of measuring outdoor illuminance information at scenic spots in a preferred embodiment of the present invention.

[0012] Figure 5 This is a schematic diagram of the process of acquiring scenic spot brightness information in a preferred embodiment of the present invention. Detailed Implementation

[0013] Embodiments of the present invention are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0014] In the description of this invention, it should be understood that the terms "longitudinal", "lateral", "up", "down", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0015] In the description of this invention, unless otherwise specified and limited, it should be noted that the terms "installation", "connection" and "linking" should be interpreted broadly. For example, they can refer to mechanical or electrical connections, or internal connections between two components. They can be direct connections or indirect connections through an intermediate medium. Those skilled in the art can understand the specific meaning of the above terms according to the specific circumstances.

[0016] The execution entity of the human-based light scene perception-based tour recommendation method provided by this invention includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in the embodiments of this application: a server, a terminal, etc. In other words, the human-based light scene perception-based tour recommendation method provided by this invention can be executed by software or hardware installed on a terminal device or a server device. The software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0017] This invention provides a tour recommendation method based on human perception of light and scenery. In a preferred embodiment, such as... Figure 1 and Figure 2 As shown, it includes:

[0018] Step S1: Obtain the predicted time period and light climate prediction type corresponding to the target visit time, and obtain the travel distance representation between attractions within the scenic area.

[0019] In this embodiment, the scenic area is preferably, but not limited to, a park, garden, or exhibition area. The scenic area includes multiple attractions, and the travel distance between any two attractions is obtained. The travel distance between two attractions is linearly mapped to a dimensionless numerical interval, and the mapped value obtained within this interval is used as the travel distance between the two attractions for subsequent calculations. The numerical interval is preferably, but not limited to, [1,2], [1,10], etc. The inventors, through analysis of a large amount of tourist visit data from 9:00 to 17:00, found that dividing the visit time of the scenic area into three time periods—morning, noon, and afternoon—can basically cover most tourist visit time types. Generally, the morning period refers to 9:00-12:00, the noon period refers to 12:00-14:00, and the afternoon period refers to 14:00-17:00. In one example, assuming the target visit time is 10:00 AM on [Date], the predicted time period is morning. The light climate type for either the morning of [Date] or 10:00 AM on [Date] is obtained from the weather forecast platform and used as the light climate prediction type. Light climate refers to the local outdoor illumination conditions and the sum of meteorological factors influencing its changes. It mainly consists of the average natural light conditions formed by direct sunlight, diffused skylight, and reflected ground light. Light climate types include sunny day with high solar altitude angle, sunny day with low solar altitude angle, all cloudy, cloudy turning sunny, overcast, and rainy. Different light climate types represent different illuminance levels, resulting in different visual landscapes and varying visitor experiences.

[0020] Step S2: Obtain the scenic experience evaluation of the attraction under the predicted time period and light climate prediction type from the scenic experience relationship table.

[0021] A pre-constructed and stored light and scene experience relationship table is used. This table includes light and scene experience evaluations for each scenic spot under different time periods and light climate types. Each scenic spot has multiple light and scene experience evaluations. A unique light and scene experience evaluation is determined from these multiple evaluations based on the predicted time period and light climate prediction type. The light and scene experience relationship table establishes a link between measured light and scene data and subjective human evaluations.

[0022] Step S3: Combining the scenic experience evaluation of the attractions and the travel distance between attractions, determine the optimal tour route for the target tour time. The optimal tour route can balance the scenic experience evaluation and the travel distance. The optimal tour route passes through different attractions and starts from the entrance of the scenic area and ends at the exit of the scenic area.

[0023] In this embodiment, the scenic area may include multiple entrances and multiple exits. This application allows the main entrance to be preset for ease of management, while any exit can be any point within the scenic area. The optimal tour route passing through different attractions indicates that the attractions it includes are not repeated. Generally, on the one hand, the longer the travel distance within a scenic area, the higher the tourist fatigue level, which negatively impacts the tour experience; on the other hand, being able to visit more interesting attractions helps improve tour experience satisfaction. Therefore, the optimal tour route of this application can balance the evaluation of scenic experience and the travel distance representation to maximize tourist experience satisfaction.

[0024] Step S4: Recommend the best tour route to tourists.

[0025] In this embodiment, it is preferred, but not limited to, recommending the best tour route to tourists through a tourist terminal application (APP) or display devices or broadcasting devices at the scenic area entrance.

[0026] In a preferred embodiment, in order to establish an accurate link between the scenery and the tourist's subjective evaluation system, and to form a quantifiable evaluation system for the perception of scenery, thereby achieving precise tour route recommendations, such as... Figure 2 As shown, the process of constructing the light and scene experience relationship table includes:

[0027] Step B1: Construct multiple dimensions for evaluating the lighting experience. Preferably, four dimensions are constructed: light comfort, light perception, visual impression, and light environment experience. The weights of these four dimensions are determined and denoted as w1, w2, w3, and w4. Each dimension is based on the objective environmental conditions of the landscape node. A five-point Likert scale (four sets of questions for the four dimensions) is used to assess the factors that primarily influence a given dimension. Within each dimension, all questions have equal weight.

[0028] Step B2: Obtain ratings from multiple tourists for each scenic spot's lighting experience across different time periods and light climate types, across each light and weather dimension.

[0029] The five-level options of the scale are quantified as 5, 4, 3, 2, and 1. For each scenic spot, at each time period, and under each light and climate type, the score for each tourist's evaluation of each light and scenery experience dimension is calculated as follows: the average score of a set of items for that light and scenery experience evaluation dimension is calculated to obtain the score for that light and scenery experience evaluation dimension. Let the scores for the four light and scenery experience evaluation dimensions be a, b, c, and d.

[0030] In this embodiment, to improve accuracy, a reliability analysis of the survey results using a five-point Likert scale is performed.

[0031] The specific steps are as follows:

[0032] 1) Summarize the answer data for each question in each group of each scene experience evaluation dimension.

[0033] 2) Use SPSSAU for reliability analysis and calculate the Cronbach's alpha coefficient ε:

[0034]

[0035] Where K is the number of questions in each group, and S v S represents the variance of the scores of all tourists for the v-th question in each set of questions. T 2 This represents the variance of the total scores of all tourists for the K questions in each set of questions.

[0036] 3) If the Cronbach's coefficient ε is above 0.7, the questionnaire can be further calculated and analyzed; otherwise, the scale should be redesigned or the items adjusted.

[0037] Step B3: Based on the ratings of multiple tourists for each scenic spot under different light and climate conditions at different time periods, obtain the measured light and climate experience evaluation of each scenic spot under different light and climate conditions at different time periods.

[0038] For each tourist at each time period and under each light climate type, the weighted average score of the four light experience evaluation dimensions is calculated based on their respective weights:

[0039] E1=(a*w1+b*w2+c*w3+d*w4) / (w1+w2+w3+w4);

[0040] For each attraction, each time period, and each light climate type, calculate the weighted average of the scores from all tourists across the four dimensions of light experience evaluation. Use this average as the measured light experience evaluation for each attraction, each time period, and each light climate type.

[0041] The above process was repeated at different time periods under different light climate types (weather) at various scenic spots to obtain the light and scenery experience evaluation of each scenic spot in three time periods throughout the day under various light climate types, which is also the measured light and scenery experience evaluation of each scenic spot under different conditions.

[0042] Step B4 involves constructing a light experience relationship table using measured light experience evaluations of each attraction at different time periods and under different light climate types. Specifically, the measured light experience evaluations are directly used as the overall light experience evaluation. The light experience relationship table includes a storage tree corresponding to all attractions. Each attraction corresponds to a four-level storage tree. The first-level nodes consist of only one root node, representing the attraction. Second-level nodes are all connected to the root node of the first level, and each second-level node contains multiple second-level nodes, each representing a time period. Each second-level node is connected to multiple third-level nodes, each representing a light climate type. Each third-level node is connected to only one fourth-level node (leaf node), and each leaf node represents a light experience evaluation.

[0043] In a preferred embodiment, to enrich the evaluation data and improve the accuracy of the lighting experience evaluation in the lighting experience relationship table, such as... Figure 2 As shown, the process of constructing the light and scene experience relationship table also includes:

[0044] Step C1: Obtain optical data for each scenic spot under different light climate types at different time periods. The optical data includes illuminance information and brightness information of the scenic spot.

[0045] In this embodiment, the illuminance information of the scenic spot includes indoor illuminance and outdoor illuminance. The principle of indoor illuminance measurement is as follows: Figure 3 As shown, either the four-corner point method or the center point method is used. During actual measurements, measurement points are set up starting from the indoor entrance of the scenic spot. For the measurement of illuminance at the entrance, the four-corner point method is used, measuring illuminance at the four corners of the light-receiving opening and then calculating the average. For the measurement of illuminance on the indoor floor of the scenic spot, the center point method is used. The grid size is generally 2m, and the grid shape is square or approximately square. During the time period of 9:00-17:00 under various light climate types, the average illuminance at the indoor entrance of the scenic spot and the illuminance at multiple measurement points inside the scenic spot are recorded every hour. The principle of outdoor illuminance measurement is as follows... Figure 4 As shown, select an unobstructed open space around the scenic spot. The occlusion angle α formed by the light receiver and surrounding obstructions should be less than 10°, or the ratio of l to the height h of the obstruction should be greater than 6. Figure 4 When measuring outdoor illuminance, the receiver should be placed horizontally to avoid the influence of ground reflections. Illuminance should be measured at points evenly spaced in a 2m grid on the outdoor ground surface. Measure the illuminance at each point for each hour, and calculate the average illuminance for that hour and area. Summarize the data for the entire day, calculating the average illuminance over three time periods, which represents the average outdoor illuminance value for that location under the given light climate conditions. All recorded data from indoor and outdoor illuminance measurements constitute the illuminance information for the scenic spot under different time periods and light climate types.

[0046] Step C2: Construct a virtual model for each scenic spot, and use optical data of each scenic spot under different light and climate types at different times to render the virtual model of each scenic spot to obtain the rendered model.

[0047] In this embodiment, a virtual model of each scenic spot can be constructed using existing oblique photogrammetry methods. Multiple rendering models are obtained in step C2, each model simulating the real lighting conditions of a scenic spot under a specific light climate type over a certain time period.

[0048] Step C3: Obtain the ratings of the rendered model from multiple tourists across multiple visual experience evaluation dimensions.

[0049] Step C4 involves obtaining virtual light and shadow experience evaluations for each attraction at different times and under different light and weather conditions based on the ratings of multiple tourists on the rendered model across multiple light and shadow experience evaluation dimensions. Preferably, the tourist rating for each rendered model is obtained by weighted summation of each tourist's ratings across multiple light and shadow experience evaluation dimensions according to the weight of each light and shadow experience evaluation dimension. Then, the average of all tourist ratings for each rendered model is taken to obtain the virtual light and shadow experience evaluation for each rendered model, thus obtaining the virtual light and shadow experience evaluations for each attraction at different times and under different light and weather conditions.

[0050] Step C5: Construct a light and shadow experience relationship table by combining the measured light and shadow experience evaluations and virtual light and shadow experience evaluations for each scenic spot at different time periods and under different light and climate types. Preferably, the measured light and shadow experience evaluations and virtual light and shadow experience evaluations for each scenic spot at different time periods and under different light and climate types are weighted and summed to obtain the light and shadow experience evaluations for each scenic spot at different time periods and under different light and climate types. The light and shadow experience relationship table can be constructed according to the method in step B4 above.

[0051] In this embodiment, to accurately obtain the brightness information of the scenic spot, refer to Figure 5 As shown, the process of obtaining the brightness information of each scenic spot under different time periods and light climate types includes:

[0052] Step D1: Take multiple original images of the scenic spot at different exposures from a preset viewing angle. All original images should include multiple reference points set up at the same location. The preset viewing angle can be the main perspective for tourists visiting the scenic spot, such as a direct viewpoint. Figure 5 The example shown acquires seven original images with different exposure intensities (overexposed, normally exposed, and underexposed) from a preset viewpoint. Four reference points are set at the center of the multiple original images, and these four reference points are distributed in a matrix.

[0053] Step D2: Use Photoshop to combine multiple original images into an HDR image. HDR images, or High Dynamic Range images, offer a wider dynamic range and richer detail compared to ordinary images, better reflecting the visual effects of the real environment.

[0054] Step D3: Import the HDR image into an HDR image editing and analysis tool for Falsecolor analysis to generate a luminance falsecolor map; the HDR image editing and analysis tool is preferably, but not limited to, HDRscope. Falsecolor analysis mainly highlights the luminance information of the HDR image by artificially assigning different colors to it.

[0055] Step D4: Obtain the average brightness of multiple reference points in multiple original images, denoted as the first average brightness; obtain the average brightness of multiple reference points in the brightness pseudo-color map, denoted as the second average brightness; compare the consistency between the second average brightness and the first average brightness to obtain the brightness comparison result.

[0056] Step D5: Based on the brightness comparison results, continuously adjust the exposure of the HDR image in Photoshop until the second average brightness value matches the first average brightness value (matching can mean the same value or the difference between the two is within an allowable range). Then, use the brightness of the adjusted HDR image and multiple reference points in the brightness pseudo-color map as the brightness information of the scenic spot.

[0057] In a preferred embodiment, to improve the accuracy of the scenic experience evaluation in the revised scenic experience relationship table, after the above-mentioned tour recommendation method is implemented, a step of revising the scenic experience relationship table is further included:

[0058] Step E1 involves receiving perception evaluations uploaded from multiple visitor terminals. Specifically, visitor terminals can be configured with a mini-program or link for uploading perception evaluations.

[0059] Step E2: Calculate the average e and standard deviation σ of multiple perceived evaluations, and then calculate the reliability Z of the perceived evaluation X using the following formula:

[0060]

[0061] Step E3: Iterate through all perception evaluations. If the confidence level Z of perception evaluation X exceeds ±3, then remove perception evaluation X; otherwise, retain perception evaluation X. This can remove outliers.

[0062] Step E4 involves fusing all retained perception evaluations with the corresponding time periods and light climate types in the light experience relationship table after the traversal is complete. The corresponding time periods and light climate types can be obtained as follows: when tourists upload their perception evaluations, they simultaneously upload the transmission time; the corresponding time period is obtained based on the transmission time, and the corresponding light climate type is obtained from the weather forecast platform based on the transmission time. Alternatively, tourists can simultaneously upload the time period of their visit and the light climate type at that time. The specific fusion process can be as follows: calculate the average or weighted average of all retained perception evaluations and the corresponding time periods and light climate types in the light experience relationship table; use this average or weighted average as the updated value of the corresponding time periods and light climate types in the light experience relationship table.

[0063] In this embodiment, more preferably, when the tourist terminal uploads the perception evaluation, the tourist terminal (such as a smartphone or smart tablet) also uses the software Light Meter photometer in incident light metering mode (the front camera of the smartphone is perpendicular to the light source) to measure the brightness data of the location of the smartphone under direct sunlight, and uploads the brightness data display screenshot or brightness data as the brightness information of the new scenic spot. After obtaining the brightness information of the new scenic spot, the corresponding leaf node is found from the light and scenery experience relationship table according to the current time period and current light climate type determined above, and the original scenic spot brightness information associated with the leaf node is replaced with the new scenic spot brightness information so as to render the virtual model of the scenic spot in the future.

[0064] This implementation method uses the verification of tourist authenticity to correct the scenic experience evaluation in the scenic experience relationship table. Therefore, as the number of users increases and the operating time increases, the accuracy of the scenic experience relationship table continuously improves, thereby continuously improving the accuracy of the optimal tour route recommendation, enhancing user satisfaction and the professionalism of the recommendation.

[0065] In a preferred embodiment, to improve the efficiency of human resource scheduling in scenic areas and to establish daily and emergency management models for different weather conditions in advance, the above method also includes predicting visitor flow based on the optimal tour route, including:

[0066] Step F1: Obtain the average historical visitor flow for each attraction in the optimal tour route during the predicted time period corresponding to the target tour time under all light and weather types, and record it as the historical visitor flow average.

[0067] Step F2: Adjust the historical average visitor flow of each attraction in the optimal tour route based on the light experience evaluation of each attraction under the predicted time period and light climate prediction type at the target tour time, to obtain the predicted visitor flow of each attraction at the target tour time. Specifically, the light experience evaluation of each attraction under the predicted time period and light climate prediction type at the target tour time can be linearly mapped to a numerical interval, which can be [1,2]. Use the mapped value as a weight, and weight the historical average visitor flow of each attraction to obtain the predicted visitor flow of each attraction at the target tour time.

[0068] Step F3 outputs the predicted visitor flow for each attraction in the optimal tour route during the target tour time.

[0069] In a preferred embodiment, to achieve automated and highly accurate acquisition of the optimal tour route, step S3, determining the optimal tour route for the target tour time, includes:

[0070] Step A1: Initialize the pheromone concentration of the path segments between attractions. Treat attractions as nodes. The scenic area entrance and exit are both treated as special nodes, with a visual experience rating of 0.

[0071] Step A2: Perform iterative search until the preset maximum number of searches T is reached. The t-th search process includes:

[0072] Step a: Release all ants at the entrance of the scenic area and initialize the taboo list for each ant. The taboo list is used to store the scenic spots that each ant has visited in this search.

[0073] Step b: Each ant selects the next attraction according to the selection probability and updates the taboo table until each ant reaches the exit of the scenic area or enters a deadlock state; the deadlock state means that the ants are stuck in a loop or cannot move forward in the process of finding the optimal path.

[0074] Step c: Discard the ants that have entered a deadlock state, and update the pheromone concentration of the path segments in the path taken by the ants reaching the scenic area exit; the pheromone concentration update formula for the path segment (i,j) in a certain path S is as follows:

[0075] τ ij (t+1)←(1-ρ)·τ ij (t)+Δτ ij

[0076] ρ represents the evaporation coefficient, a positive number less than 1, typically taken as 0.5. τ ij (t) represents the pheromone concentration of path segment (i,j) in path S during the t-th search, τ ij(t + 1) represents the pheromone concentration of the path segment (i, j) in the path S at the (t + 1)-th search; Δτ ij represents the increment of the pheromone concentration of the path segment (i, j) in the path S:

[0077]

[0078] where Q is a constant used to adjust the scale of the pheromone increment.

[0079] Step d, if t < T, then enter the (t + 1)-th search, if t ≥ T, then enter Step A3;

[0080] Step A3, calculate the fitness of all the passing paths of the ants that reach the scenic area exit obtained from the T-th search, and select the passing path with the maximum fitness as the optimal tour route for the target tour time;

[0081] where the fitness calculation formula of the passing path S is:

[0082]

[0083] i and j respectively represent the scenic spot indexes, i ≠ j, k represents the number of scenic spots on the passing path S, E(i, t g ) represents the scenery experience evaluation of scenic spot i under the predicted time period and light climate prediction type corresponding to the target tour time t g (i, j) represents a path segment in the passing path S, D(i, j) represents the travel distance of the path segment (i, j), and T is a positive integer. [[ID=二十九]]

[0084] In this embodiment, further preferably, in Step A2, the selection probability calculation formula for each ant to select the next scenic spot j at scenic spot i is:

[0085]

[0086] where i, j, and m are all scenic spot indexes, i ≠ j, allowed represents the set of all scenic spots in the scenic area except the scenic spots in the taboo list of each ant, j, m ∈ allowed; τ ij represents the pheromone concentration of the path segment from scenic spot i to scenic spot j, τ im represents the pheromone concentration of the path segment from scenic spot i to scenic spot m; δ ij represents the heuristic function for the ant to select scenic spot j as the next scenic spot at scenic spot i, δ im represents the heuristic function for the ant to select scenic spot m as the next scenic spot at scenic spot i, α represents the first adjustment parameter, generally taking values between 1 and 2; β represents the second adjustment parameter, generally taking values between 2 and 5.

[0087] This implementation method is based on intelligent bionic algorithms, combined with real-time lighting experience data and distances between attractions, to generate the optimal tour route for users, thereby improving the accuracy and applicability of the optimal tour route.

[0088] In a preferred embodiment, step S3, determining the optimal tour route for the target tour time, includes:

[0089] Step G1: Enumerate all candidate paths. Each candidate path starts at the scenic area entrance and ends at the scenic area exit, passing through k attractions without repetition, where k∈[1,n] and n represents the number of attractions in the scenic area.

[0090] Step G2: Calculate the objective function value for each candidate path, and select the candidate path with the largest objective function value as the optimal tour route for the target tour time;

[0091] The objective function formula is as follows:

[0092]

[0093] S' represents a candidate path, where i and j are the indices of attractions on the candidate path S', and E(i,t) g () indicates that attraction i is within the target visit time t. g The evaluation of the light and scenery experience under the corresponding predicted time period and light climate prediction type; (i,j) represents a path segment in the route S', and D(i,j) represents the travel distance of the path segment (i,j); T i Let represent the estimated stay time at attraction i (i.e., the sightseeing time). The estimated stay time is obtained by linearly mapping the average sightseeing time of attraction i to a dimensionless numerical range; γ represents the first weighting coefficient, and μ represents the second weighting coefficient.

[0094] In this embodiment, the objective function is used to balance walking time, sightseeing time, and scenic experience during the path generation process. This embodiment combines real-time scenic experience data, distances between attractions, and sightseeing time to generate the optimal tour route for the user. The system also uses a reliability calculation method to select from user-uploaded data to ensure the accuracy and applicability of the recommended routes.

[0095] This invention also discloses a tour recommendation device based on human light and scene perception, used to implement the aforementioned tour recommendation method based on human light and scene perception. In a preferred embodiment, the device includes:

[0096] The data acquisition module obtains the predicted time period and light climate prediction type corresponding to the target visit time, and obtains the travel distance representation between attractions within the scenic area;

[0097] The query module retrieves the scenic experience evaluation of attractions under the predicted time period and light climate prediction type from the scenic experience relationship table;

[0098] The optimal tour route determination module combines the scenic experience evaluation of attractions with the travel distance between attractions to determine the optimal tour route for the target tour time. The optimal tour route can balance the scenic experience evaluation and the travel distance. The optimal tour route passes through different attractions and starts from the scenic area entrance and ends at the scenic area exit.

[0099] The recommendation module suggests the best tour routes to tourists.

[0100] In this embodiment, the data acquisition module, query module, optimal tour route determination module, and recommendation module correspond one-to-one with steps S1, S2, S3, and S4 in the above method, and will not be described again here.

[0101] In the description of this specification, the references to terms such as "an embodiment," "some embodiments," "example," "specific example," "a implementation," "a preferred implementation," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0102] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

Claims

1. A tour recommendation method based on human perception of light and scenery, characterized in that, Including: Obtain the predicted time period corresponding to the target tour time and the light climate prediction type, and obtain the representation of the travel distance between scenic spots in the scenic area; Obtain the light and scene experience evaluation of the scenic spots under the predicted time period and the light climate prediction type from the light and scene experience relationship table; wherein, the light and scene experience evaluation of the scenic spots includes light comfort, light perception degree, visual impression and light environment experience; Combine the light and scene experience evaluation of the scenic spots and the representation of the travel distance between the scenic spots to determine the optimal tour route under the target tour time, and the optimal tour route passes through different scenic spots and starts from the scenic area entrance and ends at the scenic area exit; Recommend the optimal tour route to tourists; The determination of the optimal tour route under the target tour time includes: Step A1, initialize the pheromone concentration of the path segments between the scenic spots; Step A2, perform iterative search until the number of searches reaches the preset maximum number of searches T. The t-th search process includes: Release all ants at the scenic area entrance and initialize the taboo list of each ant; Each ant selects the next scenic spot according to the selection probability and updates the taboo list until each ant reaches the scenic area exit or enters a deadlock state; Discard the ants that enter the deadlock state and update the pheromone concentration of the path segments in the passing paths of the ants that reach the scenic area exit; If t < T, then enter the (t + 1)-th search. If t ≥ T, then enter Step A3; Step A3, calculate the fitness of the passing paths of all ants that reach the scenic area exit obtained from T searches, and select the passing path with the maximum fitness as the optimal tour route under the target tour time; Among them, the fitness calculation formula of the passing path S is: i and j represent the attraction indices, i ≠ j, k represents the number of attractions on the path S, and E(i,t) represents the number of attractions on the path S. g () indicates that attraction i is within the target visit time t. g The evaluation of the light and scenery experience under the corresponding predicted time period and light climate prediction type; (i,j) represents a path segment in the route S, D(i,j) represents the travel distance of the path segment (i,j), and T is a positive integer; Alternatively, the determination of the optimal tour route under the target tour time includes: Enumerate all candidate paths. Each candidate path starts from the scenic area entrance, ends at the scenic area exit and passes through k scenic spots without repetition, where k ∈ [1, n], and n represents the number of scenic spots in the scenic area; Calculate the objective function value of each candidate path, and select the candidate path with the maximum objective function value as the optimal tour route under the target tour time; Among them, the objective function formula is: S' represents a candidate path, where i and j are the indices of attractions on the candidate path S', and E(i,t) g () indicates that attraction i is within the target visit time t. g The evaluation of the light and scenery experience under the corresponding predicted time period and light climate prediction type; (i,j) represents a path segment in the route S', and D(i,j) represents the travel distance of the path segment (i,j); T i γ represents the estimated time spent at attraction i; μ represents the first weighting coefficient; and μ represents the second weighting coefficient.

2. The tour recommendation method based on human perception of light and scenery as described in claim 1, characterized in that, The construction process of the light and scene experience relationship table includes: Construct multiple light and scene experience evaluation dimensions; Obtain the scores of multiple tourists on each scenic spot in each light and scene experience evaluation dimension under different time periods and different light climate types; Based on the scores of multiple tourists on each scenic spot in each light and scene experience evaluation dimension under different time periods and different light climate types, obtain the measured light and scene experience evaluation of each scenic spot under different time periods and different light climate types; Use the measured light and scene experience evaluation of each scenic spot under different time periods and different light climate types to construct the light and scene experience relationship table.

3. The tour recommendation method based on human perception of light and scenery as described in claim 2, characterized in that, The construction process of the light and scene experience relationship table further includes: Obtain the optical data of each scenic spot under different time periods and different light climate types, and the optical data includes the illuminance information and brightness information of the scenic spot; Construct a virtual model of each scenic spot, and use the optical data of each scenic spot under different time periods and different light climate types to render the virtual model of each scenic spot to obtain a rendered model; Obtain the scores of multiple tourists on the rendered model in multiple light and scene experience evaluation dimensions; The virtual light and shadow experience evaluation of each attraction at different time periods and under different light and weather conditions is obtained by scoring the rendering model by multiple tourists on multiple light and shadow experience evaluation dimensions. A light and shadow experience relationship table is constructed by combining measured light and shadow experience evaluations and virtual light and shadow experience evaluations for each scenic spot at different times and under different light and climate types.

4. The tour recommendation method based on human perception of light and scenery as described in claim 3, characterized in that, The process of obtaining brightness information for each scenic spot under different time periods and light climate types includes: Multiple original images of the scenic spot with different exposures were taken from a preset angle. All original images had multiple reference points set at the same location. Use Photoshop to combine multiple original images into an HDR image; Import the HDR image into an HDR image editing and analysis tool for Falsecolor analysis to generate a brightness falsecolor map. Obtain the average brightness of multiple reference points in multiple original images, denoted as the first average brightness; obtain the average brightness of multiple reference points in the brightness pseudo-color map, denoted as the second average brightness; compare the consistency between the second average brightness and the first average brightness to obtain the brightness comparison result. Based on the brightness comparison results, the exposure of the HDR image is continuously adjusted in Photoshop until the second brightness average value matches the first brightness average value. The brightness of the adjusted HDR image and multiple reference points in the brightness pseudo-color map are then used as the brightness information of the scenic spot.

5. The tour recommendation method based on human perception of light and scenery as described in claim 3, characterized in that, It also includes the steps to revise the light and shadow experience relationship table: Receive perception evaluations uploaded from multiple tourist terminals; Calculate the mean e and standard deviation σ of multiple perceived ratings, and then calculate the reliability Z of the perceived rating X using the following formula: Iterate through all perception evaluations. If the confidence level Z of perception evaluation X exceeds ±3, then remove perception evaluation X; otherwise, retain perception evaluation X. After the traversal is completed, all the perception evaluations and the corresponding time periods and light climate types in the table of light and scene experience relationships are merged.

6. The tour recommendation method based on human perception of light and scenery as described in claim 1, characterized in that, This also includes predicting visitor flow in scenic areas based on the optimal tour route: The average historical visitor flow for each attraction in the optimal tour route during the predicted time period corresponding to the target tour time under all light climate types is obtained and denoted as the historical visitor flow average. Based on the light and scenery experience evaluation of each attraction in the optimal tour route under the predicted time period and the corresponding light and weather prediction type, the historical average number of visitors to each attraction is adjusted to obtain the predicted number of visitors to each attraction at the target tour time. Output the predicted visitor flow for each attraction in the optimal tour route during the target tour time.

7. The tour recommendation method based on human perception of light and scenery as described in claim 1, characterized in that, In step A2, the probability of each ant choosing the next scenic spot j from scenic spot i is calculated using the following formula: Where i, j, m are all scenic spot indices, i ≠ j, allowed represents the set of all scenic spots in the scenic area except for those in the forbidden list for each ant, j, m ∈ allowed; τ ij τ represents the pheromone concentration of a segment along the path from attraction i to attraction j. im δ represents the pheromone concentration of a segment along the path from attraction i to attraction m; ij Let represent the heuristic function by which an ant chooses location j as its next location from location i. δ im Let α represent the heuristic function by which an ant selects location m as its next location at location i; α represents the first adjustment parameter, and β represents the second adjustment parameter.

8. A tour recommendation device based on human perception of light and scenery, characterized in that, A method for implementing a tour recommendation based on human light and scene perception as described in any one of claims 1-7 includes: The data acquisition module obtains the predicted time period and light climate prediction type corresponding to the target visit time, and obtains the travel distance representation between attractions within the scenic area; The query module retrieves the light experience evaluation of attractions under the predicted time period and light climate prediction type from the light experience relationship table; among them, the light experience evaluation of attractions includes light comfort, light perception level, visual impression and light environment experience; The optimal tour route determination module determines the optimal tour route under the target tour time by combining the scenic experience evaluation of scenic spots and the representation of the travel distance between scenic spots. The optimal tour route passes through different scenic spots, starts from the scenic area entrance, and ends at the scenic area exit; The recommendation module recommends the optimal tour route to tourists; The determination of the optimal tour route under the target tour time includes: Step A1, initialize the pheromone concentration of the path segments between scenic spots; Step A2, perform iterative search until the number of searches reaches the preset maximum number of searches T. The t-th search process includes: Release all ants at the scenic area entrance and initialize the taboo list of each ant; Each ant selects the next scenic spot according to the selection probability and updates the taboo list until each ant reaches the scenic area exit or enters a deadlock state; Discard the ants that enter the deadlock state and update the pheromone concentration of the path segments in the passing paths of the ants that reach the scenic area exit; If t < T, then enter the (t + 1)-th search. If t ≥ T, then enter Step A3; Step A3, calculate the fitness of the passing paths of all ants that reach the scenic area exit obtained from T searches, and select the passing path with the maximum fitness as the optimal tour route for the target tour time; Among them, the fitness calculation formula of the passing path S is: i and j represent the attraction indices, i ≠ j, k represents the number of attractions on the path S, and E(i,t) represents the number of attractions on the path S. g () indicates that attraction i is within the target visit time t. g The evaluation of the light and scenery experience under the corresponding predicted time period and light climate prediction type; (i,j) represents a path segment in the route S, D(i,j) represents the travel distance of the path segment (i,j), and T is a positive integer; Alternatively, the determination of the optimal tour route under the target tour time includes: Enumerate all candidate paths. Each candidate path starts from the scenic area entrance, ends at the scenic area exit, and passes through k scenic spots without repetition, where k ∈ [1, n], and n represents the number of scenic spots in the scenic area; Calculate the objective function value of each candidate path, and select the candidate path with the maximum objective function value as the optimal tour route for the target tour time; Among them, the objective function formula is: S' represents a candidate path, where i and j are the indices of attractions on the candidate path S', and E(i,t) g () indicates that attraction i is within the target visit time t. g The evaluation of the light and scenery experience under the corresponding predicted time period and light climate prediction type; (i,j) represents a path segment in the route S', and D(i,j) represents the travel distance of the path segment (i,j); T i γ represents the estimated time spent at attraction i; μ represents the first weighting coefficient; and μ represents the second weighting coefficient.

Images