Vent travel content recommendation system based on meta universe

Abstract

The invention relates to the technical field of travel content recommendation, in particular to a travel content recommendation system based on meta universe, which comprises a travel content recommendation platform, a classification item matching unit, a refining matching unit, a content division unit and a video sorting unit, according to the method, reasonable recommendation is carried out on the text travel content of the meta universe in a layer-by-layer progressive mode, so that the matching degree of text travel content recommendation and the watching effect of the user are improved, and video division feedback analysis is carried out on the text travel content classification items interested by the user in an information feedback mode; therefore, the tendency of the user to the playing duration of the played video in the main recommendation item or the priority recommendation item is known from the historical perspective, the played video is further divided and matched, and playing sequence information processing recommendation analysis is deeply performed on the scenic spot popularity information. And reasonable travel content recommendation can be carried out according to the interest tendency of the user and the popularity of the scenic spot in the played video content.

Description

Technical Field

[0001] The present invention relates to the technical field of cultural and tourism content recommendation, and in particular to a cultural and tourism content recommendation system based on metaverse. Background Art

[0002] The Metaverse is a virtual reality space where users can communicate and interact with other people in an environment generated by technological means. The Metaverse involves a lot of technologies, including artificial intelligence, digital twins, blockchain, cloud computing, etc. The ecological landscape of the Metaverse includes underlying technology support, front-end device platforms, and scene content portals.

[0003] The application of Metaverse in the cultural tourism industry is also more extensive. The cultural tourism Metaverse expands time and space. We can see far away in the local space where virtual and real are integrated, and gain fun and immersion. However, in the existing technology, it is impossible to divide the cultural tourism content items that users are interested in based on their historical browsing information, and thus it is impossible to make reasonable cultural tourism content recommendations based on users' preferences and tendencies, thereby reducing the user's experience and the viewing effect of cultural tourism content.

[0004] In view of the above technical defects, a solution is now proposed. Summary of the invention

[0005] The purpose of the present invention is to provide a cultural and tourism content recommendation system based on the metaverse to solve the technical defects mentioned above. The present invention rationally recommends the cultural and tourism content of the metaverse in a progressive manner, thereby helping to improve the matching degree of cultural and tourism content recommendations and the viewing effect of users, that is, to preliminarily perform cultural and tourism content matching recommendation analysis on historical cultural and tourism browsing information, so as to match and recommend cultural and tourism content classification items that users are interested in from the perspective of historical information, and to perform video division feedback analysis on cultural and tourism content classification items that users are interested in through information feedback, so as to understand the user's tendency to play the video in the main recommendation item or the priority recommendation item from a historical perspective, so as to further divide and match the played video to improve the matching degree between the cultural and tourism content recommendation and the user's preferences, and to perform in-depth playback order information processing recommendation analysis on the scenic spot popularity information, that is, to sort and analyze from the perspective of the popularity of the scenic spot itself in the played video content, thereby helping to rationalize the cultural and tourism content recommendation based on the user's interest tendency and the popularity of the scenic spot itself in the played video content, and helping to improve the reliability and accuracy of the cultural and tourism content recommendation.

[0006] The object of the present invention can be achieved by the following technical solutions: A cultural and tourism content recommendation system based on the metaverse, comprising a cultural and tourism content recommendation platform, a classification item matching unit, a refinement matching unit, a content division unit, and a video sorting unit;

[0007] The classification item matching unit is used to collect the user's historical cultural and travel browsing information of each cultural and travel content classification item in the cloud universe, and perform cultural and travel content matching recommendation analysis on the historical cultural and travel browsing information, and perform discriminant analysis on the obtained cultural and travel interest value Xmax to obtain the main recommendation item or feedback instruction;

[0008] The refinement matching unit responds to the feedback instruction, collects the playback information of the videos played in each item to be recommended, and performs a period browsing trend supervision analysis on the playback information to obtain a priority recommendation item;

[0009] The content division unit is used to collect historical video information of the main recommendation item or the priority recommendation item, perform video division feedback analysis on the historical video information, and perform discrimination processing on the obtained main recommendation travel time to obtain the main recommendation time video;

[0010] After receiving the main long-duration video, the video sorting unit immediately collects the scenic spot popularity information of the main long-duration video, and performs playback order information processing and recommendation analysis on the scenic spot popularity information to obtain the recommendation evaluation coefficient Tk of each main long-duration video, and sends the sorted recommendation evaluation coefficient Tk to the cultural and tourism content recommendation platform.

[0011] Preferably, the cultural and travel content matching recommendation analysis process of the classification item matching unit is as follows:

[0012] The duration of a historical period of time is collected, and the duration of a historical period of time is set as the time threshold, and the cultural and tourism content classification items of the cloud universe within the time threshold are obtained, and then the historical cultural and tourism browsing information of the user in each cultural and tourism content classification item in the cloud universe within the time threshold is obtained. The historical cultural and tourism browsing information includes the browsing index and the interaction index. The cultural and tourism content classification item is set to g, g is a natural number greater than zero, and the browsing index and the interaction index are labeled LLg and HDg respectively, and substituted into the formula Xg = (LLg × a1) 2 ×(HDg×a2) 2 ×a3 obtains the stay evaluation index of each cultural and tourism content classification item, where a1 and a2 are the preset proportional factor coefficients of the browsing index LLg and the interaction index HDg respectively, a3 is the preset correction factor coefficient, a1, a2 and a3 are all greater than zero, Xg is the stay evaluation index of each cultural and tourism content classification item, and then the maximum value of the stay evaluation index Xg is obtained, and the maximum value of the stay evaluation index Xg is set as the cultural and tourism interest value Xmax, and the cultural and tourism interest value Xmax is discriminated:

[0013] If the cultural and tourism interest value Xmax is a unique value, the cultural and tourism content category item corresponding to the cultural and tourism interest value Xmax is set as the main recommendation item;

[0014] If the cultural and tourism interest value Xmax is not a unique value, a feedback instruction is generated.

[0015] Preferably, the browsing index represents the total browsing time of the corresponding playback videos in each cultural and tourism content classification item and the number of playbacks of the corresponding playback videos in the cultural and tourism content classification item; the interaction index represents the total number of user operation information corresponding to the playback videos in each cultural and tourism content classification item, and the operation information includes likes and comments.

[0016] Preferably, the time period browsing trend supervision and analysis process of the refined matching unit is as follows:

[0017] Obtain the cultural and tourism content classification item corresponding to the cultural and tourism interest value Xmax, set the cultural and tourism content classification item corresponding to the cultural and tourism interest value Xmax as the item to be recommended, obtain the playback information of the videos played in each item to be recommended within the time threshold, the playback information includes the number of playbacks and the length of time a single video is viewed, establish a rectangular coordinate system with the number of playbacks as the X-axis and the length of time a single video is viewed as the Y-axis, draw a curve of the length of time a single video is viewed by drawing points, and then obtain the change trend value of the curve of the length of time a single video is viewed, set the change trend value of the curve of the length of time a single video is viewed as the browsing trend coefficient, obtain the maximum value in the browsing trend coefficient, and set the item to be recommended corresponding to the maximum value in the browsing trend coefficient as the priority recommendation item.

[0018] Preferably, the video division feedback analysis process of the content division unit is as follows:

[0019] Get the historical video information of the main recommendation item or the priority recommendation item within the time threshold. The historical video information includes the video duration and the total number of played videos. Get the video duration corresponding to a single played video, and compare and analyze the video duration with the preset video duration range stored in the content division unit:

[0020] If the video duration is greater than the maximum value in the preset video duration range, the corresponding played video is determined to be a long-duration video;

[0021] If the video duration falls within the preset video duration range, the corresponding played video is determined to be a medium-length video;

[0022] If the video duration is less than the minimum value in the preset video duration range, the corresponding played video is determined to be a short-duration video.

[0023] Preferably, the number of long-duration videos, medium-duration videos and short-duration videos in the total number of played videos is obtained, and the number of long-duration videos, medium-duration videos and short-duration videos in the total number of played videos is set as the long-duration ratio, the medium-duration ratio and the short-duration ratio, respectively, and the maximum value among the long-duration ratio, the medium-duration ratio and the short-duration ratio is obtained, and the maximum value among the long-duration ratio, the medium-duration ratio and the short-duration ratio is set as the main push travel duration, and the main push travel duration is discriminated:

[0024] If the main promotion duration is the long duration ratio, the long duration video is determined as the main promotion duration video;

[0025] If the main promotion duration is the medium duration ratio, the medium duration video is determined as the main promotion duration video;

[0026] If the main promotion duration is the short duration ratio, the short duration video is determined as the main promotion duration video.

[0027] Preferably, the play order information processing recommendation analysis process of the video sorting unit is as follows:

[0028] Get the scenic spot popularity information of each scenic spot in the main push duration video content within the time threshold. The scenic spot popularity information includes the passenger flow index and the video flow index. Set the main push duration video to k, where k is a natural number greater than zero. Label the passenger flow index and the video flow index as KZk and SLk respectively. Substitute the passenger flow index KZk and the video flow index SLk into the formula The recommendation evaluation coefficient of each main-time video is obtained, where f1 and f2 are the preset weight factor coefficients of the passenger flow index KZk and the video flow index SLk respectively, f3 is the preset fault tolerance factor coefficient, f1, f2 and f3 are all greater than zero, Tk is the recommendation evaluation coefficient of each main-time video, and the recommendation evaluation coefficient Tk is sorted in order from large to small, and the sorted recommendation evaluation coefficient Tk is sent to the cultural and tourism content recommendation platform.

[0029] The beneficial effects of the present invention are as follows:

[0030] (1) The present invention rationally recommends the cultural and tourism content of the Metaverse in a progressive manner, thereby helping to improve the matching degree of cultural and tourism content recommendations and the viewing effect of users, that is, to preliminarily perform cultural and tourism content matching recommendation analysis on historical cultural and tourism browsing information, so as to match and recommend cultural and tourism content classification items that users are interested in from the perspective of historical information;

[0031] (2) The present invention conducts video segmentation feedback analysis on the cultural and tourism content classification items that users are interested in through information feedback, so as to understand the user's tendency to play the video in the main recommendation item or the priority recommendation item for a long time from a historical perspective, so as to further divide and match the played videos to improve the matching degree between the cultural and tourism content recommendation and the user's preferences, and conducts in-depth playback sequence information processing recommendation analysis on the scenic spot popularity information, that is, to sort and analyze from the perspective of the popularity of the scenic spot itself in the played video content, thereby helping to make reasonable cultural and tourism content recommendations based on the user's interest tendencies and the popularity of the scenic spot itself in the played video content, and helping to improve the reliability and accuracy of cultural and tourism content recommendations. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The present invention will be further described below in conjunction with the accompanying drawings;

[0033] Figure 1 It is a flowchart of the system of the present invention;

[0034] Figure 2 It is a local reference analysis diagram of an embodiment of the present invention. DETAILED DESCRIPTION

[0035] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0036] Embodiment 1:

[0037] See also Figure 1 to Figure 2 As shown, the present invention is a cultural and tourism content recommendation system based on the metaverse, including a cultural and tourism content recommendation platform, a classification item matching unit, a refinement matching unit, a content division unit and a video sorting unit, the cultural and tourism content recommendation platform is in a two-way communication connection with the classification item matching unit, the classification item matching unit is in a one-way communication connection with the refinement matching unit, the refinement matching unit is in a one-way communication connection with the cultural and tourism content recommendation platform, the cultural and tourism content recommendation platform is in a one-way communication connection with the content division unit, the content division unit is in a one-way communication connection with the video sorting unit, and the video sorting unit is in a one-way communication connection with the cultural and tourism content recommendation platform;

[0038] When the cultural and tourism content recommendation platform generates a recommendation instruction, it sends the recommendation instruction to the category item matching unit. After receiving the recommendation instruction, the category item matching unit immediately collects the user's historical cultural and tourism browsing information of each cultural and tourism content category item in the cloud universe, and performs a cultural and tourism content matching recommendation analysis on the historical cultural and tourism browsing information, so as to recommend cultural and tourism content from the perspective of historical information, so as to improve the matching degree of cultural and tourism content recommendations, thereby helping to improve the user's experience and viewing effect. The specific cultural and tourism content matching recommendation analysis process is as follows:

[0039] The duration of a historical period of time is collected, and the duration of a historical period of time is set as the time threshold, and the cultural and tourism content classification items of the cloud universe within the time threshold are obtained, and then the historical cultural and tourism browsing information of the user in each cultural and tourism content classification item in the cloud universe within the time threshold is obtained. The historical cultural and tourism browsing information includes the browsing index and the interaction index. The cultural and tourism content classification item is set to g, g is a natural number greater than zero, and the browsing index and the interaction index are labeled LLg and HDg respectively, and substituted into the formula Xg = (LLg × a1) 2 ×(HDg×a2)2 ×a3 obtains the stay evaluation index of each cultural and tourism content classification item, where a1 and a2 are the preset proportional factor coefficients of the browsing index LLg and the interaction index HDg respectively. The proportional factor coefficient is used to correct the deviation of each parameter in the formula calculation process, so as to make the calculation result more accurate. a3 is the preset correction factor coefficient. a1, a2 and a3 are all greater than zero. Xg is the stay evaluation index of each cultural and tourism content classification item, and then the maximum value of the stay evaluation index Xg is obtained, and the maximum value of the stay evaluation index Xg is set as the cultural and tourism interest value Xmax, and the cultural and tourism interest value Xmax is discriminated:

[0040] If the cultural and tourism interest value Xmax is a unique value, the cultural and tourism content category item corresponding to the cultural and tourism interest value Xmax is set as the main recommendation item, and the main recommendation item is sent to the cultural and tourism content recommendation platform;

[0041] If the cultural and tourism interest value Xmax is not a unique value, a feedback instruction is generated and sent to the refinement matching unit;

[0042] In the embodiment of the present invention, the browsing index represents the total browsing time of the corresponding playback video in each cultural and tourism content classification item and the number of playbacks of the corresponding playback video in the cultural and tourism content classification item. It should be noted that the larger the value of the browsing index is, the higher the interest in the cultural and tourism content classification item is;

[0043] In the embodiment of the present invention, the interaction index indicates the total number of times the user's operation information corresponding to the video playback in each cultural and tourism content classification item, and the operation information includes likes, comments, etc. It should be noted that the larger the value of the interaction index, the higher the interest in the cultural and tourism content classification item;

[0044] When a feedback instruction is generated, the refinement matching unit responds to the feedback instruction, collects the playback information of the videos played in each item to be recommended, and performs a period browsing trend supervision analysis on the playback information, so as to refine the matching of the recommended items from the perspective of trends, so as to further improve the rationality of the recommendation of cultural and tourism content. The specific period browsing trend supervision analysis process is as follows:

[0045] Obtain the cultural and tourism content classification item corresponding to the cultural and tourism interest value Xmax, set the cultural and tourism content classification item corresponding to the cultural and tourism interest value Xmax as the item to be recommended, obtain the playback information of the videos played in each item to be recommended within the time threshold, the playback information includes the number of playbacks and the length of time a single video is viewed, establish a rectangular coordinate system with the number of playbacks as the X-axis and the length of time a single video is viewed as the Y-axis, draw a curve of the length of time a single video is viewed by drawing points, and then obtain the change trend value of the curve of the length of time a single video is viewed, set the change trend value of the curve of the length of time a single video is viewed as the browsing trend coefficient, obtain the maximum value in the browsing trend coefficient, set the item to be recommended corresponding to the maximum value in the browsing trend coefficient as the priority item, and send the priority item to the cultural and tourism content recommendation platform.

[0046] Embodiment 2:

[0047] After receiving the main recommendation item or the priority recommendation item, the cultural and tourism content recommendation platform generates a sorting instruction. After the sorting instruction is generated, the sorting instruction is sent to the content division unit. After receiving the sorting instruction, the content division unit immediately collects the historical video information of the main recommendation item or the priority recommendation item, and performs video division feedback analysis on the historical video information, so as to understand the user's interest in the playback time of the main recommendation item or the priority recommendation item from a historical perspective, so as to provide data support for subsequent recommendations. The specific video division feedback analysis process is as follows:

[0048] Get the historical video information of the main recommendation item or the priority recommendation item within the time threshold. The historical video information includes the video duration and the total number of played videos. Get the video duration corresponding to a single played video, and compare and analyze the video duration with the preset video duration range stored in the content division unit:

[0049] If the video duration is greater than the maximum value in the preset video duration range, the corresponding played video is determined to be a long-duration video;

[0050] If the video duration falls within the preset video duration range, the corresponding played video is determined to be a medium-length video;

[0051] If the video duration is less than the minimum value in the preset video duration range, the corresponding played video is determined to be a short-duration video;

[0052] The number of long-duration videos, medium-duration videos and short-duration videos in the total number of played videos is obtained, and the number of long-duration videos, medium-duration videos and short-duration videos in the total number of played videos is set as the long-duration ratio, medium-duration ratio and short-duration ratio respectively, and the maximum value among the long-duration ratio, medium-duration ratio and short-duration ratio is obtained, and the maximum value among the long-duration ratio, medium-duration ratio and short-duration ratio is set as the main push travel duration, and the main push travel duration is judged:

[0053] If the main promotion duration is the long duration ratio, the long duration video is determined as the main promotion duration video;

[0054] If the main promotion duration is the medium duration ratio, the medium duration video is determined as the main promotion duration video;

[0055] If the main push duration is a proportion of the short duration video, the short duration video is determined to be the main push duration video, and the main push duration video is sent to the video sorting unit;

[0056] After receiving the main push duration video, the video sorting unit immediately collects the scenic spot popularity information of the main push duration video, and performs a play order information processing and recommendation analysis on the scenic spot popularity information, so as to rationally sort the play order of the main push duration video in the main recommendation item or priority recommendation item of the cultural travel content in the metaverse, so as to reasonably play the main push duration video. The specific play order information processing and recommendation analysis process is as follows:

[0057] Get the scenic spot popularity information of each scenic spot in the main push duration video content within the time threshold. The scenic spot popularity information includes the passenger flow index and the video flow index. Set the main push duration video to k, where k is a natural number greater than zero. Label the passenger flow index and the video flow index as KZk and SLk respectively. Substitute the passenger flow index KZk and the video flow index SLk into the formula The recommendation evaluation coefficients of each main push duration video are obtained, wherein f1 and f2 are respectively the preset weight factor coefficients of the passenger flow index KZk and the video flow index SLk, f3 is the preset fault tolerance factor coefficient, f1, f2 and f3 are all greater than zero, Tk is the recommendation evaluation coefficient of each main push duration video, the recommendation evaluation coefficients Tk are sorted in order from large to small, and the sorted recommendation evaluation coefficients Tk are sent to the cultural tourism content recommendation platform. After receiving the sorted recommendation evaluation coefficients Tk, the cultural tourism content recommendation platform plays the corresponding main push duration videos in the order of the sorted recommendation evaluation coefficients Tk, which helps to make reasonable cultural tourism content recommendations based on the user's interest tendencies, and through the analysis in a layered progressive manner, it helps to improve the reliability and accuracy of cultural tourism content recommendations;

[0058] In the embodiment of the present invention, the passenger flow index represents the product value obtained by multiplying the average daily passenger flow of the scenic spot in the main push time video content and the total video forwarding amount after data normalization processing. It should be noted that the larger the value of the passenger flow index is, the better the playing experience of the scenic spot in the main push time video content is;

[0059] In the embodiment of the present invention, the video flow index represents the product value obtained by multiplying the total number of likes and the total number of comments of the main push time video after data normalization, and then multiplying the value corresponding to the total number of online playbacks. It should be noted that the larger the value of the video flow index is, the better the popularity of the main push time video itself is, and the more popular the scenic spot in the main push time video content is;

[0060] In summary, the present invention rationally recommends the cultural and tourism contents of the metaverse in a progressive manner, thereby helping to improve the matching degree of cultural and tourism content recommendations and the viewing effect of users, that is, a preliminary cultural and tourism content matching recommendation analysis is performed on historical cultural and tourism browsing information, so as to match and recommend cultural and tourism content classification items that users are interested in from the perspective of historical information, and a video division feedback analysis is performed on the cultural and tourism content classification items that users are interested in through information feedback, so as to understand the user's tendency to play the video in the main recommendation item or the priority recommendation item from a historical perspective, so as to further divide and match the played video to improve the matching degree between the cultural and tourism content recommendation and the user's preferences, and an in-depth playback order information processing recommendation analysis is performed on the scenic spot popularity information, that is, a ranking analysis is performed from the perspective of the popularity of the scenic spot itself in the played video content, which helps to rationalize the cultural and tourism content recommendation based on the user's interest tendency and the popularity of the scenic spot itself in the played video content, and helps to improve the reliability and accuracy of the cultural and tourism content recommendation.

[0061] The threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by technicians in this field for each group of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0062] The above formulas are obtained by collecting a large amount of data for software simulation and selecting a formula that is close to the actual value. The coefficients in the formula are set by technical personnel in this field according to actual conditions. The above is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited to this. Any technical personnel familiar with the technical field within the technical scope disclosed by the present invention, according to the technical solution and the inventive concept of the present invention, make equivalent replacement or change, which should be covered within the protection scope of the present invention.

Claims

1. A cultural and tourism content recommendation system based on the metaverse, characterized in that: It includes a cultural and tourism content recommendation platform, a classification item matching unit, a detailed matching unit, a content division unit, and a video sorting unit; The classification item matching unit is used to collect the user's historical cultural and travel browsing information of each cultural and travel content classification item in the cloud universe, and perform cultural and travel content matching recommendation analysis on the historical cultural and travel browsing information, and perform discriminant analysis on the obtained cultural and travel interest value Xmax to obtain the main recommendation item or feedback instruction; The refinement matching unit responds to the feedback instruction, collects the playback information of the videos played in each item to be recommended, and performs a period browsing trend supervision analysis on the playback information to obtain a priority recommendation item; The content division unit is used to collect historical video information of the main recommendation item or the priority recommendation item, perform video division feedback analysis on the historical video information, and perform discrimination processing on the obtained main recommendation travel time to obtain the main recommendation time video; After receiving the main long-duration video, the video sorting unit immediately collects the scenic spot popularity information of the main long-duration video, and performs playback order information processing and recommendation analysis on the scenic spot popularity information to obtain the recommendation evaluation coefficient Tk of each main long-duration video, and sends the sorted recommendation evaluation coefficient Tk to the cultural and tourism content recommendation platform.

2. According to the metaverse-based cultural and tourism content recommendation system of claim 1, it is characterized in that: The cultural and tourism content matching recommendation analysis process of the classification item matching unit is as follows: The duration of a historical period of time is collected, and the duration of a historical period of time is set as the time threshold, and the cultural and tourism content classification items of the cloud universe within the time threshold are obtained, and then the historical cultural and tourism browsing information of the user in each cultural and tourism content classification item in the cloud universe within the time threshold is obtained. The historical cultural and tourism browsing information includes the browsing index and the interaction index. The cultural and tourism content classification item is set to g, g is a natural number greater than zero, and the browsing index and the interaction index are labeled LLg and HDg respectively, and substituted into the formula Xg = (LLg × a1) 2 ×(HDg×a2) 2 ×a3 obtains the stay evaluation index of each cultural and tourism content classification item, where a1 and a2 are the preset proportional factor coefficients of the browsing index LLg and the interaction index HDg respectively, a3 is the preset correction factor coefficient, a1, a2 and a3 are all greater than zero, Xg is the stay evaluation index of each cultural and tourism content classification item, and then the maximum value of the stay evaluation index Xg is obtained, and the maximum value of the stay evaluation index Xg is set as the cultural and tourism interest value Xmax, and the cultural and tourism interest value Xmax is discriminated: If the cultural and tourism interest value Xmax is a unique value, the cultural and tourism content category item corresponding to the cultural and tourism interest value Xmax is set as the main recommendation item; If the cultural and tourism interest value Xmax is not a unique value, a feedback instruction is generated.

3. According to the metaverse-based cultural and tourism content recommendation system of claim 2, it is characterized in that: The browsing index represents the total browsing time of the corresponding videos in each cultural and tourism content classification item and the number of plays of the corresponding videos in the cultural and tourism content classification item; the interaction index represents the total number of times the user's operation information of the corresponding videos in each cultural and tourism content classification item corresponds to the operation information, and the operation information includes likes and comments.

4. A cultural and tourism content recommendation system based on the metaverse according to claim 3, characterized in that: The period browsing trend supervision and analysis process of the refined matching unit is as follows: Obtain the cultural and tourism content classification item corresponding to the cultural and tourism interest value Xmax, set the cultural and tourism content classification item corresponding to the cultural and tourism interest value Xmax as the item to be recommended, obtain the playback information of the videos played in each item to be recommended within the time threshold, the playback information includes the number of playbacks and the length of time a single video is viewed, establish a rectangular coordinate system with the number of playbacks as the X-axis and the length of time a single video is viewed as the Y-axis, draw a curve of the length of time a single video is viewed by drawing points, and then obtain the change trend value of the curve of the length of time a single video is viewed, set the change trend value of the curve of the length of time a single video is viewed as the browsing trend coefficient, obtain the maximum value in the browsing trend coefficient, and set the item to be recommended corresponding to the maximum value in the browsing trend coefficient as the priority recommendation item.

5. According to the metaverse-based cultural and tourism content recommendation system of claim 2, it is characterized in that: The video division feedback analysis process of the content division unit is as follows: Get the historical video information of the main recommendation item or the priority recommendation item within the time threshold. The historical video information includes the video duration and the total number of played videos. Get the video duration corresponding to a single played video, and compare and analyze the video duration with the preset video duration range stored in the content division unit: If the video duration is greater than the maximum value in the preset video duration range, the corresponding played video is determined to be a long-duration video; If the video duration falls within the preset video duration range, the corresponding played video is determined to be a medium-length video; If the video duration is less than the minimum value in the preset video duration range, the corresponding played video is determined to be a short-duration video.

6. A cultural and travel content recommendation system based on the metaverse according to claim 5, characterized in that: The number of long-duration videos, medium-duration videos and short-duration videos in the total number of played videos is obtained, and the number of long-duration videos, medium-duration videos and short-duration videos in the total number of played videos is set as the long-duration ratio, medium-duration ratio and short-duration ratio respectively, and the maximum value among the long-duration ratio, medium-duration ratio and short-duration ratio is obtained, and the maximum value among the long-duration ratio, medium-duration ratio and short-duration ratio is set as the main push travel duration, and the main push travel duration is judged: If the main promotion duration is the long duration ratio, the long duration video is determined as the main promotion duration video; If the main promotion duration is the medium duration ratio, the medium duration video is determined as the main promotion duration video; If the main promotion duration is the short duration ratio, the short duration video is determined as the main promotion duration video.

7. The cultural and tourism content recommendation system based on the metaverse according to claim 2 is characterized in that: The video sorting unit's play order information processing recommendation analysis process is as follows: Get the scenic spot popularity information of each scenic spot in the main push duration video content within the time threshold. The scenic spot popularity information includes the passenger flow index and the video flow index. Set the main push duration video to k, where k is a natural number greater than zero. Label the passenger flow index and the video flow index as KZk and SLk respectively. Substitute the passenger flow index KZk and the video flow index SLk into the formula The recommendation evaluation coefficient of each main-time video is obtained, where f1 and f2 are the preset weight factor coefficients of the passenger flow index KZk and the video flow index SLk respectively, f3 is the preset fault tolerance factor coefficient, f1, f2 and f3 are all greater than zero, Tk is the recommendation evaluation coefficient of each main-time video, and the recommendation evaluation coefficient Tk is sorted in order from large to small, and the sorted recommendation evaluation coefficient Tk is sent to the cultural and tourism content recommendation platform.

Images