Intelligent matching system and method for text travel demand supply based on linkage of double private domains

Abstract

The invention discloses a text travel demand supply intelligent matching system and method based on double private domain linkage, and relates to the technical field of intelligent matching. The system comprises a historical data analysis and grading module, a real-time demand identification and scheme generation module, an implementation feedback and analysis module and a dynamic adjustment and intelligent recommendation module. The historical data analysis and grade division module is used for analyzing historical data, calculating a demand fluctuation coefficient and dividing demand fluctuation grades; the real-time demand identification and scheme generation module is used for analyzing real-time user behaviors, identifying demand fluctuation levels and generating a preliminary matching scheme; the implementation feedback and analysis module is used for tracking implementation conditions of real-time users, calculating deviations and feeding back the deviations; and the dynamic adjustment and intelligent recommendation module is used for generating an adjustment scheme and providing a matching scheme according to the adjusted travel demand confirmed by the user.

Description

Technical Field

[0001] The present invention relates to the field of intelligent matching technology, and specifically to an intelligent matching system and method for cultural and tourism demand supply based on dual private domain linkage. Background Art

[0002] With the rapid development of the internet and mobile technology, the tourism industry has undergone unprecedented transformation, with the cultural tourism industry gradually shifting towards personalized, targeted, and intelligent service models. Traditional approaches to matching tourism demand and supply often rely on large-scale marketing campaigns and extensive recommendations. These approaches fail to deeply tap into users' individual needs and effectively implement precise resource allocation, resulting in a poor user experience and suboptimal marketing results. As user needs become increasingly diverse and complex, traditional matching systems are no longer able to meet the expectations of modern travel consumers.

[0003] To enhance user experience and improve operational efficiency in the cultural and tourism industry, more and more cultural and tourism enterprises are experimenting with operating models based on private domain traffic. This involves establishing and maintaining direct relationships between brands and users, and meticulously managing and leveraging user data. Private domain traffic can effectively deepen connections between brands and consumers, enhance user loyalty, and enable precision marketing. However, existing intelligent matching systems typically generate recommendations based on static data models and preliminary user behavior analysis. These systems are unable to adapt to the dynamic changes in cultural and tourism consumer demand, resulting in recommendations that may fail in practice. For example, users may adjust their travel plans based on current weather conditions, unexpected events, or changes in personal interests, resulting in a mismatch between the originally recommended travel plans and their real-time needs. Summary of the Invention

[0004] The purpose of the present invention is to provide an intelligent matching system and method for cultural and tourism demand supply based on dual private domain linkage to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] The intelligent matching method for cultural tourism demand and supply based on dual private domain linkage includes the following steps:

[0007] Step S100: Obtain historical user data and the cultural tourism demand supply records corresponding to the historical users in the database, analyze the demand fluctuation coefficient of the historical users based on the historical user data and the cultural tourism demand supply records, and classify the historical users into several demand fluctuation levels based on the demand fluctuation coefficient;

[0008] Step S200: Acquire real-time user data, analyze the real-time user data with historical user data for each demand fluctuation level, identify the real-time user demand fluctuation level, and obtain an initial list of cultural tourism demand supply matching solutions based on the real-time user demand fluctuation level;

[0009] Step S300: Output the list of initial cultural tourism demand and supply matching solutions to the real-time user, who then selects the initial cultural tourism demand and supply matching solution. Obtain the real-time user's location information, obtain corresponding environmental data based on the real-time user's location information and current timestamp, and analyze the deviation relationship between the current real-time user's implemented cultural tourism demand and supply matching solution and the initial cultural tourism demand and supply matching solution.

[0010] Step S400. Obtain a corresponding deviation index based on the deviation relationship between the current real-time user's implemented cultural and tourism demand supply matching plan and the initial cultural and tourism demand supply matching plan; compare the deviation index with the deviation threshold, and obtain an adjusted cultural and tourism demand supply matching plan based on the comparison result.

[0011] Furthermore, step S100 includes:

[0012] S101. Obtain historical user data and cultural tourism demand supply records corresponding to historical users in the database, wherein the historical user data refers to all interaction data of users in the historical time period, specifically including: user browsing behavior (such as click stream, search keywords), user movement trajectory (time and location of visiting attractions, staying in hotels), user purchase records (such as booking tickets, hotels, activities, etc.) and user social behavior (such as comments, likes, shared content), etc.; the cultural tourism demand supply record refers to the matching record between the supply of cultural tourism resources and user demand in the historical time period, specifically including: resource supply records and demand matching status, etc.; wherein the resource supply record refers to the specific supply status of cultural tourism resources (such as attractions, hotels, activities, etc.) in the historical time period, including: attraction information: such as opening hours, tourist carrying capacity, ticket price, attraction facilities, etc.; hotel information: such as room type, room rate, check-in and check-out time, hotel's geographical location, etc.; activity information: such as activity type, time, number of participants, ticket price, activity participation conditions, etc. Demand matching refers to recording the matching of user demand and supply, for example: the relationship between the user's browsing, searching, or purchasing of specific cultural and tourism resources and the supply of cultural and tourism resources; the user's selection, reservation, participation and other behavioral records of recommended resources; the dynamic changes in user demand (such as user demand for different time periods, different activities or preferences for different tourism resources) and changes in supply resources. For each historical user, the corresponding historical user data is obtained, the user behavior in the historical user data is classified into several categories, and the number of times each type of behavior of the historical user occurs in the historical time period is counted, so as to calculate the probability of occurrence of each type of behavior Pl(Bi), and Pl(Bi) = f(Bi) / N, where f(Bi) represents the number of times the behavior category Bi appears, Bi represents the i-th behavior category of the historical user, and N represents the total number of all user behaviors in the historical user data; according to the probability of occurrence of each type of behavior Pl(Bi), the behavior entropy H of the historical user is calculated, and Where n represents the number of historical user behavior categories; based on the cultural and tourism demand supply records, the emergency event impact TF of historical users is calculated, and TF = fm / M, where fm represents the number of emergency events in the historical user data, and an emergency event is defined as: if the match between the supply of cultural and tourism resources (such as tourist attractions, accommodation, etc.) and user demand changes, it can be considered an emergency event; M represents the total number of all cultural and tourism demand supply records in the historical user data;

[0013] S102. According to the behavioral entropy and the impact of emergencies, the demand fluctuation coefficient DVI of historical users is calculated, and DVI = H × (1 + TF / α), where α represents the adjustment factor; the demand fluctuation coefficients DVI of all historical users are summarized, and according to the number L of preset demand fluctuation levels, the span of the demand fluctuation coefficient interval Q of the demand fluctuation level is calculated, and the corresponding calculation formula is: Q_width = (DVI_max-DVI_min) / L, and the interval Q of each demand fluctuation level can be obtained according to the span of the demand fluctuation coefficient interval Q, the demand fluctuation coefficient interval Q of the first demand fluctuation level is Q1 = [DVI_min, DVI_min+Q_width), the demand fluctuation coefficient interval Q2 of the second demand fluctuation level is Q2 = [DVI_min+Q_width, DVI_min+2×Q_width), and so on, the demand fluctuation coefficient interval QL of the Lth demand fluctuation level is QL = [DVI_min+(L-1)×Q_width, DVI_max], and the higher the demand fluctuation level, the greater the demand volatility of the corresponding user.

[0014] Furthermore, step S200 includes:

[0015] S201. Acquire real-time user data and analyze the real-time user data according to the analysis method of historical user data to obtain the behavior categories of the real-time users, and calculate the occurrence probability Ps(Bi) of each behavior category, where Bi in Ps(Bi) corresponds to the behavior category of the historical users; summarize the occurrence probability Ps(Bi) of each behavior category of the real-time users to form a real-time user behavior category set Ps, where Ps = {Ps(B1), Ps(B2), ..., Ps(Bn)}, where Ps(B1) represents the occurrence probability corresponding to the first behavior category of the real-time user, Ps(B2) represents the occurrence probability corresponding to the second behavior category of the real-time user, and so on, Ps(Bn) represents the occurrence probability corresponding to the nth behavior category of the real-time user;

[0016] S202. For each demand fluctuation level, obtain the occurrence probability Pl(Bi) of each type of behavior of each historical user corresponding to each demand fluctuation level, thereby forming a historical user behavior category set Pl for each historical user, where Pl = {Pl(B1), Pl(B2), ..., Pl(Bn)}. Similarly, Pl(B1) represents the occurrence probability corresponding to the first behavior category of the historical user, Pl(B2) represents the occurrence probability corresponding to the second behavior category of the historical user, and Pl(Bn) represents the occurrence probability corresponding to the nth behavior category of the historical user. Normalize the elements in the real-time user behavior category set Ps and the historical user behavior category set Pl, and sequentially calculate the similarity between the normalized real-time user behavior category set Ps and the historical user behavior category set Pl for each demand fluctuation level, and average the similarities. The average of the calculated similarities is used as the similarity of the corresponding demand fluctuation level. The similarities of the demand fluctuation levels are arranged in ascending order, and the demand fluctuation level with the greatest similarity is selected as the demand fluctuation level of the real-time user.

[0017] S203. Calculate the behavior entropy H1 of the real-time user based on the occurrence probability Ps(Bi) of each behavior category of the real-time user; obtain the behavior entropy H of all historical users corresponding to the demand fluctuation level of the real-time user, calculate the absolute value of the difference between the behavior entropy H1 of the real-time user and the behavior entropy H of the historical users, obtain the cultural and tourism demand supply record corresponding to the historical user with the smallest absolute value of the difference, and generate an initial cultural and tourism demand supply matching plan list based on the cultural and tourism demand supply records corresponding to the historical users.

[0018] Furthermore, step S300 includes:

[0019] S301. Output the initial cultural tourism demand and supply matching plan list to the real-time user, and let the real-time user select the initial cultural tourism demand and supply matching plan; obtain the real-time user's location information once every selected time period, and obtain the environmental data of the real-time user's location based on the real-time user's location information and the current timestamp; the environmental data includes but is not limited to weather conditions (temperature, humidity, wind speed, precipitation probability, etc.), traffic conditions (congestion index, public transportation operation status, etc.), scenic spot passenger flow, etc. Combine the real-time user's location information and the environmental data of the location, and extract the cultural tourism demand and supply matching plan that the real-time user has implemented;

[0020] S302. Based on the initial cultural tourism demand and supply matching solution, extract the corresponding initial tourism path CL, where the initial tourism path CL refers to the cultural tourism activities and route arrangement selected by the real-time user, and the nodes of the initial tourism path CL refer to the specific scenic spots in the cultural tourism activities. Based on the cultural tourism demand and supply matching solution implemented by the real-time user, extract the actual tourism path SL of the current real-time user. Based on the number of nodes and the actual starting point of the actual tourism path SL, match the actual starting point of the actual tourism path SL with the initial starting point of the initial tourism path CL. Based on the number of nodes in the actual tourism path SL, extract the initial tourism path segment CL1 with the same number of nodes.

[0021] S303. Calculate the node sequence deviation J between the actual travel path SL and the corresponding initial travel path segment CL1, and Wherein SL(sj) represents the position number of node sj in the actual travel path SL, CL1(sj) represents the position number of node sj in the initial travel path segment CL1, and node sj is an element in the intersection of the nodes of the actual travel path SL and the initial travel path segment CL1; the node visit deviation V of the actual travel path SL and the initial travel path segment CL1 is calculated, and V = |Visited(SL)\Planned(CL1)|+|Planned(CL1)\Visited(SL)|, where Visited(SL) represents the set of nodes that the real-time user has visited in the actual travel path SL, Planned(CL1) represents the set of nodes planned to be visited in the initial travel path segment CL1, |Visited(SL)\Planned(CL1)| represents the number of nodes visited in the actual travel path SL but not included in the initial travel path segment CL1; |Planned(CL1)\Visited(SL)| represents the number of nodes planned to be visited in the initial travel path segment CL1 but not visited in the actual travel path SL.

[0022] Furthermore, step S400 includes:

[0023] S401. Based on the node sequence deviation J and node access deviation V between the implemented cultural tourism demand and supply matching solution of the current real-time user and the initial cultural tourism demand and supply matching solution, the corresponding deviation index R is comprehensively calculated, and R = w1 × J + w2 × V, where w1 and w2 represent weight coefficients, and w1 + w2 = 1; the deviation index R of the current real-time user is compared with the preset deviation threshold R0. If the deviation index R is less than the deviation threshold R0, then there is no need to adjust the initial cultural tourism demand and supply matching solution; if the deviation index R is greater than or equal to the deviation threshold R0, then it is necessary to adjust the initial cultural tourism demand and supply matching solution, and the process goes to S402;

[0024] S402. Based on the current real-time user's location information and environmental data, extract the node closest to the current real-time user's location and the corresponding historical environmental data from the historical user data in the demand fluctuation level corresponding to the real-time user, calculate the similarity between the current real-time user's environmental data and the historical environmental data, select the cultural and tourism demand supply record corresponding to the historical user with the highest similarity, and generate corresponding adjustment suggestions based on the corresponding cultural and tourism demand supply records. Output the adjustment suggestions to the real-time user for confirmation by the real-time user, thereby obtaining an adjusted cultural and tourism demand supply matching plan.

[0025] An intelligent matching system for cultural tourism demand and supply based on dual private domain linkage, including: historical data analysis and grading module, real-time demand identification and solution generation module, implementation feedback and analysis module, and dynamic adjustment and intelligent recommendation module;

[0026] The historical data analysis and grading module obtains historical user data and the cultural tourism demand and supply matching scheme corresponding to the historical users in the database, analyzes the user demand fluctuation coefficient of the historical users based on the historical user data and the cultural tourism demand and supply matching scheme, and divides the historical users into several demand fluctuation levels based on the user demand fluctuation coefficient;

[0027] The real-time demand identification and solution generation module obtains real-time user data, analyzes the real-time user data with the historical user data of each demand fluctuation level in turn, identifies the real-time user's demand fluctuation level; and obtains an initial list of cultural tourism demand supply matching solutions based on the real-time user's demand fluctuation level;

[0028] The implementation feedback and analysis module outputs the list of initial cultural tourism demand and supply matching solutions to the real-time user, who then selects the initial cultural tourism demand and supply matching solution. The module obtains the real-time user's location information, obtains the corresponding environmental data based on the real-time user's location information and the current timestamp, and analyzes the deviation relationship between the current real-time user's implemented cultural tourism demand and supply matching solution and the initial cultural tourism demand and supply matching solution.

[0029] The dynamic adjustment and intelligent recommendation module obtains the corresponding deviation index based on the deviation relationship between the current real-time user's implemented cultural and tourism demand supply matching plan and the initial cultural and tourism demand supply matching plan; compares the deviation index with the deviation threshold, and obtains the adjusted cultural and tourism demand supply matching plan based on the comparison result.

[0030] Furthermore, the historical data analysis and grading module includes a historical data analysis unit and a demand fluctuation grading unit;

[0031] The historical data analysis unit obtains the historical user data in the database and the cultural and tourism demand supply matching plan corresponding to the historical users, and analyzes the user demand fluctuation coefficient of the historical users based on the historical user data and the cultural and tourism demand supply matching plan; the demand fluctuation level classification unit divides the historical users into several demand fluctuation levels according to the distribution of the user demand fluctuation coefficient, and determines the range of the user demand fluctuation coefficient of each fluctuation level.

[0032] Furthermore, the real-time demand identification and solution generation module includes a real-time user demand identification unit and a solution list generation unit that matches the initial cultural tourism demand supply;

[0033] The real-time user demand identification unit obtains real-time user data, analyzes the real-time user data with the historical user data of each demand fluctuation level in turn, and identifies the demand fluctuation level of the real-time user; the initial cultural and tourism demand supply matching solution list generation unit obtains the initial cultural and tourism demand supply matching solution list according to the real-time user's demand fluctuation level.

[0034] Furthermore, the implementation feedback and analysis module includes an implementation feedback unit and a deviation analysis unit;

[0035] The implementation feedback unit outputs the list of initial cultural and tourism demand supply matching solutions to the real-time user, and the real-time user selects the initial cultural and tourism demand supply matching solution; obtains the real-time user's location information, and obtains the corresponding environmental data based on the real-time user's location information and current timestamp; the deviation analysis unit analyzes the deviation relationship between the current real-time user's implemented cultural and tourism demand supply matching solution and the initial cultural and tourism demand supply matching solution based on the real-time user's location information and current timestamp.

[0036] Furthermore, the dynamic adjustment and intelligent recommendation module includes a deviation index calculation unit and an adjustment plan output and confirmation unit;

[0037] The deviation index calculation unit calculates the corresponding deviation index based on the deviation relationship between the current real-time user's implemented cultural and tourism demand and supply matching plan and the initial cultural and tourism demand and supply matching plan; the adjustment plan output and confirmation unit generates corresponding adjustment suggestions based on the size relationship between the real-time user's deviation index and the deviation threshold, outputs the adjustment suggestions to the real-time user, and the real-time user confirms them, thereby obtaining the adjusted cultural and tourism demand and supply matching plan.

[0038] Compared with existing technologies, the present invention offers the following advantages: By combining historical and real-time user data, it establishes a dual-private-domain traffic model, enabling precise user data management and optimizing cultural and travel matching. This two-way linkage model not only deepens the connection between brands and consumers but also enables real-time responses to changes in user behavior, enhancing the user's personalized experience. By introducing a demand fluctuation coefficient and a dual-private-domain linkage model, the present invention enables more accurate identification and matching of users' personalized needs. The system dynamically adjusts recommendations based on historical and real-time behavioral data to ensure that recommendations meet users' real-time needs, avoiding the "blind recommendations" of traditional methods. By combining real-time user data analysis with real-time environmental data, the present invention can rapidly respond to changes in user needs and the external environment, adjusting matching solutions in real time. This dynamic adaptation mechanism makes the recommendation system more flexible and intelligent, better meeting users' immediate needs. The present invention calculates a deviation index to quantify the gap between recommended solutions and actual user needs, and adjusts solutions based on this gap. This optimization method based on deviation analysis enables real-time modification of solutions, avoiding negative impacts on user experience and improving user satisfaction and loyalty. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0040] Figure 1 It is a module diagram of the intelligent matching system for cultural and tourism demand supply based on the linkage of dual private domains of the present invention. DETAILED DESCRIPTION

[0041] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0042] See also Figure 1 , the present invention provides a technical solution:

[0043] An intelligent matching system for cultural tourism demand and supply based on dual private domain linkage, including: historical data analysis and grading module, real-time demand identification and solution generation module, implementation feedback and analysis module, and dynamic adjustment and intelligent recommendation module;

[0044] The historical data analysis and grading module obtains historical user data and the cultural tourism demand and supply matching scheme corresponding to the historical users in the database, analyzes the user demand fluctuation coefficient of the historical users based on the historical user data and the cultural tourism demand and supply matching scheme, and divides the historical users into several demand fluctuation levels based on the user demand fluctuation coefficient;

[0045] The real-time demand identification and solution generation module obtains real-time user data, analyzes the real-time user data with the historical user data of each demand fluctuation level in turn, identifies the real-time user's demand fluctuation level; and obtains an initial list of cultural tourism demand supply matching solutions based on the real-time user's demand fluctuation level;

[0046] The implementation feedback and analysis module outputs the list of initial cultural tourism demand and supply matching solutions to the real-time user, who then selects the initial cultural tourism demand and supply matching solution. The module obtains the real-time user's location information, obtains the corresponding environmental data based on the real-time user's location information and the current timestamp, and analyzes the deviation relationship between the current real-time user's implemented cultural tourism demand and supply matching solution and the initial cultural tourism demand and supply matching solution.

[0047] The dynamic adjustment and intelligent recommendation module obtains the corresponding deviation index based on the deviation relationship between the current real-time user's implemented cultural and tourism demand supply matching plan and the initial cultural and tourism demand supply matching plan; compares the deviation index with the deviation threshold, and obtains the adjusted cultural and tourism demand supply matching plan based on the comparison result.

[0048] The historical data analysis and grading module includes a historical data analysis unit and a demand fluctuation grading unit;

[0049] The historical data analysis unit obtains the historical user data in the database and the cultural and tourism demand supply matching plan corresponding to the historical users, and analyzes the user demand fluctuation coefficient of the historical users based on the historical user data and the cultural and tourism demand supply matching plan; the demand fluctuation level classification unit divides the historical users into several demand fluctuation levels according to the distribution of the user demand fluctuation coefficient, and determines the range of the user demand fluctuation coefficient of each fluctuation level.

[0050] The real-time demand identification and solution generation module includes a real-time user demand identification unit and a solution list generation unit that matches the initial cultural and tourism demand supply;

[0051] The real-time user demand identification unit obtains real-time user data, analyzes the real-time user data with the historical user data of each demand fluctuation level in turn, and identifies the demand fluctuation level of the real-time user; the initial cultural and tourism demand supply matching solution list generation unit obtains the initial cultural and tourism demand supply matching solution list according to the real-time user's demand fluctuation level.

[0052] The implementation feedback and analysis module includes the implementation feedback unit and the deviation analysis unit;

[0053] The implementation feedback unit outputs the list of initial cultural and tourism demand supply matching solutions to the real-time user, and the real-time user selects the initial cultural and tourism demand supply matching solution; obtains the real-time user's location information, and obtains the corresponding environmental data based on the real-time user's location information and current timestamp; the deviation analysis unit analyzes the deviation relationship between the current real-time user's implemented cultural and tourism demand supply matching solution and the initial cultural and tourism demand supply matching solution based on the real-time user's location information and current timestamp.

[0054] The dynamic adjustment and intelligent recommendation module includes a deviation index calculation unit and an adjustment plan output and confirmation unit;

[0055] The deviation index calculation unit calculates the corresponding deviation index based on the deviation relationship between the current real-time user's implemented cultural and tourism demand and supply matching plan and the initial cultural and tourism demand and supply matching plan; the adjustment plan output and confirmation unit generates corresponding adjustment suggestions based on the size relationship between the real-time user's deviation index and the deviation threshold, outputs the adjustment suggestions to the real-time user, and the real-time user confirms them, thereby obtaining the adjusted cultural and tourism demand and supply matching plan.

[0056] The intelligent matching method for cultural tourism demand and supply based on dual private domain linkage includes the following steps:

[0057] Step S100: Obtain historical user data and the cultural tourism demand supply records corresponding to the historical users in the database, analyze the demand fluctuation coefficient of the historical users based on the historical user data and the cultural tourism demand supply records, and classify the historical users into several demand fluctuation levels based on the demand fluctuation coefficient;

[0058] Step S200: Acquire real-time user data, analyze the real-time user data with historical user data for each demand fluctuation level, identify the real-time user demand fluctuation level, and obtain an initial list of cultural tourism demand supply matching solutions based on the real-time user demand fluctuation level;

[0059] Step S300: Output the list of initial cultural tourism demand and supply matching solutions to the real-time user, who then selects the initial cultural tourism demand and supply matching solution. Obtain the real-time user's location information, obtain corresponding environmental data based on the real-time user's location information and current timestamp, and analyze the deviation relationship between the current real-time user's implemented cultural tourism demand and supply matching solution and the initial cultural tourism demand and supply matching solution.

[0060] Step S400. Obtain a corresponding deviation index based on the deviation relationship between the current real-time user's implemented cultural and tourism demand supply matching plan and the initial cultural and tourism demand supply matching plan; compare the deviation index with the deviation threshold, and obtain an adjusted cultural and tourism demand supply matching plan based on the comparison result.

[0061] Step S100 includes:

[0062] S101. Obtain historical user data and cultural tourism demand supply records corresponding to historical users in the database, wherein the historical user data refers to all interaction data of users in the historical time period, specifically including: user browsing behavior (such as click stream, search keywords), user movement trajectory (time and location of visiting attractions, staying in hotels), user purchase records (such as booking tickets, hotels, activities, etc.) and user social behavior (such as comments, likes, shared content), etc.; the cultural tourism demand supply record refers to the matching record between the supply of cultural tourism resources and user demand in the historical time period, specifically including: resource supply records and demand matching status, etc.; wherein the resource supply record refers to the specific supply status of cultural tourism resources (such as attractions, hotels, activities, etc.) in the historical time period, including: attraction information: such as opening hours, tourist carrying capacity, ticket price, attraction facilities, etc.; hotel information: such as room type, room rate, check-in and check-out time, hotel's geographical location, etc.; activity information: such as activity type, time, number of participants, ticket price, activity participation conditions, etc. Demand matching refers to recording the matching of user demand and supply, for example: the relationship between the user's browsing, searching, or purchasing of specific cultural and tourism resources and the supply of cultural and tourism resources; the user's selection, reservation, participation and other behavioral records of recommended resources; the dynamic changes in user demand (such as user demand for different time periods, different activities or preferences for different tourism resources) and changes in supply resources. For each historical user, the corresponding historical user data is obtained, the user behavior in the historical user data is classified into several categories, and the number of times each type of behavior of the historical user occurs in the historical time period is counted, so as to calculate the probability of occurrence of each type of behavior Pl(Bi), and Pl(Bi) = f(Bi) / N, where f(Bi) represents the number of times the behavior category Bi appears, Bi represents the i-th behavior category of the historical user, and N represents the total number of all user behaviors in the historical user data; according to the probability of occurrence of each type of behavior Pl(Bi), the behavior entropy H of the historical user is calculated, and Where n represents the number of historical user behavior categories; based on the cultural and tourism demand supply records, the emergency event impact TF of historical users is calculated, and TF = fm / M, where fm represents the number of emergency events in the historical user data, and an emergency event is defined as: if the match between the supply of cultural and tourism resources (such as tourist attractions, accommodation, etc.) and user demand changes, it can be considered an emergency event; M represents the total number of all cultural and tourism demand supply records in the historical user data;

[0063] In this embodiment, the specific process of classifying user behaviors in historical user data is as follows:

[0064] Historical user data is obtained from the database, including all user interaction data within the historical time period. This data includes user visits, purchase records, clicks, comments, search records, favorites, and other forms of interaction. Based on the characteristics of user behavior, several behavior categories are pre-defined (for example, browsing, purchasing, commenting, searching, favorites, etc.). Each category represents a specific type of user behavior on the platform.

[0065] For each behavior record in historical user data, it is assigned to the corresponding behavior category based on its characteristics, specific rule engine, keyword matching, etc., for example:

[0066] If the user behavior is browsing tourist attraction pages, it belongs to the "browsing" category;

[0067] If the user makes a purchase, it falls into the "Purchase" category;

[0068] If a user reviews a travel product or attraction, it falls into the "Comment" category;

[0069] If the user has performed a search operation, it is classified as "Search";

[0070] If a user collects a travel resource or activity, it will be classified as "Collection".

[0071] User behavior can also be automatically identified and classified through training models. Therefore, through the above process, all historical user behavior data can be successfully classified into categories, and the probability of occurrence of each type of behavior can be calculated, which is convenient for the subsequent calculation and analysis of behavior entropy.

[0072] S102. According to the behavioral entropy and the impact of emergencies, the demand fluctuation coefficient DVI of historical users is calculated, and DVI = H × (1 + TF / α), where α represents the adjustment factor; the demand fluctuation coefficients DVI of all historical users are summarized, and according to the number L of preset demand fluctuation levels, the span of the demand fluctuation coefficient interval Q of the demand fluctuation level is calculated, and the corresponding calculation formula is: Q_width = (DVI_max-DVI_min) / L, and the interval Q of each demand fluctuation level can be obtained according to the span of the demand fluctuation coefficient interval Q, the demand fluctuation coefficient interval Q of the first demand fluctuation level is Q1 = [DVI_min, DVI_min+Q_width), the demand fluctuation coefficient interval Q2 of the second demand fluctuation level is Q2 = [DVI_min+Q_width, DVI_min+2×Q_width), and so on, the demand fluctuation coefficient interval QL of the Lth demand fluctuation level is QL = [DVI_min+(L-1)×Q_width, DVI_max], and the higher the demand fluctuation level, the greater the demand volatility of the corresponding user.

[0073] Step S200 includes:

[0074] S201. Acquire real-time user data and analyze the real-time user data according to the analysis method of historical user data to obtain the behavior categories of the real-time users, and calculate the occurrence probability Ps(Bi) of each behavior category, where Bi in Ps(Bi) corresponds to the behavior category of the historical users; summarize the occurrence probability Ps(Bi) of each behavior category of the real-time users to form a real-time user behavior category set Ps, where Ps = {Ps(B1), Ps(B2), ..., Ps(Bn)}, where Ps(B1) represents the occurrence probability corresponding to the first behavior category of the real-time user, Ps(B2) represents the occurrence probability corresponding to the second behavior category of the real-time user, and so on, Ps(Bn) represents the occurrence probability corresponding to the nth behavior category of the real-time user;

[0075] S202. For each demand fluctuation level, obtain the occurrence probability Pl(Bi) of each type of behavior of each historical user corresponding to each demand fluctuation level, thereby forming a historical user behavior category set Pl for each historical user, where Pl = {Pl(B1), Pl(B2), ..., Pl(Bn)}. Similarly, Pl(B1) represents the occurrence probability corresponding to the first behavior category of the historical user, Pl(B2) represents the occurrence probability corresponding to the second behavior category of the historical user, and Pl(Bn) represents the occurrence probability corresponding to the nth behavior category of the historical user. Normalize the elements in the real-time user behavior category set Ps and the historical user behavior category set Pl, and sequentially calculate the similarity between the normalized real-time user behavior category set Ps and the historical user behavior category set Pl for each demand fluctuation level, and average the similarities. The average of the calculated similarities is used as the similarity of the corresponding demand fluctuation level. The similarities of the demand fluctuation levels are arranged in ascending order, and the demand fluctuation level with the greatest similarity is selected as the demand fluctuation level of the real-time user.

[0076] S203. Calculate the behavior entropy H1 of the real-time user based on the occurrence probability Ps(Bi) of each behavior category of the real-time user; obtain the behavior entropy H of all historical users corresponding to the demand fluctuation level of the real-time user, calculate the absolute value of the difference between the behavior entropy H1 of the real-time user and the behavior entropy H of the historical users, obtain the cultural and tourism demand supply record corresponding to the historical user with the smallest absolute value of the difference, and generate an initial cultural and tourism demand supply matching plan list based on the cultural and tourism demand supply records corresponding to the historical users.

[0077] Step S300 includes:

[0078] S301. Output the initial cultural tourism demand and supply matching plan list to the real-time user, and let the real-time user select the initial cultural tourism demand and supply matching plan; obtain the real-time user's location information once every selected time period, and obtain the environmental data of the real-time user's location based on the real-time user's location information and the current timestamp; the environmental data includes but is not limited to weather conditions (temperature, humidity, wind speed, precipitation probability, etc.), traffic conditions (congestion index, public transportation operation status, etc.), scenic spot passenger flow, etc. Combine the real-time user's location information and the environmental data of the location, and extract the cultural tourism demand and supply matching plan that the real-time user has implemented;

[0079] S302. Based on the initial cultural tourism demand and supply matching solution, extract the corresponding initial tourism path CL, where the initial tourism path CL refers to the cultural tourism activities and route arrangement selected by the real-time user, and the nodes of the initial tourism path CL refer to the specific scenic spots in the cultural tourism activities. Based on the cultural tourism demand and supply matching solution implemented by the real-time user, extract the actual tourism path SL of the current real-time user. Based on the number of nodes and the actual starting point of the actual tourism path SL, match the actual starting point of the actual tourism path SL with the initial starting point of the initial tourism path CL. Based on the number of nodes in the actual tourism path SL, extract the initial tourism path segment CL1 with the same number of nodes.

[0080] S303. Calculate the node sequence deviation J between the actual travel path SL and the corresponding initial travel path segment CL1, and Wherein SL(sj) represents the position number of node sj in the actual travel path SL, CL1(sj) represents the position number of node sj in the initial travel path segment CL1, and node sj is an element in the intersection of the nodes of the actual travel path SL and the initial travel path segment CL1; the node visit deviation V of the actual travel path SL and the initial travel path segment CL1 is calculated, and V = |Visited(SL)\Planned(CL1)|+|Planned(CL1)\Visited(SL)|, where Visited(SL) represents the set of nodes that the real-time user has visited in the actual travel path SL, Planned(CL1) represents the set of nodes planned to be visited in the initial travel path segment CL1, |Visited(SL)\Planned(CL1)| represents the number of nodes visited in the actual travel path SL but not included in the initial travel path segment CL1; |Planned(CL1)\Visited(SL)| represents the number of nodes planned to be visited in the initial travel path segment CL1 but not visited in the actual travel path SL.

[0081] In this embodiment, the specific analysis content of the deviation relationship between the current real-time user's implemented cultural tourism demand and supply matching solution and the initial cultural tourism demand and supply matching solution is as follows:

[0082] Assume that the initial travel path CL selected by the real-time user is: {A, B, C, D, E}, and assume that the current real-time user's location information is node E. Extract the real-time user's current real-time user's actual travel path SL. Assume that the actual travel path SL is: {A, B, E}; match the actual starting point of the actual travel path SL with the initial starting point of the initial travel path CL. According to the number of nodes in the actual travel path SL, intercept the initial travel path segment CL1 with the same number of nodes, and the initial travel path segment CL1 is: {A, B, C}; calculate the node sequence deviation J between the two, and Calculate the node visit deviation V between the two, and V=|Visited(SL)\Planned(CL1)|+|Planned(CL1)\Visited(SL)|=2.

[0083] Step S400 includes:

[0084] S401. Based on the node sequence deviation J and node access deviation V between the implemented cultural tourism demand and supply matching solution of the current real-time user and the initial cultural tourism demand and supply matching solution, the corresponding deviation index R is comprehensively calculated, and R = w1 × J + w2 × V, where w1 and w2 represent weight coefficients, and w1 + w2 = 1; the deviation index R of the current real-time user is compared with the preset deviation threshold R0. If the deviation index R is less than the deviation threshold R0, then there is no need to adjust the initial cultural tourism demand and supply matching solution; if the deviation index R is greater than or equal to the deviation threshold R0, then it is necessary to adjust the initial cultural tourism demand and supply matching solution, and the process goes to S402;

[0085] S402. Based on the current real-time user's location information and environmental data, extract the node closest to the current real-time user's location and the corresponding historical environmental data from the historical user data in the demand fluctuation level corresponding to the real-time user, calculate the similarity between the current real-time user's environmental data and the historical environmental data, select the cultural and tourism demand supply record corresponding to the historical user with the highest similarity, and generate corresponding adjustment suggestions based on the corresponding cultural and tourism demand supply records. Output the adjustment suggestions to the real-time user for confirmation by the real-time user, thereby obtaining an adjusted cultural and tourism demand supply matching plan.

[0086] In this embodiment, it is assumed that a user A is visiting a popular scenic spot, and the system provides him with a preliminary cultural tourism demand supply matching plan (such as visiting scenic spot A → scenic spot B → scenic spot C). During the tour, user A found that the queue at scenic spot C was very long, so he chose to skip scenic spot C and go directly to scenic spot D. After calculation, the system found that the node sequence deviation and node access deviation were large, and the calculated deviation index R exceeded the preset threshold R0. Therefore, the system enters S402, generates an adjustment suggestion based on historical data (for example: "User A once chose scenic spot D → scenic spot E in a similar environment, you can refer to this route"), and sends the adjustment suggestion to user A. After user A confirms, the system will generate a new tour route matching plan.

[0087] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0088] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art will be able to modify the technical solutions described in the aforementioned embodiments or substitute equivalents for some of the technical features. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. An intelligent matching method for cultural tourism demand and supply based on dual private domain linkage, characterized by: The method comprises the following steps: Step S100: Obtain historical user data and the cultural tourism demand supply records corresponding to the historical users in the database, analyze the demand fluctuation coefficient of the historical users based on the historical user data and the cultural tourism demand supply records, and classify the historical users into several demand fluctuation levels based on the demand fluctuation coefficient; Step S200: Acquire real-time user data, analyze the real-time user data with historical user data for each demand fluctuation level, identify the real-time user demand fluctuation level, and obtain an initial list of cultural tourism demand supply matching solutions based on the real-time user demand fluctuation level; Step S300: Output the list of initial cultural tourism demand and supply matching solutions to the real-time user, who then selects the initial cultural tourism demand and supply matching solution. Obtain the real-time user's location information, obtain corresponding environmental data based on the real-time user's location information and current timestamp, and analyze the deviation relationship between the current real-time user's implemented cultural tourism demand and supply matching solution and the initial cultural tourism demand and supply matching solution. Step S400. Obtain a corresponding deviation index based on the deviation relationship between the current real-time user's implemented cultural and tourism demand supply matching plan and the initial cultural and tourism demand supply matching plan; compare the deviation index with the deviation threshold, and obtain an adjusted cultural and tourism demand supply matching plan based on the comparison result.

2. The method for intelligent matching of cultural tourism demand and supply based on dual private domain linkage according to claim 1 is characterized by: The step S100 includes: S101. Obtain historical user data and the cultural tourism demand supply records corresponding to historical users in the database, wherein the historical user data refers to all interaction data of users in the historical time period; the cultural tourism demand supply record refers to the matching record between the supply of cultural tourism resources and user demand in the historical time period; for each historical user, obtain the corresponding historical user data, classify the user behaviors in the historical user data into several categories, and count the number of occurrences of each type of behavior of the historical user in the historical time period, thereby calculating the occurrence probability Pl(Bi) of each type of behavior, and Pl(Bi)=f(Bi) / N, where f(Bi) represents the number of occurrences of the behavior category Bi, Bi represents the i-th behavior category of the historical user, and N represents the total number of all user behaviors in the historical user data; according to the occurrence probability Pl(Bi) of each type of behavior, calculate the behavior entropy H of the historical user, and Where n represents the number of historical user behavior categories; based on the cultural and tourism demand supply records, the emergency event impact TF of historical users is calculated, and TF = fm / M, where fm represents the number of emergency events in the historical user data, and the definition of an emergency event is: if the match between the supply of cultural and tourism resources and user demand changes, it can be considered an emergency event; M represents the total number of all cultural and tourism demand supply records in the historical user data; S102. Calculate the historical user demand fluctuation coefficient DVI based on the behavioral entropy and the impact of the emergency, and DVI = H × (1 + TF / α), where α represents the adjustment factor; Summarize the demand fluctuation coefficient DVI of all historical users, and calculate the span of the demand fluctuation coefficient interval Q of the demand fluctuation level according to the number L of preset demand fluctuation levels, and the corresponding calculation formula is: Q_width = (DVI_max-DVI_min) / L. According to the span of the demand fluctuation coefficient interval Q, the interval Q of each demand fluctuation level can be obtained. The demand fluctuation coefficient interval Q1 of the first demand fluctuation level is Q1 = [DVI_min, DVI_min+Q_width), the demand fluctuation coefficient interval Q2 of the second demand fluctuation level is Q2 = [DVI_min+Q_width, DVI_min+2×Q_width), and so on. The demand fluctuation coefficient interval QL of the Lth demand fluctuation level is QL = [DVI_min+(L-1)×Q_width, DVI_max]. The higher the demand fluctuation level, the greater the demand volatility of the corresponding user.

3. The method for intelligent matching of cultural tourism demand and supply based on dual private domain linkage according to claim 2 is characterized by: The step S200 includes: S201. Acquire real-time user data and analyze the real-time user data according to the analysis method of historical user data to obtain the behavior categories of the real-time users, and calculate the occurrence probability Ps(Bi) of each behavior category, where Bi in Ps(Bi) corresponds to the behavior category of the historical users; summarize the occurrence probability Ps(Bi) of each behavior category of the real-time users to form a real-time user behavior category set Ps, where Ps = {Ps(B1), Ps(B2), ..., Ps(Bn)}, where Ps(B1) represents the occurrence probability corresponding to the first behavior category of the real-time user, Ps(B2) represents the occurrence probability corresponding to the second behavior category of the real-time user, and so on, Ps(Bn) represents the occurrence probability corresponding to the nth behavior category of the real-time user; S202. For each demand fluctuation level, obtain the occurrence probability Pl(Bi) of each type of behavior of each historical user corresponding to each demand fluctuation level, thereby forming a historical user behavior category set Pl for each historical user, where Pl = {Pl(B1), Pl(B2), ..., Pl(Bn)}. Similarly, Pl(B1) represents the occurrence probability corresponding to the first behavior category of the historical user, Pl(B2) represents the occurrence probability corresponding to the second behavior category of the historical user, and Pl(Bn) represents the occurrence probability corresponding to the nth behavior category of the historical user. Normalize the elements in the real-time user behavior category set Ps and the historical user behavior category set Pl, and sequentially calculate the similarity between the normalized real-time user behavior category set Ps and the historical user behavior category set Pl for each demand fluctuation level, and average the similarities. The average of the calculated similarities is used as the similarity of the corresponding demand fluctuation level. The similarities of the demand fluctuation levels are arranged in ascending order, and the demand fluctuation level with the greatest similarity is selected as the demand fluctuation level of the real-time user. S203. Calculate the behavior entropy H1 of the real-time user based on the occurrence probability Ps(Bi) of each behavior category of the real-time user; obtain the behavior entropy H of all historical users corresponding to the demand fluctuation level of the real-time user, calculate the absolute value of the difference between the behavior entropy H1 of the real-time user and the behavior entropy H of the historical users, obtain the cultural and tourism demand supply record corresponding to the historical user with the smallest absolute value of the difference, and generate an initial cultural and tourism demand supply matching plan list based on the cultural and tourism demand supply records corresponding to the historical users.

4. The method for intelligent matching of cultural tourism demand and supply based on dual private domain linkage according to claim 3 is characterized by: The step S300 includes: S301. Output the initial cultural tourism demand and supply matching plan list to the real-time user, and the real-time user selects the initial cultural tourism demand and supply matching plan; obtain the real-time user's location information once every selected time period, and obtain the environmental data of the real-time user's location based on the real-time user's location information and the current timestamp; combine the real-time user's location information and the environmental data of the location to extract the cultural tourism demand and supply matching plan implemented by the real-time user; S302. Based on the initial cultural tourism demand and supply matching solution, extract the corresponding initial tourism path CL, where the initial tourism path CL refers to the cultural tourism activities and route arrangement selected by the real-time user, and the nodes of the initial tourism path CL refer to the specific scenic spots in the cultural tourism activities. Based on the cultural tourism demand and supply matching solution implemented by the real-time user, extract the actual tourism path SL of the current real-time user. Based on the number of nodes and the actual starting point of the actual tourism path SL, match the actual starting point of the actual tourism path SL with the initial starting point of the initial tourism path CL. Based on the number of nodes in the actual tourism path SL, extract the initial tourism path segment CL1 with the same number of nodes. S303. Calculate the node sequence deviation J between the actual travel path SL and the corresponding initial travel path segment CL1, and Wherein SL(sj) represents the position number of node sj in the actual travel path SL, CL1(sj) represents the position number of node sj in the initial travel path segment CL1, and node sj is an element in the intersection of the nodes of the actual travel path SL and the initial travel path segment CL1; the node visit deviation V of the actual travel path SL and the initial travel path segment CL1 is calculated, and V = |Visited(SL)\Planned(CL1)|+|Planned(CL1)\Visited(SL)|, where Visited(SL) represents the set of nodes that the real-time user has visited in the actual travel path SL, Planned(CL1) represents the set of nodes planned to be visited in the initial travel path segment CL1, |Visited(SL)\Planned(CL1)| represents the number of nodes visited in the actual travel path SL but not included in the initial travel path segment CL1; |Planned(CL1)\Visited(SL)| represents the number of nodes planned to be visited in the initial travel path segment CL1 but not visited in the actual travel path SL.

5. The method for intelligent matching of cultural tourism demand and supply based on dual private domain linkage according to claim 4 is characterized by: The step S400 includes: S401. Based on the node sequence deviation J and node access deviation V between the implemented cultural tourism demand and supply matching solution of the current real-time user and the initial cultural tourism demand and supply matching solution, the corresponding deviation index R is comprehensively calculated, and R = w1 × J + w2 × V, where w1 and w2 represent weight coefficients, and w1 + w2 = 1; the deviation index R of the current real-time user is compared with the preset deviation threshold R0. If the deviation index R is less than the deviation threshold R0, then there is no need to adjust the initial cultural tourism demand and supply matching solution; if the deviation index R is greater than or equal to the deviation threshold R0, then it is necessary to adjust the initial cultural tourism demand and supply matching solution, and the process goes to S402; S402. Based on the current real-time user's location information and environmental data, extract the node closest to the current real-time user's location and the corresponding historical environmental data from the historical user data in the demand fluctuation level corresponding to the real-time user, calculate the similarity between the current real-time user's environmental data and the historical environmental data, select the cultural and tourism demand supply record corresponding to the historical user with the highest similarity, and generate corresponding adjustment suggestions based on the corresponding cultural and tourism demand supply records. Output the adjustment suggestions to the real-time user for confirmation by the real-time user, thereby obtaining an adjusted cultural and tourism demand supply matching plan.

6. A system for intelligently matching cultural and tourism demand and supply based on dual private domain linkage, applied to a method for intelligently matching cultural and tourism demand and supply based on dual private domain linkage as described in any one of claims 1-5, characterized in that: The system includes: a historical data analysis and grading module, a real-time demand identification and solution generation module, an implementation feedback and analysis module, and a dynamic adjustment and intelligent recommendation module; The historical data analysis and grading module obtains historical user data and the cultural tourism demand and supply matching scheme corresponding to the historical users in the database, analyzes the user demand fluctuation coefficient of the historical users based on the historical user data and the cultural tourism demand and supply matching scheme, and divides the historical users into several demand fluctuation levels based on the user demand fluctuation coefficient; The real-time demand identification and solution generation module obtains real-time user data, analyzes the real-time user data with historical user data of each demand fluctuation level in turn, identifies the demand fluctuation level of the real-time user; and obtains an initial cultural tourism demand supply matching solution list based on the real-time user demand fluctuation level; The implementation feedback and analysis module outputs the list of initial cultural tourism demand and supply matching solutions to the real-time user, and the real-time user selects the initial cultural tourism demand and supply matching solution; obtains the real-time user's location information, obtains corresponding environmental data based on the real-time user's location information and the current timestamp, and analyzes the deviation relationship between the current real-time user's implemented cultural tourism demand and supply matching solution and the initial cultural tourism demand and supply matching solution; The dynamic adjustment and intelligent recommendation module obtains a corresponding deviation index based on the deviation relationship between the current real-time user's implemented cultural and tourism demand supply matching plan and the initial cultural and tourism demand supply matching plan; compares the deviation index with the deviation threshold, and obtains the adjusted cultural and tourism demand supply matching plan based on the comparison result.

7. The intelligent matching system for cultural tourism demand and supply based on dual private domain linkage according to claim 6 is characterized by: The historical data analysis and grading module includes a historical data analysis unit and a demand fluctuation grading unit; The historical data analysis unit obtains the historical user data and the cultural and tourism demand supply matching plan corresponding to the historical users in the database, and analyzes the user demand fluctuation coefficient of the historical users based on the historical user data and the cultural and tourism demand supply matching plan; the demand fluctuation level classification unit divides the historical users into several demand fluctuation levels according to the distribution of the user demand fluctuation coefficient, and determines the range of the user demand fluctuation coefficient of each fluctuation level.

8. The intelligent matching system for cultural tourism demand and supply based on dual private domain linkage according to claim 6 is characterized by: The real-time demand identification and solution generation module includes a real-time user demand identification unit and a solution list generation unit that matches the initial cultural and tourism demand supply; The real-time user demand identification unit obtains real-time user data, analyzes the real-time user data with the historical user data of each demand fluctuation level in turn, and identifies the demand fluctuation level of the real-time user; the initial cultural and tourism demand supply matching solution list generation unit obtains the initial cultural and tourism demand supply matching solution list according to the real-time user's demand fluctuation level.

9. The intelligent matching system for cultural tourism demand and supply based on dual private domain linkage according to claim 6 is characterized by: The implementation feedback and analysis module includes an implementation feedback unit and a deviation analysis unit; The implementation feedback unit outputs the initial cultural tourism demand supply matching solution list to the real-time user, and the real-time user selects the initial cultural tourism demand supply matching solution; obtains the real-time user's location information, and obtains corresponding environmental data based on the real-time user's location information and the current timestamp; The deviation analysis unit analyzes the deviation relationship between the implemented cultural tourism demand and supply matching solution of the current real-time user and the initial cultural tourism demand and supply matching solution based on the real-time user's location information and the current timestamp.

10. The intelligent matching system for cultural tourism demand and supply based on dual private domain linkage according to claim 6 is characterized by: The dynamic adjustment and intelligent recommendation module includes a deviation index calculation unit and an adjustment plan output and confirmation unit; The deviation index calculation unit calculates the corresponding deviation index based on the deviation relationship between the current real-time user's implemented cultural and tourism demand supply matching plan and the initial cultural and tourism demand supply matching plan; the adjustment plan output and confirmation unit generates corresponding adjustment suggestions based on the size relationship between the real-time user's deviation index and the deviation threshold, outputs the adjustment suggestions to the real-time user, and the real-time user confirms them, thereby obtaining the adjusted cultural and tourism demand supply matching plan.

Images