Intelligent terminal tourism resource query method and system

Abstract

The invention relates to the technical field of tourism resource query, and discloses an intelligent terminal tourism resource query method and system, and the system comprises a data collection unit, a feature extraction unit, a preference analysis unit, and a query recommendation unit. According to the method, multi-dimensional data such as historical query records, behavior data, query time, content, number of times, residence time and evaluation scores of the user are comprehensively collected, and a foundation is laid for accurate analysis; secondly, scientifically extracting query times, residence time and evaluation score weights, comprehensively judging preference feature values, and ensuring that user preferences are accurately reflected; furthermore, by calculating a preference ratio and an adjacent period difference value, a preference change trend and stability are clearly presented, and accurate recommendation is facilitated; in a recommendation link, according to a preference analysis result, tourism resources are classified, screened and recommended according to different conditions such as rising and stability, rising but instability, fluctuation and falling, individual demands of users are fully met, and user experience and satisfaction are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of tourism resource query, and in particular to a tourism resource query method and system for an intelligent terminal. Background Art

[0002] With the improvement of people's living standards and the growing demand for tourism, the tourism market is booming and tourism resources are becoming more and more abundant and diverse. At the same time, the widespread popularity of smart terminals has made users tend to query tourism resources through such devices. However, there are many problems with the existing smart terminal tourism resource query methods.

[0003] On the one hand, in the data collection process, traditional methods often only collect single-dimensional data, such as simple query records, which makes it difficult to fully understand users' travel preferences. The inability to effectively collect multi-dimensional data corresponding to user historical query records, behavioral data, and multi-dimensional preference information leads to an insufficient understanding of user needs and an inability to provide users with accurate travel resource recommendations.

[0004] On the other hand, in the feature extraction and preference analysis stage, there is a lack of effective extraction and analysis of the preference features of tourism resource types in different specified periods. The existing methods cannot accurately extract the features of the collected data, and it is difficult to obtain the preference features of various tourism resource types in different specified periods. At the same time, it is also impossible to determine the changing trend of the preference proportion of tourism resource types based on the proportion of preference feature values ​​in different periods, and it is even more impossible to accurately determine the stability of preference features by calculating the average absolute value of the difference in preference proportions between adjacent periods. This makes it impossible to fully consider the changes in user interests over time when querying and recommending tourism resources, and the recommendation results lack pertinence and timeliness.

[0005] In addition, in the query and recommendation process, due to the inadequacy of the previous links, the existing intelligent terminal tourism resource query method cannot provide users with reasonable and personalized tourism resource query recommendations based on the comprehensive and accurate user preference analysis results and the tourism area input by the user. Users often screen a large number of irrelevant tourism resources by themselves, wasting a lot of time and energy, reducing user experience, and affecting the quality and effect of tourism resource query services. Summary of the invention

[0006] The purpose of the present invention is to provide a method and system for querying tourism resources by an intelligent terminal, which solves the technical problems raised in the background technology.

[0007] The purpose of the present invention can be achieved through the following technical solutions: A method for querying tourism resources by an intelligent terminal comprises the following steps: Step 1: Data collection: Collect multi-dimensional data corresponding to user historical query records, behavior data, and multi-dimensional preference information; Step 2: Feature extraction: Perform feature extraction on the collected multi-dimensional data and derive the preference characteristics of various tourism resource types in different specified periods; Step 3: Preference Analysis: According to the preference proportion of each type of tourism resource in each different specified period in the sum of the preference characteristic values ​​in all different specified periods, the changing trend of the preference proportion of each type of tourism resource in different periods is determined; at the same time, by calculating the average of the absolute values ​​of the differences in the preference proportions of all adjacent periods, it is determined whether the preference characteristics of the corresponding tourism resource type are stable; Step 4: Query recommendations: Based on the analysis results of users' preferences for different types of tourism resources, and combined with the tourism area input by the user, tourism resource queries and recommendations are made to the user.

[0008] As a further solution of the present invention: the multi-dimensional data specifically refers to: the user's query time of tourism resources on the tourism resource platform, the query content of tourism resources and its corresponding tourism resource type, the number of queries, the stay time, and the evaluation score.

[0009] As a further solution of the present invention: the feature extraction processing method is as follows: Step A1: Extract query times weight: In the user's corresponding multiple types of tourism resources, according to the query time of tourism resources, in multiple different specified periods, the query times of the query content in each type of tourism resources are obtained and marked as N i，j ; Where i = 1, 2, ... n, j = 1, 2, ... m, n represents the number of types of tourism resources corresponding to the user, and m represents the number of different specified periods; The specified period is the preset value, and j is the ordinal variable of different specified periods; pass: ; Calculate the query weight F of the i-th tourism resource type in each different specified period i，j ; Step A2: Extracting residence time weight: In the case of multiple types of tourism resources corresponding to the user, according to the query time of the tourism resources, the stay time of the query content in each type of tourism resources is obtained within multiple different specified periods and marked as T i，j ; pass: ; Calculate the stay time weight T of the i-th tourism resource type in each different specified period i，j ; Step A3: Extracting evaluation score weights: In the case of multiple types of tourism resources corresponding to the user, according to the query time of the tourism resources, in multiple different specified periods, the evaluation scores of the query content in each type of tourism resources are obtained and marked as P i，j ; Then, according to the pre-set score-emotional tendency table, the algorithm for assigning the emotional tendency coefficients corresponding to each evaluation score is determined; pass: ; Calculate the evaluation score weight K of the i-th tourism resource type in each different specified period i，j ; In the formula, is the emotion regulation coefficient algorithm, β0 is the emotion regulation coefficient preset in the emotion regulation coefficient algorithm; Step A4: Comprehensive determination of preference characteristics: Extract the query times weights F of various tourism resource types in different specified periods i，j , residence time weight T i，j , Evaluation score weight K i，j ; pass: ; Calculate the preference characteristic values ​​HT of various tourism resource types in different specified periods i,j ; In the formula, α P , α T , α K is the corresponding preset proportional coefficient.

[0010] As a further solution of the present invention: wherein the score-emotional tendency table includes score intervals corresponding to different emotional tendencies, and each score interval corresponds to an emotional tendency assignment coefficient algorithm: Different emotional tendencies include positive, neutral, and negative, where positive emotional tendencies refer to users’ high interest in the corresponding type of tourism resources, neutral emotional tendencies refer to users’ general interest in the corresponding type of tourism resources, and negative emotional tendencies refer to users’ low interest in the corresponding type of tourism resources. The total score of the evaluation score is set to Gc, the score interval corresponding to the positive emotional tendency is set to (Gb, Gc], the score interval corresponding to the neutral emotional tendency is set to (Ga, Gb], and the score interval corresponding to the negative emotional tendency is set to [0, Ga]; Wherein, Ga, Gb, and Gc are pre-set fractional values, Ga<Gb<Gc; The algorithm for assigning the coefficient of the positive sentiment tendency to the scoring interval is P i，j ×βc; the algorithm for assigning the sentiment tendency coefficient of the scoring interval corresponding to the neutral sentiment tendency is P i，j ×βb; The algorithm for assigning the coefficient of the negative sentiment tendency to the scoring interval is P i，j ×βa; Among them, βc, βb, and βa represent the dynamic adjustment factors of the emotional tendency weight distribution respectively; βc is the positive emotion adjustment coefficient; βb is the neutral emotion adjustment coefficient; βa is the negative emotion adjustment coefficient.

[0011] As a further solution of the present invention: when calculating the evaluation score weight, β0∈[βc,βb,βa], where P i，j ∈(Gb,Gc], then β0=βc, when P i，j ∈(Ga,Gb], then β0=βb, when P i，j ∈[0,Ga], then β0=βa.

[0012] As a further solution of the present invention: the change trend of the preference feature is determined as follows: First, in all different specified periods, the sum of the preference characteristic values ​​of each tourism resource type in the period is calculated; The calculation formula is: ; In the formula, S j is the sum of the preference characteristic values ​​of each tourism resource type in the corresponding period; Then, the preference proportion of each tourism resource type in each different specified period’s preference characteristic value in the sum of the preference characteristic values ​​in all different specified periods is calculated; The calculation formula is: ; Where PH i,j The preference proportion of the preference characteristic value of each tourism resource type in each different specified period to the sum of the preference characteristic values ​​in the corresponding different specified periods; Then, with the specified period j as the horizontal axis, the preference proportion PH of each tourism resource type i is i,j Draw a line chart or a bar chart for the vertical axis; Then, by observing the drawn line graph or bar graph, the changing trend of the preference proportion of each type of tourism resources in different periods can be determined; Among them, select a type of tourism resources: When the preference ratio of this type of tourism resource shows an upward trend as the period becomes longer, it means that users' interest in this type of tourism resource is gradually accumulating and deepening; When the preference ratio of this type of tourism resource shows a downward trend as the period gets longer, it means that the user's novelty of this type of tourism resource is gradually disappearing, or they have encountered some unsatisfactory situations in the early search experience; When the preference proportion of this type of tourism resource shows a fluctuating trend as the period becomes longer, it is determined that the interest in this type of tourism resource changes due to time factors.

[0013] As a further solution of the present invention: the stability of the preference feature is determined as follows: Select a type of tourism resource as follows: ; Where U i is the average of the absolute values ​​of the differences in the preference proportions of all adjacent periods, and is marked as the preference stability index of this type of tourism resource type; Compare the preference stability index of this type of tourism resource with the pre-set stability value threshold: When the preference stability index is ≤ the stability value threshold, it means that the preference proportion of this type of tourism resources does not change much in different periods, that is, the user's preference for this type of tourism resources is stable; When the preference stability index is greater than the stability value threshold, it means that the preference proportion of this type of tourism resource fluctuates greatly in different periods, that is, the user's preference for this type of tourism resource is unstable.

[0014] As a further solution of the present invention: the query recommendation method is as follows: For a type of tourism resource whose preference ratio shows an upward trend and whose preference is stable, the tourism resources of this type are screened out from the tourism resource database corresponding to the tourism area, and recorded as the first recommended resource, which is then recommended to the user in priority; For a type of tourism resource whose preference ratio shows an upward trend and whose preference is unstable, the tourism resources of this type are screened out from the tourism resource database corresponding to the tourism area, and recorded as the second recommended resource, and then placed after all the tourism resources corresponding to the first recommended resource, and then recommended to the user; For the preference proportion, which shows a fluctuating trend, but the preference for this type of tourism resources is stable, Then, from the tourism resource database corresponding to the tourism area, the tourism resources of this type are screened out and recorded as the third recommended resource, and then placed after all the tourism resources corresponding to the second recommended resource, and then recommended to the user; If the preference ratio shows a fluctuating trend but the preference for this type of tourism resources is unstable, the tourism resources of this type are screened out from the tourism resource database corresponding to the tourism area, and recorded as the fourth recommended resource, and then placed after all the tourism resources corresponding to the third recommended resources, and then recommended to the user; If the preference ratio shows a downward trend but the preference for this type of tourism resources is stable, the tourism resources of this type are screened out from the tourism resource database corresponding to the tourism area, and recorded as the fifth recommended resource, and then placed after all the tourism resources corresponding to the fourth recommended resource, and then recommended to the user; The preference ratio shows a downward trend, but the preference for this type of tourism resources is unstable. Then, the tourism resources of this type are screened out from the tourism resource database corresponding to the tourism area and placed at the end of all recommended tourism resources.

[0015] A smart terminal tourism resource query system, the system is used to implement a smart terminal tourism resource query method, the system includes: A data collection unit, used to collect user historical query records, behavior data, and multi-dimensional data corresponding to multi-dimensional preference information; A feature extraction unit is used to perform feature extraction processing on the collected multi-dimensional data and obtain the preference features of various tourism resource types in different specified periods; The preference analysis unit is used to determine the change trend of the preference ratio of each type of tourism resources in different periods according to the preference ratio of the preference characteristic value of each type of tourism resources in each different specified period to the sum of the preference characteristic values ​​in all different specified periods; at the same time, by calculating the average value of the absolute value of the difference of the preference ratio of all adjacent periods, it is determined whether the preference characteristics of the corresponding tourism resource type are stable; The query recommendation unit is used to make query recommendations on tourism resources to users based on the analysis results of the user's preferences for different types of tourism resources and then in combination with the tourism area input by the user.

[0016] Beneficial effects of the present invention: Multi-dimensional data collection and analysis: By collecting user historical query records, behavioral data, and multi-dimensional data including query time, query content, tourism resource type, query times, stay time, evaluation scores, etc., we can fully and deeply understand the user's preferences for tourism resources. Compared with single-dimensional data collection, multi-dimensional data analysis can more accurately capture the user's interests and provide a solid data foundation for subsequent preference analysis and query recommendations, thereby improving the accuracy and pertinence of recommendations.

[0017] Scientific feature extraction: A scientific and reasonable feature extraction method is adopted to extract from three aspects: query number weight, stay time weight, and evaluation score weight, and comprehensively determine the preference feature value. This multi-factor comprehensive feature extraction method fully considers the various behaviors of users in the query process, and can more accurately reflect the user's true preference for different types of tourism resources, avoiding the one-sidedness of preference judgment by a single factor.

[0018] Accurate preference analysis: Calculate the preference ratio based on the preference feature value, and determine the changing trend of the preference ratio in different periods by drawing a line graph or a bar graph. At the same time, determine the stability of the preference feature by calculating the average absolute value of the difference between the preference ratios in adjacent periods. This analysis method can clearly present the changes in users' interest in different types of tourism resources, including the accumulation and disappearance of interest, the influence of time factors, and the stability of preference, thereby providing a more valuable reference for the accurate recommendation of tourism resources.

[0019] Accurate query recommendation: According to different preference ratio change trends and preference stability, tourism resources are classified and recommended. Resources with increasing and stable preference ratios are recommended first, while resources with decreasing and unstable preference ratios are recommended last. This personalized recommendation strategy can better meet user needs and improve user satisfaction with recommendation results. It also helps to improve the user experience and service quality of the tourism resource platform.

[0020] Adapting to the needs of different users: Considering that users' interest in tourism resources may change with time and query experience, through dynamic analysis and classification recommendation of preference characteristics, it can better adapt to the personalized needs and interest changes of different users, and provide users with tourism resource recommendations that are more in line with their current interests and needs, thereby improving the flexibility and adaptability of the recommendation system.

[0021] Improve platform operation efficiency: Through accurate recommendation of tourism resources, it can improve the query efficiency and satisfaction of users on the platform, increase the frequency and stickiness of users to the platform, thus helping to improve the operation efficiency and commercial value of the platform. At the same time, it can also better promote the promotion and utilization of tourism resources, and achieve a win-win situation for the platform and users. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The present invention will be further described below in conjunction with the accompanying drawings.

[0023] Figure 1 The present invention is a system block diagram of a smart terminal tourism resource query system.

[0024] Figure 2 It is a flow chart of a method for querying tourism resources by an intelligent terminal according to the present invention. DETAILED DESCRIPTION

[0025] 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.

[0026] Embodiment 1 See also Figure 1 As shown, the present invention provides a method for querying tourism resources by an intelligent terminal, comprising: Step 1: Data collection: Collect multi-dimensional data corresponding to user historical query records, behavior data, and multi-dimensional preference information; The multi-dimensional data specifically refers to: the time when users search for tourism resources on the tourism resource platform, the search content of tourism resources and the corresponding tourism resource type, the number of queries, the length of stay, and the evaluation score; Step 2: Feature extraction: Perform feature extraction on the collected multi-dimensional data. The feature extraction processing method is as follows: Step A1: Extract query times weight: In the user's corresponding multiple types of tourism resources, according to the query time of tourism resources, in multiple different specified periods, the query times of the query content in each type of tourism resources are obtained and marked as N i，j ; Where i = 1, 2, ... n, j = 1, 2, ... m, n represents the number of types of tourism resources corresponding to the user, and m represents the number of different specified periods; The specified period is the preset value, and j is the ordinal variable of different specified periods; pass: ; Calculate the query weight F of the i-th tourism resource type in each different specified period i，j ; Step A2: Extracting residence time weight: In the case of multiple types of tourism resources corresponding to the user, according to the query time of the tourism resources, the stay time of the query content in each type of tourism resources is obtained within multiple different specified periods and marked as T i，j ; pass: ; Calculate the stay time weight T of the i-th tourism resource type in each different specified period i，j ; Step A3: Extracting evaluation score weights: In the case of multiple types of tourism resources corresponding to the user, according to the query time of the tourism resources, in multiple different specified periods, the evaluation scores of the query content in each type of tourism resources are obtained and marked as P i，j ; Then, according to the pre-set score-emotional tendency table, the corresponding emotional tendency assignment coefficient is calculated for each evaluation score; Among them, the score-sentiment tendency table contains the score intervals corresponding to different sentiment tendencies, and each score interval corresponds to a sentiment tendency assignment coefficient algorithm: In this embodiment, different emotional tendencies include positive, neutral, and negative, wherein: positive emotional tendency refers to the user's high interest in the corresponding type of tourism resources, neutral emotional tendency refers to the user's general interest in the corresponding type of tourism resources, and negative emotional tendency refers to the user's low interest in the corresponding type of tourism resources; The total score of the evaluation score is set to Gc, the score interval corresponding to the positive emotional tendency is set to (Gb, Gc], the score interval corresponding to the neutral emotional tendency is set to (Ga, Gb], and the score interval corresponding to the negative emotional tendency is set to [0, Ga]; Wherein, Ga, Gb, and Gc are pre-set fractional values, Ga<Gb<Gc; In this embodiment, Ga may be 45, Gb may be 75, and Gc may be 100; The algorithm for assigning the coefficient of the positive sentiment tendency to the scoring interval is P i，j ×βc; the algorithm for assigning the sentiment tendency coefficient of the scoring interval corresponding to the neutral sentiment tendency is P i，j ×βb; The algorithm for assigning the coefficient of the negative sentiment tendency to the scoring interval is P i，j ×βa; Among them, βc, βb, and βa represent the dynamic adjustment factors of the emotional tendency weight distribution respectively; βc is the positive emotional adjustment coefficient, which acts on the scoring interval (Gb, Gc]; βb is the neutral emotional adjustment coefficient, which acts on the scoring interval (Ga, Gb]; βa is the negative emotional adjustment coefficient, which acts on the scoring interval [0, Ga]; In this embodiment, βa may be 45, βb may be 75, and βc may be 100; pass: ; Calculate the evaluation score weight K of the i-th tourism resource type in each different specified period i，j ; In the formula, β0∈[βc,βb,βa], when P i，j∈(Gb,Gc], then β0 is βc, when P i，j ∈(Ga,Gb], then β0 is βb, when P i，j ∈[0,Ga], then β0 is βa; Step A4: Comprehensive determination of preference characteristics: Extract the query times weights F of various tourism resource types in different specified periods i，j , residence time weight T i，j , Evaluation score weight K i，j ; pass: ; Calculate the preference characteristic values ​​HT of various tourism resource types in different specified periods i,j ; In the formula, α P , α T , α K is the corresponding preset proportional coefficient; Step 3: Preference ratio analysis: First, in all different specified periods, the sum of the preference characteristic values ​​of each tourism resource type in the period is calculated; The calculation formula is: ; In the formula, S j is the sum of the preference characteristic values ​​of each tourism resource type in the corresponding period; Then, the preference proportion of each tourism resource type in each different specified period to the sum of the preference characteristic values ​​in the corresponding different specified periods is calculated; The calculation formula is: ; Where PH i,j The preference proportion of the preference characteristic value of each tourism resource type in each different specified period to the sum of the preference characteristic values ​​in the corresponding different specified periods; Then, with the specified period j as the horizontal axis, the preference proportion PH of each tourism resource type i is i,j Draw a line chart or a bar chart for the vertical axis; Then, by observing the drawn line graph or bar graph, the changing trend of the preference proportion of each type of tourism resources in different periods can be determined; Among them, select a type of tourism resources: When the preference ratio of this type of tourism resource shows an upward trend as the period becomes longer, it means that users' interest in this type of tourism resource is gradually accumulating and deepening; When the preference ratio of this type of tourism resource shows a downward trend as the period gets longer, it means that the user's novelty of this type of tourism resource is gradually disappearing, or they have encountered some unsatisfactory situations in the early search experience; When the preference ratio of this type of tourism resource shows a fluctuating trend as the period becomes longer, it is determined that the interest in this type of tourism resource changes due to time factors; Step 4: Query recommendations: Based on the analysis results of the user's preference for different types of tourism resources, and then combined with the tourism area entered by the user, the user is recommended to query tourism resources; The details are as follows: For the tourism resource types whose preference ratios show an increasing trend, the tourism resources of this type are screened out from the tourism resource database corresponding to the tourism area, and recorded as the first recommended resource, which is then recommended to the user in priority; For a type of tourism resource whose preference ratio shows a fluctuating trend, the tourism resources of this type are screened out from the tourism resource database corresponding to the tourism area, and recorded as the second recommended resource, and then placed after all the tourism resources corresponding to the first recommended resource, and then recommended to the user; For the tourism resource types whose preference ratios show a downward trend, the tourism resources of this type are screened out from the tourism resource database corresponding to the tourism area and placed at the end of all recommended tourism resources.

[0027] The intelligent terminal tourism resource query method and system of embodiment 1 comprehensively collects user historical query records, behavior data and multi-dimensional preference information to perform in-depth feature extraction and preference ratio analysis. The preference feature values ​​are calculated using multi-dimensional weights such as the number of queries, residence time and evaluation scores, and then the changing trend of the preference ratio of each type of tourism resource is analyzed. This method can accurately grasp the changes in user interest in different types of tourism resources, such as rising, falling or fluctuating trends. Based on this analysis result, tourism resources are recommended in combination with the tourism area input by the user, and resources with an increased preference ratio are recommended first, which can better fit the user's interests, improve the accuracy of the recommendation and the user's satisfaction with tourism resource queries, and provide users with more personalized tourism resource recommendation services.

[0028] Embodiment 2 See also Figure 1 As shown, as the second embodiment of the present invention, when the present application is implemented, compared with the first embodiment, the technical solution of this embodiment is different from that of the first embodiment only in that: the preference proportion analysis of the first embodiment is modified to the preference stability analysis, and the method is as follows: By calculating the average absolute value of the difference in preference proportions of all adjacent periods, we can determine whether the preference characteristics of the corresponding tourism resource type are stable. Select a type of tourism resource as follows: ; Where U iis the average of the absolute values ​​of the differences in the preference proportions of all adjacent periods, and is marked as the preference stability index of this type of tourism resource type; Compare the preference stability index of this type of tourism resource with the pre-set stability value threshold: When the preference stability index is ≤ the stability value threshold, it means that the preference proportion of this type of tourism resources does not change much in different periods, that is, the user's preference for this type of tourism resources is stable; When the preference stability index is greater than the stability value threshold, it means that the preference proportion of this type of tourism resource fluctuates greatly in different periods, that is, the user's preference for this type of tourism resource is unstable; This embodiment also makes a query recommendation of tourism resources to the user based on the stability analysis result of the user's preference for different types of tourism resources and then combines it with the tourism area input by the user; The details are as follows: For the type of tourism resources that prefer stable tourism, the tourism resources of this type are screened out from the tourism resource database corresponding to the tourism area, and are recommended to users first; For tourism resource types with unstable preferences, tourism resources of this type are screened out from the tourism resource database corresponding to the tourism area and placed at the end of all priority recommended tourism resources.

[0029] Embodiment 2 is based on Embodiment 1, and the preference ratio analysis is modified into the preference stability analysis. The preference stability index is obtained by calculating the average value of the absolute value of the difference in preference ratios of adjacent periods, and compared with the stability value threshold, so as to clearly judge the stability of the user's preference for different types of tourism resources. Tourism resources are recommended based on the results of the preference stability analysis, and resources with stable preferences are recommended first, which can meet the user's stable tourism interest needs, reduce the situation where the recommended resources do not meet the user's needs due to fluctuations in user preferences, make the recommended tourism resources more in line with the user's long-term stable interests, and enhance the user's tourism resource query experience.

[0030] Embodiment 3 See also Figure 1 As shown, as the third embodiment of the present invention, when the present application is implemented, compared with the first and second embodiments, the technical solution of this embodiment is to combine the solutions of the first and second embodiments, and the difference between the technical solution of this embodiment and the first and second embodiments is only in this embodiment; Based on the analysis results of the user's preference ratio and preference stability for different types of tourism resources, and then combined with the tourism area input by the user, the user is recommended to query tourism resources; The details are as follows: For a type of tourism resource whose preference ratio shows an upward trend and whose preference is stable, the tourism resources of this type are screened out from the tourism resource database corresponding to the tourism area, and recorded as the first recommended resource, which is then recommended to the user in priority; For a type of tourism resource whose preference ratio shows an upward trend and whose preference is unstable, the tourism resources of this type are screened out from the tourism resource database corresponding to the tourism area, and recorded as the second recommended resource, and then placed after all the tourism resources corresponding to the first recommended resource, and then recommended to the user; For the preference proportion, which shows a fluctuating trend, but the preference for this type of tourism resources is stable, Then, from the tourism resource database corresponding to the tourism area, the tourism resources of this type are screened out and recorded as the third recommended resource, and then placed after all the tourism resources corresponding to the second recommended resource, and then recommended to the user; If the preference ratio shows a fluctuating trend but the preference for this type of tourism resources is unstable, the tourism resources of this type are screened out from the tourism resource database corresponding to the tourism area, and recorded as the fourth recommended resource, and then placed after all the tourism resources corresponding to the third recommended resources, and then recommended to the user; If the preference ratio shows a downward trend but the preference for this type of tourism resources is stable, the tourism resources of this type are screened out from the tourism resource database corresponding to the tourism area, and recorded as the fifth recommended resource, and then placed after all the tourism resources corresponding to the fourth recommended resource, and then recommended to the user; The preference ratio shows a downward trend, but the preference for this type of tourism resources is unstable. Then, the tourist resources of this type are selected from the tourist resource database corresponding to the tourist area, and are placed at the end of all the recommended tourist resources; Embodiment 3 combines the solutions of Embodiment 1 and Embodiment 2, and comprehensively considers the results of preference ratio analysis and preference stability analysis to recommend tourism resources. The types of tourism resources are subdivided according to the preference ratio trend and preference stability, such as the preference ratio rising and stable, rising but unstable, and other situations, and graded recommendations are made according to different situations. This comprehensive and detailed recommendation method can fully consider the dynamic changes and stability of user interests, further improve the accuracy and personalization of tourism resource recommendations, provide users with tourism resource recommendations that are more in line with their interests and needs, and improve users' satisfaction and experience in the process of tourism resource query.

[0031] Embodiment 4 See also Figure 1As shown, as the fourth embodiment of the present invention, when the present application is implemented specifically, compared with the first, second and third embodiments, the technical solution of this embodiment is to combine the solutions of the above-mentioned first, second and third embodiments for implementation.

[0032] Embodiment 4 combines the solutions of Embodiment 1, Embodiment 2 and Embodiment 3, integrating multiple analysis dimensions and recommendation strategies. By comprehensively integrating the advantages of each embodiment, it can analyze the user's preference for tourism resources more comprehensively and in-depth, taking into account both the changing trend of the preference proportion and the stability of the preference. This comprehensive method can provide more accurate, detailed and personalized tourism resource recommendations, meet the user's diverse tourism interest needs to the greatest extent, provide users with the best tourism resource query recommendation service, and significantly improve the user's experience and satisfaction in the tourism resource query process.

[0033] See also Figure 2 As shown, the present invention also provides a smart terminal tourism resource query system, which is used to implement a smart terminal tourism resource query method, and the system includes: A data collection unit, used to collect user historical query records, behavior data, and multi-dimensional data corresponding to multi-dimensional preference information; A feature extraction unit is used to perform feature extraction processing on the collected multi-dimensional data and obtain the preference features of various tourism resource types in different specified periods; The preference analysis unit is used to determine the change trend of the preference ratio of each type of tourism resources in different periods according to the preference ratio of the preference characteristic value of each type of tourism resources in each different specified period to the sum of the preference characteristic values ​​in all different specified periods; at the same time, by calculating the average value of the absolute value of the difference of the preference ratio of all adjacent periods, it is determined whether the preference characteristics of the corresponding tourism resource type are stable; The query recommendation unit is used to make query recommendations on tourism resources to users based on the analysis results of the user's preferences for different types of tourism resources and then in combination with the tourism area input by the user.

[0034] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0035] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for querying tourism resources by an intelligent terminal, characterized in that: The following steps are involved: Collect multi-dimensional data corresponding to the user's query time, query content and corresponding tourism resource type, query times, stay time and evaluation score on the tourism resource platform; perform feature extraction processing on the collected multi-dimensional data, and derive preference features of various tourism resource types in different specified periods; According to the preference proportion of each type of tourism resource in each different specified period in the sum of the preference characteristic values ​​in all different specified periods, the changing trend of the preference proportion of each type of tourism resource in different periods is determined; at the same time, by calculating the average of the absolute values ​​of the differences in the preference proportions of all adjacent periods, it is determined whether the preference characteristics of the corresponding tourism resource type are stable; Based on the analysis results of users' preferences for different types of tourism resources, and combined with the tourism area input by the user, tourism resource queries and recommendations are made to the user.

2. A method for querying tourism resources by an intelligent terminal according to claim 1, characterized in that: The feature extraction process is as follows: Among the multiple types of tourism resources corresponding to the user, according to the query time of the tourism resources, in multiple different specified periods, the query times of the query content in each type of tourism resources are obtained, and then the proportion of the query times of the query content in a single type of tourism resources in the total query times of the query content in all types of tourism resources is calculated, and the proportion is recorded as the query times weight of various tourism resource types in each different specified period; Among the multiple types of tourism resources corresponding to the user, according to the query time of the tourism resources, within multiple different specified periods, the residence time of the query content in each type of tourism resources is obtained, and then the proportion of the residence time of the query content in a single type of tourism resources in the total residence time of the query content in all types of tourism resources is calculated, and it is recorded as the residence time weight of each type of tourism resource in each different specified period; Among the various types of tourism resources corresponding to the user, the evaluation scores of the query contents in each type of tourism resources are obtained within a plurality of different specified periods according to the query time of the tourism resources; then, according to a pre-set score-sentiment tendency table, the sentiment tendency assignment coefficient algorithm corresponding to each evaluation score is determined, and then, according to the evaluation score combined with the sentiment tendency assignment coefficient algorithm, the sentiment tendency assignment coefficient is obtained; Then, the proportion of the sentiment tendency assignment coefficient corresponding to a single type of tourism resources in the sum of the sentiment tendency assignment coefficients corresponding to all types of tourism resources is calculated, and recorded as the evaluation score weight of various types of tourism resources in different specified periods; pass: ; Calculate the preference characteristic values ​​HT of various tourism resource types in different specified periods i,j ; In the formula, α P , α T , α K is the corresponding preset proportional coefficient; F i，j , T i，j , K i，j They are the query count weight, stay time weight, and evaluation score weight of various tourism resource types in different specified periods, i=1, 2, ...n, j=1, 2, ...m, n represents the number of tourism resource types corresponding to users, and m represents the number of different specified periods.

3. A method for querying tourism resources by an intelligent terminal according to claim 2, characterized in that: in, The score-sentiment tendency table contains the score intervals corresponding to different sentiment tendencies, and each score interval corresponds to a sentiment tendency assignment coefficient algorithm: Different emotional tendencies include positive, neutral, and negative; The total score of the evaluation score is set to Gc, the score interval corresponding to the positive emotional tendency is set to (Gb, Gc], the score interval corresponding to the neutral emotional tendency is set to (Ga, Gb], and the score interval corresponding to the negative emotional tendency is set to [0, Ga]; where Ga, Gb, and Gc are pre-set score values, and Ga<Gb<Gc; The algorithm for assigning the coefficient of the positive sentiment tendency to the scoring interval is P i，j ×βc; the algorithm for assigning the sentiment tendency coefficient of the scoring interval corresponding to the neutral sentiment tendency is P i，j ×βb; The algorithm for assigning the coefficient of the negative sentiment tendency to the scoring interval is P i，j ×βa; where βc, βb, and βa represent the dynamic regulatory factors of the emotional tendency weight distribution respectively; βc is the positive emotional regulation coefficient; βb is the neutral emotional regulation coefficient; and βa is the negative emotional regulation coefficient.

4. A method for querying tourism resources by an intelligent terminal according to claim 3, characterized in that: Evaluation score weight K i，j The calculation formula is: ; In the formula, is the emotion regulation coefficient algorithm, The result value is the emotion regulation coefficient, and β0 is the emotion regulation coefficient pre-set in the emotion regulation coefficient algorithm.

5. A method for querying tourism resources by an intelligent terminal according to claim 4, characterized in that: When calculating the evaluation score weight, β0∈[βc,βb,βa], where P i，j ∈(Gb,Gc], then β0=βc, when P i，j ∈(Ga,Gb], then β0=βb, when P i，j ∈[0,Ga], then β0=βa.

6. A method for querying tourism resources by an intelligent terminal according to claim 2, characterized in that: The changing trend of preference characteristics is determined as follows: First, in all different specified periods, the sum of the preference characteristic values ​​of each tourism resource type in the period is calculated; Then, the preference ratio of each tourism resource type in each different specified period to the sum of the preference characteristic values ​​in all different specified periods is calculated and marked as PH i,j ; Then, with the specified period j as the horizontal axis, the preference proportion PH of each tourism resource type i is i,j Draw a line chart or a bar chart for the vertical axis; Subsequently, by observing the drawn line graph or bar graph, the changing trend of the preference proportion of each type of tourism resources in different periods can be determined; Changing trends include: upward trend, downward trend and fluctuating trend.

7. A method for querying tourism resources by an intelligent terminal according to claim 6, characterized in that: The stability of the preference feature is determined as follows: Select a type of tourism resource as follows: ; Where U i is the average of the absolute values ​​of the differences in the preference proportions of all adjacent periods, and is marked as the preference stability index of this type of tourism resource type; The preference stability index of this type of tourism resource is compared with a preset stability value threshold, and based on the comparison result, it is determined whether the user's preference for this type of tourism resource is stable.

8. A method for querying tourism resources by an intelligent terminal according to claim 7, characterized in that: When the preference stability index is ≤ the stability value threshold, it means that the user's preference for this type of tourism resources is stable; otherwise, it means that the user's preference for this type of tourism resources is unstable.

9. A method for querying tourism resources by an intelligent terminal according to claim 8, characterized in that: The recommended query methods are as follows: For a type of tourism resource whose preference ratio shows an upward trend and whose preference is stable, the tourism resources of this type are screened out from the tourism resource database corresponding to the tourism area, and recorded as the first recommended resource, which is then recommended to the user in priority; For a type of tourism resource whose preference ratio shows an upward trend and whose preference is unstable, the tourism resources of this type are screened out from the tourism resource database corresponding to the tourism area, and recorded as the second recommended resource, and then placed after all the tourism resources corresponding to the first recommended resource, and then recommended to the user; For the preference proportion, which shows a fluctuating trend, but the preference for this type of tourism resources is stable, Then, from the tourism resource database corresponding to the tourism area, the tourism resources of this type are screened out and recorded as the third recommended resource, and then placed after all the tourism resources corresponding to the second recommended resource, and then recommended to the user; If the preference ratio shows a fluctuating trend but the preference for this type of tourism resources is unstable, the tourism resources of this type are screened out from the tourism resource database corresponding to the tourism area, and recorded as the fourth recommended resource, and then placed after all the tourism resources corresponding to the third recommended resources, and then recommended to the user; If the preference ratio shows a downward trend but the preference for this type of tourism resources is stable, the tourism resources of this type are screened out from the tourism resource database corresponding to the tourism area, and recorded as the fifth recommended resource, and then placed after all the tourism resources corresponding to the fourth recommended resource, and then recommended to the user; The preference ratio shows a downward trend, but the preference for this type of tourism resources is unstable. Then, the tourist resources of this type are selected from the tourist resource database corresponding to the tourist area and placed at the end of all the recommended tourist resources.

10. A smart terminal tourism resource query system, the system is used to implement a smart terminal tourism resource query method according to any one of claims 1 to 9, characterized in that: The system includes: A data collection unit, used to collect user historical query records, behavior data, and multi-dimensional data corresponding to multi-dimensional preference information; A feature extraction unit is used to perform feature extraction processing on the collected multi-dimensional data and obtain the preference features of various tourism resource types in different specified periods; The preference analysis unit is used to determine the change trend of the preference ratio of each type of tourism resources in different periods according to the preference ratio of the preference characteristic value of each type of tourism resources in each different specified period to the sum of the preference characteristic values ​​in all different specified periods; at the same time, by calculating the average value of the absolute value of the difference of the preference ratio of all adjacent periods, it is determined whether the preference characteristics of the corresponding tourism resource type are stable; The query recommendation unit is used to make query recommendations on tourism resources to users based on the analysis results of the user's preferences for different types of tourism resources and then in combination with the tourism area input by the user.

Images