Big data analysis-based online exhibition service management system and method

Abstract

The invention relates to the field of service management, and discloses a big data analysis-based online exhibition service management system and method, which uploads collected and recorded exhibition information data to a cloud database for processing, and analyzes the exhibition information data during an exhibition to perform traffic analysis, thereby improving the service management efficiency. And then the matching degree of the exhibitors and the booths is analyzed based on the flow analysis result, and the booth matching degree and the audience preference degree are comprehensively analyzed in combination with the analysis result of the browsing paths and the interactive behaviors of the audiences, so that the booths are subjected to priority ranking, and intelligent recommendation is performed to the exhibitors. The effect evaluation module evaluates the recommendation effect of the booth, and dynamically adjusts the booth sequence in real time according to the evaluation result, thereby facilitating the continuous optimization of the recommendation effect of the booth, improving the accuracy, reliability and recommendation efficiency of the booth recommendation, and improving the recommendation efficiency of the booth. Therefore, automation and intelligentization of booth recommendation and distribution are realized more comprehensively.

Description

Technical Field

[0001] The present invention relates to the field of service management technology, and more specifically to an online exhibition service management system and method based on big data analysis. Background Art

[0002] With the rapid development of e-commerce and Internet technology, online exhibitions have become an important form of exhibitions, providing exhibitors and visitors with a more convenient and efficient communication platform. Therefore, the problem that offline exhibition activities are greatly restricted can be solved through the online exhibition service management system. The online exhibition service management system can manage booth resources more effectively, mainly through big data technology analysis and prediction of booth demand, so that exhibitors can understand booth information in a timely manner, and make online reservations and adjustments to booths;

[0003] However, the above process still has the following disadvantages:

[0004] First, the existing online exhibition service management system lacks in-depth data analysis capabilities and is unable to perform complex traffic analysis, preference analysis, and matching degree calculations, which may result in inaccurate and unreliable booth recommendation results;

[0005] Second, the existing online exhibition service management system lacks the ability to collect and monitor visitors' browsing paths and interactive behaviors, making it impossible to make intelligent recommendations for booths efficiently and accurately, resulting in low recommendation efficiency. At the same time, it lacks the ability to dynamically adjust recommendation strategies based on real-time data, resulting in the inability to continuously optimize recommendation effects. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art, the present invention provides an online exhibition service management system and method for big data analysis to solve the problems existing in the above-mentioned background technology.

[0007] The present invention provides the following technical solution: an online exhibition service management system for big data analysis, comprising:

[0008] Exhibition information collection module: used to collect and record exhibition information data in real time, including exhibitor information, booth information and visitor information, and upload the collected exhibition information data to the cloud database;

[0009] Traffic analysis module: used to monitor and analyze exhibition information data in real time during the exhibition, obtain the distribution of traffic flow and the attention of exhibits, and transmit the traffic analysis results to the booth matching analysis module;

[0010] Booth matching analysis module: Analyzes the matching degree between exhibitors and booths based on the traffic analysis results, calculates the booth matching degree, and transmits the booth matching analysis results to the intelligent recommendation module;

[0011] Audience behavior analysis module: obtains audience preferences by analyzing audience browsing paths and interactive behaviors, and transmits audience behavior analysis results to the intelligent recommendation module;

[0012] Intelligent recommendation module: Analyzes booth matching and visitor preference, calculates booth recommendation coefficients, prioritizes booths based on the best booth recommendation coefficients, and makes intelligent recommendations to exhibitors;

[0013] Effect evaluation module: used to evaluate the effect of booth recommendations. By collecting and analyzing booth reservation rates, booth renewal rates, and booth utilization rates, the recommendation effect evaluation coefficient is obtained, and the recommended booths are adjusted dynamically in real time based on the recommendation effect evaluation coefficient.

[0014] Preferably, the exhibition information collection module establishes an online exhibition service platform and sets up a database in the cloud to store exhibitor information, booth information and visitor information, automatically collects exhibitor information, booth information and visitor information through forms, questionnaires and platform interactions, and transmits the collected data in real time to the cloud database through an API interface for storage;

[0015] The exhibitor information includes the number of exhibitors, exhibition history and exhibition payment fees; the booth information includes the number of reservations, usage time, booth area, the number of exhibitors that can be accommodated and booth price; the audience information includes online stay time, interaction frequency and the number of visits to the booth.

[0016] Preferably, the traffic analysis module first performs data preprocessing on the collected exhibition information data, and the data preprocessing process includes data cleaning and data integration, by real-time tracking of visitors' activities on the platform, recording visit time and access path, and monitoring the number of visits to booths and activities;

[0017] The flow distribution degree is calculated by analyzing the distribution of visitors in various booths and activities over a period of time.

[0018] The exhibit attention degree A2 is calculated by counting and analyzing the number of visits, the number of interactions and the dwell time of the exhibits within a period of time.

[0019] Preferably, the booth matching analysis module constructs a booth feature vector X={A1, A2, A3, A4} for each booth, which includes the distribution of traffic flow, exhibit attention, booth price and booth area, and constructs a preference feature vector Y={B1, B2, B3, B4} according to the exhibitors' preferences, which includes the traffic flow preference value, exhibit attention preference value, booth price preference value and booth area preference value, and then comprehensively analyzes and calculates the booth matching degree;

[0020] The specific analysis method of the booth matching degree is as follows:

[0021] Step S311: Analyze based on the booth feature vector X = {A1, A2, A3, A4} and the preference feature vector Y = {B1, B2, B3, B4}, and calculate the distance between the booth feature vector and the preference feature vector as

[0022] Step S312: Analyze based on the distance Distance(X, Y) between the booth feature vector and the preference feature vector, and calculate the booth matching degree as max(Distance) represents the maximum distance between the booth feature vector and the preference feature vector;

[0023] By presetting a booth matching threshold θ, the booth matching degree K is compared with the booth matching threshold θ, and the booths matching the exhibitors' needs are screened out. If the booth matching degree K ≥ the booth matching threshold θ, these booths are considered to be more matched with the exhibitors' needs, and the qualified booths are screened out, and the booth matching degree values ​​of these screened booths are transmitted to the intelligent recommendation module for intelligent recommendation analysis. If the booth matching degree K < the booth matching threshold θ, these booths are considered to be unmatched with the exhibitors' needs and are screened out.

[0024] Preferably, the audience behavior analysis module analyzes the audience's browsing path and interactive behavior, and calculates the audience's preference level using the specific calculation formula: l represents the number of interactions of visitors at the booth, l′ represents the total number of interactions of visitors at all booths, r represents the total number of characters of comments of visitors at the booth, r′ represents the total number of characters of comments of visitors at all booths, T represents the duration of visitors’ stay at the booth, and T′ represents the total browsing time of visitors at the exhibition.

[0025] Preferably, the intelligent recommendation module recommends the best booth for each exhibitor by intelligently recommending and allocating booths and sorting the booths according to their priority levels, and the recommendation results include multiple screened booths for the exhibitors to choose from;

[0026] The specific calculation formula of the booth recommendation coefficient is: K represents the booth matching degree, P represents the audience preference degree, c represents a positive number, and c>1;

[0027] The selected booths are sorted in descending order by the booth recommendation coefficient R. The larger the booth recommendation coefficient value calculated for the booth is, the higher the priority of the booth is. According to the booth sorting results, a recommendation list is generated and the booth sorting is recommended to exhibitors in the form of a recommendation list.

[0028] Preferably, the effect evaluation module monitors the intelligent recommendation process of booths in real time, analyzes and evaluates the recommended effect of booths, thereby dynamically adjusting the recommended order of booths in the recommendation list, and then re-recommends the adjusted booth order to the exhibitors;

[0029] The specific calculation formula of the recommended effect evaluation coefficient is: q represents the booth reservation rate, p represents the booth renewal rate, and d represents the booth utilization rate;

[0030] The recommendation effect evaluation coefficient I is compared with the preset recommendation threshold μ. If the recommendation effect evaluation coefficient I<the preset recommendation threshold μ, it means that the effect of recommending the recommended order of booths to exhibitors is not ideal, and the order of booths in the recommendation list needs to be re-sorted according to the recommendation effect evaluation coefficient; if the recommendation effect evaluation coefficient I≥the preset recommendation threshold μ, it means that the effect of recommending the recommended order of booths to exhibitors is relatively ideal, and there is no need to adjust the order of booths.

[0031] To achieve the above object, the present invention provides the following technical solution: an online exhibition service management method based on big data analysis, using the above online exhibition service management system based on big data analysis, comprising the following steps:

[0032] S1: Used to collect and record exhibition information data in real time, including exhibitor information, booth information and visitor information, and upload the collected exhibition information data to the cloud database;

[0033] S2: Used to monitor and analyze exhibition information data in real time during the exhibition to obtain the distribution of traffic flow and the attention paid to exhibits;

[0034] S3: Analyze the matching degree between exhibitors and booths based on the traffic analysis results, and calculate the booth matching degree;

[0035] S4: Get the audience's preference by analyzing the audience's browsing path and interactive behavior;

[0036] S5: Analyze the booth matching degree and visitor preference, calculate the booth recommendation coefficient, prioritize the booths according to the best booth recommendation coefficient, and make intelligent recommendations to exhibitors;

[0037] S6: By collecting and analyzing the booth reservation rate, booth renewal rate and booth utilization rate, the recommendation effect evaluation coefficient is obtained, and the recommended booth is dynamically adjusted in real time according to the recommendation effect evaluation coefficient.

[0038] Technical effects and advantages of the present invention:

[0039] The present invention collects and records exhibition information data in real time through an exhibition information collection module, and uploads the collected exhibition information data to a cloud database; monitors and analyzes the exhibition information data during the exhibition in real time through a traffic analysis module to obtain the distribution degree of human traffic and the degree of attention to exhibits; analyzes the degree of matching between exhibitors and booths based on the traffic analysis results through a booth matching analysis module; analyzes the browsing path and interactive behavior of the audience through an audience behavior analysis module; comprehensively analyzes the booth matching degree and the audience preference degree through an intelligent recommendation module, thereby prioritizing the booths and making intelligent recommendations to exhibitors; evaluates the recommended effect of the booths through an effect evaluation module, and dynamically adjusts the booth sequence in real time according to the evaluation results, which is conducive to continuously optimizing the recommended effect of the booths; analyzes by combining traffic analysis, preference analysis and matching degree, which is conducive to improving the accuracy and reliability of booth recommendations; analyzes the recommended order of booths in combination with the browsing path and interactive behavior of the audience, which is conducive to improving the recommendation efficiency of booths, thereby more comprehensively realizing the automation and intelligence of booth recommendation allocation. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a system structure block diagram of the present invention.

[0041] Figure 2 It is a diagram of the method steps of the present invention. DETAILED DESCRIPTION

[0042] The technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the present invention. In addition, the forms of the various structures recorded in the following embodiments are merely illustrative. The online exhibition service management system and method for big data analysis involved in the present invention are not limited to the various structures recorded in the following embodiments. All other implementations obtained by ordinary technicians in this field without making creative work belong to the scope of protection of the present invention.

[0043] like Figure 1 This embodiment provides an online exhibition service management system for big data analysis, including:

[0044] Exhibition information collection module: used to collect and record exhibition information data in real time, including exhibitor information, booth information and visitor information, and upload the collected exhibition information data to the cloud database.

[0045] In this embodiment, the exhibition information collection module establishes an online exhibition service platform and sets up a database in the cloud to store exhibitor information, booth information and visitor information, automatically collects exhibitor information, booth information and visitor information through forms, questionnaires and platform interactions, and transmits the collected data in real time to the cloud database through the API interface for storage;

[0046] The exhibitor information includes the number of exhibitors, exhibition history and exhibition payment fees; the booth information includes the number of reservations, usage time, booth area, the number of exhibitors that can be accommodated and booth price; the audience information includes online stay time, interaction frequency and the number of visits to the booth.

[0047] It should be noted that the specific operations for collecting exhibition information data include:

[0048] Exhibitor information collection: Design an online registration form, requiring exhibitors to fill in relevant information, and automatically collect exhibitors' login information and booth configuration requirements through the platform background;

[0049] Booth information collection: Create a configuration form for each booth on the platform and ask exhibitors to fill in the booth's specific information. Collect the booth's interactive content and design elements through the interactive platform;

[0050] Audience information collection: Design audience registration forms, collect basic information and interest preference information, and track audience browsing behavior and interaction records through the platform;

[0051] By establishing corresponding data tables in the cloud database, it is used to store exhibitor, booth and visitor information.

[0052] Traffic analysis module: used to monitor and analyze exhibition information data in real time during the exhibition, obtain the distribution of traffic flow and the attention of exhibits, and transmit the traffic analysis results to the booth matching analysis module.

[0053] In this embodiment, the traffic analysis module first performs data preprocessing on the collected exhibition information data. The data preprocessing process includes data cleaning and data integration. By real-time tracking of visitors' activities on the platform, recording access time and access path, and monitoring the number of visits to booths and activities;

[0054] The flow distribution degree is calculated by analyzing the distribution of visitors in various booths and activities over a period of time.

[0055] The exhibit attention degree A2 is calculated by counting and analyzing the number of visits, the number of interactions and the dwell time of the exhibits within a period of time.

[0056] It should be noted that the specific calculation formula for the distribution of passenger flow is: N represents the number of booth visits, S represents the booth area, and N i represents the number of visits to the ith booth, N′ represents the total number of visits to the exhibition, n represents the total number of booths, T represents the visitor's stay time at the booth, T′ represents the total browsing time of the visitor at the exhibition, α, β, γ represent weight coefficients;

[0057] The specific calculation formula for the exhibits’ attention is: V represents the total number of times each exhibit is viewed, V′ represents the total number of times all exhibits are viewed, I represents the number of interactions on each exhibit, I′ represents the sum of the number of interactions on all exhibits, C represents the average length of time visitors spend on each exhibit, and C′ represents the average length of time visitors spend on all exhibits.

[0058] Booth matching analysis module: Analyze the matching degree between exhibitors and booths based on the traffic analysis results, calculate the booth matching degree, and transmit the booth matching analysis results to the intelligent recommendation module.

[0059] In this embodiment, the booth matching analysis module constructs a booth feature vector X={A1, A2, A3, A4} for each booth, which includes the distribution of traffic flow, exhibit attention, booth price and booth area, and constructs a preference feature vector Y={B1, B2, B3, B4} according to the exhibitors' preferences, which includes the traffic flow preference value, exhibit attention preference value, booth price preference value and booth area preference value, and then comprehensively analyzes and calculates the booth matching degree;

[0060] The specific analysis method of the booth matching degree is as follows:

[0061] Step S311: Analyze based on the booth feature vector X = {A1, A2, A3, A4} and the preference feature vector Y = {B1, B2, B3, B4}, and calculate the distance between the booth feature vector and the preference feature vector as

[0062] Step S312: Analyze based on the distance Distance(X, Y) between the booth feature vector and the preference feature vector, and calculate the booth matching degree as max(Distance) represents the maximum distance between the booth feature vector and the preference feature vector;

[0063] By presetting a booth matching threshold θ, the booth matching degree K is compared with the booth matching threshold θ, and the booths matching the exhibitors' needs are screened out. If the booth matching degree K ≥ the booth matching threshold θ, these booths are considered to be more matched with the exhibitors' needs, and the qualified booths are screened out, and the booth matching degree values ​​of these screened booths are transmitted to the intelligent recommendation module for intelligent recommendation analysis. If the booth matching degree K < the booth matching threshold θ, these booths are considered to be unmatched with the exhibitors' needs and are screened out.

[0064] It should be noted that the specific calculation formula for the traffic preference value is: Q 实 represents the actual monitored flow of people, Q 预 represents the expected flow of visitors, w1 represents the weight coefficient, and the specific value is set according to the exhibitors’ emphasis on the flow of visitors;

[0065] The specific calculation formula for the exhibit attention preference value is: L represents the number of times an exhibit has been noticed, L′ represents the number of times an exhibit has been visited, and w2 represents the weight coefficient, the specific value of which is set according to the exhibitor’s emphasis on the flow of people;

[0066] The specific calculation formula for the booth price preference value is: R 预 A3 represents the booth budget, A4 represents the booth price, and W3 represents the weight coefficient. The specific value is set according to the exhibitor's emphasis on traffic flow.

[0067] The specific calculation formula for the booth area preference value is: A4 stands for booth area, H 需 It represents the required booth area, w4 represents the weight coefficient, and the specific value is set according to the exhibitors' emphasis on the flow of people.

[0068] Audience behavior analysis module: By analyzing the audience's browsing path and interactive behavior, the audience's preference level is obtained, and the audience behavior analysis results are transmitted to the intelligent recommendation module.

[0069] In this embodiment, the audience behavior analysis module analyzes the audience's browsing path and interactive behavior, and calculates the audience's preference level using the specific calculation formula: l represents the number of interactions of visitors at the booth, l′ represents the total number of interactions of visitors at all booths, r represents the total number of characters of comments of visitors at the booth, r′ represents the total number of characters of comments of visitors at all booths, T represents the duration of visitors’ stay at the booth, and T′ represents the total browsing time of visitors at the exhibition.

[0070] Intelligent recommendation module: Analyze the booth matching degree and audience preference, calculate the booth recommendation coefficient, prioritize the booths according to the best booth recommendation coefficient, and make intelligent recommendations to exhibitors.

[0071] In this embodiment, the intelligent recommendation module recommends the best booth for each exhibitor by intelligently recommending and allocating booths and ranking the booths according to their priority. The recommendation results include multiple screened booths for exhibitors to choose from.

[0072] The specific calculation formula of the booth recommendation coefficient is: K represents the booth matching degree, P represents the audience preference degree, c represents a positive number, and c>1;

[0073] The selected booths are sorted in descending order by the booth recommendation coefficient R. The larger the booth recommendation coefficient value calculated for the booth is, the higher the priority of the booth is. According to the booth sorting results, a recommendation list is generated and the booth sorting is recommended to exhibitors in the form of a recommendation list.

[0074] Effect evaluation module: used to evaluate the effect of booth recommendations. By collecting and analyzing booth reservation rates, booth renewal rates, and booth utilization rates, the recommendation effect evaluation coefficient is obtained, and the recommended booths are adjusted dynamically in real time based on the recommendation effect evaluation coefficient.

[0075] In this embodiment, the effect evaluation module monitors the intelligent recommendation process of booths in real time, analyzes and evaluates the recommended effect of booths, thereby dynamically adjusting the recommended order of booths in the recommendation list, and then re-recommends the adjusted booth order to exhibitors;

[0076] The specific calculation formula of the recommended effect evaluation coefficient is: q represents the booth reservation rate, p represents the booth renewal rate, and d represents the booth utilization rate;

[0077] The recommendation effect evaluation coefficient I is compared with the preset recommendation threshold μ. If the recommendation effect evaluation coefficient I<the preset recommendation threshold μ, it means that the effect of recommending the recommended order of booths to exhibitors is not ideal, and the order of booths in the recommendation list needs to be re-sorted according to the recommendation effect evaluation coefficient; if the recommendation effect evaluation coefficient I≥the preset recommendation threshold μ, it means that the effect of recommending the recommended order of booths to exhibitors is relatively ideal, and there is no need to adjust the order of booths.

[0078] like Figure 2 This embodiment provides an online exhibition service management method based on big data analysis, including the following steps:

[0079] S1: Used to collect and record exhibition information data in real time, including exhibitor information, booth information and visitor information, and upload the collected exhibition information data to the cloud database;

[0080] S2: Used to monitor and analyze exhibition information data in real time during the exhibition to obtain the distribution of traffic flow and the attention paid to exhibits;

[0081] S3: Analyze the matching degree between exhibitors and booths based on the traffic analysis results, and calculate the booth matching degree;

[0082] S4: Get the audience's preference by analyzing the audience's browsing path and interactive behavior;

[0083] S5: Analyze the booth matching degree and visitor preference, calculate the booth recommendation coefficient, prioritize the booths according to the best booth recommendation coefficient, and make intelligent recommendations to exhibitors;

[0084] S6: By collecting and analyzing the booth reservation rate, booth renewal rate and booth utilization rate, the recommendation effect evaluation coefficient is obtained, and the recommended booth is dynamically adjusted in real time according to the recommendation effect evaluation coefficient.

[0085] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

[0086] 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. Online exhibition service management system based on big data analysis, characterized by: include: Exhibition information collection module: used to collect and record exhibition information data in real time, including exhibitor information, booth information and visitor information, and upload the collected exhibition information data to the cloud database; Traffic analysis module: used to monitor and analyze exhibition information data in real time during the exhibition, obtain the distribution of traffic flow and the attention of exhibits, and transmit the traffic analysis results to the booth matching analysis module; Booth matching analysis module: Analyzes the matching degree between exhibitors and booths based on the traffic analysis results, calculates the booth matching degree, and transmits the booth matching analysis results to the intelligent recommendation module; Audience behavior analysis module: obtains audience preferences by analyzing audience browsing paths and interactive behaviors, and transmits audience behavior analysis results to the intelligent recommendation module; Intelligent recommendation module: Analyzes booth matching and visitor preference, calculates booth recommendation coefficients, prioritizes booths based on the best booth recommendation coefficients, and makes intelligent recommendations to exhibitors; Effect evaluation module: used to evaluate the effect of booth recommendations. By collecting and analyzing booth reservation rates, booth renewal rates, and booth utilization rates, the recommendation effect evaluation coefficient is obtained, and the recommended booths are adjusted dynamically in real time based on the recommendation effect evaluation coefficient.

2. The online exhibition service management system based on big data analysis according to claim 1, characterized in that: The exhibition information collection module establishes an online exhibition service platform and sets up a database in the cloud to store exhibitor information, booth information and visitor information. It automatically collects exhibitor information, booth information and visitor information through forms, questionnaires and platform interactions, and transmits the collected data to the cloud database in real time through the API interface for storage; The exhibitor information includes the number of exhibitors, exhibition history and exhibition payment fees; the booth information includes the number of reservations, usage time, booth area, the number of exhibitors that can be accommodated and booth price; the audience information includes online stay time, interaction frequency and the number of visits to the booth.

3. The online exhibition service management system based on big data analysis according to claim 1, characterized in that: The traffic analysis module first performs data preprocessing on the collected exhibition information data. The data preprocessing process includes data cleaning and data integration. By real-time tracking of visitors' activities on the platform, recording visit time and access path, and monitoring the number of visits to booths and activities; The flow distribution degree is calculated by analyzing the distribution of visitors in various booths and activities over a period of time. The exhibit attention degree A2 is calculated by counting and analyzing the number of visits, the number of interactions and the dwell time of the exhibits within a period of time.

4. The online exhibition service management system based on big data analysis according to claim 1, characterized in that: The booth matching analysis module constructs a booth feature vector X={A1, A2, A3, A4} for each booth, which includes the distribution of traffic flow, exhibit attention, booth price and booth area, and constructs a preference feature vector Y={B1, B2, B3, B4} according to the exhibitors' preferences, which includes the traffic flow preference value, exhibit attention preference value, booth price preference value and booth area preference value, and then comprehensively analyzes and calculates the booth matching degree; The specific analysis method of the booth matching degree is as follows: Step S311: Analyze based on the booth feature vector X = {A1, A2, A3, A4} and the preference feature vector Y = {B1, B2, B3, B4}, and calculate the distance between the booth feature vector and the preference feature vector as Step S312: Analyze based on the distance Distance(X, Y) between the booth feature vector and the preference feature vector, and calculate the booth matching degree as max(Distance) represents the maximum distance between the booth feature vector and the preference feature vector; By presetting a booth matching threshold θ, the booth matching degree K is compared with the booth matching threshold θ, and the booths matching the exhibitors' needs are screened out. If the booth matching degree K ≥ the booth matching threshold θ, these booths are considered to be more matched with the exhibitors' needs, and the qualified booths are screened out, and the booth matching degree values ​​of these screened booths are transmitted to the intelligent recommendation module for intelligent recommendation analysis. If the booth matching degree K < the booth matching threshold θ, these booths are considered to be unmatched with the exhibitors' needs and are screened out.

5. The online exhibition service management system based on big data analysis according to claim 1, characterized in that: The audience behavior analysis module analyzes the audience's browsing path and interactive behavior, and calculates the audience's preference level using the specific calculation formula: l represents the number of interactions of visitors at the booth, l′ represents the total number of interactions of visitors at all booths, r represents the total number of characters of comments of visitors at the booth, r′ represents the total number of characters of comments of visitors at all booths, T represents the duration of visitors’ stay at the booth, and T′ represents the total browsing time of visitors at the exhibition.

6. The online exhibition service management system based on big data analysis according to claim 1, characterized in that: The intelligent recommendation module recommends the best booth for each exhibitor by intelligently recommending and allocating booths and sorting them according to booth priority. The recommendation results include multiple screened booths for exhibitors to choose from. The specific calculation formula of the booth recommendation coefficient is: K represents the booth matching degree, P represents the audience preference degree, c represents a positive number, and c>1; The selected booths are sorted in descending order by the booth recommendation coefficient R. The larger the booth recommendation coefficient value calculated for the booth is, the higher the priority of the booth is. According to the booth sorting results, a recommendation list is generated and the booth sorting is recommended to exhibitors in the form of a recommendation list.

7. The online exhibition service management system based on big data analysis according to claim 1, characterized in that: The effect evaluation module monitors the intelligent recommendation process of booths in real time, analyzes and evaluates the recommended effect of booths, thereby dynamically adjusting the recommended order of booths in the recommendation list, and then re-recommends the adjusted booth order to exhibitors; The specific calculation formula of the recommended effect evaluation coefficient is: q represents the booth reservation rate, p represents the booth renewal rate, and d represents the booth utilization rate; Compare the recommendation effect evaluation coefficient I with the preset recommendation threshold μ. If the recommendation effect evaluation coefficient I < the preset recommendation threshold μ, it means that the effect of recommending the recommended order of booths to exhibitors is not ideal, and the order of booths in the recommendation list needs to be re-sorted according to the recommendation effect evaluation coefficient; If the recommendation effect evaluation coefficient I ≥ the preset recommendation threshold μ, it means that the effect of recommending the recommended order of booths to exhibitors is relatively ideal, and there is no need to adjust the order of booths.

8. An online exhibition service management method based on big data analysis, using the online exhibition service management system based on big data analysis as claimed in any one of claims 1 to 7, characterized in that: The following steps are involved: S1: Used to collect and record exhibition information data in real time, including exhibitor information, booth information and visitor information, and upload the collected exhibition information data to the cloud database; S2: Used to monitor and analyze exhibition information data in real time during the exhibition to obtain the distribution of traffic flow and the attention paid to exhibits; S3: Analyze the matching degree between exhibitors and booths based on the traffic analysis results, and calculate the booth matching degree; S4: Get the audience's preference by analyzing the audience's browsing path and interactive behavior; S5: Analyze the booth matching degree and visitor preference, calculate the booth recommendation coefficient, prioritize the booths according to the best booth recommendation coefficient, and make intelligent recommendations to exhibitors; S6: By collecting and analyzing the booth reservation rate, booth renewal rate and booth utilization rate, the recommendation effect evaluation coefficient is obtained, and the recommended booth is dynamically adjusted in real time according to the recommendation effect evaluation coefficient.

Images