Site point location queuing query method based on big data

Abstract

The invention particularly relates to a field point location queuing query method based on big data. According to the field point location queuing query method based on the big data, through statistics of click conditions and query times of a user on each point location, a crowd condition of each current point location is analyzed and predicted based on a big data model, and the number of queuing people of the user and queuing time are estimated; meanwhile, a 5G video function and user mobile phone signal vector data are combined to comprehensively judge the real-time busy condition of a site point location, and an ElasticSearch search engine and a Redis cache technology are used to realize user query experience under the conditions of high concurrency and big data. According to the method, real-time and rapid point location query can be provided under the scene that the number of people in the site cannot be counted, and the user experience under the site point location query scene is optimized.

Description

Technical Field

[0001] The present invention relates to the field of digital audio technology, and in particular to a venue location queuing query method based on big data. Background Art

[0002] In modern society, with the growth of population and the acceleration of urbanization, people often face large crowds of people waiting in line. Whether in public transportation, tourist attractions, hospitals, banks or entertainment venues, queuing has become an inevitable part of people's lives. However, queuing is not only time-consuming and laborious, but may also cause people's dissatisfaction and anxiety. Therefore, how to effectively predict and manage the flow of people has become an urgent problem to be solved.

[0003] For managers, if there are no means to control the flow of people, such as people counting gates or appointment restrictions, then other methods need to be relied upon to predict the flow of people and develop corresponding management strategies.

[0004] In order to effectively predict and manage the flow of people, the present invention proposes a venue location queuing query method based on big data. Summary of the invention

[0005] In order to make up for the defects of the prior art, the present invention provides a simple and efficient venue location queuing query method based on big data.

[0006] The present invention is achieved through the following technical solutions:

[0007] A method for querying the queue of a venue location based on big data, characterized in that: by counting the number of clicks and queries of users on each location, the crowd congestion of each location is predicted based on the big data model analysis, and the number of users queuing and the time required for queuing are estimated;

[0008] At the same time, combined with 5G video functions and user mobile phone signal vector data, the real-time busyness of the venue location is comprehensively judged, and the ElasticSearch search engine and Redis cache technology are used to achieve user query experience in high concurrency and big data situations.

[0009] The following steps are involved:

[0010] Step S1, performing computational simulation based on a big data model;

[0011] Collect user click and query data through the website and mobile application interactive interface, pre-process the data, remove invalid or erroneous records, and output standardized data format;

[0012] Use time series analysis models (ARIMA, Holt-Winters) or random forest models to analyze and predict the crowd congestion at each location;

[0013] By calculating the number of times users query a point within a unit time, the click data on the point after querying the corresponding point, and the distance data between the user's latitude and longitude and the corresponding point, the model parameters are optimized, and the queue threshold of each point is calculated for each point to simulate and estimate the user queue situation at the point;

[0014] Step S2: Using 5G video technology to obtain the crowd congestion situation at each point;

[0015] Install real-time video surveillance cameras at each point, count the number of people at the current point, and use 5G video technology to analyze and upload the number of people at the corresponding point in real time, judge the working status of the point, and guide users to find the point to queue reasonably;

[0016] Step S3, analyzing the crowd congestion situation at each point according to the mobile phone signal vector situation;

[0017] By cooperating with mobile base station operators, we can calculate the mobile phone signal vector within the custom area and estimate the crowding situation in the area.

[0018] Step S4, manually upload the point working status;

[0019] Customize key points based on usage scenarios, and arrange dedicated personnel to work on-site at key nodes. Manually scan the code in real time to upload the number of people at the corresponding area points, and promptly feedback to the query system and provide it to users for query;

[0020] Step S5, optimizing the calculation search capability;

[0021] Use Hadoop big data technology and ElasticSearch search engine technology to optimize system computing and query capabilities to improve user query efficiency.

[0022] In step S1, the pre-processed data is classified according to different dimensions, including time, geographic location and user group;

[0023] Useful features can be customized from categorical data according to usage scenarios, and trend and periodic features can be extracted from time series data.

[0024] In step S1, the extracted features include click frequency, query type, active time period and user stay time.

[0025] In step S1, a statistical analysis method is used to describe the basic situation of the data, and exploratory data analysis (EDA) is performed to identify patterns and correlations by using the distribution of average click counts and query counts;

[0026] Use historical data to build a training dataset, train the model, and adjust the model parameters until the best performance is achieved;

[0027] The cross-validation method is used to evaluate the accuracy and generalization ability of the trained model; at the same time, feedback from users and managers is collected to continuously optimize the data analysis and prediction process.

[0028] A system for implementing the venue location queuing query method based on big data of the present invention comprises a big data prediction module, a 5G video module, a mobile phone signal vector analysis module, a manual feedback module and a search engine module;

[0029] The big data prediction module is responsible for using time series analysis models (ARIMA, Holt-Winters) or random forest models to analyze and predict the crowd congestion at each point;

[0030] By calculating the number of times users query a point within a unit time, the click data on the point after querying the corresponding point, and the distance data between the user's latitude and longitude and the corresponding point, the model parameters are optimized, and the queue threshold of each point is calculated for each point to simulate and estimate the user queue situation at the point;

[0031] The 5G video module installs real-time video surveillance cameras at various points to count the number of people at the current point. Only then can the 5G video technology analyze and upload the number of people at the corresponding point in real time, judge the working conditions of the point, and guide users to find the point and queue up reasonably;

[0032] The mobile phone signal vector analysis module is used to calculate the mobile phone signal vector situation within the custom area through cooperation with the mobile base station operator, and estimate the crowding situation in the area;

[0033] The manual feedback module is used to manually scan the code in real time to upload the number of people at the corresponding area point, and timely feedback to the query system and provide it to the user for query;

[0034] The search engine module is responsible for using Hadoop big data technology and ElasticSearch search engine technology to optimize system computing and query capabilities in order to improve user query efficiency.

[0035] A venue location queue query device based on big data, characterized in that it includes a memory and a processor; the memory is used to store a computer program, and the processor is used to implement the above-mentioned method steps when executing the computer program.

[0036] A readable storage medium, characterized in that: a computer program is stored on the readable storage medium, and the computer program implements the above method steps when executed by a processor.

[0037] The beneficial effect of the present invention is that the venue location queuing query method based on big data can provide real-time and fast location query in the scenario where the number of people present cannot be counted, thereby optimizing the user experience in the venue location query scenario. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0039] Attached Figure 1 It is a schematic diagram of the venue location queuing method based on big data of the present invention. DETAILED DESCRIPTION

[0040] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the embodiments of the present invention. Obviously, the described embodiments are only a 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 should fall within the scope of protection of the present invention.

[0041] This method of querying the location queues of venues based on big data, by counting the number of clicks and queries of users on each location, predicts the crowd congestion of each location based on the big data model analysis, and estimates the number of users queuing and the time required for queuing;

[0042] At the same time, combined with 5G video functions and user mobile phone signal vector data, the real-time busyness of the venue location is comprehensively judged, and the ElasticSearch search engine and Redis cache technology are used to achieve user query experience in high concurrency and big data situations.

[0043] The following steps are involved:

[0044] Step S1, performing computational simulation based on a big data model;

[0045] Collect user click and query data through the website and mobile application interactive interface, pre-process the data, remove invalid or erroneous records, and output standardized data format;

[0046] Use time series analysis models (ARIMA, Holt-Winters) or random forest models to analyze and predict the crowd congestion at each location;

[0047] By calculating the number of times users query a point within a unit time, the click data on the point after querying the corresponding point, and the distance data between the user's latitude and longitude and the corresponding point, the model parameters are optimized, and the queue threshold of each point is calculated for each point to simulate and estimate the user queue situation at the point;

[0048] Step S2: Using 5G video technology to obtain the crowd congestion situation at each point;

[0049] Install real-time video surveillance cameras at each point, count the number of people at the current point, and use 5G video technology to analyze and upload the number of people at the corresponding point in real time, judge the working status of the point, and guide users to find the point to queue reasonably;

[0050] Step S3, analyzing the crowd congestion situation at each point according to the mobile phone signal vector situation;

[0051] By cooperating with mobile base station operators, we can calculate the mobile phone signal vector within the custom area and estimate the crowding situation in the area.

[0052] Step S4, manually upload the point working status;

[0053] Customize key points based on usage scenarios, and arrange dedicated personnel to work on-site at key nodes. Manually scan the code in real time to upload the number of people at the corresponding area points, and promptly feedback to the query system and provide it to users for query;

[0054] Step S5, optimizing the calculation search capability;

[0055] Use Hadoop big data technology and ElasticSearch search engine technology to optimize system computing and query capabilities to improve user query efficiency.

[0056] In step S1, the pre-processed data is classified according to different dimensions, including time, geographic location and user group;

[0057] Useful features can be customized from categorical data according to usage scenarios, and trend and periodic features can be extracted from time series data.

[0058] In step S1, the extracted features include click frequency, query type, active time period and user stay time.

[0059] In step S1, a statistical analysis method is used to describe the basic situation of the data, and exploratory data analysis (EDA) is performed to identify patterns and correlations by using the distribution of average click counts and query counts;

[0060] Use historical data to build a training dataset, train the model, and adjust the model parameters until the best performance is achieved;

[0061] The cross-validation method is used to evaluate the accuracy and generalization ability of the trained model; at the same time, feedback from users and managers is collected to continuously optimize the data analysis and prediction process.

[0062] The system for implementing the venue location queuing query method based on big data includes a big data prediction module, a 5G video module, a mobile phone signal vector analysis module, a manual feedback module and a search engine module;

[0063] The big data prediction module is responsible for using time series analysis models (ARIMA, Holt-Winters) or random forest models to analyze and predict the crowd congestion at each point;

[0064] By calculating the number of times users query a point within a unit time, the click data on the point after querying the corresponding point, and the distance data between the user's latitude and longitude and the corresponding point, the model parameters are optimized, and the queue threshold of each point is calculated for each point to simulate and estimate the user queue situation at the point;

[0065] The 5G video module installs real-time video surveillance cameras at various points to count the number of people at the current point. Only then can the 5G video technology analyze and upload the number of people at the corresponding point in real time, judge the working conditions of the point, and guide users to find the point and queue up reasonably;

[0066] The mobile phone signal vector analysis module is used to calculate the mobile phone signal vector situation within the custom area through cooperation with the mobile base station operator, and estimate the crowding situation in the area;

[0067] The manual feedback module is used to manually scan the code in real time to upload the number of people at the corresponding area point, and timely feedback to the query system and provide it to the user for query;

[0068] The search engine module is responsible for using Hadoop big data technology and ElasticSearch search engine technology to optimize system computing and query capabilities in order to improve user query efficiency.

[0069] The venue location queue query device based on big data includes a memory and a processor; the memory is used to store a computer program, and the processor is used to implement the above method steps when executing the computer program.

[0070] The readable storage medium stores a computer program, and when the computer program is executed by a processor, the above method steps are implemented.

[0071] This venue location queuing query method based on big data optimizes the user experience in the venue location query scenario, especially when there is no reservation function and gate restrictions. It can calculate the number of people queuing at simulated locations by mining data such as user clicks and user searches, and provide feedback to users who are querying in real time. It is suitable for temporary venues or places with insufficient technical conditions.

[0072] The embodiment described above is only one specific implementation of the present invention. Common changes and substitutions made by those skilled in the art within the scope of the technical solution of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for querying venue locations based on big data, characterized in that: By counting the number of clicks and inquiries of users at each location, the crowd congestion at each location is predicted based on big data model analysis, and the number of users queuing and the time required to queue are estimated; At the same time, combined with 5G video functions and user mobile phone signal vector data, the real-time busyness of the venue location is comprehensively judged, and the ElasticSearch search engine and Redis cache technology are used to achieve user query experience in high concurrency and big data situations.

2. The method for querying venue locations based on big data according to claim 1, characterized in that: The following steps are involved: Step S1, performing computational simulation based on a big data model; Collect user click and query data through the website and mobile application interactive interface, pre-process the data, remove invalid or erroneous records, and output standardized data format; Use time series analysis model or random forest model to analyze and predict the crowd congestion situation at each point; By calculating the number of times users query a point within a unit time, the click data on the point after querying the corresponding point, and the distance data between the user's latitude and longitude and the corresponding point, the model parameters are optimized, and the queue threshold of each point is calculated for each point to simulate and estimate the user queue situation at the point; Step S2: Using 5G video technology to obtain the crowd congestion situation at each point; Install real-time video surveillance cameras at each point, count the number of people at the current point, and use 5G video technology to analyze and upload the number of people at the corresponding point in real time, judge the working status of the point, and guide users to find the point to queue reasonably; Step S3, analyzing the crowd congestion situation at each point according to the mobile phone signal vector situation; By cooperating with mobile base station operators, we can calculate the mobile phone signal vector within the custom area and estimate the crowding situation in the area. Step S4, manually upload the point working status; Customize key points based on usage scenarios, and arrange dedicated personnel to work on-site at key nodes. Manually scan the code in real time to upload the number of people at the corresponding area points, and promptly feedback to the query system and provide it to users for query; Step S5, optimizing the calculation search capability; Use Hadoop big data technology and ElasticSearch search engine technology to optimize system computing and query capabilities to improve user query efficiency.

3. The method for querying venue locations based on big data according to claim 2, characterized in that: In step S1, the pre-processed data is classified according to different dimensions, including time, geographic location and user group; Useful features can be customized from categorical data according to usage scenarios, and trend and periodic features can be extracted from time series data.

4. The method for querying venue locations based on big data according to claim 3 is characterized by: In step S1, the extracted features include click frequency, query type, active time period and user stay time.

5. The method for querying venue locations based on big data according to claim 2 is characterized by: In step S1, a statistical analysis method is used to describe the basic situation of the data, and exploratory data analysis is performed to identify patterns and correlations by using the distribution of average click counts and query counts; Use historical data to build a training dataset, train the model, and adjust the model parameters until the best performance is achieved; The cross-validation method is used to evaluate the accuracy and generalization ability of the trained model; at the same time, feedback from users and managers is collected to continuously optimize the data analysis and prediction process.

6. A system for implementing the venue location queuing query method based on big data according to claims 1 to 5, characterized in that: Including big data prediction module, 5G video module, mobile signal vector analysis module, manual feedback module and search engine module; The big data prediction module is responsible for analyzing and predicting the crowd congestion situation at each location using a time series analysis model or a random forest model; By calculating the number of times users query a point within a unit time, the click data on the point after querying the corresponding point, and the distance data between the user's latitude and longitude and the corresponding point, the model parameters are optimized, and the queue threshold of each point is calculated for each point to simulate and estimate the user queue situation at the point; The 5G video module installs real-time video surveillance cameras at various points to count the number of people at the current point. Only then can the 5G video technology analyze and upload the number of people at the corresponding point in real time, judge the working conditions of the point, and guide users to find the point and queue up reasonably; The mobile phone signal vector analysis module is used to calculate the mobile phone signal vector situation within the custom area through cooperation with the mobile base station operator, and estimate the crowding situation in the area; The manual feedback module is used to manually scan the code in real time to upload the number of people at the corresponding area point, and timely feedback to the query system and provide it to the user for query; The search engine module is responsible for using Hadoop big data technology and ElasticSearch search engine technology to optimize system computing and query capabilities in order to improve user query efficiency.

7. A venue location queuing query device based on big data, characterized by: The method comprises a memory and a processor; the memory is used to store a computer program, and the processor is used to implement the method according to any one of claims 1 to 5 when executing the computer program.

8. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images