Explanation system for tourists in museum

Abstract

The invention discloses an explanation system for tourists in a museum, which relates to the technical field of tourist explanation and comprises a Bluetooth channel monitoring module, a data preprocessing module, a feature extraction and evaluation module, a channel classification module and a broadcast frequency dynamic adjustment module. And the Bluetooth channel monitoring module is deployed in each Bluetooth beacon in the museum, scans and monitors the Bluetooth channel state in the current environment in real time, and collects the data of the channel use condition. According to the method, the beacon broadcast frequency is dynamically adjusted by monitoring the state of the Bluetooth channel in real time and evaluating the congestion condition by using the machine learning model, so that the use efficiency of the channel is optimized. For a normal channel, maintaining high-frequency broadcast to ensure the positioning accuracy; for a congested channel, the broadcast frequency is reduced to reduce load and interference, the explanation equipment is ensured to accurately position tourists, correct exhibit explanation is provided, the visiting experience is improved, wrong guidance and disordered moving lines are reduced, and finally the service quality of a museum and the satisfaction degree of the tourists are improved.

Description

Technical Field

[0001] The invention relates to the technical field of tourist explanation, and in particular to an explanation system for museum tourists. Background Art

[0002] The museum visitor explanation system is an electronic device or software designed to provide guided tour services for visitors, usually including portable terminals (such as voice guides, smartphone applications) and background management systems. It can automatically or manually play detailed explanations of exhibits in various forms such as audio, video, and text to help visitors gain a deeper understanding of the historical background, artistic value, and cultural connotations of the exhibits. The system usually supports multi-language selection and personalized recommendations, and automatically identifies the location of visitors through positioning technology (such as GPS or Bluetooth), provides corresponding exhibit explanations, and realizes an intelligent, interactive, and convenient visiting experience.

[0003] Bluetooth beacons are currently the most commonly used technology for indoor positioning in museums. Multiple Bluetooth beacons are installed in the museum, and these Bluetooth beacons periodically emit unique identification signals. Visitors' interpretation devices (such as smartphones or dedicated guides) receive these signals via Bluetooth, and calculate the distance between the device and the Bluetooth beacon based on the signal strength and the known location of the Bluetooth beacon, thereby determining the approximate location of the visitor.

[0004] In museums, Bluetooth beacons broadcast their unique identifier (UUID), major value, and minor value at regular intervals (e.g., 100 milliseconds) and can be received by nearby devices. In order to increase the reception frequency, Bluetooth beacons are usually set to broadcast at a high frequency. However, in high-density crowd environments, such as exhibition openings, holidays, or special events, a large number of visitors use devices to receive beacon signals at the same time, which can cause severe congestion in the Bluetooth channel. This channel congestion can cause the device to be unable to effectively receive signals from multiple Bluetooth beacons, affecting the accuracy of signal strength (RSSI) measurements. The lack of sufficient signal data increases the error of the positioning algorithm, resulting in a significant decrease in positioning accuracy. As a result, the explanation device may not be able to accurately identify the location of the visitor, triggering the wrong exhibit explanation content, seriously affecting the visitor's experience. In addition, due to inaccurate positioning, visitors may be misled to the wrong exhibit area, further causing confusion in the visiting route.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] The purpose of the present invention is to provide a museum visitor explanation system, which optimizes the channel utilization efficiency by real-time monitoring of the Bluetooth channel status and using a machine learning model to evaluate congestion, dynamically adjusting the beacon broadcast frequency. For normal channels, high-frequency broadcasting is maintained to ensure positioning accuracy; for congested channels, the broadcast frequency is reduced to reduce load and interference, ensuring that the explanation equipment accurately locates the visitor's position, providing correct exhibit explanations, improving the visiting experience, reducing misleading and chaotic movement lines, and ultimately improving the museum's service quality and visitor satisfaction, so as to solve the problems in the above-mentioned background technology.

[0007] In order to achieve the above-mentioned object, the present invention provides the following technical solutions: a museum visitor explanation system, comprising a Bluetooth channel monitoring module, a data preprocessing module, a feature extraction and evaluation module, a channel classification module and a broadcast frequency dynamic adjustment module;

[0008] The Bluetooth channel monitoring module is deployed in each Bluetooth beacon in the museum to scan and monitor the Bluetooth channel status in the current environment in real time and collect data on channel usage;

[0009] The data preprocessing module performs data preprocessing after acquiring the original data of the Bluetooth channel to improve the data quality of the original data;

[0010] The feature extraction and evaluation module extracts Bluetooth channel feature information from the preprocessed data, analyzes the extracted Bluetooth channel feature information, and then inputs the analyzed Bluetooth channel feature information into a pre-trained machine learning model to evaluate the congestion of the Bluetooth channel.

[0011] The channel classification module divides the Bluetooth channels into normal channels and congested channels according to the evaluation results;

[0012] The broadcast frequency dynamic adjustment module dynamically adjusts the beacon broadcast frequency of each Bluetooth channel based on the real-time detected channel status. For Bluetooth beacons classified as normal channels, a pre-set high-frequency broadcast frequency is used for beacon broadcasting. For Bluetooth beacons identified as congested channels, the broadcast frequency is automatically lowered based on the high-frequency broadcast frequency based on the congestion of the Bluetooth channel, and beacon broadcasts are performed at the adjusted actual broadcast frequency.

[0013] Preferably, the Bluetooth channel monitoring module is a functional module integrated in each Bluetooth beacon in the museum, which monitors the status of Bluetooth channels in the surrounding environment in real time and collects relevant data. Each Bluetooth beacon not only serves as a device for sending broadcast signals, but also undertakes the task of monitoring the communication status of other Bluetooth devices and beacons in the environment. The Bluetooth channel monitoring module obtains the channel usage by continuously scanning all Bluetooth channels in the 2.4GHz frequency band.

[0014] Preferably, the Bluetooth channel characteristic information extracted from the preprocessed data includes the frequency of Bluetooth data packet collisions on the Bluetooth channel and the time ratio of the Bluetooth channel being used. After acquisition, the frequency of Bluetooth data packet collisions on the Bluetooth channel and the time ratio of the Bluetooth channel being used are analyzed within the detection window, and a collision frequency index and a channel occupancy index are generated respectively. The collision frequency index and the channel occupancy index are input into a pre-trained machine learning model to generate a congestion assessment coefficient, and the congestion situation of the Bluetooth channel is evaluated by the congestion assessment coefficient.

[0015] Preferably, the specific steps of generating a collision frequency index after analyzing the frequency of Bluetooth data packet collisions on the Bluetooth channel are as follows:

[0016] In a given detection window, all data packet transmission events are recorded and the number of data packets that collide is counted. A collision is defined as an event in which multiple Bluetooth devices send data packets on the same channel at the same time, resulting in the failure of successful data packet transmission. The calculation expression for the number of data packets that collide is: Where N c Indicates the number of packets that collide, C i represents the i-th detected packet collision event, and n is the total number of detections within the detection window;

[0017] Get the number of packets N successfully sent within the detection window t and the total number of packets N that are attempted to be sent within the detection window s , by the number of packets successfully sent N t and the total number of packets N that were attempted to be sent s Calculate the packet sending success rate R s , the calculation expression is:

[0018] According to the number of packets N that collide c And the packet sending success rate R s , the collision factor Φ is introduced to evaluate the impact of the collision on the channel. The calculation expression of the collision factor Φ is: Where, e is the base of the natural logarithm, and λ is the first adjustment parameter, which controls the impact of the packet sending success rate on the collision factor;

[0019] Combine the collision factor Φ and the detection window length T to calculate the collision frequency index I c , which is used to quantify the severity of channel collision, is calculated as: Where β is the second adjustment parameter, which controls the influence of the detection window on the collision frequency index and reflects the attenuation of the influence of the time length on the collision frequency.

[0020] Preferably, in the detection window, the specific steps of generating the channel occupancy index after analyzing the time ratio of the Bluetooth channel being used are as follows:

[0021] In the detection window, collect the timestamps of all data packets transmitted on the Bluetooth channel, record the start time and end time of each data transmission, and record the set of all data packet transmission times in the detection window as D, then: D = {(t k，start , t k，end )|k=1,2,…,N s}, where t k，start represents the start time of the kth data packet transmission, t k，end Indicates the end time of the kth data packet transmission;

[0022] Calculate the total time the channel is used within the detection window, that is, the total time slots occupied by the channel. The calculation expression is: Where, T occupied represents the total time slots occupied by the channel, that is, the actual time the channel is used, t overlap，start and t overlap，end Respectively represent the start time and end time of overlapping data packets, ∑ overlap (t overlap，end -t overlap，start ) represents the sum of the overlapping time of all start and end times;

[0023] Calculate the frequency modulation factor of the channel activity to adjust the channel occupation time. The expression for calculating the frequency modulation factor is:

[0024]

[0025] , where FMF represents the frequency modulation factor of the channel activity, which is used to adjust the channel occupancy time, t k+1，start and t k，end Respectively represent the start and end time of adjacent data packets, and are used to calculate the interval time between two data packets;

[0026] The channel occupancy index is calculated based on the sum of the channel occupied time slots and the channel activity frequency modulation factor to quantify the degree of channel congestion. The expression for calculating the channel occupancy index is: In the formula, COI f Represents the channel occupancy index.

[0027] Preferably, the congestion assessment coefficient generated by the machine learning model prediction under the detection window is compared and analyzed with a preset congestion assessment coefficient reference threshold, and the Bluetooth channel is divided. The specific division steps are as follows:

[0028] If the congestion assessment coefficient is greater than or equal to the congestion assessment coefficient reference threshold, the Bluetooth channel is classified as a congested channel;

[0029] If the congestion assessment coefficient is less than the congestion assessment coefficient reference threshold, the Bluetooth channel is classified as a normal channel.

[0030] Preferably, the setting standard of the high-frequency broadcast frequency is based on the channel usage, device receiving capability, required positioning accuracy and real-time requirements. The standard for setting the high-frequency broadcast frequency will take into account the power consumption capacity of the Bluetooth beacon and the limitations of the Bluetooth protocol to balance the relationship between signal stability and device battery consumption, ensuring that the broadcast frequency maintains positioning accuracy and response speed, while avoiding the set broadcast frequency causing excessive consumption of Bluetooth beacon power.

[0031] Preferably, for a Bluetooth beacon identified as a congested channel, based on the congestion of the Bluetooth channel, the broadcast frequency is automatically lowered on the basis of the high-frequency broadcast frequency, and the beacon is broadcasted at the adjusted actual broadcast frequency. The specific steps are as follows:

[0032] After a congested channel is detected, the congestion assessment coefficient Congestion τ and congestion assessment coefficient reference threshold C ref Calculate a down-adjustment factor to determine the new broadcast frequency. The calculation expression of the down-adjustment factor is:

[0033]

[0034] , where D factor represents the down-regulation factor, and γ represents the broadcast frequency adjustment coefficient, which is used to control the sensitivity of the down-regulation factor;

[0035] Based on the down-regulation factor, the adjusted actual broadcast frequency is calculated. The adjusted actual broadcast frequency is reduced according to the proportion of the down-regulation factor based on the initially set high-frequency broadcast frequency to reduce the burden and congestion of the channel. The calculation expression is: In the formula, f adjusted represents the actual broadcast frequency after adjustment, that is, the actual broadcast frequency of the Bluetooth beacon in the congested channel, f high Indicates the initially set high-frequency broadcast frequency, that is, the default broadcast frequency of the beacon in the normal channel;

[0036] The calculated adjusted actual broadcast frequency f adjusted Update the broadcast configuration of the Bluetooth beacon to make the Bluetooth beacon broadcast at the actual frequency f adjusted Signal broadcasting is performed, and based on the congestion assessment coefficient under the congested channel, the actual broadcast frequency is dynamically adjusted on the basis of the high-frequency broadcast frequency, and beacon broadcasting is performed at the adjusted actual broadcast frequency.

[0037] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0038] The present invention optimizes the channel utilization efficiency by real-time monitoring of the Bluetooth channel status, using a pre-trained machine learning model to accurately assess the congestion situation, and dynamically adjusting the beacon broadcast frequency. High-frequency broadcasting is maintained for normal channels to ensure the accuracy and timeliness of positioning, while the broadcasting frequency is reduced for congested channels to reduce channel load and interference. This intelligent broadcast frequency management mechanism ensures that the explanation equipment can continuously and accurately identify the location of visitors and provide correct exhibit explanation content, thereby enhancing the visitors' visiting experience, reducing misleading and confusion in the visiting route, and ultimately improving the service quality and visitor satisfaction of the museum. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0040] Figure 1 The present invention is a module schematic diagram of a museum visitor explanation system. DETAILED DESCRIPTION

[0041] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0042] The present invention provides Figure 1 A museum tourist explanation system shown includes a Bluetooth channel monitoring module, a data preprocessing module, a feature extraction and evaluation module, a channel classification module, and a broadcast frequency dynamic adjustment module;

[0043] The Bluetooth channel monitoring module is deployed in each Bluetooth beacon in the museum to scan and monitor the Bluetooth channel status in the current environment in real time and collect data on channel usage;

[0044] The Bluetooth channel monitoring module is a functional module integrated into each Bluetooth beacon in the museum, which is designed to monitor the status of Bluetooth channels in the surrounding environment in real time and collect relevant data. Each Bluetooth beacon is not only a device for sending broadcast signals, but also has the task of monitoring the communication status of other Bluetooth devices and beacons in the environment. The Bluetooth channel monitoring module obtains channel usage by continuously scanning all Bluetooth channels in the 2.4GHz frequency band, especially the advertising channels (channels 37, 38, and 39) commonly used by Bluetooth low energy (BLE) devices.

[0045] In actual operation, the Bluetooth channel monitoring module performs scans regularly to capture signal activities on each channel, such as the number of packets currently being transmitted, signal strength (RSSI), channel idle time, and signal interference levels (such as noise levels and signal collision frequency). These data can reflect the current channel occupancy and congestion, helping to identify which channels are in a high-load state and which are relatively idle.

[0046] The data preprocessing module performs data preprocessing after acquiring the original data of the Bluetooth channel to improve the data quality of the original data;

[0047] After obtaining the raw data of the Bluetooth channel, data preprocessing is an important step to improve the quality of the raw data to ensure the accuracy and reliability of subsequent analysis. Data preprocessing usually includes the following steps, and the role of each step is as follows:

[0048] Data cleaning: Data cleaning is the first step in data preprocessing, which is mainly used to remove or correct errors and noise in the original data. This step includes detecting and deleting duplicate data, repairing or removing missing data, and correcting outliers or unreasonable values ​​in the data. In Bluetooth channel monitoring, data cleaning can ensure that all channel usage data is accurate and reduce analysis bias caused by data errors. For example, removing abnormal peaks in the signal strength (RSSI) value can prevent these abnormal data from affecting the calculation of channel occupancy.

[0049] Data standardization: Data standardization is to convert data of different units and ranges into the same scale, so that the data are comparable under the same analysis framework. For Bluetooth channel monitoring, indicators such as channel occupancy, signal strength (RSSI), channel interference, etc. may have different numerical ranges. Through standardization, all these indicators can be scaled to a unified range (for example, between 0 and 1), thereby eliminating the magnitude differences between different indicators and ensuring the weight balance of each indicator when conducting multivariate analysis.

[0050] Data smoothing: Data smoothing aims to reduce random noise in the data and highlight the true trend of the data. Smoothing can be achieved through methods such as moving average and exponential smoothing. In Bluetooth channel monitoring, the channel status may fluctuate abnormally for a short period of time due to accidental interference. Through data smoothing, these short-term noise interferences can be removed, presenting a more stable trend of channel usage, and helping to more accurately judge the long-term status of the channel.

[0051] Data integration: Data integration combines monitoring data from different beacons or different time periods into a unified database for global analysis and decision-making. In Bluetooth channel monitoring, monitoring data from multiple beacons may reflect channel usage in different areas. Through data integration, a comprehensive picture of the entire museum's Bluetooth environment can be formed, which helps identify global problems and optimization points.

[0052] Data transformation: Data transformation involves converting or recalculating data to suit specific analysis requirements. This may include logarithmic transformation, square root transformation, etc. of channel usage data to make the data more consistent with normal distribution and improve the effectiveness of data analysis. In Bluetooth channel monitoring, data transformation can be used to optimize the distribution characteristics of data so that subsequent analysis models (such as machine learning models) can better fit the data and improve the accuracy of predictions.

[0053] Through these preprocessing steps, the quality of the original Bluetooth channel data can be significantly improved, providing reliable data support for subsequent data analysis, channel status evaluation, and beacon broadcast strategy optimization. These steps not only help remove noise and errors in the data, but also ensure the consistency and comparability of the data, so that the entire Bluetooth channel monitoring system can operate more stably and accurately.

[0054] The feature extraction and evaluation module extracts Bluetooth channel feature information from the preprocessed data, analyzes the extracted Bluetooth channel feature information, and then inputs the analyzed Bluetooth channel feature information into a pre-trained machine learning model to evaluate the congestion of the Bluetooth channel.

[0055] The Bluetooth channel characteristic information extracted from the preprocessed data includes the frequency of Bluetooth data packet collisions on the Bluetooth channel and the proportion of time the Bluetooth channel is used. After acquisition, the frequency of Bluetooth data packet collisions on the Bluetooth channel and the proportion of time the Bluetooth channel is used are analyzed within the detection window, and a collision frequency index and a channel occupancy index are generated respectively. The collision frequency index and the channel occupancy index are input into a pre-trained machine learning model to generate a congestion assessment coefficient, and the congestion situation of the Bluetooth channel is evaluated by the congestion assessment coefficient.

[0056] A pre-trained machine learning model refers to a technique that uses a large amount of historical data to train the model before actual application so that it can accurately predict or classify new data. For Bluetooth channel congestion assessment, pre-trained models are usually based on supervised learning methods, which means that the model is trained by learning the relationship between input data (such as collision frequency index and channel occupancy index) and output targets (such as congestion level). During the model training phase, a large number of data samples reflecting different Bluetooth channel states are collected. These samples include known collision frequency index, channel occupancy index, and known channel congestion conditions related to these input features (usually obtained through manual labeling or based on empirical data). These data are used to "teach" the model how to identify congestion conditions under different combinations of input features. The model optimizes its internal parameters so that it can predict the output congestion status as accurately as possible.

[0057] Once the model is trained and verified, it can be applied in real-world scenarios. In actual operation, when new collision frequency indexes and channel occupancy indexes are input into the model, the model generates a congestion assessment coefficient based on the patterns and rules learned during its training process. This coefficient represents the current degree of congestion in the channel and is used to help the system evaluate and adjust the broadcast strategy of the Bluetooth channel in real time. The application of this machine learning model improves the intelligence and adaptability of the system, enabling it to more effectively cope with complex and changing Bluetooth environments, optimize channel usage, reduce congestion, and improve communication efficiency.

[0058] The high frequency of Bluetooth packet collisions on the Bluetooth channel indicates that the Bluetooth channel is highly congested, which affects the accuracy of signal strength (RSSI) measurements, leading to a significant decrease in positioning accuracy. When packet collisions occur frequently, Bluetooth devices need to retransmit multiple times, which increases the channel occupancy time and interference, resulting in unstable or inaccurate RSSI values ​​received, which affects the effectiveness of RSSI-based positioning algorithms. Reduced positioning accuracy means that the explanation device may not be able to accurately determine the specific location of the visitor, which can cause the wrong exhibit explanation content to be triggered, misleading visitors and seriously affecting the visiting experience. Therefore, a high collision frequency not only reflects channel congestion, but also directly interferes with signal reception and positioning functions.

[0059] In the detection window, the specific steps of generating the collision frequency index after analyzing the frequency of Bluetooth data packet collision on the Bluetooth channel are as follows:

[0060] In a given detection window, all data packet transmission events are recorded (through the Bluetooth channel monitoring module) and the number of data packets that collide is counted. A collision is defined as an event in which multiple Bluetooth devices send data packets simultaneously on the same channel, resulting in the failure of successful data packet transmission. The calculation expression for the number of data packets that collide is: Where Nc Indicates the number of packets that collide, C i represents the i-th detected packet collision event, and n is the total number of detections within the detection window;

[0061] Get the number of packets N successfully sent within the detection window t and the total number of packets N that are attempted to be sent within the detection window s , by the number of packets successfully sent N t and the total number of packets N that were attempted to be sent s Calculate the packet sending success rate R s , the calculation expression is:

[0062] According to the number of packets N that collide c And the packet sending success rate R s , the collision factor Φ is introduced to evaluate the impact of the collision on the channel. The calculation expression of the collision factor Φ is: Wherein, e is the base of the natural logarithm (approximately equal to 2.718), λ is the first adjustment parameter, which controls the influence of the packet sending success rate on the collision factor and can be adjusted according to the actual application scenario;

[0063] Combine the collision factor Φ and the detection window length T to calculate the collision frequency index I c , which is used to quantify the severity of channel collision, is calculated as: Where β is the second adjustment parameter, which controls the influence of the detection window on the collision frequency index and reflects the attenuation of the influence of the time length on the collision frequency.

[0064] It can be seen from the collision frequency index that, within the detection window, the larger the performance value of the collision frequency index generated after analyzing the frequency of Bluetooth data packet collisions on the Bluetooth channel, the more serious the congestion of the Bluetooth channel. The collision frequency index is an indicator calculated by the collision frequency of Bluetooth data packets within the detection window and other related factors (such as the success rate of data packet transmission and the length of the detection window time). It reflects the frequency and impact of data packet transmission failures on the channel within a specific time period. When the collision frequency index is large, it means that the data packet collision events occurring within the detection window are many and serious, the competition for channel resources is fierce, and the signal transmission is more seriously interfered with and blocked. Therefore, a large collision frequency index is an important signal of severe channel congestion.

[0065] A high percentage of time used on a Bluetooth channel indicates that the channel is highly congested. This congestion can cause data packet transmission delays and frequent retransmission requests, which can increase signal interference and affect the accuracy of signal strength (RSSI) measurements. Since signal strength is a key parameter used to determine the distance between a device and a beacon, inaccurate measurements can directly lead to reduced positioning accuracy. When positioning is inaccurate, the explanation device may not be able to correctly identify the visitor's location, resulting in the triggering of incorrect exhibit explanation content, which can seriously affect the visitor's experience, especially in a museum environment where exhibits are highly correlated with location. This misleading not only confuses the tour path, but can also cause visitors to miss the explanation of key exhibits, reducing their overall satisfaction with the visit.

[0066] In the detection window, the specific steps of generating the channel occupancy index by analyzing the proportion of time the Bluetooth channel is used are as follows:

[0067] In the detection window, the timestamps of all data packets transmitted on the Bluetooth channel are collected, and the start time and end time of each data transmission are recorded (through the Bluetooth channel monitoring module). The set of all data packet transmission times in the detection window is recorded as D, then: D = {(t k，start , t k，end )||k=1,2,…,N s}, where t k，start represents the start time of the kth data packet transmission, t k，end Indicates the end time of the kth data packet transmission (N s Indicates the total number of packets attempted to be sent within the detection window);

[0068] Calculate the total time the channel is used within the detection window, that is, the total time slots occupied by the channel. The calculation expression is: Where, T occupied represents the total time slots occupied by the channel, that is, the actual time the channel is used, t overlap，start and t overlap，end Respectively represent the start time and end time of overlapping data packets, ∑ overlap (t overlap，end -t overlap，start ) represents the sum of the overlapping time of all start and end times, and the overlapping part needs to be subtracted when calculating the time;

[0069] The frequency modulation factor of the channel activity is calculated to adjust the channel occupation time. This factor reflects the changes in the frequency and interval time of data transmission and can more accurately describe the congestion of the channel. The expression for calculating the frequency modulation factor is:

[0070]

[0071] , where FMF represents the frequency modulation factor of the channel activity, which is used to adjust the channel occupancy time, t k+1，start and t k，end Respectively represent the start and end time of adjacent data packets, and are used to calculate the interval time between two data packets;

[0072] The channel occupancy index is calculated based on the sum of the channel occupied time slots and the channel activity frequency modulation factor to quantify the degree of channel congestion. The expression for calculating the channel occupancy index is: In the formula, COI f Indicates the channel occupancy index (indicates the congestion level of the Bluetooth channel).

[0073] It can be seen from the channel occupancy index that, within the detection window, the larger the performance value of the channel occupancy index generated after analyzing the proportion of time the Bluetooth channel is occupied, the more serious the congestion of the Bluetooth channel. The channel occupancy index comprehensively considers the proportion of time the channel is actually used within the detection window and the changes in the frequency and interval of data transmission. A higher channel occupancy index means that the Bluetooth channel is occupied most of the time and the data transmission frequency is high, indicating that the Bluetooth channel is in a high load state and the degree of congestion is high. In this case, the available bandwidth of the Bluetooth channel is reduced, the communication efficiency is reduced, which may lead to increased signal interference, data transmission delays and retransmissions, and ultimately affect the positioning accuracy of the device and user experience.

[0074] The machine learning model is not specifically limited here, and can achieve the collision frequency index I c and channel occupancy index COI f Perform comprehensive analysis to generate congestion assessment coefficient Congestion τ In order to realize the technical solution of the present invention, the present invention provides a specific implementation method;

[0075] Congestion Assessment Factor τ The resulting calculation formula is: In the formula, Collision frequency index I c and channel occupancy index COI f The preset scaling factor of Both are greater than 0.

[0076] It can be seen from the congestion assessment coefficient that, within the detection window, the larger the performance value of the collision frequency index generated after analyzing the frequency of Bluetooth data packet collisions on the Bluetooth channel, the larger the performance value of the channel occupancy index generated after analyzing the proportion of time the Bluetooth channel is used, that is, the larger the performance value of the congestion assessment coefficient generated within the detection window, the more serious the congestion of the Bluetooth channel, and vice versa.

[0077] The channel classification module divides the Bluetooth channels into normal channels and congested channels according to the evaluation results;

[0078] A normal channel is a channel that is currently in good use and has low congestion, which will not significantly affect the normal broadcast of beacons and the signal reception of devices. A congested channel is a channel that is poorly used, has frequent data packet collisions, and has severe channel interference, which affects the normal reception of beacon signals by devices. By clearly dividing normal channels and congested channels, different broadcast strategies can be set for each channel, and the broadcast frequency of beacons can be flexibly adjusted.

[0079] The congestion assessment coefficient generated by the machine learning model prediction under the detection window is compared and analyzed with the pre-set congestion assessment coefficient reference threshold, and the Bluetooth channel is divided. The specific division steps are as follows:

[0080] If the congestion assessment coefficient is greater than or equal to the congestion assessment coefficient reference threshold, the Bluetooth channel is classified as a congested channel;

[0081] If the congestion assessment coefficient is less than the congestion assessment coefficient reference threshold, the Bluetooth channel is classified as a normal channel.

[0082] The broadcast frequency dynamic adjustment module dynamically adjusts the beacon broadcast frequency of each Bluetooth channel based on the channel status detected in real time. For Bluetooth beacons classified as normal channels, the pre-set high-frequency broadcast frequency is used for beacon broadcasting. For Bluetooth beacons identified as congested channels, the broadcast frequency is automatically lowered based on the high-frequency broadcast frequency based on the congestion of the Bluetooth channel, and the beacon broadcast is performed at the adjusted actual broadcast frequency.

[0083] For Bluetooth beacons that are classified as normal channels, the purpose of using a pre-set high-frequency broadcast frequency for beacon broadcasting is to ensure that the beacon signal can be received by devices (such as smartphones or tour guides) in a timely manner to provide accurate positioning and instant explanation content. This high-frequency broadcast can improve the visibility and coverage of the signal, reduce the risk of signal loss, and ensure that visitors can continue to receive explanation information related to their current location when moving in the museum, thereby optimizing the visitor experience.

[0084] The standard for setting high-frequency broadcast frequencies is usually based on channel usage, device reception capabilities, required positioning accuracy, and real-time requirements. The standard for setting high-frequency broadcast frequencies generally takes into account the power consumption capabilities of Bluetooth beacons and the limitations of the Bluetooth protocol, usually between 100 milliseconds and 500 milliseconds to balance the relationship between signal stability and device battery consumption. High-frequency broadcast frequencies are selected to be a moderate range that ensures sufficient broadcast frequencies to maintain positioning accuracy and responsiveness, while avoiding Bluetooth channel congestion and excessive beacon battery consumption caused by excessively high broadcast frequencies.

[0085] For Bluetooth beacons identified as congested channels, based on the congestion of the Bluetooth channel, the broadcast frequency is automatically lowered based on the high-frequency broadcast frequency, and the beacon is broadcast at the adjusted actual broadcast frequency. The specific steps are as follows:

[0086] After a congested channel is detected, the congestion assessment coefficient Congestion τ and congestion assessment coefficient reference threshold C ref Calculate a down-adjustment factor to determine the new broadcast frequency. The calculation expression of the down-adjustment factor is:

[0087]

[0088] , where D factor represents the down-regulation factor, γ represents the broadcast frequency adjustment coefficient, which is used to control the sensitivity of the down-regulation factor and is usually set to a constant greater than 0;

[0089] Based on the down-regulation factor, the adjusted actual broadcast frequency is calculated. The adjusted actual broadcast frequency is reduced according to the proportion of the down-regulation factor based on the initially set high-frequency broadcast frequency to reduce the burden and congestion of the channel. The calculation expression is: In the formula, f adjusted represents the actual broadcast frequency after adjustment, that is, the actual broadcast frequency of the Bluetooth beacon in the congested channel, f high Indicates the initially set high-frequency broadcast frequency, that is, the default broadcast frequency of the beacon in the normal channel;

[0090] The calculated adjusted actual broadcast frequency f adjusted Update the broadcast configuration of the Bluetooth beacon to make the Bluetooth beacon broadcast at the actual frequency f adjusted Signal broadcasting is performed, and based on the congestion assessment coefficient under the congested channel, the actual broadcast frequency is dynamically adjusted on the basis of the high-frequency broadcast frequency, and beacon broadcasting is performed at the adjusted actual broadcast frequency.

[0091] The present invention optimizes the channel utilization efficiency by monitoring the Bluetooth channel status in real time, using a pre-trained machine learning model to accurately assess the congestion situation, and dynamically adjusting the beacon broadcast frequency. High-frequency broadcasting is maintained for normal channels to ensure the accuracy and timeliness of positioning, and the broadcasting frequency is appropriately lowered for congested channels to reduce channel load and interference. This intelligent broadcast frequency management mechanism ensures that the explanation equipment can continuously and accurately identify the location of tourists and provide correct exhibit explanation content, thereby enhancing the tourists' visiting experience, reducing misleading and confusion in the visiting route, and ultimately improving the service quality and visitor satisfaction of the museum.

[0092] 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 in the formula are set by technicians in this field according to actual conditions.

[0093] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

[0094] It should be noted that, in this article, if there are relational terms such as first and second, etc., they are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or still includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "including a..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0095] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0096] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0097] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0098] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0099] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0100] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0101] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0102] 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 museum tourist explanation system, characterized in that: It includes a Bluetooth channel monitoring module, a data preprocessing module, a feature extraction and evaluation module, a channel classification module, and a broadcast frequency dynamic adjustment module; The Bluetooth channel monitoring module is deployed in each Bluetooth beacon in the museum to scan and monitor the Bluetooth channel status in the current environment in real time and collect data on channel usage; The data preprocessing module performs data preprocessing after acquiring the original data of the Bluetooth channel to improve the data quality of the original data; The feature extraction and evaluation module extracts Bluetooth channel feature information from the preprocessed data, analyzes the extracted Bluetooth channel feature information, and then inputs the analyzed Bluetooth channel feature information into a pre-trained machine learning model to evaluate the congestion of the Bluetooth channel. The channel classification module divides the Bluetooth channels into normal channels and congested channels according to the evaluation results; The broadcast frequency dynamic adjustment module dynamically adjusts the beacon broadcast frequency of each Bluetooth channel based on the real-time detected channel status. For Bluetooth beacons classified as normal channels, a pre-set high-frequency broadcast frequency is used for beacon broadcasting. For Bluetooth beacons identified as congested channels, the broadcast frequency is automatically lowered based on the high-frequency broadcast frequency based on the congestion of the Bluetooth channel, and beacon broadcasts are performed at the adjusted actual broadcast frequency.

2. A museum tourist explanation system according to claim 1, characterized in that: The Bluetooth channel monitoring module is a functional module integrated in each Bluetooth beacon in the museum. It monitors the status of Bluetooth channels in the surrounding environment in real time and collects relevant data. Each Bluetooth beacon not only serves as a device for sending broadcast signals, but also undertakes the task of monitoring the communication status of other Bluetooth devices and beacons in the environment. It obtains channel usage by continuously scanning all Bluetooth channels in the 2.4GHz frequency band.

3. A museum tourist explanation system according to claim 1, characterized in that: The Bluetooth channel characteristic information extracted from the preprocessed data includes the frequency of Bluetooth data packet collisions on the Bluetooth channel and the proportion of time the Bluetooth channel is used. After acquisition, the frequency of Bluetooth data packet collisions on the Bluetooth channel and the proportion of time the Bluetooth channel is used are analyzed within the detection window, and a collision frequency index and a channel occupancy index are generated respectively. The collision frequency index and the channel occupancy index are input into a pre-trained machine learning model to generate a congestion assessment coefficient, and the congestion situation of the Bluetooth channel is evaluated by the congestion assessment coefficient.

4. A museum tourist explanation system according to claim 3, characterized in that: In the detection window, the specific steps of generating the collision frequency index after analyzing the frequency of Bluetooth data packet collision on the Bluetooth channel are as follows: In a given detection window, all data packet transmission events are recorded and the number of data packets that collide is counted. A collision is defined as an event in which multiple Bluetooth devices send data packets on the same channel at the same time, resulting in the failure of successful data packet transmission. The calculation expression for the number of data packets that collide is: Where N c Indicates the number of packets that collide, C i represents the i-th detected packet collision event, and n is the total number of detections within the detection window; Get the number of packets N successfully sent within the detection window t and the total number of packets N that are attempted to be sent within the detection window s , by the number of packets successfully sent N t and the total number of packets N that were attempted to be sent s Calculate the packet sending success rate R s , the calculation expression is: According to the number of packets N that collide c And the packet sending success rate R s , the collision factor Φ is introduced to evaluate the impact of the collision on the channel. The calculation expression of the collision factor Φ is: Where, e is the base of the natural logarithm, and λ is the first adjustment parameter, which controls the impact of the packet sending success rate on the collision factor; Combine the collision factor Φ and the detection window length T to calculate the collision frequency index I c , which is used to quantify the severity of channel collision, is calculated as: Where β is the second adjustment parameter, which controls the impact of the detection window on the collision frequency index and reflects the attenuation of the impact of the time length on the collision frequency.

5. A museum tourist explanation system according to claim 4, characterized in that: In the detection window, the specific steps of generating the channel occupancy index by analyzing the proportion of time the Bluetooth channel is used are as follows: In the detection window, collect the timestamps of all data packets transmitted on the Bluetooth channel, record the start time and end time of each data transmission, and record the set of all data packet transmission times in the detection window as D, then: D = {(t k，start , t k，end )|k=1,2,…,N s }, where t k，start represents the start time of the kth data packet transmission, t k，end Indicates the end time of the kth data packet transmission; Calculate the total time the channel is used within the detection window, that is, the total time slots occupied by the channel. The calculation expression is: Where, T occupied represents the total time slots occupied by the channel, that is, the actual time the channel is used, t overlap，start and t overlap，end Respectively represent the start time and end time of overlapping data packets, ∑ overlap (t overlap，end -t overlap，start ) represents the sum of the overlapping time of all start and end times; Calculate the frequency modulation factor of the channel activity to adjust the channel occupation time. The expression for calculating the frequency modulation factor is: , Where FMF is the frequency modulation factor of the channel activity, which is used to adjust the channel occupancy time, t k+1，start and t k，end Respectively represent the start and end time of adjacent data packets, and are used to calculate the interval time between two data packets; The channel occupancy index is calculated based on the sum of the channel occupied time slots and the channel activity frequency modulation factor to quantify the degree of channel congestion. The expression for calculating the channel occupancy index is: Where COIf represents the channel occupancy index.

6. The museum tourist explanation system according to claim 3, characterized in that: The congestion assessment coefficient generated by the machine learning model prediction under the detection window is compared and analyzed with the pre-set congestion assessment coefficient reference threshold, and the Bluetooth channel is divided. The specific division steps are as follows: If the congestion assessment coefficient is greater than or equal to the congestion assessment coefficient reference threshold, the Bluetooth channel is classified as a congested channel; If the congestion assessment coefficient is less than the congestion assessment coefficient reference threshold, the Bluetooth channel is classified as a normal channel.

7. The museum tourist explanation system according to claim 1, characterized in that: The standard for setting high-frequency broadcast frequencies is based on channel usage, device reception capabilities, required positioning accuracy and real-time requirements. The standard for setting high-frequency broadcast frequencies takes into account the power consumption capabilities of Bluetooth beacons and the limitations of the Bluetooth protocol to balance the relationship between signal stability and device battery consumption, ensuring that the broadcast frequency maintains positioning accuracy and response speed, while avoiding the set broadcast frequency causing excessive consumption of Bluetooth beacon power.

8. The museum tourist explanation system according to claim 6, characterized in that: For Bluetooth beacons identified as congested channels, based on the congestion of the Bluetooth channel, the broadcast frequency is automatically lowered based on the high-frequency broadcast frequency, and the beacon is broadcast at the adjusted actual broadcast frequency. The specific steps are as follows: After a congested channel is detected, the congestion assessment coefficient Congestion τ and congestion assessment coefficient reference threshold C ref Calculate the down-adjustment factor to determine the new broadcast frequency. The calculation expression of the down-adjustment factor is: , Where D factor represents the down-regulation factor, and γ represents the broadcast frequency adjustment coefficient, which is used to control the sensitivity of the down-regulation factor; Based on the down-regulation factor, the adjusted actual broadcast frequency is calculated. The adjusted actual broadcast frequency is reduced according to the proportion of the down-regulation factor based on the initially set high-frequency broadcast frequency to reduce the burden and congestion of the channel. The calculation expression is: In the formula, f adjusted represents the actual broadcast frequency after adjustment, that is, the actual broadcast frequency of the Bluetooth beacon in the congested channel, f high Indicates the initially set high-frequency broadcast frequency, that is, the default broadcast frequency of the beacon in the normal channel; The calculated adjusted actual broadcast frequency f adjusted Update the broadcast configuration of the Bluetooth beacon to make the Bluetooth beacon broadcast at the actual frequency f adjusted Signal broadcasting is performed, and based on the congestion assessment coefficient under the congested channel, the actual broadcast frequency is dynamically adjusted on the basis of the high-frequency broadcast frequency, and beacon broadcasting is performed at the adjusted actual broadcast frequency.

Images