A smart tourism route planning method and system

Abstract

This invention relates to the field of tourism route planning technology, specifically disclosing a smart tourism route planning method and system, comprising: Step 1: monitoring the walking speed of target tourists and obtaining the walking anomaly coefficient of target tourists within the current monitoring period; Step 2: evaluating the current state of target tourists based on the walking anomaly coefficient and generating a state pre-evaluation signal; Step 3: analyzing whether the tourism route affects the walking state based on the walking state pre-anomaly signal and generating an impact analysis signal; Step 4: re-evaluating the current state of target tourists based on the impact analysis signal and generating a state evaluation signal; Step 5: generating a walking state anomaly warning based on the walking state anomaly signal; This invention ensures data freshness through real-time monitoring, accurately analyzes and reveals the nature of anomalies, and responds promptly to reduce safety risks, comprehensively improving the safety and management efficiency of tourism services.

Description

Technical Field

[0001] The present invention relates to the technical field of tourism route planning, and in particular to a smart tourism route planning method and system. Background Art

[0002] Follow Me is a track-following and -recording feature in the 32nd APP. Users can use Follow Me to follow the standard track, view the mark points and walking progress, share the location with the leader or teammates, understand the progress of the entire team and the location of the leader and teammates, record your track information and generate a beautiful track map for sharing after the event.

[0003] However, the existing technology for monitoring tourists' walking speed often ignores the individual differences between each tourist. Tourists have different walking speed habits, so when evaluating whether the tourists' walking speed is abnormal, it will lead to inaccurate evaluation. In addition, the existing technology cannot specifically analyze whether the abnormal walking speed of tourists is caused by tourists or interference with the travel route, which leads to misjudgment of abnormal tourist speed. Summary of the invention

[0004] The purpose of the present invention is to provide a smart tourism route planning method and system to solve the technical problems in the above background.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] In a first aspect, the present invention provides a method for smart tourism route planning, comprising the following steps:

[0007] Step 1: Monitor the walking speed of the target tourists and obtain the walking abnormality coefficient of the target tourists in the current monitoring period;

[0008] Step 2: Based on the walking abnormality coefficient, the current state of the target tourist is evaluated and a state pre-evaluation signal is generated;

[0009] The state pre-evaluation signal includes: a walking state pre-abnormal signal and a walking state normal signal;

[0010] Step 3: Based on the walking state pre-abnormal signal, analyze whether the travel route has an impact on the walking state, and generate an impact analysis signal;

[0011] Step 4: Based on the impact analysis signal, re-evaluate the current status of the target tourists and generate a status evaluation signal;

[0012] The state evaluation signal includes: abnormal walking state signal and misjudgment walking state signal;

[0013] Step 5: Generate a walking state abnormality warning based on the walking state abnormality signal.

[0014] As a further solution of the present invention: the process of obtaining the abnormal coefficient is:

[0015] Monitor the walking speed of target tourists in real time and obtain the average speed of target tourists during the monitoring period;

[0016] Based on the average speed of each monitoring period, the current walking abnormality coefficient of the current monitoring period is calculated.

[0017] As a further solution of the present invention: based on the average speed of each monitoring period, the process of calculating the current walking abnormality coefficient of the current monitoring period is:

[0018] Obtain the average speed of all monitoring cycles of the target tourists on the current travel route, and calculate the average of the average speed of all monitoring cycles to obtain the total average of the cycle;

[0019] Preset a period average speed threshold, sum the period total mean and the period average speed threshold to obtain the period total average speed maximum threshold; perform difference calculation on the period total mean and the period average speed threshold to obtain the period total average speed minimum threshold;

[0020] Compare and analyze the cycle mean of each monitoring cycle with the maximum threshold of the cycle total average speed and the minimum threshold of the cycle total average speed;

[0021] If the cycle mean value is greater than the maximum threshold value of the total average speed of the cycle, a fast cycle signal is generated and the monitoring cycle is marked as a fast cycle;

[0022] If the cycle mean is ≤ the minimum threshold of the total average speed of the cycle, a slow cycle signal is generated and the monitoring cycle is marked as a slow cycle;

[0023] If the minimum threshold of the total average speed of the cycle is less than the mean value of the cycle and less than the maximum threshold of the total average speed of the cycle, a moderate period signal is generated;

[0024] Extract the total number of fast cycles in all monitoring cycles to obtain the total number of fast cycles;

[0025] Extract the total number of slow cycles in all monitoring cycles to obtain the total number of slow cycles;

[0026] The total number of fast cycles and the total number of slow cycles are calculated by difference, and the absolute value is taken to obtain the speed floating characterization value;

[0027] The speed floating characterization value is calculated by ratio with the total number of monitoring cycles to obtain the speed floating characterization ratio;

[0028] The walking abnormality coefficient SYD of the current monitoring period is calculated by the formula: SYD = |ZSD-ZSZ| × (1-SFB), where ZSD is the average speed of the current period, ZSZ is the total mean of the period, and SFB is the speed floating characterization ratio.

[0029] As a further solution of the present invention: the process of generating the state pre-evaluation signal is:

[0030] Preset a walking abnormality coefficient threshold, and compare and analyze the walking abnormality coefficient with the walking abnormality coefficient threshold;

[0031] If the walking abnormality coefficient is less than the walking abnormality coefficient threshold, a walking state normal signal is generated;

[0032] If the walking abnormality coefficient ≥ the walking abnormality coefficient threshold, a walking state pre-abnormality signal is generated.

[0033] As a further solution of the present invention: the impact analysis signal includes: a route impact signal and a route no impact signal.

[0034] As a further solution of the present invention: the process of generating the impact analysis signal is:

[0035] Based on the walking state pre-abnormal signal, the walking path of the target tourist in the current abnormal period is extracted to obtain the current abnormal path of the target tourist;

[0036] Extract the abnormal paths of other tourists and obtain multiple abnormal paths of other tourists;

[0037] Based on all other tourists’ abnormal paths, extract other tourists’ abnormal paths that overlap with the current abnormal path of the target tourist and mark them as analysis paths;

[0038] Based on all analysis paths, the abnormal tourist ratio and the mean value of the effective coefficient are calculated;

[0039] The synchronous anomaly coefficient is obtained by multiplying the abnormal tourist number ratio with the effective coefficient mean;

[0040] Preset a synchronization anomaly coefficient threshold, and compare and analyze the synchronization anomaly coefficient with the synchronization anomaly coefficient threshold;

[0041] If the synchronization anomaly coefficient is greater than the synchronization anomaly coefficient threshold, a signal that the route is affected is generated;

[0042] If the synchronization anomaly coefficient is less than or equal to the synchronization anomaly coefficient threshold, a route-free signal is generated.

[0043] As a further solution of the present invention: the process of obtaining the abnormal tourist number ratio is as follows:

[0044] The total number of analysis paths is extracted to obtain the number of abnormal tourists, and the ratio of the number of abnormal tourists to the total number of other tourists is calculated to obtain the abnormal tourist ratio.

[0045] As a further solution of the present invention: the process of obtaining the effective coefficient mean is:

[0046] Based on a single analysis path, the overlap length between the analysis path and the current abnormal path of the target tourist is extracted to obtain the overlap path length, and the overlap path length is calculated by ratio between the overlap path length and the analysis path length to obtain the overlap ratio;

[0047] Extract the walking abnormality coefficient corresponding to the analysis path, calculate the overlap ratio and the walking abnormality coefficient, and obtain the effective coefficient of the analysis path;

[0048] The effective coefficients of all analysis paths are averaged to obtain the mean effective coefficient.

[0049] As a further solution of the present invention: the process of generating the state evaluation signal is:

[0050] Analyze signals based on impact;

[0051] When a signal that the route is affected is received, a walking state misjudgment signal is generated;

[0052] When a route-unaffected signal is received, a walking state abnormality signal is generated.

[0053] In a second aspect, the present invention provides a smart tourism route planning system, the system comprising:

[0054] Data collection module: monitors the walking speed of target tourists and obtains the walking abnormality coefficient of target tourists in the current monitoring period;

[0055] Status prediction module: Based on the walking abnormality coefficient, the current status of the target tourists is evaluated and a status prediction signal is generated;

[0056] The state pre-evaluation signal includes: a walking state pre-abnormal signal and a walking state normal signal;

[0057] Impact analysis module: Based on the walking state pre-abnormal signal, analyze whether the travel route has an impact on the walking state and generate an impact analysis signal;

[0058] Status evaluation module: based on the impact analysis signal, re-evaluates the current status of the target tourists and generates a status evaluation signal;

[0059] The state evaluation signal includes: abnormal walking state signal and misjudgment walking state signal;

[0060] Alarm module: Generates abnormal walking status warning based on abnormal walking status signal.

[0061] Beneficial effects of the present invention:

[0062] The present invention records the walking speed of tourists in real time and calculates the average speed according to a set period; if the walking abnormality coefficient in a certain period exceeds a preset threshold, the walking state of the tourists is determined to be abnormal; then, an in-depth analysis is performed to determine whether the abnormality is caused by the tourist route itself; the abnormal walking path of the target tourist is extracted, and compared with the abnormal paths of other tourists, and the overlapping part is found as the analysis path; based on these paths, the abnormal tourist number ratio and the effective coefficient mean are calculated, and the product of the two is obtained to obtain the synchronous abnormality coefficient; if the coefficient exceeds the set threshold, it is determined that the route has a significant impact on the walking speed of the tourists, and a route influence signal is generated; otherwise, it is considered that the factors of the tourists themselves are caused, and a route no influence signal is generated; according to the route impact analysis result, the walking state of the target tourists is re-evaluated; if the abnormality is caused by the route, it is determined to be a misjudgment and a misjudgment signal is generated; if it is caused by the factors of the tourists themselves, the abnormal signal is maintained; finally, when it is confirmed that the walking state is indeed abnormal, the system promptly issues a warning to the manager so that measures can be taken quickly to reduce the risk of danger for tourists on the tourist route; the present invention ensures the freshness of data through real-time monitoring, reveals the nature of abnormality through accurate analysis, and reduces safety risks through immediate response, thereby comprehensively improving the safety and management efficiency of tourism services. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] The present invention will be further described below in conjunction with the accompanying drawings.

[0064] Figure 1 is a flowchart of Embodiment 1 of the present invention;

[0065] Figure 2 It is a system block diagram of embodiment 2 of the present invention. DETAILED DESCRIPTION

[0066] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0067] Embodiment 1:

[0068] See also Figure 1 As shown, a smart tourism route planning method according to an embodiment of the present invention comprises the following steps:

[0069] Step 1: Monitor the walking speed of the target tourists and obtain the walking abnormality coefficient of the target tourists within the current monitoring period (the monitoring period includes but is not limited to: 10 minutes, 30 minutes);

[0070] In some implementation schemes, the walking speed of the target tourist is monitored in real time to obtain the target tourist's average speed during the monitoring period;

[0071] Based on the average speed of each monitoring period (the average speed is the ratio of the distance of the target tourist's walking path during the monitoring period to the duration of the monitoring period, i.e., the average speed of the target tourist during the monitoring period), the current walking abnormality coefficient of the current monitoring period is calculated;

[0072] Exemplarily, based on the average speed of each monitoring period, the process of calculating and obtaining the current walking abnormality coefficient of the current monitoring period is as follows:

[0073] Obtain the average speed of all monitoring cycles of the target tourists on the current travel route, and calculate the average of the average speed of all monitoring cycles to obtain the total average of the cycle;

[0074] Preset a period average speed threshold, sum the period total mean and the period average speed threshold to obtain the period total average speed maximum threshold; perform difference calculation on the period total mean and the period average speed threshold to obtain the period total average speed minimum threshold;

[0075] Compare and analyze the cycle mean of each monitoring cycle with the maximum threshold of the cycle total average speed and the minimum threshold of the cycle total average speed;

[0076] If the cycle mean value is greater than the maximum threshold of the total average speed of the cycle, it means that the walking speed of the target tourist in the monitoring cycle is relatively fast, that is, a fast cycle signal is generated, and the monitoring cycle is marked as a fast cycle;

[0077] If the cycle mean is ≤ the minimum threshold of the cycle total average speed, it means that the walking speed of the target tourist in the monitoring cycle is slow, that is, a slow cycle signal is generated, and the monitoring cycle is marked as a slow cycle;

[0078] If the minimum threshold of the total average speed of the cycle is less than the mean value of the cycle and less than the maximum threshold of the total average speed of the cycle, it means that the walking speed of the target tourists in the monitoring period is moderate, that is, a moderate cycle signal is generated;

[0079] Extract the total number of fast cycles in all monitoring cycles to obtain the total number of fast cycles;

[0080] Extract the total number of slow cycles in all monitoring cycles to obtain the total number of slow cycles;

[0081] The total number of fast cycles and the total number of slow cycles are calculated by difference, and the absolute value is taken to obtain the speed floating characterization value;

[0082] The speed floating representation value is calculated by ratio with the total number of monitoring cycles to obtain the speed floating representation ratio (the speed floating representation ratio reflects the stability of the walking speed of the target tourist in each monitoring cycle during the walking process; the larger the value of the speed floating representation, the smaller the stability of the walking speed of the target tourist in each monitoring cycle, that is, the walking speed of the target user is sometimes fast and sometimes slow; and the speed floating representation is less than 1, and the speed floating representation is greater than or equal to 0);

[0083] The walking abnormality coefficient SYD of the current monitoring period is calculated by the formula: SYD = |ZSD-ZSZ| × (1-SFB) (the larger the value of the walking abnormality coefficient of the current monitoring period, the higher the possibility that the target tourist has abnormal walking speed in the current monitoring period), where ZSD is the average speed of the current period (the average speed of the current period is the average speed of the period of the current monitoring period), ZSZ is the total mean of the period, and SFB is the speed floating representation ratio;

[0084] It should be explained that |ZSD-ZSZ| reflects the deviation between the target tourist's current cycle average speed and its cycle total mean. The larger the calculation result of |ZSD-ZSZ| is, the greater the deviation between the target tourist's walking speed in the current monitoring cycle and its previous walking average speed is; the smaller the calculation result of 1-SFB), the larger the speed fluctuation representation SFB is, that is, the more unstable the target tourist's walking speed is. At this time, the more the deviation between the target tourist's current cycle average speed and its cycle total mean is adjusted, that is, the more the calculation result of |ZSD-ZSZ| is reduced; it can be seen that the calculation of (1-SFB) above is an adjustment to the calculation result of |ZSD-ZSZ|. If the walking habit of the target tourist is unstable in speed, that is, the deviation between the tourist's current cycle average speed and its cycle total mean can be appropriately reduced;

[0085] Step 2: Based on the walking abnormality coefficient, the current state of the target tourist is evaluated and a state pre-evaluation signal is generated;

[0086] The state pre-evaluation signal includes: a walking state pre-abnormal signal and a walking state normal signal;

[0087] In some implementation schemes, a walking abnormality coefficient threshold is preset, and the walking abnormality coefficient is compared and analyzed with the walking abnormality coefficient threshold;

[0088] If the walking abnormality coefficient is less than the walking abnormality coefficient threshold, it means that the walking speed of the target tourist in the current monitoring period is relatively stable, and the target tourist is judged to be normal in the current state, that is, a normal walking state signal is generated;

[0089] If the walking abnormality coefficient is greater than or equal to the walking abnormality coefficient threshold, it means that the walking speed of the target tourist in the current monitoring period is relatively unstable, and the target tourist is judged to be abnormal in the current state, that is, a walking state pre-abnormal signal is generated;

[0090] Step 3: Based on the walking state pre-abnormal signal, analyze whether the travel route has an impact on the walking state, and generate an impact analysis signal;

[0091] Among them, the impact analysis signal includes: route impact signal and route non-impact signal;

[0092] In some implementation schemes, based on the walking state pre-abnormal signal, the walking path of the target tourist in the current abnormal period (the current abnormal period is the current monitoring period corresponding to the generation of the walking state abnormal signal) is extracted to obtain the current abnormal path of the target tourist;

[0093] Extract the abnormal paths of other tourists and obtain multiple abnormal paths of other tourists (the method of obtaining the abnormal paths of other tourists is the same as the method of obtaining the current abnormal path of the target tourist, which will not be repeated here);

[0094] Based on all other tourists’ abnormal paths, extract other tourists’ abnormal paths that overlap with the current abnormal path of the target tourist and mark them as analysis paths;

[0095] Based on all analysis paths, the abnormal tourist ratio and the mean value of the effective coefficient are calculated;

[0096] The synchronous anomaly coefficient is obtained by multiplying the abnormal tourist number ratio with the effective coefficient mean;

[0097] Preset a synchronization anomaly coefficient threshold, and compare and analyze the synchronization anomaly coefficient with the synchronization anomaly coefficient threshold;

[0098] If the synchronization anomaly coefficient is greater than the synchronization anomaly coefficient threshold, it means that there are many other tourists with abnormal walking speeds on the section of the target tourist's current abnormal path, that is, the section of the target tourist's current abnormal path is determined to have a greater impact on the tourists' walking speed, and a route influence signal is generated;

[0099] If the synchronization anomaly coefficient is less than or equal to the synchronization anomaly coefficient threshold, it means that the number of other tourists with abnormal walking speeds on the section of the target tourist's current abnormal path is small, that is, the section of the target tourist's current abnormal path is determined to have a small impact on the tourist's walking speed, and a route-no-impact signal is generated;

[0100] In a first exemplary embodiment, the process of obtaining the abnormal tourist number ratio is as follows:

[0101] Extract the total number of analysis paths to obtain the number of abnormal tourists, calculate the ratio of the number of abnormal tourists to the total number of other tourists, and obtain the ratio of the number of abnormal tourists;

[0102] In the second exemplary embodiment, the process of obtaining the effective coefficient mean is as follows:

[0103] Based on a single analysis path, extract the overlap length between the analysis path and the current abnormal path of the target tourist to obtain the overlap path length, calculate the ratio of the overlap path length to the analysis path length (the analysis path length is the length of the analysis path) to obtain the overlap ratio;

[0104] Extract the walking abnormality coefficient corresponding to the analysis path, calculate the overlap ratio and the walking abnormality coefficient, and obtain the effective coefficient of the analysis path;

[0105] The effective coefficients of all analysis paths are averaged to obtain the effective coefficient mean;

[0106] Step 4: Based on the impact analysis signal, re-evaluate the current status of the target tourists and generate a status evaluation signal;

[0107] The state evaluation signal includes: abnormal walking state signal and misjudgment walking state signal;

[0108] In some embodiments, the signal is analyzed based on the impact;

[0109] When a signal that the route is affected is received, it indicates that the abnormal walking state signal of the target tourist is caused by the route, not by the target tourist himself, that is, the current state of the target tourist is re-evaluated and a walking state misjudgment signal is generated;

[0110] When a signal indicating that the route has no impact is received, it indicates that the abnormal walking state signal of the target tourist is not caused by the route but by the target tourist himself, that is, the current state of the target tourist is re-evaluated and an abnormal walking state signal is generated;

[0111] Step 5: generating a walking state abnormality warning based on the walking state abnormality signal;

[0112] In some embodiments, when an abnormal walking state signal is received, an abnormal walking state warning is generated, thereby reminding the manager that the target tourist is in an abnormal state, so as to reduce the risk of danger to the target tourist;

[0113] The technical solution of the embodiment of the present invention is mainly as follows: by recording the walking speed of tourists in real time and calculating the average speed according to a set period; if the walking abnormality coefficient in a certain period exceeds a preset threshold, it is determined that the walking state of the tourists is abnormal; then, an in-depth analysis is performed to determine whether the abnormality is caused by the tourist route itself; the abnormal walking path of the target tourists is extracted, and compared with the abnormal paths of other tourists, and the overlapping parts are found as the analysis path; based on these paths, the ratio of the number of abnormal tourists and the mean of the effective coefficient are calculated, and the product of the two is used to obtain the synchronous abnormality coefficient; if the coefficient exceeds the set threshold, it is determined that the route has a significant impact on the walking speed of tourists, and a route influence signal is generated ; Otherwise, it is considered to be caused by the tourists themselves, and a route-influence-free signal is generated; according to the route impact analysis results, the walking status of the target tourists is re-evaluated; if the anomaly is caused by the route, it is determined to be a misjudgment and a misjudgment signal is generated; if it is caused by the tourists themselves, the abnormal signal is maintained; finally, when it is confirmed that the walking status is indeed abnormal, the system promptly issues a warning to the manager so that measures can be taken quickly to reduce the risk of danger to tourists on the tourist route; the present invention ensures the freshness of data through real-time monitoring, reveals the nature of anomalies through accurate analysis, and reduces safety risks through immediate response, thereby comprehensively improving the safety and management efficiency of tourism services.

[0114] Embodiment 2:

[0115] Based on Example 1, please refer to Figure 2 As shown, a smart tourism route planning system according to an embodiment of the present invention includes:

[0116] Data collection module: monitors the walking speed of target tourists and obtains the walking abnormality coefficient of target tourists in the current monitoring period;

[0117] Status prediction module: Based on the walking abnormality coefficient, the current status of the target tourists is evaluated and a status prediction signal is generated;

[0118] The state pre-evaluation signal includes: a walking state pre-abnormal signal and a walking state normal signal;

[0119] Impact analysis module: Based on the walking state pre-abnormal signal, analyze whether the travel route has an impact on the walking state and generate an impact analysis signal;

[0120] Status evaluation module: based on the impact analysis signal, re-evaluates the current status of the target tourists and generates a status evaluation signal;

[0121] The state evaluation signal includes: abnormal walking state signal and misjudgment walking state signal;

[0122] Alarm module: Generates abnormal walking status warning based on abnormal walking status signal.

[0123] The above thresholds are set for the convenience of comparison. The thresholds depend on the amount of sample data and the number of bases set by technicians in this field for each set of sample data.

[0124] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A smart tourism route planning method, characterized in that: The following steps are involved: Step 1: Monitor the walking speed of the target tourists and obtain the walking abnormality coefficient of the target tourists in the current monitoring period; Based on the average speed of each monitoring period, the process of calculating the current walking abnormality coefficient of the current monitoring period is as follows: Obtain the average speed of all monitoring cycles of the target tourists on the current travel route, and calculate the average of the average speed of all monitoring cycles to obtain the total average of the cycle; Preset a period average speed threshold, sum the period total mean and the period average speed threshold to obtain the period total average speed maximum threshold; perform difference calculation on the period total mean and the period average speed threshold to obtain the period total average speed minimum threshold; Compare and analyze the cycle mean of each monitoring cycle with the maximum threshold of the cycle total average speed and the minimum threshold of the cycle total average speed; If the cycle mean value is greater than the maximum threshold value of the total average speed of the cycle, a fast cycle signal is generated and the monitoring cycle is marked as a fast cycle; If the cycle mean is ≤ the minimum threshold of the total average speed of the cycle, a slow cycle signal is generated and the monitoring cycle is marked as a slow cycle; If the minimum threshold of the total average speed of the cycle is less than the mean value of the cycle and less than the maximum threshold of the total average speed of the cycle, a moderate period signal is generated; Extract the total number of fast cycles in all monitoring cycles to obtain the total number of fast cycles; Extract the total number of slow cycles in all monitoring cycles to obtain the total number of slow cycles; The total number of fast cycles and the total number of slow cycles are calculated by difference, and the absolute value is taken to obtain the speed floating characterization value; The speed floating characterization value is calculated by ratio with the total number of monitoring cycles to obtain the speed floating characterization ratio; The walking abnormality coefficient SYD of the current monitoring period is calculated by the formula: SYD = |ZSD-ZSZ| × (1-SFB), where ZSD is the average speed of the current period, ZSZ is the total mean of the period, and SFB is the speed floating representation ratio; Step 2: Based on the walking abnormality coefficient, the current state of the target tourist is evaluated and a state pre-evaluation signal is generated; The state pre-evaluation signal includes: a walking state pre-abnormal signal and a walking state normal signal; Step 3: Based on the walking state pre-abnormal signal, analyze whether the travel route has an impact on the walking state, and generate an impact analysis signal; The process of generating an impact analysis signal is: Based on the walking state pre-abnormal signal, the walking path of the target tourist in the current abnormal period is extracted to obtain the current abnormal path of the target tourist; Extract the abnormal paths of other tourists and obtain multiple abnormal paths of other tourists; Based on all other tourists’ abnormal paths, extract other tourists’ abnormal paths that overlap with the current abnormal path of the target tourist and mark them as analysis paths; Based on all analysis paths, the abnormal tourist ratio and the mean value of the effective coefficient are calculated; The process of obtaining the mean of effective coefficients is: Based on a single analysis path, the overlap length between the analysis path and the current abnormal path of the target tourist is extracted to obtain the overlap path length, and the overlap path length is calculated by ratio between the overlap path length and the analysis path length to obtain the overlap ratio; Extract the walking abnormality coefficient corresponding to the analysis path, calculate the product of the coincidence ratio and the walking abnormality coefficient, and obtain the effective coefficient of the analysis path; The effective coefficients of all analysis paths are averaged to obtain the effective coefficient mean; The synchronous anomaly coefficient is obtained by multiplying the abnormal tourist number ratio with the effective coefficient mean; Preset a synchronization anomaly coefficient threshold, and compare and analyze the synchronization anomaly coefficient with the synchronization anomaly coefficient threshold; If the synchronization anomaly coefficient is greater than the synchronization anomaly coefficient threshold, a signal that the route is affected is generated; If the synchronization anomaly coefficient ≤ the synchronization anomaly coefficient threshold, a signal with no impact on the route is generated; Step 4: Based on the impact analysis signal, re-evaluate the current status of the target tourists and generate a status evaluation signal; The state evaluation signal includes: abnormal walking state signal and misjudgment walking state signal; Step 5: Generate a walking state abnormality warning based on the walking state abnormality signal.

2. A smart tourism route planning method according to claim 1, characterized in that: The process of generating the status prediction signal is as follows: Preset a walking abnormality coefficient threshold, and compare and analyze the walking abnormality coefficient with the walking abnormality coefficient threshold; If the walking abnormality coefficient is less than the walking abnormality coefficient threshold, a walking state normal signal is generated; If the walking abnormality coefficient ≥ the walking abnormality coefficient threshold, a walking state pre-abnormality signal is generated.

3. A smart tourism route planning method according to claim 1, characterized in that: The process of obtaining the abnormal tourist ratio is as follows: The total number of analysis paths is extracted to obtain the number of abnormal tourists, and the ratio of the number of abnormal tourists to the total number of other tourists is calculated to obtain the abnormal tourist ratio.

4. A smart tourism route planning method according to claim 1, characterized in that: The process of generating the status evaluation signal is: Analyze signals based on impact; When a signal that the route is affected is received, a walking state misjudgment signal is generated; When a route-unaffected signal is received, a walking state abnormality signal is generated.

5. A smart tourism route planning system, characterized in that: The system is used to execute the method described in any one of claims 1 to 4, and the system comprises: Data collection module: monitors the walking speed of target tourists and obtains the walking abnormality coefficient of target tourists in the current monitoring period; Status prediction module: Based on the walking abnormality coefficient, the current status of the target tourists is evaluated and a status prediction signal is generated; The state pre-evaluation signal includes: a walking state pre-abnormal signal and a walking state normal signal; Impact analysis module: Based on the walking state pre-abnormal signal, analyze whether the travel route has an impact on the walking state and generate an impact analysis signal; Status evaluation module: based on the impact analysis signal, re-evaluates the current status of the target tourists and generates a status evaluation signal; The state evaluation signal includes: abnormal walking state signal and misjudgment walking state signal; Alarm module: Generates abnormal walking status warning based on abnormal walking status signal.

Images