CN111935637A - People flow analysis method, storage medium and processor - Google Patents

Abstract

The invention provides a people flow analysis method, a storage medium and a processor, wherein the method comprises the following steps: reading positioning information data in a specified time range from a server; performing statistical analysis on the read positioning information data; and predicting the change situation of the flow of people in a period of time in the future according to the statistical analysis result. The pedestrian flow data can be obtained by collecting the MAC of the pedestrian handheld electronic equipment in the coverage area of the AP, counting, summarizing and classifying the MAC information, deep mining is carried out on the data, the personnel input and output amounts in different time periods and the personnel stay time can be obtained, the change condition of the pedestrian flow in a period of time in the future can be predicted, the functions of counting and predicting the pedestrian flow and the like can be realized, and the occurrence of potential public safety hazard events can be effectively prevented/solved.

Description

A kind of human flow analysis method, storage medium and processor

【Technical field】

The present invention is in the technical field of human flow analysis, and in particular, relates to a human flow analysis method, a storage medium and a processor.

【Background technique】

Existing people flow counting methods roughly include two methods: manual counting and video recognition. The manual counting method has many influences such as personnel, time, cost, etc., which leads to the lack of comprehensiveness and validity of the final statistical data, and it is even more difficult in the case of particularly dense traffic, and there is no in-depth analysis of the data. Video recognition has high requirements on light intensity and recognition accuracy. For scenes with weak light, the recognition function fails and the recognition accuracy rate is low. One person will be recognized as multiple people, which will affect the results of traffic statistics. The implementation cost and operation and maintenance cost are high.

[Content of the invention]

The technical problem to be solved by the present invention is to provide a human flow analysis method, a storage medium and a processor. By collecting the MAC of pedestrians' handheld electronic devices in the AP coverage area, and performing statistics, summarization and classification on the MAC information, the human flow can be obtained. Data, and then further mining this data, you can get the number of people entering and leaving in different time periods, the time of people staying, and can predict the changes in the flow of people in a period of time in the future, and realize the functions of statistics and prediction of the flow of people, effectively Prevent and resolve potential events that endanger public safety. It can be generally applied to the statistics of passenger flow in public places such as shopping malls, supermarkets, scenic spots, stations, airports, etc., to predict the flow of people in the future; it can also be extended to conduct deeper analysis on the data of people flow, and then get potential customers. Lists, personnel attribute classification, etc.; not only can be used in civilian scenarios, but also in police systems.

In order to solve the above technical problem, on the one hand, an embodiment of the present invention provides a method for analyzing human flow, including: reading positioning information data within a specified time range from a server; performing statistical analysis on the read positioning information data; Output the total number of people flow; according to the results of statistical analysis, predict the change of people flow in a period of time in the future.

Preferably, before reading the positioning information data within the specified time range from the server, the method further includes: generating the positioning information data.

Preferably, performing statistical analysis on the read positioning information data includes: gathering the read positioning information data to obtain the total number of MACs within the time range.

Preferably, the positioning information data includes location information and time information corresponding to the location information.

Preferably, predicting the change of the flow of people in a period of time in the future includes: according to the result of statistical analysis of the read positioning information data, predicting the change of the flow of people in a period of time in the future and outputting the prediction result.

Preferably, generating the positioning information data includes: collecting the MAC of the user's handheld electronic device within the coverage area of the AP.

Preferably, the location information is latitude and longitude coordinates or pixel coordinates or area numbers.

Preferably, after the MAC is screened, the method further includes: outputting the total number of MACs after screening.

On the other hand, an embodiment of the present invention provides a storage medium, where the storage medium includes a stored program, wherein the above-mentioned method for analyzing human flow is executed when the program runs.

On the other hand, an embodiment of the present invention provides a processor for running a program, wherein the above-mentioned method for analyzing human flow is executed when the program is running.

On the other hand, an embodiment of the present invention provides a human flow analysis system, including: a positioning module, the positioning module is used to generate positioning information data; a statistical analysis module, the statistical analysis module is used to analyze the positioning information data Statistical analysis; output module, the output module is used to output the total number of people flow.

Preferably, the system further includes a forecasting module, and the forecasting module is used for forecasting the change of the flow of people in a period of time in the future.

Preferably, the positioning information data includes position information and time information corresponding to the position information.

Preferably, the positioning module includes: a WiFi probe device, a POE module, and a server, the WiFi probe device is used to detect the device MAC; the POE module is used to supply power to the WiFi probe device and send data back to the to the server; the server includes a database server and a location server, the database server is used to store the detected MAC information of the device, the location server is used to perform location calculation on the data stored in the database server, and store the MAC information. Information corresponding to the location information.

Preferably, the statistical analysis module includes a statistical analysis category setting module, and the statistical analysis category setting module sets the category of statistical analysis.

Preferably, the prediction module predicts the flow of people within a specified time range in the future according to the result of the statistical analysis by the statistical analysis module and outputs the prediction result.

Preferably, the category of the statistical analysis includes statistics based on time range, statistics based on area range, or a combination of time and area.

Preferably, the location information is latitude and longitude coordinates or pixel coordinates or area numbers.

Compared with the prior art, the above technical solution has the following advantages: by collecting the MAC of pedestrians' handheld electronic devices in the AP coverage area, and performing statistics, summarization, and classification on the MAC information, the traffic data can be obtained, and the data can be further analyzed. Digging, you can get the number of people entering and leaving in different time periods, the time of people staying, and can predict the change of the flow of people in the future, realize the statistics and prediction of the flow of people, and effectively prevent and solve the potential harm to public safety. the occurrence of the event. It can be generally applied to the statistics of passenger flow in public places such as shopping malls, supermarkets, scenic spots, stations, airports, etc., to predict the flow of people in the future; it can also be extended to conduct deeper analysis on the data of people flow, and then get potential customers. Lists, personnel attribute classification, etc.; not only can be used in civilian scenarios, but also in police systems.

【Description of drawings】

In order to illustrate the technical solutions in the embodiments of the present invention more clearly, the following briefly introduces the accompanying drawings used in the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without any creative effort.

FIG. 1 is a flow chart of the method for analyzing the flow of people according to the present invention.

FIG. 2 is a schematic diagram of MAC statistical screening in the people flow analysis method of the present invention.

FIG. 3 is a schematic diagram of the storage of the locating server by the partition method in the method for analyzing the flow of people of the present invention.

FIG. 4 is a flow chart of a method for maintaining a MAC record library in the flow analysis method of the present invention.

FIG. 5 is a schematic diagram of the storage of the MAC record library in the traffic analysis method of the present invention.

FIG. 6 is a structural diagram of the human flow analysis system of the present invention.

FIG. 7 is a structural diagram of a WiFi positioning module in the human traffic analysis system of the present invention.

FIG. 8 is a schematic diagram of data server storage in the human flow analysis system of the present invention.

FIG. 9 is a schematic diagram of the storage of the location server in the human flow analysis system of the present invention.

【Detailed ways】

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

Example 1

FIG. 1 is a flow chart of the method for analyzing the flow of people according to the present invention. As shown in Figure 1, a human flow analysis method includes steps:

S11. Read the positioning information data within the specified time range from the server.

During specific implementation, different functional analysis can be achieved through data screening in different time periods.

S111. Real-time people flow statistics.

For the same mobile phone, the packet sending frequency of the wifi signal is constantly changing when the brightness of the mobile phone is different, that is, the packet sending rate of the mobile phone is high when the screen is on, and the packet sending rate is low when the screen is off. Therefore, the statistics of real-time traffic flow can be counted as the positioning information data within 1 to 10 minutes of the current moment.

S112. Historical people flow statistics.

Expand the time range of reading to obtain historical traffic statistics. For example, if you need to obtain the daily traffic statistics, the data filtering time range can be set to 00:00:00～23:59:59; if you need to obtain the weekly traffic statistics, then the data filtering time range can be set to Scheduled from 00:00:00 on Monday to 23:59:59 on Sunday.

S113. Statistics on the flow of people in special periods.

By filtering the positioning information data of a special time period, the traffic statistics of the special time period can be obtained, and the hidden information can be obtained by further analysis in combination with this time period. For example, if it is necessary to obtain the flow of people during the evening rush hour after get off work, the screening time range of the data can be set from 17:00:00 to 19:00:00. The data screening time range can be set from 00:00:00 to 00:02:00, and the Ministry of Public Security can filter suspicious persons according to the statistical MAC information.

S12. Count the read positioning information data.

Collect the read positioning information data to obtain the total number of MACs within the specified time range.

S13. Screen the MAC.

It should be noted that the MAC consists of six bytes, of which the first three bytes are used to distinguish different manufacturers. The definition of legal MAC can be combined with the global organization unique identifier OUI library to distinguish and distinguish. The manufacturers in the OUI library not only include Mobile phone manufacturers, as well as routers, servers, medical equipment, etc., can sort out the MAC library of mobile phone manufacturers according to the OUI library, and the secondary screening process can refer to the MAC library of mobile phone manufacturers for filtering. Since the captured MACs include not only mobile phone devices, but also electronic devices with wireless network cards such as routers and servers, it is necessary to perform secondary screening on the MACs counted in step S12, and only keep the MACs of portable devices. MAC statistics to screening are shown in Figure 2. FIG. 2 is a schematic diagram of MAC statistical screening in the people flow analysis method of the present invention. For example, the total number of captured MACs within the specified time range is 5, and the MAC and device information are: 3C:15:C2:D2:24:FE, iPhone; DC:FE:18:AE:C8:56, TPLINK; 5F:85:C4:22:38:C1, HUAWEI; C8:3A:35:30:F3:A0, Tenda; 56:45:D7:82:54:CE, XiaoMi. After removing the non-defense devices, the screened MAC information is: 3C:15:C2:D2:24:FE, iPhone; 5F:85:C4:22:38:C1, HUAWEI; 56:45:D7:82 :54:CE, XiaoMi. For other numbers of MACs grabbed within the specified time frame, the screening method is as above.

S14. Output the total number of people flow.

The total number of MACs after the second screening is the total number of people in the specified time range.

It should be noted that the statistics on the flow of people can be calculated not only according to the time range, but also according to the area, or a combination of the two. The following focuses on how to divide the entire large coverage area into small areas. It mainly includes the strongest probe partition method and the geohash partition method, both of which need to add corresponding field storage to the data of the positioning server. The schematic diagram of the data storage of the positioning server corresponding to the partition method is shown in Figure 3. FIG. 3 is a schematic diagram of the storage of the locating server by the partition method in the method for analyzing the flow of people of the present invention. ID represents the acquired MAC number, the six-byte data is the specific MAC value, DEVICE represents the device name corresponding to the MAC value, the positioning coordinates X and Y represent the latitude and longitude coordinates or pixel coordinates of the device, REPORT_TIME represents the reporting time, and MAX_AP represents the strongest detection Needle information, geohash is the positioning coordinate converted to geohash value, that is, X, Y is converted to geohash value.

The strongest probe partitioning method is to divide the probe into sub-regions, and store the strongest probe number for the raw signal RSSI (Received Signal Strength Indication) of each MAC detected by the probe, such as The original signal strength of MAC1 detected is: {"AP1": -67, "AP2": -78, "AP3": -60}, then the strongest signal probe of MAC1 is AP3. If you want to count the total number of MACs near a probe or multiple probes, you only need to read the MAC data of the corresponding strongest probe number from the positioning server, and perform regional statistics according to the above steps S12 to S14. .

The geohash location hash partition method is to use the geohash idea to convert a longitude and latitude into a string encoding that can be sorted and compared. A geohash does not represent a point, but a rectangular area. Users can publish address codes, which can indicate that they are located near an address without exposing their precise coordinates, which is helpful for privacy protection. Geohash is much more efficient than using latitude and longitude directly. Convert the positioned latitude and longitude coordinates to geohash values and store them. If you need to count the flow of people near a specified location, the steps are as follows:

S1111. Obtain the latitude and longitude coordinates of the specified location, and convert them into geohash values.

S1112 , according to the geohash value of the specified location, read the matching geohash data from the positioning server.

S1113. Perform regional statistics according to the methods of S12 to S14 above.

Among them, the default geohash encoding is 12 bits, and the precision range corresponding to the first 9 bits is as follows. Different digits correspond to different precisions.

Embodiment 2

Let's analyze the time spent in traffic flow.

It can be known from the positioning information data that the positioning information includes not only the coordinate information, but also the corresponding time information. By performing statistical analysis on the time of each MAC, the corresponding stay time can be obtained. Specifically, it is divided into two processes: maintaining the MAC record database and analyzing the MAC residence time. Correspondingly, according to the MAC record database, the incoming and outgoing amount of MAC in the time range can also be distinguished.

The flow chart of maintaining the MAC record library is shown in accompanying drawing 4, and Fig. 4 is the flow chart of the method for maintaining the MAC record library in the flow analysis method of the present invention, and the concrete steps are as follows:

S21, initialize the MAC record library.

The MAC record library contains MAC information, the first detection time t _start and the last detection time t _end .

S22: Read the positioning information data of the positioning server in real time.

Set a timed task, and the timed period can be 1 to 10 minutes.

S23. Determine whether the MAC record library contains the read positioning information.

If not, go to step S24, otherwise go to step S25.

S24, simultaneously update the first detection time t _start and the last detection time t _end of the MAC to store the MAC information, and set both the first detection time t _start and the last detection time t _end as the current detection time.

S25. Only the last detection time of the MAC is updated.

The last detection time of the MAC information is updated to the current detection time.

S26, whether to complete the detection time update of all MACs in the positioning information data.

If yes, go to step S22 to implement the timing task; if not, go to step S23 to complete the traversal of all MACs.

The stored information in the MAC record library is shown in FIG. 5 . FIG. 5 is a schematic diagram of the storage of the MAC record library in the traffic analysis method of the present invention. ID represents the screened MAC number, the six-byte data is the specific MAC value, DEVICE represents the device name corresponding to the MAC value, and First Time and Last Time represent the first and last detection time.

Scalable, according to the length of stay in the MAC record library, multiple pieces of time record information can be stored for the same MAC. For example, taking the MAC that cannot be detected for 5 minutes as an example, if the MAC cannot be detected for 5 minutes, then the next time the MAC is detected again, the time will be recorded as the new arrival time of the first detection, the last time The detection time information is not covered, and the last detection time method remains unchanged.

The MAC dwell time is based on the analysis of the information in the MAC record library. The specific steps are as follows:

S211. Read the statistics of people flow within a specified time range.

For the reading method, refer to the above-mentioned people flow statistics method to obtain the corresponding MAC information within the specified time range.

S212, synchronously execute the MAC record library.

The MAC record library records multiple detection times for the same MAC.

S213. Calculate the stay time of the MAC.

Read the specified MAC information from the MAC record library, and calculate the difference of multiple detection times, that is, the length of each stay. The long accumulation of multiple stay times of the MAC is the stay time of the MAC within the specified time range.

Scalable, based on the analysis of the stay time of the MAC, it is possible to predict the change of the flow of people in the MAC in the future.

The amount of MAC inbound and outbound is based on the analysis of the information in the MAC record library. The specific steps are as follows:

S311. Read the statistics of people flow within a specified time range.

For the reading method, refer to the above-mentioned people flow statistics method to obtain the total number of people flow Cnt _total and the corresponding MAC information within the specified time range.

S312. Count newly appeared MAC information within a specified time range.

Read all MAC information whose first detection time is within the specified time range from the above-mentioned MAC record library, that is, the new MACs in this time range, and record the total number of them as Cnt _new .

S313. Count the MAC information that appears historically within the specified time range.

The total number of MACs appearing in history is Cnt _history =Cnt _total -Cnt _new .

Scalable, based on the analysis of the MAC inbound and outbound volume, it can combine specific areas to analyze the passenger flow attraction in different areas and different periods of time.

Embodiment 3

The present invention also discloses a storage medium, wherein the storage medium includes a stored program, wherein the above-mentioned method for analyzing human flow is executed when the program is running. Optionally, in this embodiment, the above-mentioned storage medium may include but is not limited to: a USB flash drive, a read-only memory (Read-Only Memory, referred to as ROM for short), a random access memory (Random Access Memory, referred to as RAM for short), mobile Various media that can store program codes, such as hard disks, magnetic disks, or optical disks. Optionally, for specific examples in this embodiment, reference may be made to the foregoing embodiments and the examples described in the specific implementation, and details are not described herein again in this embodiment.

Embodiment 4

The present invention also discloses a processor, which is used for running a program, wherein the above-mentioned method for analyzing human flow is executed when the program is running. Optionally, for specific examples in this embodiment, reference may be made to the foregoing embodiments and the examples described in the specific implementation, and details are not described herein again in this embodiment. Embodiment 5

FIG. 6 is a structural diagram of the human flow analysis system of the present invention. A human flow analysis system, comprising: a positioning module, which is used for generating positioning information data; a statistical analysis module, which is used for performing statistical analysis on the positioning information data; and an output module, which is used for outputting the total number of people flow . Prediction module, the prediction module is used to predict the change of the flow of people in a period of time in the future. The positioning information data includes position information and time information corresponding to the position information. The positioning module includes: a WiFi probe device, a POE module, and a server. The WiFi probe device is used to detect the device MAC; the POE module is used to supply power to the WiFi probe device and send data back to the server; the server includes a database server and a positioning server. , the database server is used to store the detected MAC information of the device, and the location server is used to perform location calculation on the data stored in the database server, and store the location information corresponding to the MAC information. The statistical analysis module includes a statistical analysis category setting module, and the statistical analysis category setting module sets the category of statistical analysis. The prediction module predicts the flow of people within a specified time range in the future according to the results of the statistical analysis by the statistical analysis module and outputs the prediction results. The categories of statistical analysis include statistics by time range, statistics by area range, or statistics by combining time and area. The location information is latitude and longitude coordinates or pixel coordinates or area numbers.

FIG. 7 is a structural diagram of a WiFi positioning module in the human traffic analysis system of the present invention. WiFi probes can provide basic identification data, and correlate the collected MAC address data with the data of telecommunications companies and public security organs to establish a multi-dimensional public security monitoring system. As the unique identification code of the smartphone, the MAC address can be used as the identification of the identity information. Combined with the construction of video sensing deployment location, the WiFi probe has a wide coverage, and can collect MAC addresses within the range. At the same time, the data is not limited, and MAC addresses can be collected in large quantities. The WiFi probe can realize the real-time transmission of data, and the monitoring data can be transmitted back in real time; Identity matching: The MAC address is used as the unique identification code of the mobile phone, and the identity matching can be realized in combination with other data.

The WiFi positioning module applies WiFi positioning technology to the scene of real-time tracking and identification of personnel. Through real-time positioning technology, it can timely discover and track suspicious personnel on site. The WiFi positioning system includes WiFi probe equipment, POE module, database server, and positioning server. Among them, the WiFi probe device is used for:

(1) The built-in induction module transmits high connection frequency SSID to induce device connection and increase the probability of capturing MAC.

(2) Full channel scan, grab the device MAC without missing packets.

(3) The encrypted return transmits information such as the strength of the marked MAC signal and the time difference of the connection to the location calculation server for accurate calculation of the location.

The POE module transmits data back to the database server while powering the WiFi probe device.

The database server, as a database for storing MAC addresses, runs the MAC address comparison program to quickly compare the MAC captured by the WiFi probe device, transmits the successful data to the positioning server, and connects the device with the marked MAC address for a long time. The connection time, location and other information are updated and stored, and the movement path of the marked MAC device is simulated. A schematic diagram of data server storage is shown in FIG. 2 .

The positioning server runs the positioning algorithm, calculates the position of the marked MAC, and transmits it to the database server to update the database of the marked MAC.

The WiFi probe device can scan all electronic devices in the area, integrate and summarize the captured MAC signal strength (RSSI), run the positioning algorithm, perform real-time positioning analysis on the marked MAC, and get the marked MAC. Real-time location information (p, t), where p represents location information and t represents the time corresponding to the current location.

FIG. 8 is a schematic diagram of data server storage in the human flow analysis system of the present invention. In the figure, each row of data indicates the number of the device to be located, the MAC address of the device to be located, the device name of the device to be located, the discovery time of the device to be located, the signal strength detected by the first wifi probe device RSSI ₁ , and the second wifi probe device. The signal strength detected by the needle device RSSI ₂ , ..., the signal strength RSSI _n-1 detected by the n-1th wifi probe device, the signal strength RSSI _n detected by the nth wifi probe device.

FIG. 9 is a schematic diagram of the storage of the location server in the human flow analysis system of the present invention. The storage format of the positioning server is that each line of data represents the ID of the device to be located, the MAC address of the device to be located, the device name of the device to be located, the X coordinate of the device to be located, the Y coordinate of the device to be located, and the report time.

It can be seen from the above description that using the people flow analysis method, storage medium and processor according to the present invention, the people flow data can be obtained by collecting the MAC of pedestrians' handheld electronic devices in the AP coverage area, and performing statistics, summarization and classification on the MAC information. , and then further mining this data, you can get the number of people entering and leaving in different time periods, the time of people staying, and can predict the changes in the flow of people in a period of time in the future, and realize the functions of statistics and prediction of the flow of people, and effectively prevent /Resolve the occurrence of potential events that endanger public safety. It can be generally applied to the statistics of passenger flow in public places such as shopping malls, supermarkets, scenic spots, stations, airports, etc., to predict the flow of people in the future; it can also be extended to conduct deeper analysis on the data of people flow, and then get potential customers. Lists, personnel attribute classification, etc.; not only can be used in civilian scenarios, but also in police systems.

The embodiments of the present invention have been introduced in detail above, and specific examples are used to illustrate the principles and implementations of the present invention. The descriptions of the above embodiments are only used to help understand the methods and core ideas of the present invention; at the same time, for Those skilled in the art, according to the idea of the present invention, will have changes in the specific embodiments and application scope. In conclusion, the contents of this specification should not be construed as limiting the present invention.

Claims (11)

1. a human flow analysis method, is characterized in that, comprises: Read the positioning information data within the specified time range from the server; Statistical analysis of the read positioning information data; According to the results of statistical analysis, the changes in the flow of people in the future period of time are predicted. 2 . The human flow analysis method according to claim 1 , wherein before reading the positioning information data within a specified time range from the server, the method further comprises: generating the positioning information data. 3 . 3. The human flow analysis method according to claim 1, wherein performing statistical analysis on the read positioning information data comprises: collecting the read positioning information data to obtain the total number of MACs within a specified time range. 4 . The method for analyzing the flow of people according to claim 1 , wherein the positioning information data includes position information and time information corresponding to the position information. 5 . 5. The method for analyzing the flow of people according to claim 1, wherein predicting the change of the flow of people in a period of time in the future comprises: according to the result of statistical analysis of the read positioning information data, a period of time in the future is analyzed. Predict the changes in the flow of people within the system and output the prediction results. 6 . The method for analyzing the flow of people according to claim 2 , wherein generating the positioning information data comprises: collecting the MAC of the user's handheld electronic device within the coverage area of the AP. 7 . 7 . The human flow analysis method according to claim 3 , further comprising: screening for MAC. 8 . 8 . The human flow analysis method according to claim 4 , wherein the location information is latitude and longitude coordinates or pixel coordinates or an area number. 9 . 9 . The human flow analysis method according to claim 7 , wherein after the MAC screening is performed, the method further comprises: outputting the total number of MACs after screening. 10 . 10 . A storage medium, wherein the storage medium comprises a stored program, wherein when the program runs, the method for analyzing the flow of people according to any one of claims 1 to 9 is executed. 11 . 11 . A processor, wherein the processor is configured to run a program, wherein when the program runs, the method for analyzing the flow of people according to any one of claims 1 to 9 is executed.

Images