CN114897433A - Campus personnel flow monitoring and early warning method based on big data - Google Patents

Abstract

The invention relates to the technical field of personnel flow monitoring, and discloses a campus personnel flow monitoring and early warning method based on big data; the different areas of the park are subjected to modular processing, so that differentiated monitoring and early warning of the park can be realized, the different areas can be subjected to targeted regulation and control, the monitoring effects of the different areas can be effectively improved, each data collected and counted can be standardized and normalized, each processed data can be calculated and analyzed, whether the flow states of personnel in the different divided areas are normal or not can be obtained, and the overall effect of flow monitoring and early warning of the personnel in the park can be effectively improved; the invention can solve the technical problems of low accuracy of monitoring and early warning of the flowing of the personnel in the park and fuzzy early warning results in the existing scheme.

Description

Monitoring and early warning method of people flow in the park based on big data

technical field

The invention relates to the technical field of personnel flow monitoring, in particular to a park personnel flow monitoring and early warning method based on big data.

Background technique

A park refers to an area designated by a unified plan, in which enterprises and companies of a specific industry and form are specially set up for unified management, such as industrial parks, free trade parks, industrial parks, and animation parks.

When the existing park personnel flow monitoring and early warning scheme is implemented, it is only based on sensors or surveillance video to monitor and warn the personnel movement in the park. At the same time, it is impossible to determine the cause of the abnormal state, so that the staff cannot do a good job of accurate and targeted processing, resulting in the poor overall effect of the monitoring and early warning of the flow of people in the park.

SUMMARY OF THE INVENTION

The present invention provides a large data-based monitoring and early warning method and system for the flow of people in the park.

In order to achieve the above purpose, the big data-based park personnel flow monitoring and early warning method provided by the present invention includes:

According to the names of different areas in the park and their corresponding footprints, all areas are modularized to obtain an area division set containing several divided areas;

According to the preset monitoring time period, monitor and count the number of personnel in different divided areas of the regional division set, and obtain a regional monitoring set including personnel monitoring data corresponding to several divided areas;

Extracting features and defining markers for a number of personnel monitoring data in the regional monitoring set to obtain a regional processing set containing several monitoring processing data;

Analyze and evaluate several monitoring and processing data in the regional processing set in turn, determine whether the personnel flow status of the corresponding divided areas meets the monitoring standards, and obtain a regional evaluation set containing several qualified personnel flow status and unqualified personnel flow status;

If there is a divided area that does not meet the monitoring standards in the regional evaluation set, set the divided area as the selected area, adjust the monitoring time period to verify the flow status of people in the selected area, and obtain a verification verification set;

According to the verification results in the verification verification set, it can adaptively warn and prompt the flow of people in the selected area, and take corresponding measures to evacuate or limit the flow.

Preferably, all areas are modularized according to the names of different areas in the park and their corresponding footprints, including:

Obtain the names of different areas in the park, match the obtained area names with the pre-built area name table to obtain the corresponding area weight value and set it as the first division value;

Obtain the area area corresponding to different area names in the park, extract the value of the area area and set it as the second division value;

Obtain the result of the product of the first division value and the second division value and set it as the division standard value, and set the area corresponding to the division standard value as the division area;

According to the size of the division standard value, the corresponding division areas are arranged in descending order to obtain the area division set.

Preferably, feature extraction and definition marks are performed on several pieces of personnel monitoring data in the regional monitoring set, including:

According to the size of the division standard value, the corresponding division area numbers are marked as i, i∈{1, 2, 3, ..., n}, where n is a positive integer, which is expressed as the total number;

Obtain the total number of people, the number of people entering and the number of people leaving in the people monitoring data;

The total number of people, the number of people entering and the number of people leaving in each divided area are valued and marked as RZi, JRi and LRi;

The marked data items are arranged and combined in order to obtain monitoring and processing data corresponding to each divided area; several monitoring and processing data constitute a regional processing set.

Preferably, several monitoring and processing data in the regional processing set are sequentially analyzed and evaluated, including:

Obtain the total number RZi of persons marked with values in the monitoring and processing data corresponding to each divided area;

Mark the division standard value corresponding to each division area as HBi;

The total number of marked personnel RZi corresponding to each division area and the division standard value HBi are combined, and the estimated RG of people in each division area is obtained by formula calculation; the formula is:

RG=HBi×(RZi-RZi0)

In the formula, RZi0 is the total number of standard personnel corresponding to each divided area;

Obtain the human estimation threshold corresponding to each division area according to the division standard value, determine that the personnel flow status of the divided area corresponding to the person estimation less than the person estimation threshold is qualified, and generate the first person estimation signal; The personnel flow status of the divided area corresponding to the value is unqualified and a second person estimation signal is generated;

The qualified personnel flow state corresponding to several divided areas and the corresponding first person estimation signal, and the unqualified personnel flow status and the corresponding second person estimation signal constitute the area assessment set.

Preferably, the monitoring time period is adjusted to verify the flow of personnel in the selected area, including:

According to the second-person evaluation signal in the regional evaluation set, the monitoring duration of the monitoring time period is shortened, the adjusted monitoring time period is set as the verification time period, and the subsequent m verification time periods are used to verify and analyze the selected area; m is a positive integer;

If the regional evaluation set of the subsequent m verification time periods contains m second human evaluation signals, it is determined that there is continuous crowding in the selected area, and a first early warning signal is generated, and the corresponding selected area is set according to the first early warning signal. For the target area, analyze and evaluate the entry and exit states of the target area to obtain an entry and exit evaluation set;

If the regional evaluation set of the subsequent m verification time periods contains k second human evaluation signals, it is determined that there is intermittent crowding in the selected area, and a second early warning signal is generated, and the corresponding selected area is set according to the second early warning signal. is the observation area; k is a positive integer less than m;

If the regional evaluation set of the subsequent m verification time periods contains 0 second-person evaluation signals, it is determined that there is a short-term crowding in the selected area, and a third early warning signal is generated;

The first early warning signal and the target area, the second early warning signal and the observation area, the third early warning signal and the entry and exit evaluation set constitute the verification validation set.

Preferably, analyzing and evaluating the entering state and leaving state of the target area, including:

Obtain the total number of people, the number of people entering and the number of people leaving in the personnel monitoring data corresponding to the target area, and the total number of people RZi, the number of people entering JRi and the number of people leaving LRi in each divided area are combined, and the target area is obtained by formula calculation. The in and out evaluation value JCP of ; the formula is:

JCP=HBi×(a1×JRi/RZi+a2×LRi/RZi)

In the formula, a1 and a2 are different proportional coefficients that are both greater than zero, and a1<a2;

Obtain the entry and exit evaluation thresholds corresponding to each target area according to the division standard value;

If the entry and exit evaluation value is less than the entry and exit evaluation threshold value, determine that the entry state of the target area is abnormal and generate a first evaluation signal;

If the entry and exit evaluation value is not less than the entry and exit evaluation threshold value and is not greater than p% of the entry and exit evaluation threshold value, and p is a real number greater than one hundred, it is determined that the exit state of the target area is abnormal and a second evaluation signal is generated;

If the entry and exit evaluation value is greater than p% of the entry and exit evaluation threshold, it is determined that both the entry state and the exit state of the target area are abnormal and a third evaluation signal is generated;

The first evaluation signal, the second evaluation signal, and the third evaluation signal constitute an incoming and outgoing evaluation set.

Preferably, according to the verification results in the verification verification set, the early warning and prompting of the flow of people in the selected area are adaptively performed, including:

According to the different early warning signals in the verification set, the related early warnings and prompts are carried out, and at the same time, according to the different evaluation signals in the entry and exit evaluation set, the entry personnel are adaptively restricted and the exit personnel are regulated to leave quickly.

Compared with the existing scheme, the beneficial effects that the present invention can achieve are:

The present invention can realize differentiated monitoring and early warning of the park by performing modular processing on different areas of the park, so that different areas can be regulated in a targeted manner, and the monitoring effect of different areas can be effectively improved. The processing of each data can standardize and standardize the data. By calculating and analyzing the processed data, it is possible to obtain whether the flow of people in different areas is normal, which can effectively improve the overall effect of monitoring and early warning of the flow of people in the park. .

By analyzing and classifying the flow status of people in different divided areas, the present invention can accurately and efficiently analyze the abnormal flow status of people, and can determine whether the entry status and exit status of the target area are normal, so that the staff can accurately and efficiently For maintenance, compared with the fuzzy early warning prompt based on a single number of people in the existing solution, the embodiment of the present invention can realize more accurate and efficient early warning and regulation.

Description of drawings

FIG. 1 is a schematic flowchart of a method for monitoring and early warning of people flow in a park based on big data according to an embodiment of the present invention.

The object realization, functional features and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with the embodiments.

Detailed ways

The technical solutions of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all 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.

The terminology used herein is used to describe the embodiments and is not intended to limit and/or limit the present disclosure; it should be noted that the singular forms "a", "an" and "the" also include "a", "an" and "the" unless the context clearly dictates otherwise. plural; also, although the terms "first," "second," etc. may be used herein to describe various elements, the elements are not limited by these terms, which are only used to distinguish one element from another.

Referring to FIG. 1 , it is a schematic flowchart of a method for monitoring and early warning of people flow in a park based on big data provided by an embodiment of the present invention.

The big data-based monitoring and early warning method for the flow of people in the park, the specific steps include:

S1: Modularize all areas according to the names of different areas in the park and their corresponding footprints, and obtain an area division set containing several divided areas; including:

Obtain the names of different areas in the park, match the obtained area names with the pre-built area name table to obtain the corresponding area weight value and set it as the first division value;

Among them, the area name table consists of several area names and their corresponding area weight values. Different area names are preset with a corresponding area weight value. The specific value of the area weight value can be determined according to the location of the area or the big data corresponding to the function. make settings;

Obtain the area area corresponding to different area names in the park, extract the value of area area and set it as the second division value; The area of the area can also be obtained based on the big data of the park;

Obtain the result of the product of the first division value and the second division value and set it as the division standard value, and set the area corresponding to the division standard value as the division area;

According to the size of the division standard value, the corresponding division areas are arranged in descending order to obtain the area division set.

It should be noted that the purpose of modularizing different areas of the park is to achieve differentiated monitoring and early warning of the park, so that different areas can be regulated in a targeted manner, and the monitoring effect of different areas can be effectively improved. The purpose of the weight value is to achieve a digital representation of regions with different weights.

S2: according to the preset monitoring time period, monitor and count the number of personnel in different divided areas in the area division set, and obtain a regional monitoring set including personnel monitoring data corresponding to several divided areas;

In the implementation of the present invention, the number of people in the divided area can be monitored and counted through the counter and the monitoring device, the monitoring device is used to obtain the video of the movement of the people in the divided area, and the number of people entering and the direction of the movement of the people in the video can be determined. The number of people leaving; the preset monitoring time period can be 60 seconds;

Among them, the divided area can be a rectangle, and one direction is set as the entry direction, and the reverse direction is the exit direction. When the person leaves the divided area, the corresponding number of people entering and leaving the area is added by one, and the direction of movement of the person is the direction of departure. However, when it is still in the divided area, it is not counted.

S3: Perform feature extraction and definition marking on several personnel monitoring data in the regional monitoring set to obtain a regional processing set containing several monitoring processing data, including:

According to the size of the division standard value, the corresponding division area numbers are marked as i, i∈{1, 2, 3, ..., n}, where n is a positive integer, which is expressed as the total number;

Obtain the total number of people, the number of people entering and the number of people leaving in the people monitoring data;

The total number of people, the number of people entering and the number of people leaving in each divided area are valued and marked as RZi, JRi and LRi;

Arrange and combine the marked data items in order to obtain monitoring and processing data corresponding to each divided area; several monitoring and processing data form a regional processing set;

In the embodiment of the present invention, by processing each data collected and counted, each data item can be standardized and normalized, which is beneficial for subsequent simultaneous calculation of each data item.

S4: Analyze and evaluate several monitoring and processing data in the regional processing set in turn, determine whether the personnel flow status of the corresponding divided areas meets the monitoring standards, and obtain a regional evaluation set including several qualified personnel flow status and unqualified personnel flow status. ;include:

Obtain the total number RZi of persons marked with values in the monitoring and processing data corresponding to each divided area;

Mark the division standard value corresponding to each division area as HBi;

The total number of marked personnel RZi corresponding to each division area and the division standard value HBi are combined, and the estimated RG of people in each division area is obtained by formula calculation; the formula is:

RG=HBi×(RZi-RZi0)

In the formula, RZi0 is the total number of standard personnel corresponding to each divided area;

It should be noted that the people valuation is a value used to combine the total number of people in different divided areas with the division standard value to evaluate the overall flow of personnel; according to the division standard value, the flow of people corresponding to the divided areas can be obtained. Status monitoring standards, through the analysis of people's valuation, it can be obtained whether the flow status of people in different areas is normal, and the abnormal flow status of people in different areas needs to be further analyzed and confirmed.

Obtain the human estimation threshold corresponding to each divided area according to the dividing standard value, determine that the personnel flow status of the divided area corresponding to the person estimated smaller than the human estimation threshold is qualified, and generate the first person estimation signal;

At the same time, it is determined that the personnel flow status of the divided area corresponding to the person estimation not less than the person estimation threshold is unqualified, and a second person estimation signal is generated;

The qualified personnel flow state corresponding to several divided areas and the corresponding first person estimation signal, and the unqualified personnel flow status and the corresponding second person estimation signal constitute the area assessment set.

In the embodiment of the present invention, by analyzing and classifying the flow status of people in different divided areas, it is possible to accurately and efficiently regulate the divided areas corresponding to abnormal flow status of people, which can effectively improve the overall effect of monitoring and early warning of people flow in the park.

S5: If there is a divided area that does not meet the monitoring standards in the regional assessment set, set the divided area as the selected area, adjust the monitoring time period to verify the flow of personnel in the selected area, and obtain a verification verification set; including:

According to the second-person evaluation signal in the regional evaluation set, shorten the monitoring period of the monitoring period, set the adjusted monitoring period as the verification period, and the verification period can be 30 seconds. The selected area is checked and analyzed; m is a positive integer, which can be 5;

If the regional evaluation set of the subsequent m verification time periods contains m second human evaluation signals, it is determined that there is continuous crowding in the selected area, and a first early warning signal is generated, and the corresponding selected area is set according to the first early warning signal. for the target area;

Among them, continuous crowding means that the overall movement speed of people is low;

Analyze and evaluate the entry and exit states of the target area to obtain an entry and exit evaluation set, including:

Obtain the total number of people, the number of people entering and the number of people leaving in the personnel monitoring data corresponding to the target area, and the total number of people RZi, the number of people entering JRi and the number of people leaving LRi in each divided area are combined, and the target area is obtained by formula calculation. The in and out evaluation value JCP of ; the formula is:

JCP=HBi×(a1×JRi/RZi+a2×LRi/RZi)

In the formula, a1 and a2 are different proportional coefficients that are all greater than zero, and a1<a2, a1 can take a value of 0.635, a2 can take a value of 3.254; the differential representation between a2 and a1 can make the corresponding data The weights of the items are different, so that the corresponding data items can be accurately analyzed and evaluated differently.

It should be noted that the entry and exit evaluation value is a numerical value used to synthesize each data item in the target area to evaluate its entry and exit state as a whole; based on the entry and exit evaluation value, it can be determined whether the entry state and exit state of the target area are normal, In order for the staff to perform maintenance accurately and efficiently, compared with the fuzzy early warning prompt based on a single number of people in the existing solution, the embodiment of the present invention can realize more accurate and efficient early warning and prompt.

Obtain the entry and exit evaluation thresholds corresponding to each target area according to the division standard value;

If the entry and exit evaluation value is less than the entry and exit evaluation threshold value, determine that the entry state of the target area is abnormal and generate a first evaluation signal;

If the entry and exit evaluation value is not less than the entry and exit evaluation threshold and is not greater than p% of the entry and exit evaluation threshold, and p is a real number greater than one hundred, and can be 150, it is determined that the exit state of the target area is abnormal and a second evaluation signal is generated;

If the entry and exit evaluation value is greater than p% of the entry and exit evaluation threshold, it is determined that both the entry state and the exit state of the target area are abnormal and a third evaluation signal is generated;

The first evaluation signal, the second evaluation signal, and the third evaluation signal constitute an entry and exit evaluation set;

If the regional evaluation set of the subsequent m verification time periods contains k second human evaluation signals, it is determined that there is intermittent crowding in the selected area, and a second early warning signal is generated, and the corresponding selected area is set according to the second early warning signal. is the observation area; k is a positive integer less than m, which can be 3;

Among them, the intermittent crowding refers to the intermittent occurrence of crowding for a while and not crowding for a while;

If the regional evaluation set of the subsequent m verification time periods contains 0 second-person evaluation signals, it is determined that there is a short-term crowding in the selected area, and a third early warning signal is generated;

Among them, short-term crowding means that there is only one crowding;

The first early warning signal and the target area, the second early warning signal and the observation area, the third early warning signal and the entry and exit evaluation set constitute the verification validation set.

In the embodiment of the present invention, the purpose of verifying the abnormal state of the divided areas is to improve the accuracy of the monitoring and analysis results, and at the same time, the monitoring time period is adaptively shortened so that the verification can be performed more efficiently, and it is judged that the congestion of the corresponding divided areas is in the Which state can eliminate the defect in the existing scheme that the error in the single monitoring result affects the overall early warning effect.

S6: According to the centralized verification results of verification verification, it will adaptively give early warning and prompt to the flow of people in the selected area, and take corresponding measures to evacuate or limit the flow, including:

According to the different early warning signals in the verification set, the related early warnings and prompts are carried out, and at the same time, according to the different evaluation signals in the entry and exit evaluation set, the entry personnel are adaptively restricted and the exit personnel are regulated to leave quickly.

In the embodiment of the present invention, by analyzing and verifying the specific abnormal state of the target area, staff can be arranged to deal with it accurately and efficiently, so that the target area in the abnormal state can be solved in a timely and effective manner. By controlling the number of people, the embodiment of the present invention can achieve a better processing effect of personnel flow monitoring and early warning.

In the description of this specification, description with reference to the terms "one embodiment," "example," "specific example," etc. means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one aspect of the present invention. in one embodiment or example. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

The above content is only an example and description of the structure of the present invention, and those skilled in the art can make various modifications or supplements to the specific embodiments described or replace them in similar ways, as long as they do not deviate from the structure of the invention or Anything beyond the scope defined by the claims shall belong to the protection scope of the present invention.

Claims (8)

1. The park personnel flow monitoring and early warning method based on big data is characterized in that, comprising: According to the names of different areas in the park and their corresponding footprints, all areas are modularized to obtain an area division set containing several divided areas; According to the preset monitoring time period, monitor and count the number of personnel in different divided areas of the regional division set, and obtain a regional monitoring set including personnel monitoring data corresponding to several divided areas; Extracting features and defining markers for a number of personnel monitoring data in the regional monitoring set to obtain a regional processing set containing several monitoring processing data; Analyze and evaluate several monitoring and processing data in the regional processing set in turn, determine whether the personnel flow status of the corresponding divided areas meets the monitoring standards, and obtain a regional evaluation set containing several qualified personnel flow status and unqualified personnel flow status; If there is a divided area that does not meet the monitoring standards in the regional evaluation set, set the divided area as the selected area, adjust the monitoring time period to verify the flow status of people in the selected area, and obtain a verification verification set; According to the verification results in the verification verification set, it can adaptively warn and prompt the flow of people in the selected area, and take corresponding measures to evacuate or limit the flow. 2. The large-data-based park personnel flow monitoring and early warning method as claimed in claim 1, characterized in that, according to the names of different areas in the park and their corresponding footprints, all areas are modularized, including: Get the names of different areas in the park and their corresponding area weights; Obtain the area area corresponding to different area names in the park; Multiply the area weight value and the area footprint to obtain the division standard value of the area, and set the area corresponding to the division standard value as the division area; According to the size of the division standard value, the corresponding division areas are arranged in descending order to obtain the area division set. 3. The large-data-based park personnel flow monitoring and early warning method according to claim 1, characterized in that, feature extraction and definition marks are performed on several personnel monitoring data in the regional monitoring set, including: Mark the corresponding number of divided areas according to the size of the division standard value; Obtain the total number of people, the number of people entering and the number of people leaving in the personnel monitoring data, and take values and define markers; The marked data items are arranged and combined in order to obtain monitoring and processing data corresponding to each divided area; several monitoring and processing data constitute a regional processing set. 4. The large-data-based monitoring and early-warning method for the flow of people in the park according to claim 1, characterized in that, successively analyzing and evaluating several monitoring and processing data in the regional processing concentration, including: The total number of people marked corresponding to each division area and the division standard value are simultaneously obtained to obtain the estimates of people in each division area; Obtain the human estimation threshold corresponding to each division area according to the division standard value, determine that the personnel flow status of the divided area corresponding to the person estimation less than the person estimation threshold is qualified, and generate the first person estimation signal; The personnel flow status of the divided area corresponding to the value is unqualified and a second person estimation signal is generated; The qualified personnel flow state corresponding to several divided areas and the corresponding first person estimation signal, and the unqualified personnel flow status and the corresponding second person estimation signal constitute the area assessment set. 5. The large-data-based park personnel flow monitoring and early warning method according to claim 1, wherein adjusting the monitoring time period to verify the personnel flow state of the selected area, comprising: According to the second-person evaluation signal in the regional evaluation set, the monitoring duration of the monitoring time period is shortened, the adjusted monitoring time period is set as the verification time period, and the subsequent m verification time periods are used to verify and analyze the selected area; m is a positive integer; If the regional evaluation set of the subsequent m verification time periods contains m second human evaluation signals, a first early warning signal is generated, and the corresponding selected area is set as the target area according to the first early warning signal, and the entry status of the target area is determined. Analyze and evaluate with the leaving state, and get the entry and exit evaluation set; If the regional evaluation set of the subsequent m verification time periods contains k second human evaluation signals, a second early warning signal is generated, and the corresponding selected area is set as the observation area according to the second early warning signal; k is a positive value less than m integer; If the regional evaluation set of the subsequent m verification time periods contains 0 second-person evaluation signals, a third early warning signal is generated; The first early warning signal and the target area, the second early warning signal and the observation area, the third early warning signal and the entry and exit evaluation set constitute the verification validation set. 6. The large-data-based park personnel flow monitoring and early warning method according to claim 5, wherein the analysis and evaluation are performed on the entry state and the exit state of the target area, including: Obtain the total number of people, the number of people entering and the number of people leaving in the personnel monitoring data corresponding to the target area, and the total number of people, the number of people entering and the number of people leaving the target area will be simultaneously obtained in each divided area. The entry and exit evaluation thresholds corresponding to each target area are obtained according to the division standard values, and are matched and analyzed with the entry and exit evaluation values to obtain an entry and exit evaluation set including the first evaluation signal, the second evaluation signal, and the third evaluation signal. 7. The park personnel flow monitoring and early warning method based on big data as claimed in claim 6, wherein if the entry and exit evaluation value is less than the entry and exit evaluation threshold, it is determined that the entry state of the target area is abnormal and the first evaluation signal is generated; If the entry and exit evaluation value is not less than the entry and exit evaluation threshold value and is not greater than p% of the entry and exit evaluation threshold value, and p is a real number greater than one hundred, it is determined that the exit state of the target area is abnormal and a second evaluation signal is generated; If the entry and exit evaluation value is greater than p% of the entry and exit evaluation threshold, it is determined that both the entry state and the exit state of the target area are abnormal and a third evaluation signal is generated. 8. The large-data-based park personnel flow monitoring and early warning method according to claim 1, characterized in that, according to the centralized verification result of verification and verification, self-adaptive early warning and prompting are carried out to the personnel flow in the selected area, comprising: According to the different early warning signals in the verification set, the related early warnings and prompts are carried out, and at the same time, according to the different evaluation signals in the entry and exit evaluation set, the entry personnel are adaptively restricted and the exit personnel are regulated to leave quickly.

Images