A smart store management method and system based on big data

Abstract

The present invention belongs to the field of intelligent monitoring technology and provides an intelligent store management method and system based on big data. The method obtains monitoring videos outside the store through cameras, obtains behavioral information of each mobile target in the video, identifies and analyzes the behavioral characteristics of the mobile targets based on the behavioral information, and intelligently controls the working status of the store based on the identification and analysis results, which can significantly improve the intelligent management effect of the store. At the same time, by identifying and analyzing the behavioral characteristics of the mobile targets, it can achieve accurate prediction of the behavior of targets outside the store, making up for the current singleness of intelligent store management that is only aimed at the inside of the store.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent monitoring technology, and specifically relates to an intelligent store management method and system based on big data. Background Art

[0002] Smart stores are a retail model that leverages advanced technology and digital tools to improve retail operational efficiency, optimize user experience, and enhance market competitiveness. Integrated online and offline operations, including unmanned vending machines, are examples of smart store operations. To facilitate customer access, these smart stores typically install a sensor system outside the store. This sensor system features a sensor detector that emits an infrared or microwave signal. When this signal is reflected by an approaching object, an echo signal is received at the detector's receiving end. This echo signal controls the automatic opening and closing of the sensor door. However, current automatic sensor doors on the market are not intelligent enough. When the sensor detector detects a moving object approaching within a preset distance, the door opens automatically, but the timing of the door opening cannot be controlled based on specific circumstances. Furthermore, current designs for contactless shopping systems for multiple people typically focus on tracking in-store items and analyzing customer behavior to improve safety and reduce operational risks. However, these systems lack the ability to identify and analyze customer behavior outside the store, resulting in an inability to accurately understand customer activity outside the store and predict customer behavior in advance. Summary of the Invention

[0003] The purpose of the present invention is to propose an intelligent store management method and system based on big data to solve one or more technical problems existing in the prior art and at least provide a beneficial option or create conditions.

[0004] To achieve the above objectives, according to one aspect of the present invention, a smart store management method based on big data is provided, wherein the smart store management method based on big data comprises the following steps:

[0005] S100, obtaining behavior information of a moving target in a surveillance video outside the store;

[0006] S200, calculating the fuzzy coefficient of the moving target based on the behavior information;

[0007] S300, marking fuzzy information in the behavior information according to the fuzzy coefficient;

[0008] S400, calculating the mobile target's store entry intention based on the fuzzy information;

[0009] S500: Correcting the number of people entering the store based on the store entry intention;

[0010] Furthermore, the store is an unmanned store.

[0011] Furthermore, in S100, a high-definition camera is used to capture a video of the monitored area.

[0012] Furthermore, the high-definition camera adopts a binocular camera.

[0013] Furthermore, the monitoring area is a square or supermarket around the monitoring store.

[0014] Currently, the access control management system of smart stores adopts the smart home system, which detects whether there are objects approaching within the range by installing infrared or microwave sensors on the doors. However, the above system is prone to misidentification, that is, as long as there is any movement of an object within the detection range, the sensor door will open. Especially in hot weather, the sensor door will open frequently, causing air conditioning to leak out, causing unnecessary losses to the store. Moreover, when the camera captures the target, it not only shows the real-time image of a single time, but more often shows the scene over a period of time. When the objects in the scene move, the image of the scene must show the complete combination of all positions of those objects within the exposure time (depending on the shutter speed) and the camera's perspective. In such a picture, any object moving in the direction relative to the camera will appear blurred or shaken. Researchers call this phenomenon motion blur.

[0015] At present, in order to eliminate the problem of motion blur, the movement parameters of the camera and the captured target (movement parameters include movement speed and movement direction) are usually kept consistent to eliminate the relative movement error between the camera and the captured target to eliminate the motion blur phenomenon in the video. However, when facing the capture of multiple targets, there will be a short period of parameter inconsistency, resulting in all objects experiencing motion blur in a short period of time, which introduces a lot of interference to the subsequent behavior recognition work of a single target; or the part of the image that produces motion blur is corrected by extracting the pixel value where the motion blur occurs and correcting the surrounding pixel values. However, the above methods cannot be applied to target capture in complex background environments. In order to solve the above problems, the present invention provides the following method to quickly eliminate motion blur interference in complex environments by calculating the intention to enter the store:

[0016] Furthermore, in S100, the method for obtaining the behavior information of the mobile target in the surveillance video outside the store is as follows: a plurality of mobile targets are marked in the video captured by the high-definition camera installed outside the store to form a monitoring target set MOT, and i is used as the serial number of the mobile target, mot i is the i-th moving target;

[0017] The video processing software Tracker is used to extract the speed and trajectory of the moving target, and the speed of all moving targets is formed into a speed set SPD, spd iThe speed of the i-th moving target is calculated, and the distance between the moving target and the geometric center of the area occupied by the store is calculated. The distances between all moving targets and the geometric center of the area occupied by the store form a distance set DST, dst i is the distance between the i-th moving target and the geometric center of the area occupied by the store. The speed set SPD and the distance set DST together constitute the behavior information of the moving target.

[0018] Furthermore, any one of the frame difference method, background subtraction method, YOLO algorithm, and SSD algorithm is used to mark the moving target.

[0019] Furthermore, in S200, the method for calculating the fuzzy coefficient of the moving target based on the behavior information is:

[0020] In the speed set, the speed of all moving targets is decomposed as follows:

[0021] The direction from the target to the geometric center of the store area is the horizontal direction, and the direction perpendicular to the geometric center of the store area is the vertical direction. The projection of the velocity in the horizontal direction is spd_xi, and the projection of the velocity in the vertical direction is spd_yi.

[0022] Set the projection coefficient to m, and set its initial value to 1, calculate the difference between spd_xi and spd_yi, and modify the projection coefficient m based on the difference result;

[0023] Furthermore, the specific method of modifying the projection coefficient m according to the difference result is:

[0024] If the difference between spd_xi and spd_yi is less than or equal to zero, then the value of m is modified to 0, otherwise the value of m is not modified;

[0025] The video is divided into multiple video images according to the preset time t, and the distance between the moving target and the geometric center of the store area is obtained at the same time. The distance of all moving targets and the corresponding acquisition time are plotted to generate a distance change curve XL, where the distance change curve XL is a curve composed of time and distance. The point on the XL curve is called the distance point dip, and k is the serial number of the acquisition time. k For T k The distance between the first target obtained at the moment and the geometric center of the area occupied by the store, where T k Indicates the kth acquisition time;

[0026] Set the distance coefficient to x and set its initial value to 1. Calculate the sum of the derivatives at all distance points on the curve XL and modify the distance coefficient x based on the calculation result.

[0027] Furthermore, the specific method of modifying the distance coefficient x according to the calculation result is:

[0028] If the sum of the derivatives at all distance points on the curve XL is less than zero, then the value of x is modified to 0, otherwise the value of x is not modified;

[0029] Use the same method to obtain the speed of the moving target, and plot all the speeds of the moving target against the acquisition time to generate a speed change curve VL. The points on the curve VL are recorded as speed points rat, and k is the serial number of the acquisition time. k For T k The speed of the moving target obtained at all times;

[0030] Set the velocity coefficient to v, and set its initial value to 1. Calculate the sum of the derivatives at all velocity points on the curve VL, and modify the velocity coefficient v based on the calculation result.

[0031] Furthermore, the specific method of modifying the speed coefficient v according to the calculation result is:

[0032] If the sum of the derivatives at all velocity points on the curve VL is less than zero, the v value is modified to 0, otherwise the v value is not modified;

[0033] The fuzzy coefficient of the moving target is calculated according to the formula m+x+v.

[0034] Furthermore, in S300, the specific method of marking fuzzy information in behavior information according to the fuzzy coefficient is: all moving targets with fuzzy coefficients equal to zero are recorded as relevant targets, all video images containing relevant targets constitute a behavior set, and the behavior information of the relevant targets is recorded as fuzzy information.

[0035] Furthermore, in S400, the specific method for calculating the mobile target's store-entry intention based on the deblurred information is as follows:

[0036] Record the speed rat and distance dip of the relevant target collected at the latest moment on curves VL and XL, and convert the speed and distance according to the formula P=Ln( ) calculates the store entry intention of the current relevant target, where the Ln() function is a logarithmic function with the natural constant e as the base, where a represents the speed parameter of the relevant target in the acquired video, according to the formula a= , where rum represents the number of images with a speed greater than the average speed in the behavior set, Nnum represents the total number of images in the behavior set; b represents the distance parameter of the relevant target in the acquired video, according to the formula b= , where dum represents the number of images in the behavior set that are smaller than the average distance.

[0037] The current causes of motion blur include: (1) when the shutter speed is insufficient, the target moves during the exposure period, resulting in pixel displacement; (2) multiple targets move at different speeds and directions, and the blur pattern becomes complicated (such as crowds and traffic monitoring scenes). Traditional deblurring algorithms are difficult to confirm the blur kernels of multiple blurred targets. The existing method is to use an algorithm to mark the targets and then estimate the blur kernel of each target. However, it is impossible to complete the deblurring work of multiple targets in a complex environment, resulting in poor quality of the captured target trajectory. The above method uses the Ln logarithmic function to use the scaling principle of the function to quickly eliminate the movement of a single target during the exposure period when capturing the target. At the same time, the linear fitting method eliminates the phenomenon of temporary disappearance when the camera obtains the movement parameters when multiple moving targets have partial repetition in the path. It can quickly correct the target's movement trajectory in a short time without the help of an anti-shake hardware module, which significantly improves the practicality of real-time target analysis.

[0038] However, the above method only draws trajectories based on separate speed and distance as parameters, and does not take into account the influence of the interaction force on the trajectory, whether it is a single individual or multiple groups, or between individuals and groups, that is, the group attraction effect. Moreover, the attraction of different groups to individuals is greater than the attraction of a single group multiple times, that is, individuals will produce a replication effect in multiple groups. See reference: Cluster Coding and Replication Effect of Group Attraction; However, the above method obviously fails to take into account the group attraction effect and replication effect. In practical applications, if the group attraction effect and replication effect are not taken into account, the captured trajectory will show a missing phenomenon, that is, the trajectory obtained at this time has a slight difference from the actual trajectory. In order to eliminate the interference of the group attraction effect and replication effect on behavioral information, the present invention proposes the following preferred solution to calculate store entry intention:

[0039] In the video, the crowd density calculation algorithm is used to mark multiple groups of people to form a set GP, and let j be the sequence number of the group, gp j Denotes the jth group of people. In the monitoring target set MOT, the curve ATY consisting of the trajectory of each moving target is obtained in turn. The curve ATY is a curve consisting of the modulus of the time and velocity vector. The velocity vector of the moving target is obtained as the target vector according to the preset period t. At the same time, the velocity vectors of all groups of people are obtained as the influence vector to form the influence set;

[0040] Furthermore, the crowd density calculation algorithm is any one of the models including MCNN, CrowdNet, Slicing CNN, and ConvLSTM.

[0041] Traverse all velocity vectors on the curve ATY. If the velocity vector modulus at the current moment is smaller than the velocity vector modulus at the previous moment and also smaller than the velocity vector modulus at the next moment, or if the velocity vector modulus at the current moment is larger than the velocity vector modulus at the previous moment and also larger than the velocity vector modulus at the next moment, then mark the velocity vector at this moment as an affected vector. In the influence set, subtract all affected vectors from the influence vector in turn to calculate the magnitude of the resulting vector modulus. Record the crowd corresponding to the influence vector with the largest modulus as the main influence group. Calculate the distance between the geometric center of the main influence group and the current moving target as the reference moment at the current time point. Calculate the distance between the geometric center of all crowds and the moving target and the magnitude of the reference moment. If it is larger than the reference moment, then record the current crowd as a weak influence group, otherwise it is recorded as a strong influence group.

[0042] Traverse all marked crowds in turn. If it is a strong influence group, subtract the velocity vector of the moving target at the current moment from the influence vector corresponding to the crowd, and then record the projection of the operation result in the vertical direction as rat_h. If it is a weak influence group, add the target vector of the moving target at the current moment to the influence vector corresponding to the crowd, and then record the projection of the operation result in the vertical direction as rat_h. The ratio of rat_h to the distance between the moving target and the geometric center of the area occupied by the store (the numerator of the calculated ratio is rat_h, and the denominator of the calculated ratio is the distance between the moving target and the geometric center of the area occupied by the store) is used as the local store-entry intention of the crowd towards the moving target at the current moment. According to the above method, the local store-entry intention of the crowd towards the moving target at all moments is calculated, and the sum of all local store-entry intentions is the store-entry intention of the current moving target.

[0043] The above method detects and updates the main influence group in real time, divides the remaining people into strong influence groups and weak influence groups according to the main influence group, and then calculates the influence of all people on individuals in real time, thereby avoiding the replication effect of multiple groups on individuals. By performing feature recognition on the behavioral information detected at this time, it is possible to predict the behavior more accurately in a more complex environment. At the same time, the above method corrects the mutual influence between detection targets in a complex environment, thereby eliminating the errors in parameters, and also repairs the slight differences in the movement trajectory of the target drawn according to the parameters, thereby realizing accurate and rapid analysis and identification of the target's characteristic behavior.

[0044] Although the above method can achieve real-time prediction of moving targets, it still cannot solve the problem of sensor door pinching caused by inconsistent target entry time. At present, the problem of sensor door pinching is generally faced by continuously sensing whether there is a biological signal between the doors through the infrared sensor on the sensor door. If there is, the sensor door is kept open. If not, the sensor door is controlled to close after a period of time. However, this method cannot guarantee good safety and real-time performance. If a biological signal is detected all the time, it will remain open. If the flow of people cannot be controlled during peak hours, it may cause trampling or other serious consequences. In order to solve the above problems, real-time counting of sensor doors and in-store monitoring are currently used. A method combining human flow statistics with manual order maintenance. However, in order for the induction door to achieve real-time counting, the sensor must have extremely high sensitivity. However, when an overly sensitive sensor encounters a swinging object (a swinging object refers to the same object repeatedly sensed by the sensor), glitches and missing phenomena will appear on the pulse waveform, resulting in delayed processing or erroneous processing results when the sensor receives the above abnormal pulses. These are extremely likely to interfere with the counting results, especially during peak traffic hours, which greatly increases safety hazards. To this end, the present invention solves the above problems by marking the abnormal pulse group in the pulse signal generated by the sensor to assist in monitoring and correcting the abnormal waveform that produces glitches and missing:

[0045] Furthermore, in S500, the specific method for correcting the counting of the flow of people entering the store based on the intention of entering the store is:

[0046] The pulse signal generated by the sensor is obtained at time intervals T within a preset period. The time when a valid pulse (a valid pulse refers to the pulse signal generated when the sensor receives an echo signal) is generated is recorded as TIM_1, and the time when the corresponding valid pulse disappears is recorded as TIM_2. A variable M is set with an initial value of 0. Whenever a complete set of TIM_1 and TIM_2 is detected, or whenever a complete set of pulse signals is detected, the variable M is incremented by 1. After the preset period ends, the value of the variable M is accessed as the store traffic during this period.

[0047] The acquired pulse signal is plotted as a square wave signal SL, where the square wave signal SL is a curve composed of time and pulse signal. The size of the pulse signal is compared on the curve SL starting from the second acquisition time. If the current signal size is greater than the signal size at the previous moment, the time point corresponding to the current signal is recorded as ST. On the curve SL, search backward from ST for the first point that satisfies the condition that the current signal is greater than the signal at the next moment, and the time point corresponding to the searched signal is recorded as ET. Repeat the above operation until all STs and ETs are marked. Starting from the first ST, each ST and the adjacent ET are respectively formed into a valid pulse group. The time interval between ST and ET of each valid pulse group is calculated in turn as the signal duration TIM of the group. With n as the serial number, TIM n Indicates the signal duration of the nth valid pulse group;

[0048] Traverse all TIMs in the range of n. When TIM satisfies the formula Ln(TIM n )<ε, mark the valid pulse group corresponding to the current TIM as an abnormal pulse group, where ε is any positive number, traverse all abnormal pulse groups, if it satisfies the formula Ln(TIM n )+ Ln(TIM n+1 )<ε or satisfy the formula Ln(TIM n )+ Ln(TIM n-1 )<ε, mark the current abnormal pulse group as a repeated pulse group, otherwise mark the current abnormal pulse group as a lost pulse group;

[0049] The statistical flow of people entering the store is corrected based on the abnormal pulse group. The specific method is: the flow of people entering the store is added with the number of missing pulse groups and then subtracted with the number of repeated pulse groups as the corrected flow of people entering the store.

[0050] The abnormal pulse group in the above method represents the abnormal square wave signal generated by the sensor due to the induction of the swing object. If the current pulse group signal meets Ln(TIM n )<ε, it means that multiple objects are sensed at the same time and thus mistakenly identified as one object, which generates burrs on the pulse signal. If the current pulse group signal satisfies Ln(TIM n )+ Ln(TIM n+1 )<ε or Ln(TIM n )+ Ln(TIM n-1)<ε, it means that the same object is sensed multiple times and the missing part is generated in one pulse signal. By using ε as the marking rule, the response time of the sensor when facing abnormal pulse signals can be eliminated, avoiding the limitations of the above method due to inconsistent sensor performance. It can significantly improve the practicality of the method and timely prevent trampling and other accidents caused by excessive human flow.

[0051] The present invention also provides a smart store management system based on big data, the system comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to run in the following system units:

[0052] A real-time video capture unit is used to capture surveillance videos outside the store through an outside camera;

[0053] A behavior information acquisition unit, configured to acquire behavior information of a moving target from the captured surveillance video outside the store;

[0054] A fuzzy coefficient calculation unit, configured to calculate the fuzzy coefficient of the moving target based on the acquired behavior information;

[0055] a fuzzy information marking unit, configured to mark fuzzy information in the behavior information according to the calculated fuzzy coefficient;

[0056] a store entry intention calculation unit, configured to calculate the store entry intention of the mobile target based on the fuzzy information of the mobile target;

[0057] The store entry flow counting unit is used to correct the current store entry flow according to the mobile target's store entry intention.

[0058] The beneficial effects of the present invention are as follows: the present invention provides an intelligent store management method and system based on big data, which obtains the behavioral information of mobile targets outside the store and performs behavioral feature analysis to intelligently control the store, significantly improving the intelligence of store management, while eliminating the interference of group attraction effect and replication effect on behavioral information, and can perform real-time and accurate feature analysis of mobile targets, thereby making up for the current singleness of intelligent management systems that only focus on in-store management, monitoring the flow of people in the store in real time, and avoiding the hidden danger of stampede during peak hours due to the statistical flow of people not being consistent with the actual flow due to inconsistent sensor performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 Shown is a flow chart of an intelligent store management method based on big data;

[0060] Figure 2 Shown is a structural diagram of an intelligent store management system based on big data. DETAILED DESCRIPTION

[0061] The following describes embodiments of the present invention in detail, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and are not to be construed as limiting the present invention.

[0062] Example 1: Figure 1 Shown is a flow chart of an intelligent store management method based on big data.

[0063] Reference Figure 1 The present invention proposes a smart store management method based on big data, which includes the following steps:

[0064] S100, obtaining behavior information of a moving target in a surveillance video outside the store;

[0065] S200, calculating the fuzzy coefficient of the moving target based on the behavior information;

[0066] S300, marking fuzzy information in the behavior information according to the fuzzy coefficient;

[0067] S400, calculating the mobile target's store entry intention based on the fuzzy information;

[0068] S500: Correcting the number of people entering the store based on the store entry intention;

[0069] Furthermore, the store is an unmanned store.

[0070] Furthermore, in S100, a high-definition camera is used to capture a video of the monitored area.

[0071] Furthermore, the high-definition camera adopts a binocular camera.

[0072] Furthermore, the monitoring area is a square or supermarket around the monitoring store.

[0073] Furthermore, in S100, the method for obtaining the behavior information of the mobile target in the surveillance video outside the store is as follows: a plurality of mobile targets are marked in the video captured by the high-definition camera installed outside the store to form a monitoring target set MOT, and i is used as the serial number of the mobile target, mot i is the i-th moving target;

[0074] The video processing software Tracker is used to extract the speed and trajectory of the moving target, and the speed of all moving targets is formed into a speed set SPD, spd iThe speed of the i-th moving target is calculated, and the distance between the moving target and the geometric center of the area occupied by the store is calculated. The distances between all moving targets and the geometric center of the area occupied by the store form a distance set DST, dst i is the distance between the i-th moving target and the geometric center of the area occupied by the store. The speed set SPD and the distance set DST together constitute the behavior information of the moving target.

[0075] Furthermore, the YOLO algorithm is used to mark the moving targets.

[0076] Furthermore, in S200, the method for calculating the fuzzy coefficient of the moving target based on the behavior information is:

[0077] In the speed set, the speed of all moving targets is decomposed as follows:

[0078] The direction from the target to the geometric center of the store area is the horizontal direction, and the direction perpendicular to the geometric center of the store area is the vertical direction. The projection of the velocity in the horizontal direction is spd_xi, and the projection of the velocity in the vertical direction is spd_yi.

[0079] Set the projection coefficient to m, and set its initial value to 1, calculate the difference between spd_xi and spd_yi, and modify the projection coefficient m based on the difference result;

[0080] Furthermore, the specific method of modifying the projection coefficient m according to the difference result is:

[0081] If the difference between spd_xi and spd_yi is less than or equal to zero, then the value of m is modified to 0, otherwise the value of m is not modified;

[0082] The video is divided into multiple video images with a period of 2000ms, and the distance between the moving target and the geometric center of the store area is obtained at the same time. The distance of all moving targets and the corresponding acquisition time are plotted to generate a distance change curve XL, where the distance change curve XL is a curve composed of time and distance. The point on the XL curve is called the distance point dip, and k is the serial number of the acquisition time. k For T k The distance between the first target obtained at the moment and the geometric center of the area occupied by the store, where T k Indicates the kth acquisition time;

[0083] Set the distance coefficient to x and set its initial value to 1. Calculate the sum of the derivatives at all distance points on the curve XL and modify the distance coefficient x based on the calculation result.

[0084] Furthermore, the specific method of modifying the distance coefficient x according to the calculation result is:

[0085] If the sum of the derivatives at all distance points on the curve XL is less than zero, then the value of x is modified to 0, otherwise the value of x is not modified;

[0086] Use the same method to obtain the speed of the moving target, and plot all the speeds of the moving target against the acquisition time to generate a speed change curve VL. The points on the curve VL are recorded as speed points rat, and k is the serial number of the acquisition time. k For T k The speed of the moving target obtained at all times;

[0087] Set the velocity coefficient to v, and set its initial value to 1. Calculate the sum of the derivatives at all velocity points on the curve VL, and modify the velocity coefficient v based on the calculation result.

[0088] Furthermore, the specific method of modifying the speed coefficient v according to the calculation result is:

[0089] If the sum of the derivatives at all velocity points on the curve VL is less than zero, the v value is modified to 0, otherwise the v value is not modified;

[0090] The fuzzy coefficient of the moving target is calculated according to the formula m+x+v.

[0091] Furthermore, in S300, the specific method of marking fuzzy information in behavior information according to the fuzzy coefficient is: all moving targets with fuzzy coefficients equal to zero are recorded as relevant targets, all video images containing relevant targets constitute a behavior set, and the behavior information of the relevant targets is recorded as fuzzy information.

[0092] Furthermore, in S400, the specific method for calculating the mobile target's store-entry intention based on the deblurred information is as follows:

[0093] Record the speed rat and distance dip of the relevant target collected at the latest moment on curves VL and XL, and convert the speed and distance according to the formula P=Ln( ) calculates the store entry intention of the current relevant target, where the Ln() function is a logarithmic function with the natural constant e as the base, where a represents the speed parameter of the relevant target in the acquired video, according to the formula a= , where rum represents the number of images with a speed greater than the average speed in the behavior set, Nnum represents the total number of images in the behavior set; b represents the distance parameter of the relevant target in the acquired video, according to the formula b= , where dum represents the number of images in the behavior set that are smaller than the average distance.

[0094] Furthermore, in S500, the specific method for correcting the counting of the flow of people entering the store based on the intention of entering the store is:

[0095] Within every 60 seconds, periodically acquire the pulse signal generated by the sensor at 1-second intervals. The time when a valid pulse (a valid pulse refers to the pulse signal generated when the sensor receives an echo signal) is generated is recorded as TIM_1, and the time when the corresponding valid pulse disappears is recorded as TIM_2. A variable M is set with an initial value of 0. Whenever a complete set of TIM_1 and TIM_2 is detected, or whenever a complete set of pulse signals is detected, the variable M is incremented by 1. After the preset period, the value of the variable M is accessed as the store traffic volume during that period.

[0096] The acquired pulse signal is plotted as a square wave signal SL, where the square wave signal SL is a curve composed of time and pulse signal. The size of the pulse signal is compared on the curve SL starting from the second acquisition time. If the current signal size is greater than the signal size at the previous moment, the time point corresponding to the current signal is recorded as ST. On the curve SL, search backward from ST for the first point that satisfies the condition that the current signal is greater than the signal at the next moment, and the time point corresponding to the searched signal is recorded as ET. Repeat the above operation until all STs and ETs are marked. Starting from the first ST, each ST and the adjacent ET are respectively formed into a valid pulse group. The time interval between ST and ET of each valid pulse group is calculated in turn as the signal duration TIM of the group. With n as the serial number, TIM n Indicates the signal duration of the nth valid pulse group;

[0097] Traverse all TIMs in the range of n. When TIM satisfies the formula Ln(TIM n )<ε, mark the valid pulse group corresponding to the current TIM as an abnormal pulse group, where ε is any positive number, traverse all abnormal pulse groups, if it satisfies the formula Ln(TIM n )+ Ln(TIM n+1 )<ε or satisfy the formula Ln(TIM n )+ Ln(TIM n-1 )<ε, mark the current abnormal pulse group as a repeated pulse group, otherwise mark the current abnormal pulse group as a lost pulse group;

[0098] The statistical flow of people entering the store is corrected based on the abnormal pulse group. The specific method is: the flow of people entering the store is added with the number of missing pulse groups and then subtracted with the number of repeated pulse groups as the corrected flow of people entering the store.

[0099] Example 2: This example 2 replaces the method of calculating the mobile target's store-entry intention based on behavior information in Example 1. Specifically,

[0100] In the video, the crowd density calculation algorithm is used to mark multiple groups of people to form a set GP, and let j be the sequence number of the group, gpj Indicates the jth group of people. In the monitoring target set MOT, the curve ATY consisting of the movement trajectory of each moving target is obtained in turn. The curve ATY is a curve consisting of the modulus of the time and velocity vector. The velocity vector of the moving target is obtained as the target vector with a 2ms acquisition cycle. At the same time, the velocity vectors of all people are obtained as the influence vector to form the influence set;

[0101] Furthermore, the MCNN crowd density calculation algorithm is used to mark multiple crowds.

[0102] Traverse all velocity vectors on the curve ATY. If the velocity vector modulus at the current moment is smaller than the velocity vector modulus at the previous moment and also smaller than the velocity vector modulus at the next moment, or if the velocity vector modulus at the current moment is larger than the velocity vector modulus at the previous moment and also larger than the velocity vector modulus at the next moment, then mark the velocity vector at this moment as an affected vector. In the influence set, subtract all affected vectors from the influence vector in turn to calculate the magnitude of the resulting vector modulus. Record the crowd corresponding to the influence vector with the largest modulus as the main influence group. Calculate the distance between the geometric center of the main influence group and the current moving target as the reference moment at the current time point. Calculate the distance between the geometric center of all crowds and the moving target and the magnitude of the reference moment. If it is larger than the reference moment, then record the current crowd as a weak influence group, otherwise it is recorded as a strong influence group.

[0103] Traverse all marked groups of people in turn. If it is a strong influence group, subtract the velocity vector of the moving target at the current moment from the influence vector corresponding to the group, and then record the projection of the operation result in the vertical direction as rat_h. If it is a weak influence group, add the target vector of the moving target at the current moment to the influence vector corresponding to the group, and then record the projection of the operation result in the vertical direction as rat_h. The ratio of rat_h to the distance between the moving target and the store (the numerator of the calculated ratio is rat_h, and the denominator of the calculated ratio is the distance between the moving target and the store) is used as the local store-entry intention of the group for the moving target at the current moment. According to the above method, the local store-entry intention of the group for the moving target at all moments is calculated, and the sum of all local store-entry intentions is the store-entry intention of the current moving target.

[0104] In addition, the present invention also provides an embodiment of an intelligent store management system based on big data, such as Figure 2 Shown is a structural diagram of an intelligent store management system based on big data of the present invention. An intelligent store management system based on big data of this embodiment includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the above-mentioned embodiment of the intelligent store management system based on big data are implemented.

[0105] The system includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to run in the following units of the system:

[0106] A real-time video capture unit is used to capture surveillance videos outside the store through an outside camera;

[0107] A behavior information acquisition unit, configured to acquire behavior information of a moving target from the captured surveillance video outside the store;

[0108] A fuzzy coefficient calculation unit, configured to calculate the fuzzy coefficient of the moving target based on the acquired behavior information;

[0109] a fuzzy information marking unit, configured to mark fuzzy information in the behavior information according to the calculated fuzzy coefficient;

[0110] a store entry intention calculation unit, configured to calculate the store entry intention of the mobile target based on the fuzzy information of the mobile target;

[0111] The store entry flow counting unit is used to correct the current store entry flow according to the mobile target's store entry intention.

[0112] The intelligent store management system based on big data can be run on computing devices such as desktop computers, notebooks, PDAs, and cloud servers. The intelligent store management system based on big data can run on systems that include, but are not limited to, processors and memories. Those skilled in the art will understand that the example is merely an example of an intelligent store management system based on big data and does not constitute a limitation on an intelligent store management system based on big data. The system may include more or fewer components than the example, or a combination of certain components, or different components. For example, the intelligent store management system based on big data may also include input and output devices, network access devices, buses, etc.

[0113] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the operating system of the intelligent store management system based on big data, and uses various interfaces and lines to connect the various parts of the operating system of the intelligent store management system based on big data.

[0114] The memory can be used to store the computer programs and / or modules. The processor implements the various functions of the big data-based smart store management system by running or executing the computer programs and / or modules stored in the memory and accessing the data stored in the memory. The memory may primarily include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function (such as a sound playback function or an image playback function); the data storage area may store data generated based on the use of the mobile phone (such as audio data and a phone book). Furthermore, the memory may include high-speed random access memory (RAM) and non-volatile memory, such as a hard disk, internal memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0115] Although the present invention has been described in considerable detail and with particularity with respect to several embodiments, it is not intended to limit the present invention to any of these details or embodiments or any particular embodiment, so as to effectively encompass the intended scope of the present invention. In addition, the present invention has been described above with respect to embodiments foreseen by the inventors for the purpose of providing a useful description, and those insubstantial modifications of the present invention that are not currently foreseen may still represent equivalent modifications of the present invention.

Claims

1. A smart store management method based on big data, characterized in that: The method comprises the following steps: S100, obtaining behavior information of a moving target in a surveillance video outside the store; S200, calculating the fuzzy coefficient of the moving target based on the behavior information; S300, marking fuzzy information in the behavior information according to the fuzzy coefficient; S400, calculating the mobile target's store entry intention based on the fuzzy information; S500: Correcting the number of people entering the store based on the store entry intention; In S100, the method for obtaining the behavior information of the mobile target in the surveillance video outside the store is as follows: a plurality of mobile targets are marked in the video captured by the high-definition camera installed outside the store to form a monitoring target set MOT, and i is used as the sequence number of the mobile target, mot i is the i-th moving target; The video processing software Tracker is used to extract the speed and trajectory of the moving target, and the speed of all moving targets is formed into a speed set SPD, spd i The speed of the i-th moving target is calculated, and the distance between the moving target and the geometric center of the area occupied by the store is calculated. The distances between all moving targets and the geometric center of the area occupied by the store form a distance set DST, dst i is the distance between the i-th moving target and the geometric center of the area occupied by the store. The speed set SPD and the distance set DST together constitute the behavior information of the moving target; In S200, the method for calculating the fuzzy coefficient of the moving target based on the behavior information is: In the speed set, the speed of all moving targets is decomposed as follows: The direction from the moving target to the geometric center of the store area is the horizontal direction, and the direction perpendicular to the moving target to the geometric center of the store area is the vertical direction. The projection of the velocity in the horizontal direction is spd_xi, and the projection of the velocity in the vertical direction is spd_yi. Set the projection coefficient to m, and set its initial value to 1, calculate the difference between spd_xi and spd_yi, and modify the projection coefficient m based on the difference result; The video is divided into multiple video images according to the preset time t, and the distance between the moving target and the geometric center of the store area is obtained at the same time. The distance of all moving targets and the corresponding acquisition time are plotted to generate a distance change curve XL, where the distance change curve XL is a curve composed of time and distance. The point on the XL curve is called the distance point dip, and k is the serial number of the acquisition time. k For T k The distance between the moving target and the geometric center of the area occupied by the store at each moment, where T k Indicates the kth acquisition time; Set the distance coefficient to x and set its initial value to 1. Calculate the sum of the derivatives at all distance points on the curve XL and modify the distance coefficient x based on the calculation result. Use the same method to obtain the speed of the moving target, and plot all the speeds of the moving target against the acquisition time to generate a speed change curve VL. The points on the curve VL are recorded as speed points rat, and k is the serial number of the acquisition time. k For T k The speed of the moving target obtained at all times; Set the velocity coefficient to v, and set its initial value to 1. Calculate the sum of the derivatives at all velocity points on the curve VL, and modify the velocity coefficient v based on the calculation result. The fuzzy coefficient of the moving target is calculated based on the projection coefficient m, distance coefficient x and speed coefficient v.

2. The intelligent store management method based on big data according to claim 1 is characterized in that In S300, the method of marking fuzzy information in behavior information according to the fuzzy coefficient is as follows: all moving targets with fuzzy coefficients equal to zero are recorded as relevant targets, all video images containing relevant targets constitute a behavior set, and the behavior information of the relevant targets is recorded as fuzzy information.

3. The smart store management method based on big data according to claim 2, characterized in that: In S400, the method for calculating the mobile target's intention to enter the store based on the fuzzy information is as follows: record the speed rat and distance dip corresponding to the relevant target collected at the most recent moment on curves VL and XL, and calculate the current relevant target's intention to enter the store based on the speed rat and distance dip.

4. The method for intelligent store management based on big data according to claim 3, characterized in that: The method of calculating the mobile target's intention to enter the store based on fuzzy information is replaced by: using the crowd density calculation algorithm in the video to mark multiple groups of people to form a set GP, let j be the sequence number of the group, gp j Denotes the jth group of people. In the monitoring target set MOT, the curve ATY consisting of the trajectory of each moving target is obtained in turn. The curve ATY is a curve consisting of the modulus of the time and velocity vector. The velocity vector of the moving target is obtained as the target vector according to the preset period t. At the same time, the velocity vectors of all groups of people are obtained as the influence vector to form the influence set; Traverse all velocity vectors on the curve ATY. If the velocity vector modulus at the current moment is smaller than the velocity vector modulus at the previous moment and also smaller than the velocity vector modulus at the next moment, or if the velocity vector modulus at the current moment is larger than the velocity vector modulus at the previous moment and also larger than the velocity vector modulus at the next moment, then mark the velocity vector at this moment as an affected vector. In the influence set, subtract all affected vectors from the influence vector in turn to calculate the magnitude of the resulting vector modulus. Record the crowd corresponding to the influence vector with the largest modulus as the main influence group. Calculate the distance between the geometric center of the main influence group and the current moving target as the reference moment at the current time point. Calculate the distance between the geometric center of all crowds and the moving target and the magnitude of the reference moment. If it is larger than the reference moment, then record the current crowd as a weak influence group, otherwise it is recorded as a strong influence group. Traverse all marked crowds in turn. If it is a strong influence group, subtract the velocity vector of the moving target at the current moment from the influence vector corresponding to the crowd, and then record the projection of the operation result in the vertical direction as rat_h. If it is a weak influence group, add the target vector of the moving target at the current moment to the influence vector corresponding to the crowd, and then record the projection of the operation result in the vertical direction as rat_h. The ratio of rat_h to the distance between the moving target and the geometric center of the area occupied by the store is used as the local store-entry intention of the crowd towards the moving target at the current moment. Calculate the local store-entry intention of the crowd towards the moving target at all moments according to the above method, and calculate the sum of all local store-entry intentions as the store-entry intention of the current moving target.

5. The method for intelligent store management based on big data according to claim 4, characterized in that: In S500, the method for correcting the counting of the flow of people entering the store based on the intention of entering the store is: The pulse signal generated by the sensor is obtained at time intervals T within a preset period. The time when a valid pulse is generated is recorded as TIM_1, and the time when the corresponding valid pulse disappears is recorded as TIM_2. A variable M is set, and its initial value is set to 0. Whenever a complete set of TIM_1 and TIM_2 is detected, or whenever a complete set of pulse signals is detected, the variable M is incremented by 1. After the preset period ends, the value of the variable M is accessed as the store traffic during this period. The acquired pulse signal is plotted as a square wave signal SL, where the square wave signal SL is a curve composed of time and pulse signal. The size of the pulse signal is compared on the curve SL starting from the second acquisition time. If the current signal size is greater than the signal size at the previous moment, the time point corresponding to the current signal is recorded as ST. On the curve SL, the first time point that satisfies the condition that the current signal is greater than the signal at the next moment is searched backward from ST and the time point corresponding to the searched signal is recorded as ET. The operation is repeated until all STs and ETs are marked. Starting from the first ST, each ST and the adjacent ET are respectively formed into a valid pulse group. The time interval between ST and ET of each valid pulse group is calculated in turn as the signal duration TIM of the group. With n as the serial number, TIM n Indicates the signal duration of the nth valid pulse group; After traversing all TIMs, mark the lost pulse groups and repeated pulse groups in all valid pulse groups, and then add the number of lost pulse groups to the store flow and subtract the number of repeated pulse groups to get the corrected store flow.

6. An intelligent store management system based on big data, characterized in that: The smart store management system based on big data includes: a processor, a memory, and a computer program stored in the memory and runnable on the processor. When the processor executes the computer program, it implements the steps of the smart store management method based on big data described in any one of claims 1-5.

Images