CN113068215B - Weight and filtering-based multi-WiFi probe MAC address dynamic line algorithm - Google Patents

Weight and filtering-based multi-WiFi probe MAC address dynamic line algorithm Download PDF

Info

Publication number
CN113068215B
CN113068215B CN202110272127.9A CN202110272127A CN113068215B CN 113068215 B CN113068215 B CN 113068215B CN 202110272127 A CN202110272127 A CN 202110272127A CN 113068215 B CN113068215 B CN 113068215B
Authority
CN
China
Prior art keywords
time
mac address
winning area
votes
weight
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202110272127.9A
Other languages
Chinese (zh)
Other versions
CN113068215A (en
Inventor
苏同
吴斌
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Huayang Lianzhong Digital Technology Shenzhen Co ltd
Original Assignee
Huayang Lianzhong Digital Technology Shenzhen Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Huayang Lianzhong Digital Technology Shenzhen Co ltd filed Critical Huayang Lianzhong Digital Technology Shenzhen Co ltd
Priority to CN202110272127.9A priority Critical patent/CN113068215B/en
Publication of CN113068215A publication Critical patent/CN113068215A/en
Application granted granted Critical
Publication of CN113068215B publication Critical patent/CN113068215B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/08—Testing, supervising or monitoring using real traffic
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B17/00—Monitoring; Testing
    • H04B17/30—Monitoring; Testing of propagation channels
    • H04B17/309—Measuring or estimating channel quality parameters
    • H04B17/318—Received signal strength
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02—Services making use of location information
    • H04W4/025—Services making use of location information using location based information parameters
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L2101/00—Indexing scheme associated with group H04L61/00
    • H04L2101/60—Types of network addresses
    • H04L2101/618—Details of network addresses
    • H04L2101/622—Layer-2 addresses, e.g. medium access control [MAC] addresses

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Quality & Reliability (AREA)
  • Physics & Mathematics (AREA)
  • Electromagnetism (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a weight and filtering based multi-WiFi probe MAC address dynamic line algorithm, which comprises the following steps of: step S1, acquiring at least one MAC address for user action analysis and an analysis time period for user action analysis; and step S2, dividing the analysis time interval into blocks, and realizing weight quantization on the blocks to obtain the dominant region of the MAC address radiation. According to the invention, more scientific and accurate data are provided for the user action line analysis by the multi-probe three-dimensional WiFi probe, in the action line analysis process, a voting system is adopted to obtain a leading area representing the stay of the user in the analysis time period and the stay duration in the leading area in the user action line, and a voting number setting threshold value for inhibiting the irregular jumping of the user action line and a parameter for retaining the previous user action line analysis result are set, so that the accuracy of the user action line analysis can be effectively improved, and more accurate data support is provided for a market.

Description

Weight and filtering-based multi-WiFi probe MAC address dynamic line algorithm
Technical Field
The invention relates to the technical field of WiFi wireless, in particular to a multi-WiFi-probe MAC address dynamic line algorithm based on weight and filtering.
Background
With the improvement of living standard of people, the mobile phone becomes an important part in the life of people, but the consumption and the shopping in a shopping mall become the normal thing, so that the combination of the WiFi of the mobile phone and various marketing means becomes the breakthrough point and the development point of a plurality of commercial institutions. Therefore, by using the uniqueness of the mobile phone MAC, Mac and RSSI of the mobile phone of the user can be uploaded to the background server through the scanning equipment for data analysis, so that the marketing can be guided by passenger flow data information of the user, such as visiting frequency, staying time, mobile phone brand, staying area and the like.
Under the condition that a three-dimensional space is large and an electromagnetic environment is complex, a large error is necessarily caused in passenger flow data obtained by calculation only by using a traditional, planar and small number of probes, and accurate data for guiding a plurality of commercial activities of a market is difficult to provide for the market through user action line analysis obtained based on the passenger flow data.
Disclosure of Invention
The invention aims to provide a weight and filtering-based multi-WiFi-probe MAC address dynamic line algorithm to solve the technical problems that in the prior art, the custom data must have larger errors and the accurate data is difficult to provide for a market to guide a plurality of commercial activities of the market.
In order to solve the technical problems, the invention specifically provides the following technical scheme:
a weight and filtering-based multi-WiFi probe MAC address dynamic line algorithm comprises the following steps:
step S1, acquiring at least one MAC address for user action analysis and an analysis time period for user action analysis;
step S2, dividing the analysis time interval into blocks, and realizing weight quantization on the blocks to obtain the dominant region of the MAC address radiation;
and step S3, performing slide voting on the dominant area, and determining the final winning area and the stay time of the final winning area based on the number of votes to obtain the result of the user action line analysis of the MAC address.
As a preferable aspect of the present invention, in step S2, the analysis time interval is a first continuous time interval for user action analysis, and a specific manner of dividing blocks in the analysis time interval is as follows:
planning N-1 division points with the first duration as an interval on the analysis time period, and dividing the analysis time period into N time blocks with the first duration along the N-1 division points, wherein the N time blocks are marked as { C0,C1,C2,…,CN-1}。
As a preferred embodiment of the present invention, in step S3, weights of all WiFi probes in each time block receiving the signal data of the MAC address are sequentially calculated by using a weight formula, and a position of the WiFi probe with the largest weight is used as a dominant region of the MAC address radiation of each time block, the WiFi probes are three-dimensionally installed in a MAC address radiation range in a matrix form, and each WiFi probe stores position information and records the intensity and the number of times of receiving the signal data of the MAC address, and a specific manner of obtaining the dominant region of the MAC address radiation is realized by quantizing the weights of the blocks:
sequentially calculating the time block C by using a weight formulai(i ═ {0,1,2, …, N-1}) each WiFi probe receives a single weight of signal data for the MAC address at a time, and all the single weights for each WiFi probe are accumulated to obtain a time block CiThe weight of each WiFi probe receiving signal data of the MAC address;
sequentially comparing time blocks CiThe weight of all WiFi probes receiving the signal data of the MAC address:
if the maximum value of the weight exists and is unique, selecting the position of the WiFi probe corresponding to the maximum value of the weight as a time block CiThe leading region of (2);
if the maximum value of the weight exists and is not unique, counting the time blocks C in sequenceiThe number of times and the average intensity of the signal data of the MAC address received by all the WiFi probes corresponding to the maximum value of the internal weight are as follows:
if the maximum value of the times exists and is unique, selecting the position of the WiFi probe corresponding to the maximum value of the times as a time block CiThe leading region of (2);
if the maximum value of the times exists and is not unique, selecting the position of the WiFi probe corresponding to the maximum value of the average intensity in all the WiFi probes corresponding to the maximum value of the times as a time block CiThe leading region of (2);
if the weight does not exist, time block CiThere is no main guide area.
As a preferred aspect of the present invention, the weight formula is:
Figure BDA0002974704500000031
in the formula, m: the number of times each WiFi probe receives the signal data of the MAC address;
RSSIh: the strength of the signal data of the MAC address received by each WiFi probe h time;
ω: each WiFi probe receives the weight of the signal data of the MAC address;
as a preferred embodiment of the present invention, the average intensity formula is:
Figure BDA0002974704500000032
in the formula (I), the compound is shown in the specification,
Figure BDA0002974704500000033
the average intensity of signal data of each WiFi probe receiving the MAC address;
m: the number of times each WiFi probe receives the signal data of the MAC address;
RSSIh: and each WiFi probe receives the signal data strength of the MAC address for the h time.
As a preferable scheme of the present invention, in step S3, a sliding window is planned on the analysis time period, and the sliding window is controlled to slide along the analysis time period to vote for all the dominant regions according to a first preset rule, where the sliding window is a second continuous time period formed by K first time periods, and the first preset rule is that the time block located in the sliding window range during the sliding of the sliding window on the analysis time period votes for the corresponding dominant region, and the specific manner is as follows:
region where sliding window starts over analysis period C0,C1,..,CK-1At and along C0To Cn-1The direction is gradually slid by taking the first duration as a unit length to obtain a plurality of sliding areas, and the sliding areas are marked as { P0,P1,…,Pr}；
Sequentially to the sliding region Pj(j ═ {0,1, …, r }) of K time blocksA single vote and recording the number of times of the single vote.
As a preferable aspect of the present invention, in the step S3, the specific manner of counting the votes of all the dominant regions is:
sequentially adding CiThe number of all single votes for the dominant region of (i ═ {0,1,2, …, N-1}) yields Ci(i ═ {0,1,2, …, N-1}) of the dominant region.
As a preferred scheme of the present invention, the specific rules for determining the final winning area and the staying time length of the final winning area based on the number of votes include a final winning area selection rule and a calculation rule of the staying time length, the final winning area selection rule is to select a leading area with the highest number of votes and higher than a threshold set for the number of votes, and the calculation rule of the staying time length is to calculate the interval time length between the first time when the sliding window appears for the first time and the last time when the sliding window appears for the last time.
As a preferable aspect of the present invention, the threshold for setting the number of votes includes an upper limit of the number of votes and a lower limit of the number of votes, the upper limit of the number of votes is the number of votes suppressing irregular jumping of the sliding window, the lower limit of the number of votes is the number of votes in the first winning area in the previous result of the analysis of the action line of the user, and the specific manner of determining the final winning area is:
obtaining the number of votes in the first winning area;
compare { C in order0,C1,C2,…,CN-1The voting numbers of all the leading areas in the Chinese character image are counted, and the leading area corresponding to the maximum value of the voting numbers is selected as a second winning area;
comparing the number of votes for the second winning area with a vote number setting threshold:
if the number of votes in the second winning area is larger than the upper limit of the number of votes delta or more, taking the second winning area as a final winning area;
and if the number of votes in the second winning area is less than the upper limit of the number of votes delta or less, taking the first winning area as the final winning area.
As a preferred scheme of the present invention, a specific way of calculating the stay time of the final winning area is as follows:
respectively acquiring a first time, a second first time, a first last time and a second last time of a first winning area and a second winning area appearing at the first time in a sliding window;
if the final winning area is the first winning area, the staying time length is the interval time length between the first time and the first last time;
and if the final winning area is a second winning area, segmenting the first time and the first last time, and then respectively using the segmented first time and first last time as a second first time when the second winning area appears at the first time and a second last time when the second winning area appears at the last time in the sliding window, wherein the stay time is the interval time between the second first time and the second last time.
Compared with the prior art, the invention has the following beneficial effects:
according to the invention, more scientific and accurate data are provided for the user action line analysis by the multi-probe three-dimensional WiFi probe, in the action line analysis process, a voting system is adopted to obtain a leading area representing the stay of the user in the analysis time period and the stay duration in the leading area in the user action line, and a voting number setting threshold value for inhibiting the irregular jumping of the user action line and a parameter for retaining the previous user action line analysis result are set, so that the accuracy of the user action line analysis can be effectively improved, and more accurate data support is provided for a market.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It should be apparent that the drawings in the following description are merely exemplary, and that other embodiments can be derived from the drawings provided by those of ordinary skill in the art without inventive effort.
Fig. 1 is a flowchart of a dynamic line algorithm for multi-WiFi probe MAC addresses based on weight and filtering according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, the user action line refers to a flow route of a user in a business place, the business place can master the user action line to design the layout of the business place to form a business pattern which is planned to guide the customer to stay more and consume more, and the sales volume of the business place is promoted, the invention provides a weight and filtering based action line algorithm of a multi-WiFi probe MAC address, which comprises the following steps:
step S1, acquiring at least one MAC address for user action analysis and an analysis time period for user action analysis;
the analysis time period can be set according to the analysis requirements of the application scene, for example, in a large shopping mall, the whole business hours of the large shopping mall can be used as the analysis time period, and in a dish market, the morning can be used as the analysis time period.
Step S2, dividing the analysis time interval into blocks, and realizing weight quantization on the blocks to obtain the dominant region of the MAC address radiation;
in the step S2, in the step S2, the analysis time interval is a first continuous time interval for analysis of the user' S action line, and the specific manner of dividing blocks in the analysis time interval is as follows:
planning N-1 division points with the first duration as an interval on the analysis time period, and dividing the analysis time period into N time blocks with the first duration along the N-1 division points, wherein the N time blocks are marked as { C0,C1,C2,…,CN-1}。
The selection of the first duration affects the accuracy of the user action analysis, so the first duration is preferably selected to be no more than one minute, and the longer the first duration is selected, the lower the accuracy of the user action analysis is.
Step S3, performing sliding voting on the dominant region, and determining the final winning region and the stay duration of the final winning region based on the number of votes to obtain the result of the user action line analysis of the MAC address;
in the step S3, in the step S3, weights of all WiFi probes in each time block receiving the signal data of the MAC address are sequentially calculated by using a weight formula, and a position of the WiFi probe with the largest weight is used as a dominant region of the MAC address radiation of each time block, the WiFi probes are arranged in a MAC address radiation range in a matrix stereo manner, and each WiFi probe stores position information and records the intensity and the number of times of receiving the signal data of the MAC address, and a specific manner of obtaining the dominant region of the MAC address radiation by performing weight quantization on the block is implemented:
sequentially calculating the time block C by using a weight formulai(i ═ {0,1,2, …, N-1}) each WiFi probe receives a single weight of signal data for the MAC address at a time, and all the single weights for each WiFi probe are accumulated to obtain a time block CiThe weight of each WiFi probe receiving signal data of the MAC address;
sequentially comparing time blocks CiThe weight of all WiFi probes receiving the signal data of the MAC address:
if the maximum value of the weight exists and is unique, selecting the position of the WiFi probe corresponding to the maximum value of the weight as a time block CiThe leading region of (2);
if the maximum value of the weight exists and is not unique, counting the time blocks C in sequenceiThe number of times and the average intensity of the signal data of the MAC address received by all the WiFi probes corresponding to the maximum value of the internal weight are as follows:
if the maximum value of the times exists and is unique, selecting the position of the WiFi probe corresponding to the maximum value of the times as a time block CiThe leading region of (2);
if the maximum value of the times exists and is not unique, selecting the maximum value of the average intensity in all WiFi probes corresponding to the maximum value of the timesThe position of the WiFi probe corresponding to the value is taken as a time block CiThe leading region of (2);
if the weight does not exist, time block CiThere is no main guide area.
The weight formula is as follows:
Figure BDA0002974704500000071
in the formula, m: the number of times each WiFi probe receives the signal data of the MAC address;
RSSIh: the strength of the signal data of the MAC address received by each WiFi probe h time;
ω: each WiFi probe receives the weight of the signal data of the MAC address;
as a preferred embodiment of the present invention, the average intensity formula is:
Figure BDA0002974704500000072
in the formula (I), the compound is shown in the specification,
Figure BDA0002974704500000073
the average intensity of signal data of each WiFi probe receiving the MAC address;
m: the number of times each WiFi probe receives the signal data of the MAC address;
RSSIh: and each WiFi probe receives the signal data strength of the MAC address for the h time.
The leading area is determined by using the weight and the average intensity and is matched with the actual behavior of the user, namely the area which can receive the MAC signal frequency of the mobile phone of the user and has large signal average intensity is inevitably the area with long stay time and more frequency of the user, so that the area has reasonability as the leading area for analyzing the action line of the user.
Step S3, a sliding window is planned on the analysis time period, and the sliding window is controlled to slide along the analysis time period to vote on all the dominant regions according to a first preset rule, where the sliding window is a second continuous time period formed by K first time periods, a suitable value is selected according to the characteristics of the application scene itself, if the selection is too long, the accuracy of the sliding line will be affected, the first preset rule is that the time block located in the sliding window range during the sliding of the sliding window on the analysis time period votes for the corresponding dominant region, and the specific manner is as follows:
region where sliding window starts over analysis period C0,C1,..,CK-1At and along C0To Cn-1The direction is gradually slid by taking the first duration as a unit length to obtain a plurality of sliding areas, and the sliding areas are marked as { P0,P1,…,Pr}；
In particular, P0＝{C0,C1,..,CK-1}，P1＝{C1,C2,..,CK}，P2＝{C2,C3,..,CK+1And so on.
Sequentially to the sliding region PjThe dominant regions of K time blocks contained in (j ═ {0,1, …, r }) make a single vote and record the number of times of the single vote.
Specifically, the sliding region is P0＝{C0,C1,..,CK-1At this time, time block C0,C1,..,CK-1The leading areas all obtain a single vote; p1＝{C1,C2,..,CKTime block C1,C2,..,CKThe leading areas all obtain a single vote; at this time C0,C1,..,CKThe number of votes for the dominant region of (1, 2,2, …,2, 1;
in the step S3, the specific way of counting the votes of all the dominant regions is as follows:
sequentially adding CiThe number of all single votes for the dominant region of (i ═ {0,1,2, …, N-1}) yields Ci(i ═ {0,1,2, …, N-1}) of the dominant region.
The specific rules for determining the final winning area and the stay time of the final winning area based on the number of votes comprise a final winning area selection rule and a stay time calculation rule, wherein the final winning area selection rule is a dominant area with the highest number of votes selected and higher than a set threshold of the number of votes, and the stay time calculation rule is a time interval between the first time when the final winning area appears in the sliding window for the first time and the last time when the final winning area appears for the last time.
The vote number setting threshold comprises a vote number upper limit and a vote number lower limit, the vote number upper limit is the vote number for inhibiting irregular jumping of the sliding window, the vote number lower limit is the vote number of a first winning area in the last user action line analysis result, and the specific mode for judging the final winning area is as follows:
obtaining the number of votes in the first winning area;
compare { C in order0,C1,C2,…,CN-1The voting numbers of all the leading areas in the Chinese character image are counted, and the leading area corresponding to the maximum value of the voting numbers is selected as a second winning area;
comparing the number of votes for the second winning area with a vote number setting threshold:
if the number of votes in the second winning area is larger than the upper limit of the number of votes delta or more, taking the second winning area as a final winning area;
and if the number of votes in the second winning area is less than the upper limit of the number of votes delta or less, taking the first winning area as the final winning area.
Where δ is typically 1.
The specific way of calculating the stay duration of the final winning area is as follows:
respectively acquiring a first time, a second first time, a first last time and a second last time of a first winning area and a second winning area appearing at the first time in a sliding window;
if the final winning area is the first winning area, the staying time length is the interval time length between the first time and the first last time;
and if the final winning area is a second winning area, segmenting the first time and the first last time, and then respectively using the segmented first time and first last time as a second first time when the second winning area appears at the first time and a second last time when the second winning area appears at the last time in the sliding window, wherein the stay time is the interval time between the second first time and the second last time.
There are two ways to segment the first time and the first last time, the first: and adding the first time length to the first last time to be used as a new second first time, wherein the new second last time is kept the same as the original second last time, and the second time is as follows: and averaging the first last time and the original second first time, and taking the whole and the first time length as a new second first time, wherein the new second last time is kept the same as the original second last time.
Specifically, assume that the first winning area is a, the second winning area is B, and the first time TAFirst last time TA', original second first time instant TB1Original second last time TB1'. The sliding window continues to slide a first long distance to start voting, and there are three situations:
if A is the final winning area, the staying time is TA'-TA。
If B is the final winning area, the condition of B winning is that the number of votes is the largest and not less than the lower limit of the number of votes and the difference with the number of votes of A is larger than or equal to delta. Determining T according to the division mode of the stay timeA' and TBThe boundary of (2). If the first segmentation mode is adopted, TB2＝TA'+t，TB2'＝TB1'; if equally divided, TA'＝(TA'+TB) /2 rounding, TB＝TA'+t,TB2'＝TB1'。
The above embodiments are only exemplary embodiments of the present application, and are not intended to limit the present application, and the protection scope of the present application is defined by the claims. Various modifications and equivalents may be made by those skilled in the art within the spirit and scope of the present application and such modifications and equivalents should also be considered to be within the scope of the present application.

Claims (9)

1. A multi-WiFi probe MAC address line-moving method based on weight and filtering is characterized by comprising the following steps:
step S1, acquiring at least one MAC address for user action analysis and an analysis time period for user action analysis;
step S2, dividing the analysis time interval into blocks, and realizing weight quantization on the blocks to obtain the dominant region of the MAC address radiation;
step S3, performing sliding voting on the dominant region, and determining the final winning region and the stay duration of the final winning region based on the number of votes to obtain the result of the user action line analysis of the MAC address;
in the step S3, weights of all WiFi probes in each time block receiving the signal data of the MAC address are sequentially calculated by using a weight formula, and a position of the WiFi probe with the largest weight is used as a leading area of MAC address radiation of each time block, the WiFi probes are installed in a MAC address radiation range in a matrix stereo manner, and each WiFi probe stores position information and records intensity and frequency of receiving the signal data of the MAC address, and a specific manner of obtaining the leading area of MAC address radiation by performing weight quantization on the block is implemented:
sequentially calculating the time block C by using a weight formulai(i ═ {0,1,2, …, N-1}) each WiFi probe receives a single weight of signal data for the MAC address at a time, and all the single weights for each WiFi probe are accumulated to obtain a time block CiThe weight of each WiFi probe receiving signal data of the MAC address;
sequentially comparing time blocks CiThe weight of all WiFi probes receiving the signal data of the MAC address:
if the maximum value of the weight exists and is unique, selecting the position of the WiFi probe corresponding to the maximum value of the weight as a time block CiThe leading region of (2);
if the maximum value of the weight exists and is not unique, counting the time blocks C in sequenceiMaximum value of internal weight corresponds toThe number of times and average intensity of signal data of the MAC address received by the WiFi probe:
if the maximum value of the times exists and is unique, selecting the position of the WiFi probe corresponding to the maximum value of the times as a time block CiThe leading region of (2);
if the maximum value of the times exists and is not unique, selecting the position of the WiFi probe corresponding to the maximum value of the average intensity in all the WiFi probes corresponding to the maximum value of the times as a time block CiThe leading region of (2);
if the weight does not exist, time block CiThere is no main guide area.
2. The method of claim 1, wherein the method comprises: in step S2, the analysis time interval is a first continuous time interval used for analysis of the user' S action line, and the specific way of dividing blocks in the analysis time interval is as follows:
planning N-1 division points with the first duration as an interval on the analysis time period, and dividing the analysis time period into N time blocks with the first duration along the N-1 division points, wherein the N time blocks are marked as { C0,C1,C2,…,CN-1}。
3. The method of claim 2, wherein the method comprises: the weight formula is as follows:
Figure FDA0003388708170000021
in the formula, m: the number of times each WiFi probe receives the signal data of the MAC address;
RSSIh: the strength of the signal data of the MAC address received by each WiFi probe h time;
ω: each WiFi probe receives a weight of signal data for the MAC address.
4. The method of claim 3, wherein the multi-WiFi probe MAC address walk-through method based on weight and filtering is characterized in that: the average intensity formula is:
Figure FDA0003388708170000022
in the formula (I), the compound is shown in the specification,
Figure FDA0003388708170000023
the average intensity of signal data of each WiFi probe receiving the MAC address;
m: the number of times each WiFi probe receives the signal data of the MAC address;
RSSIh: and each WiFi probe receives the signal data strength of the MAC address for the h time.
5. The method of claim 4, wherein the multi-WiFi probe MAC address walk-through method based on weight and filtering is characterized in that: in step S3, a sliding window is planned in the analysis time period, and the sliding window is controlled to slide along the analysis time period to vote for all the dominant regions according to a first preset rule, where the sliding window is a second continuous time period formed by K first time periods, and the first preset rule is that the time block located in the sliding window range during the sliding process of the sliding window in the analysis time period votes for the corresponding dominant region, and the specific manner is as follows:
region where sliding window starts over analysis period C0,C1,..,CK-1At and along C0To Cn-1The direction is gradually slid by taking the first duration as a unit length to obtain a plurality of sliding areas, and the sliding areas are marked as { P0,P1,…,Pr}；
Sequentially to the sliding region PjThe dominant regions of K time blocks contained in (j ═ {0,1, …, r }) make a single vote and record the number of times of the single vote.
6. The method for moving the multi-WiFi probe MAC address according to claim 5, wherein in step S3, the specific way to count the votes of all the dominant regions is:
sequentially adding CiThe number of all single votes for the dominant region of (i ═ {0,1,2, …, N-1}) yields Ci(i ═ {0,1,2, …, N-1}) of the dominant region.
7. The method as claimed in claim 6, wherein the specific rules for determining the final winning area and the staying time length of the final winning area based on the number of votes include a final winning area selection rule for selecting a leading area with the highest number of votes and higher than a threshold set for the number of votes, and a staying time length calculation rule for calculating the interval length between the first time when the final winning area appears in the sliding window and the last time when the final winning area appears in the sliding window.
8. The method for multi-WiFi-probe MAC-address line-walking based on weight and filtering as claimed in claim 7, wherein the threshold setting value of the number of votes comprises an upper limit of the number of votes and a lower limit of the number of votes, the upper limit of the number of votes is the number of votes for restraining irregular jumping of a sliding window, the lower limit of the number of votes is the number of votes for the first winning area in the analysis result of the previous user line-walking, and the specific way for determining the final winning area is as follows:
obtaining the number of votes in the first winning area;
compare { C in order0,C1,C2,…,CN-1The voting numbers of all the leading areas in the Chinese character image are counted, and the leading area corresponding to the maximum value of the voting numbers is selected as a second winning area;
comparing the number of votes for the second winning area with a vote number setting threshold:
if the number of votes in the second winning area is larger than the upper limit of the number of votes delta or more, taking the second winning area as a final winning area;
and if the number of votes in the second winning area is less than the upper limit of the number of votes delta or less, taking the first winning area as the final winning area.
9. The weight and filtering based multi-WiFi probe MAC address line-moving method as claimed in claim 8, wherein the specific way of calculating the stay duration of the final winning area is as follows:
respectively acquiring a first time, a second first time, a first last time and a second last time of a first winning area and a second winning area appearing at the first time in a sliding window;
if the final winning area is the first winning area, the staying time length is the interval time length between the first time and the first last time;
and if the final winning area is a second winning area, segmenting the first time and the first last time, and then respectively using the segmented first time and first last time as a second first time when the second winning area appears at the first time and a second last time when the second winning area appears at the last time in the sliding window, wherein the stay time is the interval time between the second first time and the second last time.
CN202110272127.9A 2021-03-12 2021-03-12 Weight and filtering-based multi-WiFi probe MAC address dynamic line algorithm Active CN113068215B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110272127.9A CN113068215B (en) 2021-03-12 2021-03-12 Weight and filtering-based multi-WiFi probe MAC address dynamic line algorithm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110272127.9A CN113068215B (en) 2021-03-12 2021-03-12 Weight and filtering-based multi-WiFi probe MAC address dynamic line algorithm

Publications (2)

Publication Number Publication Date
CN113068215A CN113068215A (en) 2021-07-02
CN113068215B true CN113068215B (en) 2022-01-11

Family

ID=76560279

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110272127.9A Active CN113068215B (en) 2021-03-12 2021-03-12 Weight and filtering-based multi-WiFi probe MAC address dynamic line algorithm

Country Status (1)

Country Link
CN (1) CN113068215B (en)

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103747464A (en) * 2014-01-17 2014-04-23 北京赢销通软件技术有限公司 Mobile terminal motion trail analyzing system
CN108681797A (en) * 2018-06-08 2018-10-19 北京四象网讯科技有限公司 Automatically generate the method, apparatus and readable storage medium storing program for executing of parking lot moving-wire
CN109041099A (en) * 2018-06-28 2018-12-18 新华三大数据技术有限公司 Flow of the people prediction technique, device and terminal
CN109644320A (en) * 2016-12-30 2019-04-16 同济大学 A method of using WI-FI probe in detecting people streams in public places amount
CN109697849A (en) * 2018-12-26 2019-04-30 航天科工广信智能技术有限公司 Intelligent transportation Time segments division method based on sliding average algorithm
CN110493731A (en) * 2019-09-09 2019-11-22 腾讯科技（深圳）有限公司 Motion track acquisition methods, device, storage medium and equipment
CN110493816A (en) * 2019-08-21 2019-11-22 上海工程技术大学 A kind of real-time predicting method for handing over the subway station volume of the flow of passengers for rail
CN110516866A (en) * 2019-08-21 2019-11-29 上海工程技术大学 A kind of real-time estimation method for handing over subway crowding for city rail
CN110675434A (en) * 2018-07-03 2020-01-10 杭州海康威视系统技术有限公司 Method, device, equipment and system for generating moving line
CN111372196A (en) * 2020-02-20 2020-07-03 杭州海康威视系统技术有限公司 Data processing method and device, electronic equipment and machine-readable storage medium

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP6017004B1 (en) * 2015-10-20 2016-10-26 株式会社リクルートホールディングス Suspicious person detection system and suspicious person detection method
CN106251578B (en) * 2016-08-19 2019-05-07 深圳奇迹智慧网络有限公司 Stream of people's early warning analysis method and system based on probe
EP3671120B1 (en) * 2018-12-17 2023-07-26 HERE Global B.V. Enhancing the accuracy for device localization
CN111161534A (en) * 2019-12-19 2020-05-15 南京行者易智能交通科技有限公司 Public transport accurate OD data acquisition system and method based on WiFi probe

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103747464A (en) * 2014-01-17 2014-04-23 北京赢销通软件技术有限公司 Mobile terminal motion trail analyzing system
CN109644320A (en) * 2016-12-30 2019-04-16 同济大学 A method of using WI-FI probe in detecting people streams in public places amount
CN108681797A (en) * 2018-06-08 2018-10-19 北京四象网讯科技有限公司 Automatically generate the method, apparatus and readable storage medium storing program for executing of parking lot moving-wire
CN109041099A (en) * 2018-06-28 2018-12-18 新华三大数据技术有限公司 Flow of the people prediction technique, device and terminal
CN110675434A (en) * 2018-07-03 2020-01-10 杭州海康威视系统技术有限公司 Method, device, equipment and system for generating moving line
CN109697849A (en) * 2018-12-26 2019-04-30 航天科工广信智能技术有限公司 Intelligent transportation Time segments division method based on sliding average algorithm
CN110493816A (en) * 2019-08-21 2019-11-22 上海工程技术大学 A kind of real-time predicting method for handing over the subway station volume of the flow of passengers for rail
CN110516866A (en) * 2019-08-21 2019-11-29 上海工程技术大学 A kind of real-time estimation method for handing over subway crowding for city rail
CN110493731A (en) * 2019-09-09 2019-11-22 腾讯科技（深圳）有限公司 Motion track acquisition methods, device, storage medium and equipment
CN111372196A (en) * 2020-02-20 2020-07-03 杭州海康威视系统技术有限公司 Data processing method and device, electronic equipment and machine-readable storage medium

Also Published As

Publication number Publication date
CN113068215A (en) 2021-07-02

Similar Documents

Publication Publication Date Title
CN108038500B (en) Clustering method, apparatus, computer device, storage medium, and program product
Lathia et al. The hidden image of the city: sensing community well-being from urban mobility
CN103455515B (en) User recommendation method and system in SNS (social networking services) community
US20150351069A1 (en) Determining location of a user of a mobile device
CN108460101A (en) Point of interest of the facing position social networks based on geographical location regularization recommends method
CN108288106A (en) A kind of tourist flows prediction technique based on big data
US20120225678A1 (en) Apparatus and method for constructing wireless ap map
CN109996278A (en) Road network method for evaluating quality, device, equipment and medium
JP2001501307A (en) Moving position estimation method and system
KR20200003109A (en) Method and apparatus for setting sample weight, electronic device
CN108876509A (en) Utilize the method and system of POI analysis user tag
CN111866776A (en) Population measurement and calculation method and device based on mobile phone signaling data
CN113068215B (en) Weight and filtering-based multi-WiFi probe MAC address dynamic line algorithm
CN110595502A (en) Running distance estimation method and device
CN113159408A (en) Rail transit station passenger flow prediction method and device
CN108600961A (en) Preparation method and device, equipment, the storage medium of user's similarity
CN112289405A (en) Matching speed recommendation method and device, electronic equipment and storage medium
CN110675009A (en) Method and device for evaluating convenience of cell
CN115470872A (en) Driver portrait construction method based on vehicle track data
CN115412852A (en) Method and system for determining motion trail of mobile terminal
CN114781128A (en) Chip life prediction system and method using artificial intelligence technology
CN106919580A (en) A kind of information-pushing method and device
JP3330909B2 (en) Data processing device and recording medium recording data processing program
CN108874749A (en) A kind of method for building up of college entrance will admission probabilistic model
CN111104609A (en) Interpersonal relationship prediction method, interpersonal relationship prediction device, computer program, and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant