Statistical method and device of business district passenger flow, electronic equipment and readable storage medium

Abstract

The invention provides a business district passenger flow statistical method and device, electronic equipment and a readable storage medium, and relates to the technical field of big data. The method comprises the following steps: firstly, obtaining a mobile phone signaling set formed by signaling data of all indoor base stations in a target business district in a current specified time period, wherein the signaling data comprises a user position during signaling interaction; carrying out clustering processing on the mobile phone signaling set based on the user position in each piece of signaling data to obtain a plurality of clustered signaling sets; then, on the basis of the position of the target business district and the user position in each piece of signaling data, all the clustering signaling sets are filtered and then merged, and at least one target signaling set is obtained; and finally, based on the at least one target signaling set, counting the passenger flow volume of the target business district in the current specified time period. Compared with the prior art, more comprehensive and accurate passenger flow identification is realized based on the signaling data of the indoor base station in the target business district.

Description

Technical Field

[0001] The present invention relates to the field of big data technology, and in particular to a statistical method, device, electronic device and readable storage medium for measuring passenger flow in a business district. Background Art

[0002] For business districts, accurate customer flow statistics are not only an indicator of operational efficiency, but also an important tool for understanding consumer behavior, optimizing services and increasing sales.

[0003] In the prior art, commercial district cameras are used to identify customer flow. Although this can accurately identify customer flow within the camera's field of view, commercial district cameras always have blind spots, which makes customer flow identification inaccurate. Summary of the invention

[0004] The purpose of the present invention is to provide a statistical method, device, electronic device and readable storage medium for shopping district passenger flow, so as to improve the problems existing in the prior art.

[0005] The embodiments of the present invention can be implemented as follows: In a first aspect, the present invention provides a method for counting passenger flow in a business district, comprising: Obtaining a mobile phone signaling set consisting of signaling data of all indoor base stations in the target business district within a currently specified time period; the signaling data includes the user location during signaling interaction; Based on the user location in each piece of the signaling data, clustering the mobile phone signaling set to obtain multiple clustered signaling sets; Based on the location of the target business district and the user location in each piece of the signaling data, all clustered signaling sets are filtered and merged to obtain at least one target signaling set; Based on the at least one target signaling set, the customer flow of the target business district in the current specified time period is counted.

[0006] Optionally, the step of obtaining a mobile phone signaling set consisting of signaling data of all indoor base stations in the target business district within a currently specified time period includes: Obtain each signaling data of all indoor base stations in the urban area where the target business district is located within the current specified time period to obtain a total set of mobile phone signaling; the signaling data also includes a base station code; For each piece of signaling data in the mobile phone signaling total set, searching the preset code mapping table for the base station name corresponding to the base station code contained in the signaling data to obtain the base station name corresponding to the signaling data; Obtaining the name of the target business district, and segmenting the name of the business district to obtain multiple name segmentations; Based on the multiple name participles and the base station name corresponding to each signaling data in the mobile phone signaling collection, the mobile phone signaling collection is filtered to obtain the mobile phone signaling collection.

[0007] Optionally, the step of filtering the mobile phone signaling set based on the multiple name participles and the base station name corresponding to each signaling data in the mobile phone signaling set to obtain the mobile phone signaling set includes: For each signaling data in the total mobile phone signaling set, if the base station name corresponding to the signaling data does not contain any of the name participles or does not contain all of the name participles, the signaling data is filtered; otherwise, the signaling data is retained to obtain the mobile phone signaling set.

[0008] Optionally, the step of filtering and merging all clustered signaling sets based on the location of the target business district and the user location in each piece of the signaling data to obtain at least one target signaling set includes: For each piece of signaling data in each of the clustered signaling sets, calculating the distance between the user location in the signaling data and the location of the target business district, and if the distance exceeds a preset radiation radius of the target business district, filtering the signaling data to obtain each filtered clustered signaling set; If there is a neighboring business district within a preset radius around the target business district, based on the respective positions and preset radiation radius of the target business district and the neighboring business district, calculate the adjacent center points located in the radiation overlap area between the target business district and the neighboring business district; For each of the filtered cluster signaling sets, the fitting center point corresponding to the filtered cluster signaling set is calculated based on the user position in each signaling data in the filtered cluster signaling set; if the fitting center point is located in the radiation overlap area and the projection point of the fitting center point on the business district line is located between the adjacent center point and the adjacent business district, the filtered cluster signaling set is deleted; if the fitting center point is located in the radiation overlap area and the projection point of the fitting center point on the business district line is not located between the adjacent center point and the adjacent business district, the filtered cluster signaling set is used as the target signaling set; if the fitting center point is not located in the radiation overlap area, the filtered cluster signaling set is retained; Merging at least two filtered cluster signaling sets that have density-reachable and density-connected relationships into a target signaling set, and taking each filtered cluster signaling set that is isolated in spatial distribution as the target signaling set; When there is no neighboring business district within a preset radius around the target business district, at least two filtered cluster signaling sets that are density-reachable and density-connected are directly merged into one target signaling set, and each filtered cluster signaling set that is isolated in spatial distribution is used as the target signaling set.

[0009] Optionally, the method further includes: Obtain reference passenger flow and passenger flow for each of N consecutive specified time periods; Taking the reference passenger flow as an independent variable and the passenger flow as a dependent variable, a linear regression equation is obtained by performing linear fitting based on the reference passenger flow and passenger flow of each of the N consecutive specified time periods; Based on the linear regression equation, the goodness of fit corresponding to the target business district is calculated to measure the accuracy of the customer flow of each of the N consecutive specified time periods.

[0010] Optionally, the method further includes: If there is a neighboring business district within a preset radius around the target business district, obtaining the goodness of fit corresponding to the neighboring business district; If the goodness of fit corresponding to the target business district is lower than the goodness of fit corresponding to the neighboring business district, then for each of the specified time periods, the target signaling set with an overlapping area label is removed from all target signaling sets corresponding to the target business district in the specified time period, and the passenger flow of the target business district in the specified time period is recalculated. The overlapping area label represents that the corresponding target signaling set belongs to the indoor base station of the target business district or the indoor base station of the neighboring business district.

[0011] Optionally, the signaling data further includes an interaction time and a user code, and the user codes in different signaling data are the same or different; Before the step of clustering the mobile phone signaling set based on the user location to obtain a plurality of clustered signaling sets, the method further includes: Classifying the mobile phone signaling set according to the different user codes to obtain at least one piece of signaling data corresponding to each user code in the mobile phone signaling set; For each user code in the mobile phone signaling set, if there is only one signaling data including the user code, the signaling data is deleted; if there are at least two signaling data including the user code, the earliest interaction time and the latest interaction time are obtained from all signaling data including the user code to calculate the user stay time, and if the user stay time is lower than the preset time, all signaling data including the user code are deleted.

[0012] In a second aspect, the present invention provides a statistical device for passenger flow in a business district, comprising: A signaling acquisition module is used to obtain a mobile phone signaling set consisting of signaling data of all indoor base stations in the target business district within a currently specified time period; the signaling data includes the user location during signaling interaction; A clustering module, configured to cluster the mobile phone signaling set based on the user location in each piece of the signaling data to obtain a plurality of clustered signaling sets; A filtering and merging module, configured to filter and merge all clustered signaling sets based on the location of the target business district and the user location in each piece of signaling data, to obtain at least one target signaling set; The passenger flow statistics module is used to count the passenger flow of the target business district in the current specified time period based on the at least one target signaling set.

[0013] In a third aspect, the present invention provides an electronic device, comprising: a memory and a processor, wherein the memory stores a software program, and when the electronic device is running, the processor executes the software program to implement the method for counting customer flow in a shopping district as described in the first aspect above.

[0014] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the method for counting customer flow in a shopping district as described in the first aspect.

[0015] Compared with the prior art, the embodiment of the present invention provides a method, device, electronic device and readable storage medium for counting passenger flow in a business district. First, a mobile phone signaling set consisting of signaling data of all indoor base stations in the target business district in the current specified time period is obtained, and the signaling data includes the user location during signaling interaction; then, based on the user location in each signaling data, the mobile phone signaling set is clustered to obtain multiple clustered signaling sets; then, based on the location of the target business district and the user location in each signaling data, all clustered signaling sets are filtered and merged to obtain at least one target signaling set; finally, based on at least one target signaling set, the passenger flow of the target business district in the current specified time period is counted. Compared with the prior art, the present invention realizes more comprehensive and accurate passenger flow identification based on the signaling data of indoor base stations in the target business district. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0017] Figure 1One of the flow charts of a method for counting passenger flow in a business district provided in an embodiment of the present invention.

[0018] Figure 2 The second flowchart of a method for counting passenger flow in a business district provided in an embodiment of the present invention.

[0019] Figure 3 The third flowchart of a method for counting passenger flow in a business district provided in an embodiment of the present invention.

[0020] Figure 4 A schematic diagram of attribution determination and merging of a cluster signaling set provided in an embodiment of the present invention.

[0021] Figure 5 A schematic diagram of the structure of a device for counting passenger flow in a business district provided in an embodiment of the present invention.

[0022] Figure 6 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0024] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0026] It should be noted that, in the absence of conflict, the features in the embodiments of the present invention may be combined with each other.

[0027] Here, the key words or key terms involved in the present invention are first introduced: In the prior art, commercial district cameras are used to identify customer flow. Although this can accurately identify customer flow within the camera's field of view, commercial district cameras always have blind spots, which makes customer flow identification inaccurate.

[0028] There is also a conventional passenger flow counting method based on mobile phone signaling in the prior art: find all base stations within the spatial range of the business district, and perform passenger flow statistics based on the signaling data of all the found base stations. Although this method is more timely and convenient than the method of passenger flow identification based on cameras, it is to a certain extent subject to the density of base station layout in the area, and there are certain errors in the interpolation statistics of the crowd through the base station. In addition, the base stations found include indoor base stations inside the business district, rooftop tower base stations on the top of the buildings in the business district, and micro base stations installed outdoors near the business district based on street lamp poles, monitoring poles, etc. The signaling data of the micro base stations does not necessarily belong to the actual passenger flow of the business district, making the statistical results inaccurate.

[0029] Based on the discovery of the above technical problems, the inventors have proposed the following technical solutions to solve or improve the above problems through creative work. It should be noted that the defects in the solutions in the above prior art are the results obtained by the inventors after practice and careful research. Therefore, the discovery process of the above problems and the solutions proposed in the embodiments of the present application for the above problems below should all be the contributions made by the inventors to the present application in the process of invention and creation, and should not be understood as technical contents known to those skilled in the art.

[0030] With the development of mobile communication technology and the introduction of 5G (fifth generation mobile communication technology), more and more indoor places have introduced indoor base station equipment to ensure communication quality, which provides an important technical means for us to count indoor passenger flow based on indoor base stations. The present invention mainly implements passenger flow statistics based on mobile phone signaling data of indoor base stations, which is introduced in detail below.

[0031] Please refer to Figure 1 , Figure 1 A flowchart of a method for counting passenger flow in a business district provided in an embodiment of the present invention, wherein the execution subject of the method may be an electronic device, which may be but is not limited to a smart phone, a personal computer, a server, etc., and the counting method includes the following steps S101 to S104.

[0032] S101. Obtain a mobile phone signaling set consisting of signaling data of all indoor base stations in a target business district within a currently specified time period.

[0033] In this embodiment, the specified time period may be 1 hour, 2 hours, half a day, or a day, etc. In an optional example, the current specified time period may be the previous 1 hour or the previous 2 hours, which is only an example and is not limited here.

[0034] That is, the mobile phone signaling set may include all signaling data of all indoor base stations in the target business district within the current specified time period.

[0035] Among them, signaling data is generated when a user terminal uses a mobile communication network to interact with a base station (i.e., a public mobile communication base station, referred to as a base station). A signaling data may carry a user code (representing the user terminal used by the user), a base station code (representing the base station that interacts with the user terminal in signaling), a user location, and an interaction time (i.e., the timestamp when the signaling interaction occurs).

[0036] S102: Based on the user location in each piece of signaling data, cluster the mobile phone signaling set to obtain multiple clustered signaling sets.

[0037] In this embodiment, since the signaling data carries the user location, clustering can be performed based on density to eliminate the signaling data corresponding to the noise points, thereby obtaining a plurality of clustered signaling sets.

[0038] S103: Based on the location of the target business district and the user location in each piece of signaling data, all clustered signaling sets are filtered and merged to obtain at least one target signaling set.

[0039] In this embodiment, the clustered signaling set may contain signaling data corresponding to users who have not entered the target business district and have stayed outside the radiation range of the target business district. Also, if there are other adjacent business districts to the target business district, some clustered signaling sets may actually belong to the customer flow of other business districts, but because the business districts are close to each other, the user terminal is connected to the indoor base station of the target business district. Both of these situations need to be considered and filtered.

[0040] S104: Based on at least one target signaling set, count the passenger flow of the target business district in the current specified time period.

[0041] In this embodiment, based on all target signaling sets, they can be classified according to different user codes, and each user code is counted as one person's passenger flow, so as to calculate the passenger flow of the target business district in the current specified time period.

[0042] The statistical method, device, electronic device and readable storage medium for the passenger flow in a shopping district provided by the embodiment of the present invention first obtains a mobile phone signaling set composed of signaling data of all indoor base stations in the target shopping district in the current specified time period, and the signaling data includes the user position during the signaling interaction; then, based on the user position in each signaling data, the mobile phone signaling set is clustered to obtain multiple clustered signaling sets; then, based on the location of the target shopping district and the user position in each signaling data, all clustered signaling sets are filtered and merged to obtain at least one target signaling set; finally, based on at least one target signaling set, the passenger flow of the target shopping district in the current specified time period is counted. Compared with the prior art, the present invention realizes more comprehensive and accurate passenger flow identification based on the signaling data of indoor base stations in the target shopping district.

[0043] In an optional implementation, each indoor base station installed in the target business district can be searched and matched based on the business district name of the target business district, so as to obtain all signaling data of each indoor base station in the current specified time period. Correspondingly, the process of obtaining the mobile phone signaling set composed of the signaling data of all indoor base stations in the target business district in the current specified time period in the above step S101 can include the following sub-steps S1011~S1014.

[0044] S1011. Obtain each signaling data of all indoor base stations in the urban area where the target business district is located within the current specified time period to obtain a total set of mobile phone signaling.

[0045] In this embodiment, the urban area where the target business district is located may be a city (eg, Beijing) or an administrative district (eg, Chaoyang District, Beijing).

[0046] S1012. For each piece of signaling data in the mobile phone signaling collection, search the preset code mapping table for the base station name corresponding to the base station code contained in the signaling data to obtain the base station name corresponding to the signaling data.

[0047] In this embodiment, the preset code mapping table may include a mapping relationship between the base station name of the indoor base station and the base station code. The base station name carries the base station location attribute. For example, the indoor base station in the university town business district may be named: University Town Base Station Area 1, University Town Base Station Area 2, etc. This example is only an example and is not limited here.

[0048] S1013: Obtain the name of the target business district, and segment the name of the business district to obtain multiple name segmentations.

[0049] In this embodiment, the name of the target business district can be input by the query personnel. Sometimes the name of the business district is not very accurate, so it needs to be segmented. The segmentation method can adopt any segmentation method in the prior art. For example, the name of the target business district can be segmented based on the jieba Chinese vocabulary library to obtain multiple name segmentations. The segmentation method has two segmentation modes: scenic area mode and full mode. Any segmentation mode can be adopted.

[0050] In the optional example, assuming that the full mode is adopted, after the segmentation of "Phase I of Huanmao Plaza", three name segmentations can be obtained: "Huanmao", "Huanmao Plaza", and "Phase I of Plaza". This example is only an example and is not limited here.

[0051] S1014. Filter the mobile phone signaling set based on multiple name segmentations and the base station name corresponding to each signaling data in the mobile phone signaling set to obtain a mobile phone signaling set.

[0052] In this embodiment, for each signaling data in the total mobile phone signaling set, if the base station name corresponding to the signaling data does not contain any name participle or does not contain all name participles, the signaling data is filtered; otherwise, the signaling data is retained. In this way, by matching multiple name participles with the base station name corresponding to each signaling data in the total mobile phone signaling set, the total mobile phone signaling set can be filtered to obtain the mobile phone signaling set.

[0053] The above steps S1011~S1014 first obtain each signaling data of all indoor base stations in the urban area where the target business district is located within the current specified time period, and then use multiple name segmentations of the target business district to match the base station name corresponding to each signaling data one by one, thereby filtering out the mobile phone signaling set.

[0054] In another possible implementation, a base station list including all base stations in the urban area where the target business district is located can be obtained first, and the base station list includes the name of each base station; then the name of the business district is segmented to obtain multiple name segmentations; then for each base station in the base station list, multiple name segmentations are used to match the base station name of the base station. If the base station name does not contain any name segmentation or does not contain all name segmentations, the base station is filtered; otherwise, the base station is retained. In this way, the base station list can be filtered to obtain an indoor base station list, which includes all indoor base stations in the target business district. Finally, based on the indoor base station list, each signaling data of each indoor base station in the target business district in the current specified time period is obtained to obtain a mobile phone signaling set.

[0055] In an optional implementation, when a user is just passing by the target business district but has not entered the target business district or entered a shop on the ground floor of the target business district, the user terminal used by the user may also access the indoor base station of the target business district to exchange signals and generate signaling data. Therefore, the mobile phone signaling set obtained in the above step S101 may contain signaling data of the user terminal of the passing user. In order to ensure the accuracy of the subsequent passenger flow statistics, it is necessary to identify and filter out the signaling data of such passing users. Correspondingly, in Figure 1 Based on Figure 2 Before clustering in the above step S102, the statistical method may further include steps S10a and S10b.

[0056] S10a, classifying the mobile phone signaling set according to different user codes, and obtaining at least one piece of signaling data corresponding to each user code in the mobile phone signaling set.

[0057] It can be understood that in a specified period of time, a user terminal may have more than one signaling interaction with the indoor base station, so at least one signaling data will be generated. Therefore, in the mobile phone signaling set, the user codes in different signaling data may be the same or different. The mobile phone signaling set can be classified according to different user codes to obtain at least one signaling data corresponding to each user code in the mobile phone signaling set.

[0058] S10b. For each user code in the mobile phone signaling set, if there is only one signaling data including the user code, the signaling data is deleted; if there are at least two signaling data including the user code, the earliest interaction time and the latest interaction time are obtained from all signaling data including the user code to calculate the user residence time. If the user residence time is less than the preset time, all signaling data including the user code are deleted.

[0059] In this embodiment, for any user code in the mobile phone signaling set: if there is only one signaling data including the user code in the mobile phone signaling set, that is, the user residence time is 0, it is considered that the signaling data belongs to a passing user and needs to be deleted; if there are at least two signaling data including the user code in the mobile phone signaling set, then the earliest interaction time and the latest interaction time can be obtained from this part of the signaling data to calculate the user residence time. If the user residence time is less than the preset time, it is considered that this part of the signaling data belongs to a passing user and needs to be deleted. Among them, the size of the preset time can be set according to the actual situation, for example, the preset time can be set to 5s or 10s.

[0060] In an optional implementation, in an indoor base station scenario, the user positions in the signaling data generated by a large number of users using user terminals show obvious continuity and clustering in space, so if a density clustering algorithm is used, a large amount of signaling data can be aggregated into clusters of points, which can effectively eliminate noise points. Therefore, a density clustering algorithm based on spatial distance can be used in the above step S103. Its advantage is that it is not limited by the shape of the business district boundary and can identify the complex business district population gathering points, and can remove noise point data, and only retain multiple clustered signaling sets obtained by clustering, each of which includes multiple signaling data clustered based on user positions.

[0061] Specifically, the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm can be used for clustering. The DBSCAN algorithm requires two clustering parameters, the neighborhood radius eps and the preset minimum number of members minPts, to be set in advance. In this embodiment, the sample set consisting of K pieces of signaling data in the mobile phone signaling set filtered by the above steps S10a and S10b is: , any signaling data in the sample set ( ) is regarded as a sample point. The user location in the signaling data is the sample point location. In the clustering process, the distance between the two sample point locations is used to determine the sample point. The specific clustering process is an existing technology and will not be described in detail here.

[0062] In an optional implementation, the target business district has a certain radiation radius. Users outside the radiation radius near the target business district are beyond the radiation range of the target business district and do not belong to the business district passenger flow, so they need to be filtered out. Also, in the case of a nearby adjacent business district, the influence of the adjacent business district needs to be considered. After the above clustering, it can be determined whether each cluster signaling set belongs to the target business district or the adjacent business district, so as to determine whether the cluster signaling set participates in the subsequent passenger flow statistics. Correspondingly, in Figure 1 or Figure 2 Based on Figure 3 In the above step S103, based on the location of the target business district and the user location in each signaling data, all clustered signaling sets are filtered and merged to obtain at least one target signaling set, which may include the following sub-steps S1031~S1038.

[0063] S1031. For each signaling data in each clustered signaling set, calculate the distance between the user location in the signaling data and the location of the target business district. If the distance exceeds the preset radiation radius of the target business district, filter the signaling data to obtain each filtered clustered signaling set.

[0064] In this embodiment, the preset radiation radius of the target business district can be set as appropriate based on the business district's area and the business district's popularity. For example, the preset radiation radius can be determined based on the business district's area and the outward expansion coefficient. The outward expansion coefficient depends on the business district's popularity. If the business district is popular, the outward expansion coefficient can be larger (for example, 1.5). If the business district is popular, the outward expansion coefficient can be relatively small (for example, 1.1 or 1.2).

[0065] S1032. When there is a neighboring business district within a preset radius around the target business district, based on the respective positions of the target business district and the neighboring business district and the preset radiation radius, calculate the adjacent center points located in the radiation overlap area of ​​the target business district and the neighboring business district.

[0066] In this embodiment, based on the respective positions and preset radiation radii of the target business district and the adjacent business district, the radiation ranges of the target business district and the adjacent business district can be determined, so that the radiation overlapping area of ​​the two radiation ranges can be determined, and then the center point of the radiation overlapping area can be calculated, that is, as the adjacent center point.

[0067] Among them, due to the different areas of business districts and the different popularity of business districts, the preset radiation radius of the target business district and the adjacent business district may be different or the same. For example, the preset radiation radius of the target business district and the adjacent business district is 90m, 100m or 75m respectively. The preset radius can be set based on the actual situation, and whether there is a neighboring business district within the preset radius near the target business district can determine whether the straight-line distance between the target business district and the neighboring business district is less than the preset radius. For example, the preset radius can be 125m or 100m. This example is only an example and is not limited here.

[0068] S1033: For each filtered cluster signaling set, calculate a fitting center point corresponding to the filtered cluster signaling set based on a user position in each signaling data in the filtered cluster signaling set.

[0069] S1034: If the fitting center point is located in the radiation overlap area and the projection point of the fitting center point on the commercial district line is located between the adjacent center point and the adjacent commercial district, the filtered cluster signaling set is deleted.

[0070] S1035: If the fitting center point is located in the radiation overlap area and the projection point of the fitting center point on the business district line is not located between the adjacent center point and the adjacent business district, the filtered cluster signaling set is used as the target signaling set.

[0071] S1036: If the fitting center point is not located in the radiation overlapping area, retain the filtered cluster signaling set.

[0072] S1037: merge at least two filtered cluster signaling sets that are density-reachable and density-connected into one target signaling set, and use each filtered cluster signaling set that is isolated in spatial distribution as the target signaling set.

[0073] S1038. When there is no neighboring business district within a preset radius around the target business district, directly merge at least two filtered cluster signaling sets that are density-reachable and density-connected into one target signaling set, and use each filtered cluster signaling set that is isolated in spatial distribution as the target signaling set.

[0074] Optionally, a distribution scatter plot can be drawn on a map based on the user location in the signaling data, and different filtered clustered signaling sets are distinguished by different colors. Then, based on the distribution of points of different colors on the distribution scatter plot, it can be determined whether there are at least two filtered clustered signaling sets that have density reachability and density connection.

[0075] It should be noted that, when there is a neighboring business district within the preset radius near the target business district, step S1032 is executed after executing step S1031, and then the attribution judgment is performed for each filtered cluster signaling set, that is, after executing step S1033 once, one of step S1034, step S1035, and step S1036 will continue to be executed; and when there is no neighboring business district within the preset radius near the target business district, step S1038 is directly executed after executing step S1031.

[0076] In the optional example, please combine Figure 4 , assuming that the respective locations of the target business district A and the adjacent business district B are as follows Figure 4 As shown, the preset radiation radius of the target business district A is d1, and the preset radiation radius of the adjacent business district B is d2. The radiation range of the target business district A is the circular area with a radius of d1, and the radiation range of the target business district B is the circular area with a radius of d2. The overlapping shadow area of ​​the two is the radiation overlapping area, so that the adjacent center point C can be calculated.

[0077] Assumptions Figure 4 The clustered points represented by different colors in the figure represent 7 filtered cluster signaling sets (set a~set g). First, it is necessary to determine whether each set belongs to the target business district A or the adjacent business district B, and then merge them.

[0078] (1) The fitting center points of set a, set b, set f, and set g are not located in the radiation overlap area, so it can be confirmed that the four sets completely belong to the target business district A; (2) The fitting center point of set d is located in the radiation overlap area and the projection point of the fitting center point on the business district line (i.e., line AB) is located between the adjacent center point C and the adjacent business district B. Therefore, it can be considered that set d is the signaling data generated by the passenger flow of the adjacent business district B and needs to be deleted; (3) The fitting center points of set e and set c are both located in the radiation overlap area, and the projection points of the fitting center points on the business district line (i.e., line AB) are not located between the adjacent center point C and the adjacent business district B. Therefore, it can be temporarily considered that set e and set c belong to the target business district A, and set e and set c are directly regarded as the target signaling sets participating in the subsequent passenger flow statistics.

[0079] In this way, after the attribution judgment, it is necessary to merge the sets a, b, f and g: Figure 4 It can be clearly seen that set f and set g have density reachability and density connectivity, and the two can be merged into a target signaling set; while set a and set b are isolated in spatial distribution and do not have density reachability and density connectivity with other sets. All sets a and set b belong to the target signaling set.

[0080] It should be noted that, combined with Figure 4 The examples are merely illustrative and are not intended to be limiting.

[0081] In an optional implementation, in order to verify the accuracy of passenger flow statistics, a conventional passenger flow statistics method based on mobile phone signaling can be used to count the passenger flow data of the target business district in N consecutive specified time periods as a reference, and then the accuracy of the passenger flow data of the target business district in N consecutive specified time periods obtained based on the statistical method provided by the present invention is judged. Correspondingly, the passenger flow statistics method of the business district can also include the following steps S107~S109.

[0082] S107 , obtaining reference passenger flow and passenger flow for each of N consecutive designated time periods.

[0083] In this embodiment, the reference passenger flow of each of the N consecutive designated time periods can be calculated using a conventional passenger flow counting method based on mobile phone signaling. The passenger flow of each of the N consecutive designated time periods is obtained using the counting method provided by the present invention.

[0084] S108, taking the reference passenger flow as the independent variable and the passenger flow as the dependent variable, a linear regression equation is obtained by performing linear fitting based on the reference passenger flow and passenger flow of each of N consecutive designated time periods.

[0085] S109. Based on the linear regression equation, calculate the goodness of fit corresponding to the target business district to measure the accuracy of the customer flow in each of the N consecutive specified time periods.

[0086] In this embodiment, the goodness of fit The accuracy of passenger flow in each of N consecutive specified time periods can be measured. The closer it is to 1, the more accurate the passenger flow statistics are.

[0087] Optionally, when there is a neighboring business district within a preset radius around the target business district, after the attribution judgment, for the target signaling set located in the radiation overlap area and the projection point of the fitting center point on the business district line is not located between the adjacent center point and the neighboring business district, it is only temporarily considered that it belongs to the signaling data generated by the passenger flow of the target business district. In fact, it may not belong to the signaling data generated by the passenger flow of the target business district. Therefore, an overlapping area label can be set for this target signaling set during the attribution judgment, so that when it is determined that the passenger flow statistics result is distorted later, this target signaling set can be discarded and the passenger flow statistics can be re-performed. For example, combined with Figure 4 , set e and set c are regarded as target signaling sets and both can set overlapping area labels.

[0088] Accordingly, after determining the accuracy of the passenger flow statistics of the target business district, the goodness of fit corresponding to the target business district can be compared with the goodness of fit corresponding to the adjacent business district to compare the accuracy of the passenger flow statistics of the two, and further adjust the one with poor accuracy. Correspondingly, the passenger flow statistics method of the business district can also include the following steps S110~S111.

[0089] S110. When there is a neighboring business district within a preset radius around the target business district, obtain the goodness of fit corresponding to the neighboring business district.

[0090] In this embodiment, the goodness of fit corresponding to the adjacent business district is also determined based on the reference passenger flow and passenger flow of each of the N consecutive specified time periods. The calculation method is the same as that of the target business district, which will not be elaborated here.

[0091] S111. If the goodness of fit corresponding to the target business district is lower than the goodness of fit corresponding to the adjacent business district, then for each specified time period, the target signaling set with overlapping area labels is removed from all target signaling sets corresponding to the target business district in the specified time period, and the passenger flow of the target business district in the specified time period is recalculated.

[0092] In this embodiment, the overlapping area label may represent that the corresponding target signaling set belongs to the indoor base station of the target business district or the indoor base station of the neighboring business district.

[0093] If the goodness of fit corresponding to the target business district is lower than that corresponding to the adjacent business district, it means that the accuracy of the passenger flow statistics of the target business district is lower than that of the adjacent business district. Therefore, for the target business district, it is necessary to discard the target signaling set with overlapping area labels and recalculate the passenger flow in each specified time period.

[0094] On the contrary, if the goodness of fit corresponding to the target business district is higher than that corresponding to the neighboring business district, it means that the accuracy of the passenger flow statistics results of the target business district is higher than that of the neighboring business district. Therefore, for the neighboring business district, for each specified time period, it is also necessary to remove the target signaling set with overlapping area labels from all target signaling sets corresponding to the neighboring business district in the specified time period and then recalculate the passenger flow of the neighboring business district in the specified time period.

[0095] It should be noted that the execution order of each step in the above method embodiment is not limited to that shown in the drawings, and the execution order of each step shall be based on the actual application situation.

[0096] Compared with the prior art, the embodiments of the present invention have the following beneficial effects.

[0097] First, compared with the prior art method of using cameras to count customer flow in a business district and the conventional customer flow counting method based on mobile phone signaling, the present invention uses the signaling data of indoor base stations in the target business district to achieve more comprehensive and accurate customer flow identification.

[0098] Secondly, the present invention calculates the user residence time of each user code based on the interaction time and user code in each signaling data in the mobile phone signaling set, thereby filtering out passing users with short user residence time to ensure the accuracy of subsequent passenger flow identification.

[0099] Third, the present invention uses a density clustering algorithm to cluster mobile phone signaling sets, which can not only exclude noise points, but also, when there are adjacent and close adjacent business districts in the target business district, it can also judge one by one whether each clustered signaling set located in the radiation overlap area belongs to the target business district or the adjacent business district, so as to determine whether the clustered signaling set participates in the subsequent passenger flow statistics. And in the attribution judgment, by setting an overlapping area label for the target signaling set located in the radiation overlap area and the projection point of the fitting center point on the business district line is not located between the adjacent center point and the adjacent business district, when it is determined that the passenger flow statistics result is distorted in the subsequent process, the target signaling set is discarded and the passenger flow statistics are re-performed.

[0100] Fourthly, the present invention can use the conventional passenger flow statistics method based on mobile phone signaling to count the passenger flow data of the target business district in N consecutive specified time periods as a reference, and then judge the accuracy of the passenger flow data of the target business district in N consecutive specified time periods obtained based on the statistical method provided by the present invention. The judgment method is to perform linear analysis to calculate the goodness of fit corresponding to the target business district, and use the goodness of fit to measure the accuracy of the passenger flow of each of the N consecutive specified time periods.

[0101] Fifth, when there are adjacent business districts that are close to the target business district, the goodness of fit corresponding to the target business district can be compared with the goodness of fit corresponding to the adjacent business district. If the goodness of fit corresponding to the target business district is lower than the goodness of fit corresponding to the adjacent business district, then for each specified time period, the target signaling set with overlapping area tags is removed from all target signaling sets corresponding to the target business district in the specified time period, and the passenger flow of the target business district in the specified time period is recalculated. The overlapping area tag represents that the corresponding target signaling set belongs to the indoor base station of the target business district or the indoor base station of the adjacent business district. This helps to further improve the accuracy of passenger flow statistics.

[0102] In order to execute the corresponding steps in the above method embodiment and various possible implementation modes, an implementation method of a device for counting passenger flow in a business district is provided below.

[0103] See also Figure 5 , Figure 5 The schematic diagram of the structure of the device for counting passenger flow in a business district provided by an embodiment of the present invention is shown. The device for counting passenger flow in a business district 200 comprises: a signaling acquisition module 210 , a clustering module 220 , a filtering and merging module 230 and a passenger flow counting module 240 .

[0104] The signaling acquisition module 210 is used to obtain a mobile phone signaling set composed of signaling data of all indoor base stations in the target business district within the current specified time period; the signaling data includes the user location during the signaling interaction; The clustering module 220 is used to cluster the mobile phone signaling set based on the user location in each signaling data to obtain multiple clustered signaling sets; The filtering and merging module 230 is used to filter and merge all clustered signaling sets based on the location of the target business district and the user location in each signaling data to obtain at least one target signaling set; The passenger flow statistics module 240 is used to count the passenger flow of the target business district in the current specified time period based on at least one target signaling set.

[0105] Optionally, when the signaling acquisition module 210 is used to obtain the mobile phone signaling set composed of the signaling data of all indoor base stations in the target business district within the current specified time period, it can be specifically used to: obtain each signaling data of all indoor base stations in the urban area where the target business district is located within the current specified time period to obtain the total mobile phone signaling set; the signaling data also includes a base station code; for each signaling data in the total mobile phone signaling set, search the base station name corresponding to the base station code contained in the signaling data from a preset coding mapping table to obtain the base station name corresponding to the signaling data; obtain the business district name of the target business district, and segment the business district name to obtain multiple name segmentations; based on the multiple name segmentations and the base station name corresponding to each signaling data in the total mobile phone signaling set, filter the total mobile phone signaling set to obtain the mobile phone signaling set.

[0106] Optionally, the signaling acquisition module 210 is used to filter the mobile phone signaling set based on the multiple name participles and the base station name corresponding to each signaling data in the mobile phone signaling set. When obtaining the mobile phone signaling set, it can be specifically used for: for each signaling data in the mobile phone signaling set, if the base station name corresponding to the signaling data does not contain any of the name participles or does not contain all of the name participles, filtering the signaling data; otherwise, retaining the signaling data to obtain the mobile phone signaling set.

[0107] Optionally, the filtering and merging module 230 is used to filter and merge all clustered signaling sets based on the location of the target business district and the user location in each of the signaling data to obtain at least one target signaling set. Specifically, it can be used to: for each signaling data in each of the clustered signaling sets, calculate the distance between the user location in the signaling data and the location of the target business district; if the distance exceeds the preset radiation radius of the target business district, filter the signaling data to obtain each filtered clustered signaling set; when there is a neighboring business district within a preset radius near the target business district, calculate the area within the radiation overlap area between the target business district and the neighboring business district based on their respective locations and preset radiation radii. adjacent center points; for each of the filtered cluster signaling sets, the fitting center point corresponding to the filtered cluster signaling set is calculated based on the user position in each signaling data in the filtered cluster signaling set; if the fitting center point is located in the radiation overlap area and the projection point of the fitting center point on the business district line is located between the adjacent center point and the adjacent business district, the filtered cluster signaling set is deleted; if the fitting center point is located in the radiation overlap area and the projection point of the fitting center point on the business district line is not located between the adjacent center point and the adjacent business district, the filtered cluster signaling set is used as the target signaling set; if the fitting center point is not located in the radiation overlap area, the filtered cluster signaling set is retained; At least two filtered cluster signaling sets with density reachability and density connectivity are merged into a target signaling set, and each filtered cluster signaling set isolated in spatial distribution is used as the target signaling set; when there is no adjacent business district within a preset radius near the target business district, at least two filtered cluster signaling sets with density reachability and density connectivity are directly merged into a target signaling set, and each filtered cluster signaling set isolated in spatial distribution is used as the target signaling set.

[0108] Optionally, the shopping district passenger flow statistics device 200 may further include an accurate measurement module 250 for: obtaining a reference passenger flow and passenger flow for each of N consecutive specified time periods; taking the reference passenger flow as an independent variable and the passenger flow as a dependent variable, performing linear fitting based on the reference passenger flow and passenger flow for each of the N consecutive specified time periods to obtain a linear regression equation; based on the linear regression equation, calculating the goodness of fit corresponding to the target shopping district to measure the accuracy of the passenger flow for each of the N consecutive specified time periods.

[0109] Optionally, the shopping district passenger flow statistics device 200 may further include an accurate comparison module 260 for: when there is a neighboring shopping district within a preset radius around the target shopping district, obtaining the goodness of fit corresponding to the neighboring shopping district; if the goodness of fit corresponding to the target shopping district is lower than the goodness of fit corresponding to the neighboring shopping district, then for each of the specified time periods, the passenger flow of the target shopping district in the specified time period is recalculated after removing the target signaling set with an overlapping area label from all target signaling sets corresponding to the target shopping district in the specified time period, and the overlapping area label represents that the corresponding target signaling set belongs to the indoor base station of the target shopping district or the indoor base station of the neighboring shopping district.

[0110] Optionally, the signaling data also includes interaction time and user code, and the user codes in different signaling data are the same or different. The statistical device 200 for passenger flow in the shopping district may also include a passing user judgment module 270 for: classifying the mobile phone signaling set according to the different user codes, and obtaining at least one signaling data corresponding to each user code in the mobile phone signaling set; for each user code in the mobile phone signaling set, if there is only one signaling data including the user code, then delete the signaling data; if there are at least two signaling data including the user code, then obtain the earliest interaction time and the latest interaction time from all signaling data including the user code to calculate the user residence time, and if the user residence time is less than the preset time, then delete all signaling data including the user code.

[0111] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the device 200 for counting passenger flow in a shopping district described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0112] See also Figure 6 , Figure 6 The electronic device 300 includes a processor 310 , a memory 320 , and a bus 330 , wherein the processor 310 is connected to the memory 320 via the bus 330 .

[0113] The memory 320 may be used to store software programs, for example, software programs corresponding to the device 200 for counting passenger flow in a business district provided in an embodiment of the present invention. The processor 310 executes various functional applications and data processing to implement the method for counting passenger flow in a business district provided in an embodiment of the present invention by running the software programs stored in the memory 320.

[0114] Among them, the memory 320 can be but is not limited to: RAM (Random Access Memory), ROM (Read Only Memory), FLASH (Flash Memory), PROM (Programmable Read-Only Memory), EPROM (Erasable Programmable Read-Only Memory), EEPROM (Electric Erasable Programmable Read-Only Memory), etc.

[0115] The processor 310 may be an integrated circuit chip with signal processing capability. The processor 310 may be a general-purpose processor, including: CPU (Central Processing Unit), NP (Network Processor), etc.; it may also be: DSP (Digital Signal Processing), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0116] Understandably, Figure 6 The structure shown is for illustration only. The electronic device 300 may also include Figure 6 More or fewer components as shown, or with Figure 6 Different configurations are shown. Figure 6 Each component shown in the figure can be implemented by hardware, software or a combination thereof.

[0117] The embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the statistical method of the commercial district passenger flow disclosed in the above embodiment is implemented. The computer-readable storage medium can be, but is not limited to, various media that can store program codes, such as a USB flash drive, a mobile hard disk, a ROM, a RAM, a PROM, an EPROM, an EEPROM, a FLASH disk, or an optical disk.

[0118] In summary, the embodiments of the present invention provide a method, device, electronic device and readable storage medium for counting passenger flow in a shopping district. First, a mobile phone signaling set consisting of signaling data of all indoor base stations in the target shopping district in the current specified time period is obtained, and the signaling data includes the user location during signaling interaction; then, based on the user location in each signaling data, the mobile phone signaling set is clustered to obtain multiple clustered signaling sets; then, based on the location of the target shopping district and the user location in each signaling data, all clustered signaling sets are filtered and merged to obtain at least one target signaling set; finally, based on at least one target signaling set, the passenger flow of the target shopping district in the current specified time period is counted. Compared with the prior art, the present invention realizes more comprehensive and accurate passenger flow identification based on the signaling data of indoor base stations in the target shopping district.

[0119] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A statistical method for passenger flow in a business district, characterized in that: include: Obtain the mobile phone signaling set consisting of the signaling data of all indoor base stations in the target business district within the current specified time period; The signaling data includes the user location during the signaling interaction; Based on the user location in each piece of the signaling data, clustering the mobile phone signaling set to obtain multiple clustered signaling sets; Based on the location of the target business district and the user location in each piece of the signaling data, all clustered signaling sets are filtered and merged to obtain at least one target signaling set; Based on the at least one target signaling set, the customer flow of the target business district in the current specified time period is counted.

2. The method according to claim 1, characterized in that The step of obtaining a mobile phone signaling set composed of signaling data of all indoor base stations in the target business district within the current specified time period includes: Obtain each signaling data of all indoor base stations in the urban area where the target business district is located within the current specified time period to obtain a total set of mobile phone signaling; the signaling data also includes a base station code; For each piece of signaling data in the mobile phone signaling total set, searching the preset code mapping table for the base station name corresponding to the base station code contained in the signaling data to obtain the base station name corresponding to the signaling data; Obtaining the name of the target business district, and segmenting the name of the business district to obtain multiple name segmentations; Based on the multiple name participles and the base station name corresponding to each signaling data in the mobile phone signaling collection, the mobile phone signaling collection is filtered to obtain the mobile phone signaling collection.

3. The method according to claim 2, characterized in that The step of filtering the mobile phone signaling set based on the multiple name segmentations and the base station name corresponding to each signaling data in the mobile phone signaling set to obtain the mobile phone signaling set includes: For each signaling data in the total mobile phone signaling set, if the base station name corresponding to the signaling data does not contain any of the name participles or does not contain all of the name participles, the signaling data is filtered; otherwise, the signaling data is retained to obtain the mobile phone signaling set.

4. The method according to claim 1, characterized in that: The step of filtering and merging all clustered signaling sets based on the location of the target business district and the user location in each piece of the signaling data to obtain at least one target signaling set includes: For each piece of signaling data in each of the clustered signaling sets, calculating the distance between the user location in the signaling data and the location of the target business district, and if the distance exceeds a preset radiation radius of the target business district, filtering the signaling data to obtain each filtered clustered signaling set; If there is a neighboring business district within a preset radius around the target business district, based on the respective positions and preset radiation radius of the target business district and the neighboring business district, calculate the adjacent center points located in the radiation overlap area between the target business district and the neighboring business district; For each of the filtered cluster signaling sets, the fitting center point corresponding to the filtered cluster signaling set is calculated based on the user position in each signaling data in the filtered cluster signaling set; if the fitting center point is located in the radiation overlap area and the projection point of the fitting center point on the business district line is located between the adjacent center point and the adjacent business district, the filtered cluster signaling set is deleted; if the fitting center point is located in the radiation overlap area and the projection point of the fitting center point on the business district line is not located between the adjacent center point and the adjacent business district, the filtered cluster signaling set is used as the target signaling set; if the fitting center point is not located in the radiation overlap area, the filtered cluster signaling set is retained; Merging at least two filtered cluster signaling sets that have density-reachable and density-connected relationships into a target signaling set, and taking each filtered cluster signaling set that is isolated in spatial distribution as the target signaling set; When there is no neighboring business district within a preset radius around the target business district, at least two filtered cluster signaling sets that are density-reachable and density-connected are directly merged into one target signaling set, and each filtered cluster signaling set that is isolated in spatial distribution is used as the target signaling set.

5. The method according to claim 1, characterized in that The method further comprises: Obtain reference passenger flow and passenger flow for each of N consecutive specified time periods; Taking the reference passenger flow as an independent variable and the passenger flow as a dependent variable, a linear regression equation is obtained by performing linear fitting based on the reference passenger flow and passenger flow of each of the N consecutive specified time periods; Based on the linear regression equation, the goodness of fit corresponding to the target business district is calculated to measure the accuracy of the customer flow of each of the N consecutive specified time periods.

6. The method according to claim 5, characterized in that The method further comprises: If there is a neighboring business district within a preset radius around the target business district, obtaining the goodness of fit corresponding to the neighboring business district; If the goodness of fit corresponding to the target business district is lower than the goodness of fit corresponding to the neighboring business district, then for each of the specified time periods, the target signaling set with an overlapping area label is removed from all target signaling sets corresponding to the target business district in the specified time period, and the passenger flow of the target business district in the specified time period is recalculated. The overlapping area label represents that the corresponding target signaling set belongs to the indoor base station of the target business district or the indoor base station of the neighboring business district.

7. The method according to claim 1, characterized in that The signaling data also includes an interaction time and a user code, and the user codes in different signaling data are the same or different; Before the step of clustering the mobile phone signaling set based on the user location to obtain a plurality of clustered signaling sets, the method further includes: Classifying the mobile phone signaling set according to the different user codes to obtain at least one piece of signaling data corresponding to each user code in the mobile phone signaling set; For each user code in the mobile phone signaling set, if there is only one signaling data including the user code, the signaling data is deleted; if there are at least two signaling data including the user code, the earliest interaction time and the latest interaction time are obtained from all signaling data including the user code to calculate the user stay time, and if the user stay time is lower than the preset time, all signaling data including the user code are deleted.

8. A statistical device for passenger flow in a business district, characterized in that: include: The signaling acquisition module is used to obtain the mobile phone signaling set composed of the signaling data of all indoor base stations in the target business district within the current specified time period; The signaling data includes the user location during the signaling interaction; A clustering module, configured to cluster the mobile phone signaling set based on the user location in each piece of the signaling data to obtain a plurality of clustered signaling sets; A filtering and merging module, configured to filter and merge all clustered signaling sets based on the location of the target business district and the user location in each piece of signaling data, to obtain at least one target signaling set; The passenger flow statistics module is used to count the passenger flow of the target business district in the current specified time period based on the at least one target signaling set.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the memory stores a software program, and when the electronic device is running, the processor executes the software program to implement the method for counting the passenger flow in a business district as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for counting the passenger flow in a business district according to any one of claims 1 to 7 is implemented.

Images