A method for determining a point of interest and an electronic device

Abstract

The application discloses a method for determining a point of interest and an electronic device. The method comprises: obtaining first crowd-sourced data; the first crowd-sourced data comprises crowd-sourced data corresponding to a payment behavior of a user and / or crowd-sourced data corresponding to a wireless fidelity (WiFi) connected to a store; determining a corresponding relationship between a store name and a WiFi name based on the first crowd-sourced data; determining first WiFi information corresponding to the first store name from a WiFi snapshot table according to the corresponding relationship; and determining one or more POIs corresponding to the first store name based on the first WiFi information. Through the application, the POIs can be mined, the POIs can be determined efficiently and accurately, and the normal execution of a recommendation service can be ensured.

Description

Technical Field

[0001] This application relates to the field of computers, and more particularly to a method for determining points of interest and an electronic device. Background Technology

[0002] A point of interest (POI) is typically used to identify a small object. In a geographic information system (GIS), a POI can be a building, a shop, a coffee shop, an oil drum, a gas station, a bus stop, etc. A POI can contain basic information such as name, address, category, and location information (e.g., latitude and longitude coordinates).

[0003] With the development of internet technology, service providers can generate geofences for specific areas based on crowdsourced data from user transactions. A geofence is a virtual fence that defines a virtual geographical boundary. When an electronic device enters or leaves a specific geographical area, or moves within that area, it can receive corresponding service requests. A geofence can consist of base station information, wireless fidelity (WiFi) information, latitude and longitude information, etc. Taking payment geofences as an example, crowdsourced data from user payment transactions can be collected to generate a payment geofence for a particular store. When a user connects to a base station within this payment geofence, a continuous WiFi scan is performed. When the WiFi scan result matches the WiFi information within the payment geofence, it can be considered that the user has entered the store, and appropriate payment applications or store service applications can be recommended to the user.

[0004] When collecting crowdsourced data on user payment behavior, it's possible that users may not actually visit the store but instead order and pay in advance by scanning a pre-prepared store QR code or through a brand application (APP) or mini-program. This can lead to inconsistencies between the environmental information of the payment behavior collected by the crowdsourced data and the surrounding environment of the store, ultimately resulting in decreased accuracy of payment fences. To improve the accuracy of payment fences, store POI data can be used for verification. By verifying whether the latitude and longitude information of the generated payment fence matches the latitude and longitude information of the POI, erroneous payment fences can be eliminated. However, currently, POI data is usually obtained manually in-store or through third-party platforms, which is characterized by high barriers to entry and long processing times. Therefore, how to efficiently and accurately determine POIs has become an urgent problem to be solved. Summary of the Invention

[0005] This application provides a method and electronic device for determining points of interest (POIs). Based on the method described in this application, POIs can be determined efficiently and accurately.

[0006] In a first aspect, this application provides a method for determining Points of Interest (POIs), the method comprising: acquiring first crowdsourcing data; the first crowdsourcing data including crowdsourcing data corresponding to a user's payment behavior and / or crowdsourcing data corresponding to a Wi-Fi connection to a store; determining a correspondence between a store name and a Wi-Fi name based on the first crowdsourcing data; determining first Wi-Fi information corresponding to a first store name from a Wi-Fi snapshot table according to the correspondence; and determining one or more POIs corresponding to the first store name based on the first Wi-Fi information.

[0007] Based on the method described in the first aspect, electronic devices establish a correspondence between store names and WiFi names using crowdsourced data corresponding to user payment transactions and / or crowdsourced data corresponding to Wi-Fi connections to stores. Then, a WiFi snapshot table is generated using all the user's crowdsourced data. Based on this correspondence, the WiFi information corresponding to the first store name is determined from the WiFi snapshot table. Based on this first WiFi information, one or more Points of Interest (POIs) corresponding to the first store name can be efficiently and accurately identified, enabling the mining of brand store POIs. This method is simple and convenient, eliminating the need for manual in-store visits or third-party platforms to obtain POI data. It achieves rapid iteration, high coverage, and high accuracy in maintaining the POI database, and is also more conducive to ensuring the normal execution of subsequent recommendation services.

[0008] In one possible implementation, the first WiFi information includes the identifiers of one or more WiFi networks scanned during each WiFi scan and the signal strength of those WiFi networks. Determining one or more Points of Interest (POIs) corresponding to the first store name based on the first WiFi information includes: determining one or more candidate POIs corresponding to the first store name based on the first WiFi information; determining the similarity in the number of times any two WiFi networks in each candidate POI are simultaneously scanned and the similarity in the signal strength of those two WiFi networks; grouping each candidate POI based on the similarity in the number of scans and the similarity in the signal strength to obtain one or more first groups; clustering the WiFi networks in each first group based on the latitude and longitude information of the WiFi networks in each first group to obtain one or more sub-clusters corresponding to each first group; and determining the main cluster in each of the one or more sub-clusters corresponding to each first group as a POI. Based on this method, it is possible to mine brand store POIs and quickly and effectively identify situations such as new store openings, closures, and differentiation of nearby stores, achieving high coverage and accuracy.

[0009] In one possible implementation, each candidate POI is grouped based on the frequency similarity and the signal strength similarity to obtain one or more first groups. This includes: determining a weight value between any two WiFi networks based on the frequency similarity and the signal strength similarity; grouping each candidate POI based on the weight value to obtain one or more groups; filtering a second group from these one or more groups to obtain one or more first groups; the WiFi networks included in the second group do not belong to the WiFi network corresponding to the user's payment behavior. This method helps improve the accuracy of POI determination and ensures effective mining of brand store POIs. Furthermore, due to the freedom in naming WiFi networks, WiFi networks that are not associated with the brand store can also use the same name, which could affect the accuracy of subsequent POI determination. Therefore, it is necessary to remove groups that do not correspond to the brand store to improve the accuracy of POI determination.

[0010] In one possible implementation, the similarity of these counts satisfies: Where n represents the number of times any two WiFi networks in a candidate POI are scanned simultaneously, N represents the maximum number of times any two WiFi networks in a candidate POI are scanned simultaneously, and ln(·) represents the logarithm calculation with the constant e as the base.

[0011] In one possible implementation, the signal strength similarity satisfies:

[0012] wifi_rssi_similarity=e -λ*wifi_distance*wifi_distance ;

[0013] in, The signal strengths of any two WiFi networks simultaneously detected in a candidate POI are denoted as rssi1 and rssi2, where rssi1 ≥ rssi2. λ, α, and β represent preset constants, wifi_distance represents the absolute maximum distance between the two WiFi networks, and wifi_rssi_similarity represents the similarity of the signal strengths.

[0014] In one possible implementation, determining one or more candidate POIs corresponding to the first store name based on the first WiFi information includes: determining one or more first POIs corresponding to the first store name based on the first WiFi information; filtering second POIs from the one or more first POIs to obtain one or more candidate POIs; wherein the WiFi included in the second POIs does not belong to the WiFi corresponding to the user's payment behavior. Due to the freedom in naming WiFi networks, WiFi networks not belonging to the brand's stores can also use the same name, which will affect the accuracy of subsequent POI determination. Therefore, it is necessary to remove candidate POIs for which no payment behavior occurred at the brand's store to improve the accuracy of POI determination.

[0015] In one possible implementation, determining the first WiFi information corresponding to the first store name from the WiFi snapshot table based on the correspondence includes: determining the WiFi name corresponding to the first store name based on the correspondence; and determining the first WiFi information corresponding to the first store name from the WiFi snapshot table based on the WiFi name corresponding to the first store name, where the WiFi snapshot table is generated based on all user-sourced crowdsourced data. This approach uses richer crowdsourced data to generate the WiFi snapshot table, resulting in a wider coverage of WiFi information in the generated table, which is more conducive to improving the coverage of subsequent POI determination. Furthermore, due to the universality of WiFi name naming for stores, determining the WiFi name corresponding to the first store name based on the correspondence between store names and WiFi names allows for the identification of more first WiFi information corresponding to the first store name, further improving the coverage of subsequent POI mining.

[0016] In one possible implementation, the center latitude and longitude information of each POI is the latitude and longitude information corresponding to that main cluster. Based on this method, outliers in subclusters can be eliminated, improving the accuracy of POI determination.

[0017] Secondly, this application provides a device for determining points of interest. This device can be an electronic device, a device within an electronic device, or a device compatible with an electronic device. The device can also be a chip system, and it can execute the methods performed by the electronic device in the first aspect. The function of the device can be implemented in hardware or by hardware executing corresponding software. The hardware or software includes one or more units corresponding to the aforementioned functions. These units can be software and / or hardware. The operations and beneficial effects of the device for determining points of interest can be found in the methods and beneficial effects described in the first aspect above; repetitions will not be repeated.

[0018] Thirdly, this application provides an electronic device including one or more processors and one or more memories. The one or more memories are coupled to the one or more processors, the memories being used to store a computer program, and the processors being used to invoke the computer program to cause the electronic device to perform the method described in the first aspect.

[0019] Fourthly, this application provides a chip system for use in an electronic device, the chip system including at least one processor and an interface for receiving instructions and transmitting them to the at least one processor; the at least one processor executes the instructions to cause the electronic device to perform the method described in the first aspect.

[0020] Fifthly, this application provides a system for determining points of interest, which includes an electronic device; wherein the electronic device is used to perform the method as described in the first aspect.

[0021] In a sixth aspect, this application provides an apparatus for determining points of interest, the apparatus including functions or units for performing the method as described in any of the first aspects.

[0022] In a seventh aspect, this application provides a computer storage medium having a computer program / instructions stored thereon, which, when executed by a processor, implements the method and steps described in the first aspect.

[0023] Eighthly, this application provides a computer program product including a computer program / instructions that, when executed by a processor, implement the method and steps described in the first aspect. Attached Figure Description

[0024] Figure 1A This is a schematic diagram of a recommendation service based on payment fence provided in an embodiment of this application;

[0025] Figure 1B This is a schematic diagram illustrating an inconsistency between the environmental information of a user's payment behavior and the information of the surrounding environment of the store, provided in an embodiment of this application.

[0026] Figure 2 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of this application;

[0027] Figure 3 This is a software structure block diagram of an electronic device provided in an embodiment of this application;

[0028] Figure 4 This is a flowchart illustrating a method for determining points of interest provided in an embodiment of this application;

[0029] Figure 5This is a schematic diagram illustrating the process by which an electronic device determines the first WiFi information corresponding to the first store name from a WiFi snapshot table based on a correspondence relationship, according to an embodiment of this application.

[0030] Figure 6A This is a schematic diagram of a process provided in this application embodiment of an electronic device for determining one or more POIs corresponding to a first store name based on first WiFi information;

[0031] Figure 6B This is a schematic diagram of a connection relationship provided in an embodiment of this application;

[0032] Figure 6C This is a connection diagram provided in an embodiment of the present application, using WiFi BSSID as a node;

[0033] Figure 6D This is a schematic diagram illustrating the number of times any two WiFi networks in a candidate POI are simultaneously scanned, according to an embodiment of this application.

[0034] Figure 6E This is a schematic diagram illustrating the signal strength difference between two WiFi networks when any two WiFi networks are simultaneously scanned in a candidate POI, as provided in an embodiment of this application.

[0035] Figure 7A This is a flowchart illustrating how an electronic device, based on frequency similarity and signal strength similarity, groups each candidate POI to obtain one or more first groups, according to an embodiment of this application.

[0036] Figure 7B This is a schematic diagram of a weighted undirected graph of WiFi similarity provided in an embodiment of this application;

[0037] Figure 7C This is a schematic diagram illustrating the grouping of a weighted undirected graph using the LPA algorithm, as provided in an embodiment of this application.

[0038] Figure 8A This is a flowchart illustrating another method for determining points of interest provided in an embodiment of this application;

[0039] Figure 8B This is a schematic diagram illustrating a first crowdsourcing data method provided in this application embodiment, which uses crowdsourcing data corresponding to a user's payment behavior and / or crowdsourcing data corresponding to a connection to the store's WiFi.

[0040] Figure 9 This is a schematic diagram of the structure of a point of interest determination device provided in an embodiment of this application;

[0041] Figure 10 This is a schematic diagram of the structure of a chip provided in an embodiment of this application. Detailed Implementation

[0042] The technical solutions in the embodiments of this application will be clearly and thoroughly described below with reference to the accompanying drawings. In the description of the embodiments of this application, unless otherwise stated, " / " means "or," for example, A / B can mean A or B; the word "and / or" in the text is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Furthermore, in the description of the embodiments of this application, "multiple" refers to two or more than two.

[0043] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature, and in the description of the embodiments of this application, unless otherwise stated, "multiple" means two or more.

[0044] The term "user interface (UI)" used in the following embodiments of this application refers to the medium interface through which an application or operating system interacts and exchanges information with a user. It realizes the conversion between the internal form of information and the form that the user can accept. The user interface is source code written in a specific computer language such as Java or Extensible Markup Language (XML). The interface source code is parsed and rendered on the electronic device, ultimately presenting content that the user can recognize. A common form of user interface is the graphical user interface (GUI), which refers to a user interface related to computer operation displayed graphically. It can be visual interface elements such as time, date, text, icons, buttons, menus, tabs, text boxes, dialog boxes, status bars, navigation bars, and widgets displayed on the screen of an electronic device.

[0045] To facilitate understanding of the solutions provided in the embodiments of this application, the relevant concepts involved in the embodiments of this application are introduced below:

[0046] 1. Point of Interest (POI)

[0047] Points of Interest (POIs) are typically used to identify objects that occupy a small area. In a Geographic Information System (GIS), a POI can be a building, a shop, a coffee shop, an oil drum, a gas station, a bus stop, etc. A POI can contain basic information such as name, address, category, and location information (e.g., latitude and longitude coordinates). The location information can include only the latitude and longitude coordinates of a single location point, or it can include the latitude and longitude coordinates of a center point and a radius, although this radius is usually very small.

[0048] 2. Crowdsourced data collection

[0049] Crowdsourcing data collection is a method of data collection that utilizes public networks. It involves distributing data collection tasks across a large network, and the resulting data can be called crowdsourced data. Crowdsourcing effectively utilizes public resources, reducing collection costs, improving efficiency, and ensuring high timeliness. For example, real-time traffic information for location maps can be collected through crowdsourcing. Users can upload large amounts of vehicle speed and location information to the backend via location software, allowing the backend to analyze the data and generate comprehensive real-time traffic information.

[0050] 3. Wireless Fidelity (WiFi) fingerprint

[0051] A WiFi fingerprint consists of several WiFi information entries, such as the WiFi basic service set identifier (BSSID), the WiFi name (SSID), the WiFi signal strength indicator (RSSI), and the WiFi latitude and longitude information. Each WiFi fingerprint corresponds to a Point of Interest (POI). This allows for comparison between the WiFi information scanned by an electronic device and the WiFi fingerprint. If the two are very similar, the electronic device can be considered to be within the POI corresponding to that WiFi fingerprint.

[0052] In a wireless local area network (WLAN), the WiFi BSSID stands for Basic Service Set Identifier. It is a unique identifier used to identify the physical address of a wireless access point (AP) or wireless router. The BSSID is composed of the AP's MAC address and the network interface card's MAC address, uniquely identifying a specific wireless access point within a wireless network. BSSIDs are typically represented in hexadecimal, for example, "00:1A:2B:3C:4D:5E". In a wireless network, the BSSID distinguishes different wireless access points, enabling devices to correctly connect to a specific wireless network.

[0053] A WiFi SSID is a Service Set Identifier in a Wireless Local Area Network (WLAN). It's the name of a wireless network used to identify a specific wireless network. The SSID is set by the network administrator on the wireless router or wireless access point, and users can find and connect to a specific SSID by searching for available wireless networks. An SSID is typically a human-readable string, such as "MyWiFiNetwork". In a wireless network, the SSID is used to distinguish different wireless networks so that users can select and connect to the wireless network they want.

[0054] 4. Cell

[0055] A base station (cell tower) is a device in a mobile communication network used to provide wireless communication services. It is a fixed wireless communication facility used to provide signal coverage and communication connectivity to mobile devices. A base station typically consists of an antenna, transmitter, receiver, and related equipment for wireless communication with mobile devices. The coverage area of ​​a base station is divided into multiple cells, each covered by one base station. Therefore, a base station is also called a cell base station. Mobile devices in mobile communication networks communicate with base stations to perform functions such as voice calls, SMS transmission, and data transmission. Base stations play a crucial role in mobile communication networks; they constitute the infrastructure of mobile communication networks and provide mobile communication services to users.

[0056] A cell, also known as a cellular unit, refers to the area covered by a base station in a cellular mobile communication system. Within this area, mobile stations can communicate wirelessly with the base station. Cell handover, on the other hand, refers to the process in a wireless communication system where, when a mobile station moves from one cell (referring to a base station or its coverage area) to another, the connected base station needs to be switched to maintain uninterrupted communication for the mobile user.

[0057] 5. DBSCAN clustering algorithm

[0058] DBSCAN is a density-based spatial clustering algorithm, short for density-based spatial clustering of applications with noise. This algorithm divides regions with sufficient density into clusters, and can discover clusters of arbitrary shapes in noisy spatial databases. Each cluster is the largest set of density-connected points. Intuitively, the DBSCAN clustering algorithm can find all dense regions of sample points and treat each dense region as a cluster.

[0059] Specifically, the DBSCAN clustering algorithm has two parameters: neighborhood radius (R) and minimum number of points (minpoints). A cluster is considered dense when the number of points within the neighborhood radius is greater than the minimum number of points. Points with a number of samples within the neighborhood radius R greater than or equal to minpoints are called core points; points that are not core points but are within the neighborhood of a core point are called boundary points; and points that are neither core points nor boundary points are noise points.

[0060] (1) If P is a core point and Q is within the R neighborhood of P, then P is said to be density-accessible to Q. Any core point is density-accessible to itself, and density accessibility is not symmetric. If P is density-accessible to Q, then Q is not necessarily density-accessible to P.

[0061] (2) If there exist core points P1, P2, P3, ..., Pn, and the density is directly accessible from P1 to P2, from P2 to P3, from P(n-1) to Pn, and from Pn to Q, then the density is accessible from P1 to Q. The density accessibility does not have symmetry.

[0062] (3) If there exists a core point S such that S is density-reachable from both P and Q, then P and Q are density-connected. Density connectivity is symmetric; if P and Q are density-connected, then Q and P must also be density-connected. Two density-connected points belong to the same cluster.

[0063] (4) If two points are not density-connected, then the two points are not density-connected. Two points that are not density-connected belong to different clusters, or there are noise points in them.

[0064] In summary, the DBSCAN algorithm defines a cluster simply as the set of samples connected by the highest density derived from density reachability relations. Specifically, a DBSCAN cluster can have one or more core points. If there is only one core point, all other non-core point samples in the cluster are within the R-neighborhood of this core point. If there are multiple core points, then any core point in the R-neighborhood of any given core point must contain another core point; otherwise, these two core points are not density-reachable. The set of all samples within the R-neighborhoods of these core points forms a DBSCAN cluster.

[0065] 6. Regular payment

[0066] Regular payment refers to payment behavior that follows a pattern. For example, if a user frequently makes payments at a certain time and place, this can be identified as regular payment.

[0067] 7. Payment Fence

[0068] With the development of internet technology, service providers can generate geofences for specific areas based on crowdsourced data from user requests for services. A geofence is essentially a virtual fence defining a virtual geographical boundary, an application of location-based services (LBS). A geofence typically corresponds to a Point of Interest (POI). When an electronic device enters or leaves a specific geographical area, or moves within that area, it can receive corresponding service requests. A geofence can consist of base station information, Wi-Fi information, latitude and longitude information, etc.

[0069] Taking payment fences as an example, crowdsourced data of user payment behavior can be collected to generate a payment fence for a store. When a user connects to a base station within the payment fence, a continuous WiFi scan will be performed. When the WiFi scan result matches the WiFi information within the payment fence, it can be considered that the user has entered the store, and the user can be recommended the corresponding payment application or store service application.

[0070] like Figure 1A As shown, before the user enters store A, the phone is not connected to the base station within the payment area of ​​store A, and the phone displays... Figure 1A The user interface shown in (a) includes various applications (APPs), and the first APP recommended in the recommendation bar of the user interface is file application 10.

[0071] After a user enters store A, their mobile phone connects to the base station within the payment fence of store A and continuously scans for WiFi. Once the WiFi scan result matches the WiFi information within the payment fence, it is confirmed that the mobile phone is inside store A, and the phone displays [indicating WiFi activity]. Figure 1A The user interface shown in (b) is now configured so that the first recommended app in the recommendation bar is the service application 11 of store A. Users can quickly access the service interface by clicking on the service application 11 of store A, at which point the phone displays... Figure 1A The service interface shown in (c) includes services for store A such as home delivery, in-store pickup, online store, store information, and member center, thus realizing the function of quick business through scene recognition.

[0072] After the user leaves store A, the phone disconnects from the base station within the payment area of ​​store A, and the phone displays... Figure 1A The user interface shown in (d) has its first recommended app in the recommendation bar reverted to File Application 10.

[0073] When collecting crowdsourced data on user payment behavior, such as Figure 1B As shown, it's possible that a user might not actually visit store A, but instead scan a pre-prepared store QR code or place an order in advance at location B via the store's app or mini-program. This could lead to inconsistencies between the environmental information of the payment behavior collected by crowdsourced data and the surrounding environment of the store, ultimately resulting in decreased accuracy of payment fencing. To improve the accuracy of payment fencing, store POI data can be used for verification. By verifying whether the latitude and longitude information of the generated payment fencing matches the latitude and longitude information of the POI, erroneous payment fencing can be eliminated. However, currently, POI data is usually obtained manually in-store or through third-party platforms, which is characterized by high barriers to entry and long processing times. Therefore, how to efficiently and accurately determine POIs has become an urgent problem to be solved.

[0074] Therefore, in order to efficiently and accurately determine POIs and ensure the normal execution of subsequent recommendation services, this application provides a method for determining points of interest and an electronic device. In specific implementation, the method for determining points of interest mentioned herein can be executed by electronic device 100. Electronic device 100 can be a server, laptop, tablet, personal computer (PC), ultra-mobile personal computer (UMPC), desktop computer, personal digital assistant (PDA), etc.; it can also be a mobile phone, wearable electronic device with wireless communication capabilities (such as a smartwatch), smart vehicle, etc., but is not limited to these. Among them, the server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery network (CDN), and big data and artificial intelligence platforms. Electronic device 100 can be configured with a display screen and can have a pre-installed application (APP), such as a payment APP, a store service APP, etc., which are not limited here.

[0075] The hardware structure of electronic device 100 is described below. Please refer to [link / reference]. Figure 2 , Figure 2 This is a schematic diagram of the hardware structure of the electronic device 100 provided in the embodiments of this application.

[0076] Electronic device 100 may include processor 110, external memory interface 120, internal memory 121, universal serial bus (USB) interface 130, charging management module 140, power management module 141, battery 142, antenna 1, antenna 2, mobile communication module 150, wireless communication module 160, audio module 170, speaker 170A, receiver 170B, microphone 170C, headphone jack 170D, sensor module 180, button 190, motor 191, indicator 192, camera 193, display screen 194, and subscriber identification module (SIM) card interface 195, etc. The sensor module 180 may include a pressure sensor 180A, a gyroscope sensor 180B, a barometric pressure sensor 180C, a magnetic sensor 180D, an accelerometer sensor 180E, a distance sensor 180F, a proximity sensor 180G, a fingerprint sensor 180H, a temperature sensor 180J, a touch sensor 180K, an ambient light sensor 180L, a bone conduction sensor 180M, etc.

[0077] It is understood that the structures illustrated in the embodiments of the present invention do not constitute a specific limitation on the electronic device 100. In other embodiments of this application, the electronic device 100 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0078] Processor 110 may include one or more processing units, such as: application processor (AP), modem processor, graphics processing unit (GPU), image signal processor (ISP), controller, memory, video codec, digital signal processor (DSP), baseband processor, and / or neural network processing unit (NPU), etc. Different processing units may be independent devices or integrated into one or more processors.

[0079] The controller can be the nerve center and command center of the electronic device 100. The controller can generate operation control signals according to the instruction opcode and timing signals to complete the control of fetching and executing instructions.

[0080] The processor 110 may also include a memory for storing instructions and data. In some embodiments, the memory in the processor 110 is a cache memory. This memory can store instructions or data that the processor 110 has just used or that are used repeatedly. If the processor 110 needs to use the instruction or data again, it can directly retrieve it from the memory. This avoids repeated accesses, reduces the waiting time of the processor 110, and thus improves the efficiency of the system. The processor 110 retrieves the instructions or data stored in the memory to cause the electronic device 100 to execute the point of interest determination method performed by the electronic device in the following method embodiment.

[0081] In some embodiments, the processor 110 may include one or more interfaces. Interfaces may include an inter-integrated circuit (I2C) interface, an inter-integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input / output (GPIO) interface, a subscriber identity module (SIM) interface, and / or a universal serial bus (USB) interface, etc.

[0082] The charging management module 140 is used to receive charging input from the charger. The charger can be a wireless charger or a wired charger.

[0083] The power management module 141 is used to connect the battery 142, the charging management module 140, and the processor 110. The power management module 141 receives input from the battery 142 and / or the charging management module 140 to power the processor 110, internal memory 121, external memory, display 194, camera 193, and wireless communication module 160, etc. In some other embodiments, the power management module 141 may also be located in the processor 110.

[0084] The wireless communication function of electronic device 100 can be realized through antenna 1, antenna 2, mobile communication module 150, wireless communication module 160, modem processor and baseband processor, etc.

[0085] Antenna 1 and antenna 2 are used to transmit and receive electromagnetic wave signals. Each antenna in electronic device 100 can be used to cover one or more communication frequency bands. Different antennas can also be multiplexed to improve antenna utilization. For example, antenna 1 can be multiplexed as a diversity antenna for a wireless local area network. In some other embodiments, the antennas can be used in conjunction with tuning switches.

[0086] The mobile communication module 150 can provide solutions for wireless communication, including 2G / 3G / 4G / 5G, applied to the electronic device 100. The mobile communication module 150 may include at least one filter, switch, power amplifier, low noise amplifier (LNA), etc. The mobile communication module 150 can receive electromagnetic waves via antenna 1, and perform filtering, amplification, and other processing on the received electromagnetic waves before transmitting them to a modem processor for demodulation. The mobile communication module 150 can also amplify the signal modulated by the modem processor and convert it into electromagnetic waves for radiation via antenna 1. In some embodiments, at least some functional modules of the mobile communication module 150 may be housed in the processor 110. In some embodiments, at least some functional modules of the mobile communication module 150 and at least some modules of the processor 110 may be housed in the same device.

[0087] A modem processor may include a modulator and a demodulator. The modulator modulates the low-frequency baseband signal to be transmitted into a mid-to-high frequency signal. The demodulator demodulates the received electromagnetic wave signal into a low-frequency baseband signal. The demodulator then transmits the demodulated low-frequency baseband signal to the baseband processor for processing. After processing by the baseband processor, the low-frequency baseband signal is transmitted to the application processor.

[0088] The wireless communication module 160 can provide solutions for wireless communication applications on the electronic device 100, including wireless local area networks (WLAN) (such as Wi-Fi networks), Bluetooth (BT), BLE broadcasting, global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), and infrared (IR) technologies. The wireless communication module 160 can be one or more devices integrating at least one communication processing module. The wireless communication module 160 receives electromagnetic waves via antenna 2, performs frequency modulation and filtering of the electromagnetic wave signals, and sends the processed signal to processor 110. The wireless communication module 160 can also receive signals to be transmitted from processor 110, perform frequency modulation and amplification, and convert them into electromagnetic waves for radiation via antenna 2.

[0089] In some embodiments, antenna 1 of electronic device 100 is coupled to mobile communication module 150, and antenna 2 is coupled to wireless communication module 160, so that electronic device 100 can communicate with networks and other devices through wireless communication technology.

[0090] Electronic device 100 implements display functions through a GPU, a display screen 194, and an application processor. The GPU is a microprocessor for image processing, connected to the display screen 194 and the application processor. The GPU is used to perform mathematical and geometric calculations and for graphics rendering. Processor 110 may include one or more GPUs, which execute program instructions to generate or modify display information.

[0091] The display screen 194 is used to display images, videos, etc. The display screen 194 includes a display panel. In some embodiments, the electronic device 100 may include one or N display screens 194, where N is a positive integer greater than 1.

[0092] Electronic device 100 can perform shooting functions through an ISP, camera 193, video codec, GPU, display 194, and application processor. The ISP processes data fed back from the camera 193. The camera 193 captures still images or video. The digital signal processor processes digital signals, including digital image signals and other digital signals. The video codec compresses or decompresses digital video. Electronic device 100 can support one or more video codecs.

[0093] NPU stands for Neural-Network (NN) Computing Processor. By drawing inspiration from the structure of biological neural networks, such as the transmission patterns between neurons in the human brain, it can quickly process input information and continuously learn on its own.

[0094] The external memory interface 120 can be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the electronic device 100. The external memory card communicates with the processor 110 through the external memory interface 120 to perform data storage functions.

[0095] Internal memory 121 can be used to store computer executable program code, which includes instructions. Processor 110 executes various functional applications and data processing of electronic device 100 by running the instructions stored in internal memory 121. Internal memory 121 may include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as a sound playback function), etc. The data storage area may store data created during the use of electronic device 100 (such as audio data), etc. Furthermore, internal memory 121 may include high-speed random access memory and may also include non-volatile memory, such as flash memory devices.

[0096] Electronic device 100 can implement audio functions, such as music playback and recording, through audio module 170, speaker 170A, receiver 170B, microphone 170C, headphone jack 170D, and application processor.

[0097] The audio module 170 is used to convert digital audio information into analog audio signals for output, and also to convert analog audio input into digital audio signals. The audio module 170 can also be used for encoding and decoding audio signals. In some embodiments, the audio module 170 may be located in the processor 110, or some functional modules of the audio module 170 may be located in the processor 110.

[0098] The speaker 170A, also known as a "loudspeaker," is used to convert audio electrical signals into sound signals. The receiver 170B, also known as a "handpiece," is used to convert audio electrical signals into sound signals. The microphone 170C, also known as a "microphone" or "voice transducer," is used to convert sound signals into electrical signals. The headphone jack 170D is used to connect wired headphones. The pressure sensor 180A is used to sense pressure signals and convert them into electrical signals.

[0099] In some embodiments, a pressure sensor 180A may be disposed on a display screen 194. A gyroscope sensor 180B may be used to determine the motion posture of the electronic device 100. A barometric pressure sensor 180C is used to measure barometric pressure. A magnetic sensor 180D includes a Hall effect sensor. An accelerometer sensor 180E can detect the magnitude of acceleration of the electronic device 100 in various directions (generally triaxial). A distance sensor 180F is used to measure distance. A proximity sensor 180G may include, for example, a light-emitting diode (LED) and a photodetector. An ambient light sensor 180L is used to sense ambient light intensity. A fingerprint sensor 180H is used to collect fingerprints. A temperature sensor 180J is used to detect temperature. A touch sensor 180K, also called a "touch panel," may be disposed on the display screen 194. The touch sensor 180K and the display screen 194 together form a touch screen, also called a "touchscreen." The touch sensor 180K is used to detect touch operations applied to or near it. A bone conduction sensor 180M can acquire vibration signals. Buttons 190 include a power button, volume buttons, etc. A motor 191 can generate vibration feedback. An indicator 192 can be an indicator light, used to indicate charging status, battery level changes, and also to indicate messages, missed calls, notifications, etc. A SIM card interface 195 is used to connect a SIM card.

[0100] It is understood that the structures illustrated in the embodiments of this application do not constitute a specific limitation on the electronic device 100. In other embodiments of this application, the electronic device 100 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0101] Furthermore, an operating system runs on top of the aforementioned components. Examples include iOS and Android. The operating system of electronic device 100 can adopt a layered architecture, event-driven architecture, microkernel architecture, microservice architecture, or cloud architecture. This application embodiment uses the layered architecture Android system as an example to exemplify the software structure of electronic device 100. It should be noted that although this application embodiment uses the Android system as an example for illustration, its basic principles are equally applicable to electronic devices with other operating systems.

[0102] Figure 3This is a software structure block diagram of the electronic device 100 according to an embodiment of this application. The software structure adopts a layered architecture, which divides the software into several layers, each with a clear role and division of labor. The layers communicate with each other through software interfaces. In this embodiment, the operating system (taking the Android system, which runs on an AP as an example) can be divided into six layers, from top to bottom: application layer (APP), application framework layer (FWK), Android runtime and system library, hardware abstraction layer (HAL), kernel layer, and hardware layer.

[0103] The application layer can include a series of application packages. For example... Figure 3 As shown, the application package can include applications such as camera, gallery, calendar, call, map, navigation, WLAN, Bluetooth, music, video, SMS, payment, and store services. The application layer can also include the system UI, which displays the electronic device's interface, such as the payment interface or store service interface. For example, when a user arrives at a store, the payment interface or store service interface can be displayed on the electronic device, improving the user experience.

[0104] The application framework layer provides application programming interfaces (APIs) and a programming framework for applications in the application layer. The application framework layer includes some predefined functions. For example... Figure 3 As shown, the application framework layer may include a window manager, content provider, view system, phone manager, resource manager, notification manager, camera service, etc., and this application embodiment does not impose any limitations on this.

[0105] The window manager is used to manage windowed applications. It can retrieve screen size, determine the presence of a status bar, lock the screen, and capture screenshots, among other things.

[0106] Content providers store and retrieve data, making that data accessible to applications. This data may include videos, images, audio, made and received phone calls, browsing history and bookmarks, phone books, etc.

[0107] A view system includes visual controls, such as controls for displaying text and controls for displaying images. View systems can be used to build applications. A display interface can consist of one or more views. For example, a display interface including a text notification icon could include views for displaying text and views for displaying images.

[0108] The phone manager is used to provide communication functions for electronic device 100. For example, it manages call status (including connection and disconnection).

[0109] The file explorer provides applications with various resources, such as localized strings, icons, images, layout files, video files, and more.

[0110] The notification manager allows applications to display notifications in the status bar. These notifications can be used to deliver informational messages and can disappear automatically after a short pause, requiring no user interaction. For example, the notification manager can be used to notify users of completed downloads or message alerts. The notification manager can also display notifications as icons or scrolling text in the top status bar, such as notifications from background applications, or as dialog boxes on the screen. Examples include displaying text messages in the status bar, emitting sounds, vibrating electronic devices, and flashing indicator lights.

[0111] The camera service is the core process module of the camera framework. It mainly provides API interface functions to the application layer and calls the camera hardware abstraction layer through HIDL (hardware interface definition language).

[0112] The Android runtime consists of core libraries and a virtual machine. The Android runtime is responsible for scheduling and managing the Android system.

[0113] The core library consists of two parts: one part is the functionalities that need to be called by the Java language, and the other part is the Android core library.

[0114] The application layer and application framework layer run in a virtual machine. The virtual machine executes the Java files of the application layer and application framework layer as binary files. The virtual machine is used to perform functions such as object lifecycle management, stack management, thread management, security and exception management, and garbage collection.

[0115] System libraries can include multiple functional modules. For example: surface manager, media libraries, 3D graphics processing libraries (e.g., OpenGL ES), 2D graphics engines (e.g., SGL), etc.

[0116] The Surface Manager is used to manage the display subsystem and provides the blending of 2D and 3D layers for multiple applications.

[0117] The media library supports playback and recording of various common audio and video formats, as well as still image files. It also supports multiple audio and video encoding formats.

[0118] The 3D graphics processing library is used to implement 3D graphics drawing, image rendering, compositing, and layer processing.

[0119] A 2D graphics engine is a graphics engine for 2D drawing.

[0120] The Hardware Abstraction Layer (HAL) is an interface layer located between the operating system kernel and the hardware circuitry, its purpose being to abstract the hardware. It hides the platform-specific hardware interface details, providing the operating system with a virtual hardware platform. For example, the HAL encapsulates Linux kernel drivers, providing an interface to the upper layers and shielding them from the implementation details of the lower-level hardware. Figure 3 As shown, the hardware abstraction layer can include Wi-Fi HAL, audio HAL, camera HAL, etc.

[0121] The kernel layer is the layer between hardware and software. It is the core of an operating system, the first layer of software extension based on the hardware, providing the most basic functions of the operating system. It is the foundation for the operating system's operation, responsible for managing system processes, memory, device drivers, files, and network systems, and determining the system's performance and stability. The kernel layer can include display drivers, audio drivers, camera drivers, sensor drivers, etc. Among them, the camera driver is the driver layer for camera devices, mainly responsible for interaction with the hardware.

[0122] The hardware layer includes displays, cameras, sensors, etc.

[0123] Based on the above, the method for determining points of interest provided in this application will be further described in detail below. For example... Figure 4 As shown, the method for determining the point of interest includes the following steps S401 to S404. Figure 4 The method shown can be implemented by the aforementioned electronic device. Alternatively, Figure 4 The method shown can be executed by a chip in an electronic device, but this application does not limit the implementation. Figure 4 The method will be illustrated using an electronic device as the executing entity. This electronic device can be a server.

[0124] S401, Electronic devices acquire first crowdsourced data.

[0125] In this embodiment, the electronic device can obtain first crowdsourced data through a public network. This first crowdsourced data may include crowdsourced data corresponding to a user's payment transaction and / or crowdsourced data corresponding to connecting to a store's WiFi. The store can be various chain brand stores. Of course, the first crowdsourced data may also include other data, which is not limited here.

[0126] Specifically, taking a user's mobile phone as an example, the crowdsourced data corresponding to a user's payment behavior can include WiFi information (such as WiFi BSSID, WiFi SSID, WiFi signal strength, etc.) scanned by the user's mobile phone when making a payment to a store, as well as the location information of the user's mobile phone when collecting the WiFi information, and may also include the base station information accessed by the user's mobile phone.

[0127] Crowdsourced data related to connecting to the store's WiFi can include WiFi information scanned by users when they connect to the store's WiFi using their mobile phones (such as WiFi BSSID, WiFi SSID, WiFi signal strength, etc.), as well as the location information of the user's mobile phone when collecting this WiFi information, and may also include the base station information accessed by the user's mobile phone. It should be noted that the crowdsourced data related to connecting to the store's WiFi specifically refers to the crowdsourced data (such as scanned WiFi information) generated when users are in the vicinity of the store and use their mobile phones to connect to the store's WiFi terminal.

[0128] For example, suppose a chain brand is named "aaa" and has three stores: store A, store B, and store C. The names of stores A, B, and C are all "aaa". The electronic device needs to obtain the first crowdsourced data for these chain brand stores. This first crowdsourced data may include crowdsourced data corresponding to user payments made at store A and / or crowdsourced data related to connecting to store A's Wi-Fi; it may also include crowdsourced data corresponding to user payments made at store B and / or connecting to store B's Wi-Fi; it may also include crowdsourced data corresponding to user payments made at store C and / or connecting to store C's Wi-Fi; and it may also include the user's phone's location information and the base station information accessed by the user's phone when collecting this Wi-Fi information.

[0129] S402. The electronic device determines the correspondence between the store name and the WiFi name based on the first crowdsourced data.

[0130] In this embodiment, the electronic device can obtain a high-precision WiFi fingerprint (including WiFi BSSID, WiFi SSID, WiFi signal strength, etc.) of a brand store based on the first crowdsourced data. A correspondence between the store name and the WiFi name is established by performing descriptive statistics on the WiFi names in the WiFi fingerprint. Taking a brand store as an example, the WiFi name scanned when a user makes a payment is obtained. The name of the current brand store is determined by the payee at the time of the payment. Then, combining the brand's Chinese name, Chinese abbreviation, English name, English abbreviation, and pinyin, the WiFi name with the highest semantic similarity to the current brand store name is determined from the scanned WiFi names. This WiFi name with the highest semantic similarity is used as the WiFi name corresponding to the current brand store name, thereby establishing a correspondence between the brand store name and the WiFi name.

[0131] Of course, other methods can also be used to establish the correspondence between store names and WiFi names. For example, the WiFi name (i.e., WiFi SSID) of the brand store can be collected by actually visiting the store, thereby establishing the correspondence between the brand store name and the WiFi name. This is not a limitation.

[0132] For example, the correspondence between store name and WiFi name can be shown in Table 1. When the store name is "aaa", the corresponding WiFi name (WiFi SSID) is "aaa-free-WiFi"; when the store name is "bbb", the corresponding WiFi name (WiFi SSID) is "bbb-FREE-WiFi" and "bbb-wifi"; when the store name is "ccc", the corresponding WiFi name (WiFi SSID) is "ccc-WiFi".

[0133] Table 1

[0134] Store Name (Name of the Brand Store) WiFi Name (WiFi SSID) aaa aaa-free-WiFi bbb bbb-FREE-WiFi, bbb-wifi ccc ccc-WiFi

[0135] S403. The electronic device determines the first WiFi information corresponding to the first store name from the WiFi snapshot table based on the correspondence.

[0136] In this embodiment, the WiFi snapshot table is generated based on all the user's crowdsourced data (e.g., crowdsourced data corresponding to user payment transactions, crowdsourced data corresponding to user connections to or disconnections from store WiFi, crowdsourced data generated when the user is traveling). For example, the WiFi snapshot table can be generated using data such as the WiFi BSSID and WiFi SSID collected when the user makes a payment transaction, the WiFi BSSID and WiFi SSID collected when the user connects to or disconnects from store WiFi, and the WiFi BSSID and WiFi SSID collected when the user is traveling, as well as the location information of the user's mobile phone when collecting WiFi data. Compared to the first crowdsourced data mentioned above, the crowdsourced data used to generate the WiFi snapshot table is richer, and the generated WiFi snapshot table has a wider coverage, which is more conducive to improving the accuracy of subsequent POI determination. It should be noted that the latitude and longitude information of each WiFi network can be generated by clustering and calculating the location information of the user's mobile phone when collecting WiFi data; it is also possible to determine whether the WiFi network is fixed by collecting the location information of the user's mobile phone when collecting WiFi data over a period of time, thereby obtaining fixed-point information.

[0137] Specifically, as shown in Table 2 below, this WiFi lookup table can include the identifier (WiFi BSSID), WiFi name (WiFi SSID), latitude and longitude information, and location information (i.e., whether the WiFi is fixed) of one or more WiFi networks scanned during each WiFi scan. Of course, this WiFi lookup table may also include other information, which is not limited here. For example, in the first WiFi scan, the scanned WiFi BSSID is BSSID1; the WiFi SSID is aaa-free-WiFi; the latitude and longitude information of this WiFi is 113°46′E, 22°27′N; and the location information is fixed. In the second WiFi scan, the scanned WiFi BSSID is BSSID2; the WiFi SSID is aaa-free-WiFi; the latitude and longitude information of this WiFi is 113°48′E, 22°25′N; and the location information is not fixed. In the third WiFi scan, the detected WiFi BSSID was BSSID3; the WiFi SSIDs were bbb-free-WiFi and bbb-wifi; the latitude and longitude information of this WiFi was 114°30'E, 22°42'N; the location information was fixed. In the fourth WiFi scan, the detected WiFi BSSID was BSSID4; the WiFi SSID was ccc-wifi; the latitude and longitude information of this WiFi was 114°32'E, 22°40'N; the location information was fixed.

[0138] Table 2

[0139]

[0140] In one possible implementation, the specific implementation of the electronic device determining the first WiFi information corresponding to the first store name from the WiFi snapshot table based on the correspondence may include the following steps s11 and s12, such as... Figure 5 As shown.

[0141] s11. The electronic device determines the WiFi name corresponding to the first store name based on the correspondence.

[0142] In practical implementation, electronic devices can determine the WiFi name corresponding to the first store name based on the correspondence between store names and WiFi names. For example, assuming the first store name is "aaa", then according to the correspondence shown in Table 1 above, the WiFi name (WiFi SSID) corresponding to the first store name can be determined to be "aaa-free-WiFi".

[0143] Based on this method, since stores use a common naming convention for WiFi, the WiFi name corresponding to the first store name can be determined according to the correspondence between the store name and the WiFi name. Subsequently, using this WiFi name, more information about the first WiFi corresponding to the first store name can be determined, which is more conducive to improving the coverage of subsequent POI mining.

[0144] s12. The electronic device determines the first WiFi information corresponding to the first store name from the WiFi snapshot table based on the WiFi name corresponding to the first store name.

[0145] In its implementation, the WiFi snapshot table stores information such as the identifier (WiFi BSSID), WiFi name (WiFi SSID), latitude and longitude information, and location information (i.e., whether the WiFi is fixed) of one or more WiFi networks scanned each time a WiFi scan is performed. Electronic devices can query this WiFi snapshot table to find the fixed WiFi BSSID and latitude and longitude information for each WiFi network scanned with the first store name. Here, the fixed WiFi BSSID and latitude and longitude information correspond to the first WiFi network associated with the first store name.

[0146] Taking Table 2 as an example, assuming the WiFi name corresponding to the first store name is aaa-free-WiFi, we can find that in the first WiFi scan, the scanned WiFi BSSID is BSSID1; the WiFi SSID is aaa-free-WiFi; the latitude and longitude information of this WiFi is 113°46'E, 22°27'N; and the location information is fixed. In the second WiFi scan, the scanned WiFi BSSID is BSSID2; the WiFi SSID is aaa-free-WiFi; the latitude and longitude information of this WiFi is 113°48'E, 22°25'N; and the location information is not fixed. The electronic device needs to select the WiFi with fixed location information, i.e., WiFi BSSID1, whose latitude and longitude information is 113°46'E, 22°27'N.

[0147] Similarly, electronic devices can determine all WiFi BSSIDs corresponding to the first store name and the latitude and longitude information of these WiFi networks (i.e., the first WiFi information) from the WiFi snapshot table based on the WiFi name corresponding to the first store name.

[0148] Based on this method, since the crowdsourced data used to generate the WiFi snapshot table is richer, the WiFi information coverage in the generated WiFi snapshot table is also wider, and the first WiFi information corresponding to the first store name determined from the WiFi snapshot table is also richer, which is more conducive to improving the coverage of subsequent POI determination.

[0149] S404. The electronic device determines one or more POIs corresponding to the first store name based on the first WiFi information.

[0150] In this embodiment, the electronic device uses the first WiFi information corresponding to the first store name to determine one or more Points of Interest (POIs) corresponding to the first store name, thereby realizing the mining of brand store POIs. The specific process of determining one or more first POIs is described in detail below.

[0151] In one possible implementation, the first WiFi information corresponding to the first store name includes: fixed WiFi BSSID and latitude and longitude information of each WiFi SSID corresponding to the first store name, selected from the WiFi snapshot table; additionally, it may include the signal strength of these selected WiFi networks determined from all user-sourced data. Of course, the first WiFi information may also include other information, which is not limited here.

[0152] For example, assuming the WiFi SSID corresponding to the first store name is aaa-free-WiFi, the information of the first WiFi corresponding to the first store name is shown in Table 3 below. The WiFi identifiers detected during the first WiFi scan are BSSID1 and BSSID2. The signal strength of the WiFi corresponding to BSSID1 is rssi1, and its latitude and longitude information is A. The signal strength of the WiFi corresponding to BSSID2 is rssi2, and its latitude and longitude information is B. During the second WiFi scan, the WiFi identifiers detected are BSSID1 and BSSID3. The signal strength of the WiFi corresponding to BSSID1 is rssi3, and its latitude and longitude information is A. The signal strength of the WiFi corresponding to BSSID3 is rssi4, and its latitude and longitude information is C.

[0153] Table 3

[0154]

[0155]

[0156] In other words, assuming WiFi BSSID is used as a node, one BSSID identifies a WiFi terminal, and each BSSID is associated with the signal strength of the corresponding WiFi and the latitude and longitude information of the corresponding WiFi.

[0157] Based on the above, the specific implementation process of the electronic device determining one or more POIs corresponding to the first store name based on the first WiFi information may include the following steps s21 to s25, such as... Figure 6A As shown. Based on this method, it is possible to mine brand store POIs and quickly and effectively identify situations such as store additions, closures, and differentiation of nearby stores, achieving high coverage and accuracy.

[0158] s21. The electronic device determines one or more candidate POIs corresponding to the first store name based on the first WiFi information.

[0159] In a specific implementation, the electronic device establishes a connection relationship based on the attributes of the WiFi networks that are simultaneously scanned in the first WiFi information, thereby establishing a connection graph with WiFi BSSID as the node. Each cluster in the connection graph can be regarded as a candidate POI.

[0160] Taking the first WiFi information shown in Table 3 above as an example, the electronic device filters BSSID1, BSSID2, and BSSID3 from the WiFi snapshot table. In the first WiFi scan, BSSID1 and BSSID2 are scanned simultaneously, so BSSID1 and BSSID2 are connected. In the second WiFi scan, BSSID1 and BSSID3 are scanned simultaneously, so BSSID1 and BSSID3 are connected, thus obtaining the following... Figure 6B The connection relationships shown indicate that the location of each BSSID is determined based on the latitude and longitude information of the WiFi network corresponding to each BSSID.

[0161] By analogy, a connection map can be built for all WiFi BSSIDs included in the first WiFi information, such as... Figure 6C As shown. Figure 6C In this example, each cluster can be considered a candidate POI. Here, three candidate POIs are described: candidate POI 1, candidate POI 2, and candidate POI 3. Each candidate POI can be considered as the POI data of a store. Here, there are three brand stores: candidate POI 1 can be considered as the POI data of store A, candidate POI 2 can be considered as the POI data of store B, and candidate POI 3 can be considered as the POI data of store C.

[0162] Optionally, due to the freedom in naming WiFi networks, WiFi networks that are not part of the brand's stores can also use the same name, which will affect the accuracy of POI determination. Therefore, it is necessary to remove candidate POIs (i.e., second POIs) that have not resulted in any payment to the brand's stores to improve the accuracy of POI determination.

[0163] Specifically, the electronic device first determines one or more first POIs corresponding to the first store name based on the first WiFi information; then, it filters the second POIs among the one or more first POIs to obtain one or more candidate POIs; the WiFi included in the second POI does not belong to the WiFi corresponding to the user's payment behavior.

[0164] For example Figure 6CAs shown, the electronic device determines three candidate POIs based on the connection relationships between various WiFi networks: Candidate POI 1, Candidate POI 2, and Candidate POI 3. All three candidate POIs can be considered the first POI. Candidate POI 3 includes WiFi networks scanned for the brand's store where no payment was made. Therefore, it can be considered that there are instances where WiFi networks other than those for the brand's store use the same naming convention; these are candidate POIs for which no payment was made and need to be removed to improve the accuracy of POI determination. The final candidate POIs are Candidate POI 1 and Candidate POI 2.

[0165] s22. The electronic device determines the similarity of the number of times any two WiFi networks in each candidate POI are simultaneously scanned and the similarity of the signal strength of any two WiFi networks simultaneously scanned.

[0166] In the actual implementation, using WiFi BSSID as a node, if the final POI is determined by directly performing DBCSAN clustering calculation on these BSSIDs using the latitude and longitude information of WiFi, since the latitude and longitude information of WiFi is obtained from crowdsourced data, when the brand stores in the central business district are close to each other (stores exist on different floors of the same shopping mall, such as: store aaa-2 in mall 1, store aaa-4 in mall 1), the latitude and longitude information is relatively close, which will lead to the problem of not being able to distinguish between neighboring stores.

[0167] Therefore, considering that brand stores typically deploy multiple WiFi networks, and that WiFi networks within the same store tend to have stronger signal strength and smaller signal strength differences when scanned, while WiFi networks between adjacent stores can also be scanned simultaneously, their signal strength differences are larger; furthermore, WiFi networks within the same store are easily scanned simultaneously, while WiFi networks between adjacent stores are difficult to scan simultaneously. Based on this, this application proposes further processing these WiFi networks based on frequency similarity and signal strength similarity, thereby distinguishing adjacent stores and improving the coverage rate of POI determination.

[0168] Specifically, regarding frequency similarity, this frequency similarity satisfies the following formula (1):

[0169]

[0170] In formula (1), n ​​represents the number of times any two WiFi networks in a candidate POI are scanned simultaneously, N represents the maximum number of times any two WiFi networks in a candidate POI are scanned simultaneously, and ln(·) represents the logarithm calculation with the constant e as the base.

[0171] For example, taking a candidate POI as an example, such as Figure 6D As shown, taking WiFi BSSID as a node, the value marked on the connecting line between any two BSSIDs in this candidate POI represents the number of times any two WiFi networks in this candidate POI are scanned simultaneously.

[0172] For example, in this candidate POI, the WiFi corresponding to BSSID1 and the WiFi corresponding to BSSID2 are scanned simultaneously 3 times. The maximum number of times any two WiFi networks in this candidate POI are scanned simultaneously is 17. Therefore, the similarity in the number of times the WiFi corresponding to BSSID1 and the WiFi corresponding to BSSID2 are scanned simultaneously is...

[0173] Regarding signal strength similarity, the signal strength similarity satisfies the following formula (2):

[0174] wifi_rssi_similarity=e -λ*wifi_distance*wifi_distance (2)

[0175] In formula (2), The signal strengths of any two WiFi networks simultaneously detected within a candidate POI are denoted as rssi1 and rssi2, respectively. λ, α, and β represent preset constants, wifi_distance represents the absolute maximum distance between the two WiFi networks, and wifi_rssi_similarity represents the signal strength similarity. λ can be 10. -6 α can take the value 0.07, β can take the value 0.08; rssi1≥rssi2.

[0176] Additionally, we can determine the M absolute maximum distances (i.e., M wifi_distances) when any two WiFi networks are scanned simultaneously, and take the median of the M wifi_distances as the final absolute maximum distance between the two WiFi networks.

[0177] It should be noted that, It measures the impact of the stronger signal strength (i.e., rssi1) of two scanned WiFi networks on the absolute maximum distance between the two WiFi networks. Under the same signal strength difference, the stronger rssi1, the smaller the absolute maximum distance between the two WiFi networks, and the relationship between rssi1 and the absolute maximum distance between the two WiFi networks is non-linear. This measures the impact of signal strength difference on the absolute maximum distance between two WiFi networks. With similarly strong signal strength (i.e., rssi1), a smaller signal strength difference results in a smaller absolute maximum distance between the two WiFi networks, and the relationship between signal strength difference and absolute maximum distance between the two WiFi networks is non-linear. (Utilizing...) and After determining the absolute maximum distance between two WiFi networks, normalization is performed (i.e., formula (2)) to obtain wifi_rssi_similarity, which is the signal strength similarity.

[0178] For example, taking a candidate POI as an example, such as Figure 6E As shown, using WiFi BSSID as a node, the value marked on the connecting line between any two BSSIDs in this candidate POI represents the signal strength difference between the two WiFi networks when they are simultaneously scanned within this candidate POI. For example, the signal strength difference between the WiFi network corresponding to BSSID1 and the WiFi network corresponding to BSSID2 when they are simultaneously scanned is 6.

[0179] Assuming that in a WiFi scan, the WiFi corresponding to BSSID1 and the WiFi corresponding to BSSID2 are scanned simultaneously, the signal strength rssi1 of the WiFi corresponding to BSSID1 is -21dBm, and the signal strength rssi2 of the WiFi corresponding to BSSID2 is -27dBm. The signal strength difference between the two WiFi networks when they are scanned simultaneously is 6. Let α be 0.07 and β be 0.08, then the calculated wifi_distance is 0.4. Substituting wifi_distance into formula (2), λ is set to 10. -6 The calculated signal strength similarity wifi_rssi_similarity is 0.9.

[0180] s23. The electronic device groups each candidate POI based on the similarity of the number of times and the similarity of the signal intensity, to obtain one or more first groups.

[0181] In a specific implementation, when the electronic device groups each candidate POI based on the similarity of the number of times and the similarity of the signal strength to obtain one or more first groups, the specific implementation method may include the following steps a to c, such as... Figure 7A As shown.

[0182] Step a: The electronic device determines the weight value between any two WiFi networks based on the similarity of the number of occurrences and the similarity of the signal strength.

[0183] In practical implementation, the electronic device performs a weighted sum calculation on the similarity of the number of times and the similarity of the signal strength, and uses the calculated value as the weight value between two WiFi networks in a candidate POI. Specifically, the following formula (3) can be used for calculation:

[0184] wifi_similarity=w1*signal strength similarity+w2*number similarity(3)

[0185] In formula (3), w1 and w2 represent weight coefficients, w1>0, w2>0, and w1+w2=1; wifi_similarity represents the weight value between two WiFi networks in a candidate POI.

[0186] Step b: The electronic device groups each candidate POI based on the weight value to obtain one or more groups.

[0187] In a specific implementation, taking a candidate POI (such as candidate POI 1) as an example, such as... Figure 7B As shown, using WiFi BSSID as the node and wifi_similarity as the weight value of the edge between nodes, a weighted undirected graph of WiFi similarity is established in this way. This weighted undirected graph only exemplarily labels the weight values ​​of some edges between nodes. This weighted undirected graph can also include the weight values ​​of edges between other nodes, which will not be elaborated here. For example, the weight value of the edge between BSSID1 and BSSID2 is 0.9.

[0188] Furthermore, electronic devices can utilize the label propagation algorithm (LPA) to partition the weighted undirected graph into groups, thereby obtaining one or more groups. For example... Figure 7C As shown, the weighted undirected graph was divided into two groups using the LPA algorithm: group 1 and group 2.

[0189] The LPA algorithm is a local community partitioning algorithm based on label propagation. For each node in the network, the LPA algorithm initializes a unique label in the initial stage. In each iteration, the node changes its label based on the labels of its connected nodes, choosing the community label with the most connected labels as its own. This is the meaning of label propagation. As the community label propagates, closely connected nodes will eventually share a common label. In short, it determines a node's characteristics by the circle it belongs to; closely connected nodes are grouped into the same community, achieving a clustering effect.

[0190] Step c: The electronic device filters the second group in the one or more groups to obtain one or more first groups; the WiFi included in the second group does not belong to the WiFi corresponding to the user's payment behavior.

[0191] In practice, after an electronic device obtains one or more groups, due to the freedom of naming WiFi networks, WiFi networks that are not part of the brand's stores can also use the same name, which will affect the accuracy of POI determination. Therefore, it is necessary to remove groups that have not made payments to the brand's stores (i.e., the second group) to improve the accuracy of subsequent POI determination, thereby obtaining one or more first groups.

[0192] For example, suppose an electronic device obtains three groups through the LPA algorithm: group 1, group 2, and group 3. Group 3 includes all WiFi networks that were scanned for the brand store where no payment was made. Therefore, it can be considered that there are WiFi networks that are not for the brand store but use the same name. This group is for the brand store where no payment was made and needs to be removed to improve the accuracy of subsequent POI determination. The first group obtained is group 1 and group 2.

[0193] Therefore, it can be seen that the candidate POI actually contains the POI data of two adjacent stores. In this way, the POI data of two adjacent stores can be quickly and effectively distinguished, thereby achieving the differentiation of adjacent stores and ensuring the coverage and accuracy of POIs.

[0194] s24. The electronic device clusters the WiFi in each first group based on the latitude and longitude information of the WiFi in each first group, and obtains one or more sub-clusters corresponding to each first group.

[0195] Alternatively, the electronic device can determine the latitude and longitude information of the WiFi in each first group from the WiFi snapshot table.

[0196] In the specific implementation, taking Group 1 as an example, the latitude and longitude information of the WiFi in Group 1 is used to perform DBCSAN clustering calculation on the BSSID in Group 1 to obtain one or more sub-clusters.

[0197] s25. The electronic device identifies the primary cluster in one or more sub-clusters corresponding to each first group as a POI.

[0198] Optionally, the center latitude and longitude information of each POI is the latitude and longitude information corresponding to that main cluster.

[0199] In practice, since the latitude and longitude information of the WiFi in each first group is calculated and predicted by electronic devices, there may be errors. If the latitude and longitude information of these sub-clusters is directly averaged to form the latitude and longitude information of a POI (such as the center latitude and longitude information), the accuracy of the POI's latitude and longitude information will be reduced.

[0200] Therefore, nodes far from the group need to be removed, retaining only the main clusters within these subclusters. The latitude and longitude information corresponding to the main cluster is used as the center latitude and longitude information of a POI. Here, the main cluster refers to the subcluster containing the most and most concentrated BSSIDs among one or more subclusters. The latitude and longitude information corresponding to the main cluster is the average of the latitude and longitude information of all WiFi networks within that main cluster. Based on this method, the accuracy of POI determination is improved, ensuring the effective mining of brand store POIs.

[0201] Subsequently, electronic devices can use the latitude and longitude information of each POI to verify the payment fence. Specifically, this involves verifying whether the latitude and longitude information of the POI matches the latitude and longitude information of its corresponding payment fence, eliminating inconsistent payment fences, thus cleaning up erroneous payment fences and improving the accuracy of the payment fence, which is beneficial to ensuring the normal execution of subsequent recommendation services. If the latitude and longitude information of the POI matches the latitude and longitude information of its corresponding payment fence, it can further verify whether the WiFi information in the POI matches the WiFi information of its corresponding payment fence, thereby further cleaning up erroneous payment fences and improving the accuracy of the payment fence. In addition, the latitude and longitude information of the POI can also be used as a data source for POIs in the future. For example, when a user uses their mobile phone to request nearby POIs based on their location, the location of nearby stores can also be returned to the user.

[0202] It should be noted that the latitude and longitude information of the POIs determined by the electronic devices, as well as the WiFi information within the POIs, can be used as crowdsourcing data to enrich the data and improve the accuracy of POI determination.

[0203] The following is a general overview of the embodiments of this application, such as... Figure 8A As shown, the electronic device can obtain the first crowdsourcing data, which may include crowdsourcing data corresponding to the user's payment behavior and / or crowdsourcing data corresponding to the connection to the store's WiFi; then the electronic device can obtain the brand store's high-precision WiFi fingerprint (including WiFi BSSID, WiFi SSID, WiFi signal strength, etc.) based on the first crowdsourcing data.

[0204] Furthermore, a mapping between store names and WiFi names is established by performing descriptive statistics on the WiFi names in the WiFi fingerprint. A WiFi snapshot table can be created using all the user's crowdsourced data, and the first WiFi information corresponding to the first store name can be determined from this mapping table. Here, the WiFi snapshot table is generated based on all the user's crowdsourced data.

[0205] Furthermore, based on the first WiFi information, one or more candidate POIs corresponding to the first store name are determined. Specifically, this is done by establishing connection relationships between the WiFi networks simultaneously scanned in the first WiFi information, thereby creating a connection graph with WiFi BSSIDs as nodes. Each cluster in the connection graph can be considered a candidate POI. Additionally, candidate POIs for which no payment has occurred need to be filtered.

[0206] Furthermore, the similarity of the number of times any two WiFi networks were simultaneously scanned in each candidate POI and the similarity of their signal strength are determined. Using WiFi BSSID as nodes, an undirected weighted graph is established between brand store BSSIDs, and the weight of the edges between nodes is the weighted sum of the similarity of the number of scans and the similarity of the signal strength.

[0207] Furthermore, the LPA algorithm is used to partition the undirected weighted graph into groups, resulting in one or more groups. Then, groups without payment activity are filtered out to obtain one or more first groups. Next, the WiFi networks within each first group are clustered based on their latitude and longitude information, resulting in one or more sub-clusters for each first group. Finally, the main cluster within each first group's sub-clusters is identified as a Point of Interest (POI), and the latitude and longitude information corresponding to this main cluster is the center latitude and longitude information of the POI, thus achieving POI mining. Additionally, the identified POI's latitude and longitude information, as well as the WiFi information within the POI, can be used as crowdsourcing data to enrich the data and improve the accuracy of POI identification.

[0208] For example, using the method proposed in this application, taking brand store AAA in City A as an example, as shown in Table 4, the coverage rate of the mined POIs reaches 94.03%, the accuracy rate reaches 99.37%, the accuracy rate of distinguishing nearby stores reaches 100%, and the recall rate of distinguishing nearby stores reaches 92%. City A has a total of 335 stores, and nearby stores are defined as stores with two or more locations within a 100-meter radius. Therefore, this solution, based on WiFi crowdsourcing data and crowdsourcing data of user payment behavior, achieves the mining of brand store POIs and can quickly and effectively identify store additions, closures, and nearby store distinctions, achieving high coverage and accuracy, which is more conducive to ensuring the normal execution of subsequent recommendation services.

[0209] Table 4

[0210]

[0211] It should be noted that, compared to the first crowdsourcing data which only includes crowdsourcing data corresponding to user payment behavior, the first crowdsourcing data includes crowdsourcing data corresponding to connection to the store's WiFi, or the first crowdsourcing data includes both crowdsourcing data corresponding to user payment behavior and crowdsourcing data corresponding to connection to the store's WiFi. In this case, the first crowdsourcing data is richer, which is more conducive to improving the accuracy of subsequent POI determination, and the coverage is also further improved.

[0212] like Figure 8BAs shown, when the first crowdsourced data uses the crowdsourced data corresponding to a user's payment behavior, only two WiFi BSSIDs scanned by users when making payments to the store can be collected, including: "BSSID1: '00:1f:7a:2a:0a:29'" and "BSSID2: '00:1f:7a:28:e0:bb'". When the first crowdsourced data uses the crowdsourced data corresponding to the WiFi connected to the store, four WiFi BSSIDs scanned by users when making payments to the first POI can be collected, including: "BSSID1: '00:1f:7a:2a:0a:29'", "BSSID2: '00:1f:7a:28:e0:bb'", and "BSSID3: '00:1f:7a:3c:7d:31'". When the first crowdsourcing data uses crowdsourcing data corresponding to user payments to the store and crowdsourcing data corresponding to the WiFi connection to the store, six WiFi BSSIDs scanned when users made payments to the first POI can be collected, including: "BSSID1: '00:1f:7a:2a:0a:29'", "BSSID2: '00:1f:7a:28:e0:bb'", and "BSSID3: '00:1f:7a:3c:7d:31'". Therefore, it is evident that using crowdsourcing data corresponding to the WiFi connection to the store, or combining crowdsourcing data corresponding to user payments to the store and crowdsourcing data corresponding to the WiFi connection to the store, yields richer crowdsourcing data.

[0213] The above method was verified through experiments, and the verification results are shown in Table 5 below. When the first crowdsourcing data used data corresponding to user payment behavior, the number of stores covered was 266, with a coverage rate of 79.40%. When the first crowdsourcing data used data corresponding to the WiFi connected to the stores, the number of stores covered was 311, with a coverage rate of 92.84%. Furthermore, the accuracy of the candidate payment fence was also verified to be improved to 50 meters. Therefore, it is evident that using crowdsourcing data corresponding to the WiFi connected to the stores as the first crowdsourcing data is more conducive to improving the accuracy and coverage of POI determination.

[0214] Table 5

[0215] First Crowdsourcing Data Coverage Coverage Crowdsourced data corresponding to user payment transactions 266 79.40％ Crowdsourced data connected to the store's WiFi 311 92.84％

[0216] Of course, when the first crowdsourcing data uses crowdsourcing data corresponding to user payment behavior and crowdsourcing data corresponding to WiFi connection to the store, the obtained WiFi information is also richer and more conducive to improving the accuracy and coverage of POI determination.

[0217] It can be seen that, based on Figure 4 The described method involves an electronic device establishing a mapping between store names and Wi-Fi names using crowdsourced data corresponding to user payment transactions and / or crowdsourced data corresponding to Wi-Fi connections to stores. Then, it generates a Wi-Fi snapshot table using all user crowdsourced data and determines the Wi-Fi information corresponding to a specific store name based on this mapping. This first Wi-Fi information allows for efficient and accurate identification of one or more Points of Interest (POIs) corresponding to the store name, enabling the mining of brand store POIs. This method is simple and convenient, eliminating the need for manual in-store visits or third-party platforms to acquire POI data. It allows for the maintenance of a fast-iterable, high-coverage, and highly accurate POI database, and also facilitates the normal execution of subsequent recommendation services.

[0218] Please see Figure 9 , Figure 9 A schematic diagram of the structure of a point of interest determination device 900 according to an embodiment of this application is shown. Figure 9 The device for determining the point of interest shown can be an electronic device, a device within an electronic device, or a device that can be used in conjunction with an electronic device. Figure 9 The apparatus for determining points of interest may include an acquisition unit 901, a determination unit 902, and a processing unit 903. Wherein:

[0219] The acquisition unit 901 is used to acquire first crowdsourcing data; the first crowdsourcing data includes crowdsourcing data corresponding to user payment behavior and / or crowdsourcing data corresponding to the wireless fidelity WiFi connected to the store;

[0220] The determining unit 902 is used to determine the correspondence between the store name and the WiFi name based on the first crowdsourced data;

[0221] The determining unit 902 is further configured to determine the first WiFi information corresponding to the first store name from the WiFi snapshot table based on the correspondence;

[0222] The processing unit 903 is used to determine one or more POIs corresponding to the first store name based on the first WiFi information.

[0223] In one possible implementation, the first WiFi information includes the identifiers of one or more WiFi networks scanned during each WiFi scan and the signal strength of those WiFi networks. The processing unit 903, when determining one or more POIs corresponding to the first store name based on the first WiFi information, specifically performs the following: determining one or more candidate POIs corresponding to the first store name based on the first WiFi information; determining the similarity in the number of times any two WiFi networks in each candidate POI are simultaneously scanned and the similarity in the signal strength of those two WiFi networks; grouping each candidate POI based on the similarity in the number of scans and the similarity in the signal strength to obtain one or more first groups; clustering the WiFi networks in each first group based on the latitude and longitude information of the WiFi networks in each first group to obtain one or more sub-clusters corresponding to each first group; and determining the main cluster in one or more sub-clusters corresponding to each first group as a POI.

[0224] In one possible implementation, when processing unit 903 groups each candidate POI based on the similarity of frequency and the similarity of signal strength to obtain one or more first groups, it specifically performs the following: determining the weight value between any two WiFi networks based on the similarity of frequency and the similarity of signal strength; grouping each candidate POI based on the weight value to obtain one or more groups; filtering the second groups in the one or more groups to obtain one or more first groups; wherein the WiFi networks included in the second groups do not belong to the WiFi networks corresponding to the user's payment behavior.

[0225] In one possible implementation, the similarity of these counts satisfies: Where n represents the number of times any two WiFi networks in a candidate POI are scanned simultaneously, N represents the maximum number of times any two WiFi networks in a candidate POI are scanned simultaneously, and ln(·) represents the logarithm calculation with the constant e as the base.

[0226] In one possible implementation, the signal strength similarity satisfies:

[0227] wifi_rssi_similarity=e -λ*wifi_distance*wifi_distance ;

[0228] in, The signal strengths of any two WiFi networks simultaneously detected in a candidate POI are denoted as rssi1 and rssi2, where rssi1 ≥ rssi2. λ, α, and β represent preset constants, wifi_distance represents the absolute maximum distance between the two WiFi networks, and wifi_rssi_similarity represents the similarity of the signal strengths.

[0229] In one possible implementation, when the processing unit 903 determines one or more candidate POIs corresponding to the first store name based on the first WiFi information, it is specifically used to: determine one or more first POIs corresponding to the first store name based on the first WiFi information; filter the second POIs among the one or more first POIs to obtain one or more candidate POIs; the WiFi included in the second POI does not belong to the WiFi corresponding to the user's payment behavior.

[0230] In one possible implementation, the determining unit 902, when determining the first WiFi information corresponding to the first store name from the WiFi snapshot table based on the correspondence, is specifically used to: determine the WiFi name corresponding to the first store name based on the correspondence; and determine the first WiFi information corresponding to the first store name from the WiFi snapshot table based on the WiFi name corresponding to the first store name, wherein the WiFi snapshot table is generated based on all user crowdsourced data.

[0231] In one possible implementation, the center latitude and longitude information of each POI is the latitude and longitude information corresponding to the main cluster.

[0232] For cases where the device for determining points of interest can be a chip or a chip system, please refer to [link / reference]. Figure 10 The diagram shows the structure of the chip. Figure 10 The chip 1000 shown includes a processor 1001 and an interface 1002. Optionally, it may also include a memory 1003. The number of processors 1001 can be one or more, and the number of interfaces 1002 can be multiple.

[0233] For cases where the chip is used to implement the electronic device in the embodiments of this application:

[0234] The interface 1002 is used to receive or output signals;

[0235] The processor 1001 is used to perform data processing operations of the electronic device.

[0236] It is understood that some optional features in the embodiments of this application can be implemented independently in certain scenarios without relying on other features, such as the current solution on which they are based, to solve the corresponding technical problems and achieve the corresponding effects. Alternatively, they can be combined with other features as needed in certain scenarios. Accordingly, the interest point determination device given in the embodiments of this application can also implement these features or functions, which will not be elaborated here.

[0237] It should be understood that the processor in the embodiments of this application can be an integrated circuit chip with signal processing capabilities. In implementation, the steps of the above method embodiments can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor described above can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0238] It is understood that the memory in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM). It should be noted that the memory used in the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0239] This application also provides a system for determining points of interest, which includes an electronic device; wherein the electronic device is used to perform the method executed by the electronic device in any of the above method embodiments.

[0240] This application also provides a computer storage medium storing a computer program / instructions thereon, which, when executed by a processor, implements the methods and steps as described in any of the above method embodiments.

[0241] This application also provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the methods and steps as described in any of the above method embodiments.

[0242] As used in the specification and appended claims of this application, the singular expressions “a,” “an,” “the,” “the,” “the,” and “this” are intended to include the plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the listed items. As used in the above embodiments, depending on the context, the term “when” can be interpreted as meaning “if…” or “after…” or “in response to determining…” or “in response to detecting…”. Similarly, depending on the context, the phrase “when…” or “if (the stated condition or event) is interpreted as meaning “if…” or “in response to determining…” or “when (the stated condition or event) is detected” or “in response to detecting (the stated condition or event)”.

[0243] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., high-density digital video disc (DVD)), or a semiconductor medium (e.g., solid-state disk (SSD)). Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

[0244] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for determining Points of Interest (POIs), characterized in that, The method includes: Obtain first crowdsourcing data; the first crowdsourcing data includes crowdsourcing data corresponding to user payment behavior and / or crowdsourcing data corresponding to Wi-Fi connection to the store; The correspondence between store names and WiFi names is determined based on the first crowdsourced data; The first WiFi information corresponding to the first store name is determined from the WiFi snapshot table according to the correspondence; the first WiFi information includes the identifier of one or more WiFi networks scanned each time a WiFi scan is performed and the signal strength of the WiFi network. Based on the first WiFi information, determine one or more candidate POIs corresponding to the first store name; Determine the similarity of the number of times any two WiFi networks are simultaneously scanned in each candidate POI, and the similarity of the signal strength of any two WiFi networks simultaneously scanned. Based on the frequency similarity and the signal intensity similarity, each candidate POI is grouped to obtain one or more first groups; Based on the latitude and longitude information of the WiFi in each first group, the WiFi in each first group is clustered to obtain one or more sub-clusters corresponding to each first group; The primary cluster in one or more sub-clusters corresponding to each first group is determined as a POI.

2. The method according to claim 1, characterized in that, Based on the similarity of frequency and the similarity of signal intensity, each candidate POI is grouped to obtain one or more first groups, including: The weight value between any two WiFi networks is determined based on the similarity of the number of occurrences and the similarity of the signal strength. Each candidate POI is grouped based on the weight value to obtain one or more groups; Filter the second group from the one or more groups to obtain one or more first groups; the WiFi included in the second group does not belong to the WiFi corresponding to the user's payment behavior.

3. The method according to claim 1 or 2, characterized in that, The similarity of the number of times satisfies: ; in, This represents the number of times any two WiFi networks within a candidate POI are simultaneously detected. This represents the maximum number of times any two WiFi networks within a candidate POI are simultaneously scanned. This represents the logarithmic calculation with the constant e as the base.

4. The method according to claim 1 or 2, characterized in that, The signal strength similarity satisfies: ； in, The signal strengths of any two WiFi networks simultaneously detected within a candidate POI are represented as follows: and , , , , This represents a preset constant. This represents the absolute furthest distance between any two WiFi networks. This indicates the similarity in signal strength.

5. The method according to claim 1 or 2, characterized in that, The step of determining one or more candidate POIs corresponding to the first store name based on the first WiFi information includes: Based on the first WiFi information, determine one or more first POIs corresponding to the first store name; The second POIs in the one or more first POIs are filtered to obtain one or more candidate POIs; the WiFi included in the second POIs does not belong to the WiFi corresponding to the user's payment behavior.

6. The method according to claim 1 or 2, characterized in that, The step of determining the first WiFi information corresponding to the first store name from the WiFi snapshot table according to the correspondence includes: Based on the correspondence, determine the WiFi name corresponding to the first store name; The first WiFi information corresponding to the first store name is determined from the WiFi snapshot table based on the WiFi name corresponding to the first store name. The WiFi snapshot table is generated based on all crowdsourced data of the user.

7. The method according to claim 1 or 2, characterized in that, The center latitude and longitude information of each POI is the latitude and longitude information corresponding to the main cluster.

8. An electronic device, characterized in that, include: One or more processors, one or more memories; wherein the one or more memories are coupled to the one or more processors, the one or more memories being used to store computer program code, the computer program code including computer instructions, which, when the one or more processors execute the computer instructions, cause the electronic device to perform the method as described in any one of claims 1-7.

9. A system for determining Points of Interest (POIs), characterized in that, Includes an electronic device; wherein the electronic device is used to perform the method as described in any one of claims 1-7.

10. A chip, characterized in that, The device includes a processor and an interface, the processor and the interface being coupled; the interface is used to receive or output signals, and the processor is used to execute code instructions to cause the method of any one of claims 1-7 to be performed.

11. A computer storage medium, characterized in that, The computer storage medium stores a computer program, which includes program instructions that, when executed on an electronic device, cause the electronic device to perform the method as described in any one of claims 1-7.

12. A computer program product, characterized in that, When the computer program product is run on a computer, it causes the computer to perform the method as described in any one of claims 1-7.

Images