Data processing method and related device

Abstract

Disclosed in embodiments of the present application are a data processing method and a related device, which can be applied to a point of information (POI) identification or service recommendation scenario. In the method, a terminal device obtains a POI feature of a first region and a wireless fidelity (Wi-Fi) list; the terminal device sends to a cloud device a first request carrying a candidate POI and the Wi-Fi list; and the terminal device receives a target POI sent by the cloud device, wherein the target POI belongs to at least one candidate POI. On one hand, compared with the solution in the prior art in which POI identification is entirely processed by cloud, in the present application, the terminal performs pre-identification and then the cloud performs accurate identification, such that the accuracy of POI identification is improved, and the computing load of the cloud is also reduced. On the other hand, the POI identification can be completed on the basis of one round of Wi-Fi list scanning, which can reduce the time delay of overall identification compared with continuous multi-rounds of Wi-Fi scanning in the prior art.

Description

A data processing method and related equipment

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office on December 1, 2023, with application number 202311658146.0 and application name “A data processing method and related equipment”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of communications, and in particular to a data processing method and related equipment. Background Art

[0003] With the development of mobile communications, smart mobile terminals and positioning services are becoming more and more popular. Positioning services can give accurate time and space stamps to people, things and events through corresponding positioning systems, sensor networks, the Internet, communication networks and other ubiquitous networks. Based on the real-time dynamic acquisition of multi-source heterogeneous information such as location coordinates, location attributes, location relationships, location time characteristics, etc., through information fusion and other processing, a location service map with consistent semantic relationships and unified spatiotemporal geographical associations is established. It will play a vital role in public location services, government decision-making, public opinion situation awareness, crowd behavior characteristics analysis, epidemic prediction and other aspects.

[0004] Point of information (POI) search is a fundamental user need in the mobile internet era and has become integral to every aspect of life, including daily travel, tourism, and dining. In existing technologies, the POI identification process generally involves the following: After obtaining location information, the client requests POI data from the server. The server then uses a pre-built database to match the data, completing the POI identification process.

[0005] However, in scenarios with excessive passenger flow, such as scenic spots and entertainment venues, the large number of clients will lead to a high cloud computing load and increase the hardware cost of the server.

[0006] Summary of the Invention

[0007] The embodiments of the present application provide a data processing method and related equipment, which performs pre-identification through a terminal and then performs accurate identification through the cloud, thereby reducing the computing load on the cloud.

[0008] The first aspect of the present application provides a data processing method, which can be applied to POI identification or service recommendation scenarios. The method is executed by a terminal device, or the method is executed by some components in the terminal device (such as a processor, a chip or a chip system, etc.), or the method can also be implemented by a logic module or software that can realize all or part of the terminal device functions. In the first aspect and its possible implementation, the method is described as being executed by a terminal device. In the method, the point of interest POI features of the first area are obtained, and the POI features include a POI identifier, a first basic service set identifier (BSSID) corresponding to the POI identifier, and related information of the first BSSID; a wireless fidelity (WIREless Fidelity, WIFI) list is obtained, and the WIFI list includes at least one WIFI, and each WIFI in the at least one WIFI includes its own second BSSID and strength; a first request is sent to a cloud device, and the first request carries at least one candidate POI and a WIFI list, and at least one candidate POI is related to the POI features and the WIFI list; a target POI sent by the cloud device is received, and the target POI belongs to at least one candidate POI.

[0009] In the embodiments of this application, compared to existing solutions that rely entirely on the cloud for POI identification, this application performs pre-identification on the terminal before performing precise identification in the cloud. This not only improves POI identification accuracy but also reduces the computing load on the cloud. Furthermore, POI identification can be completed based on a single round of Wi-Fi list scanning, which reduces overall identification latency compared to the existing multiple rounds of Wi-Fi scanning.

[0010] Optionally, in a possible implementation manner of the first aspect, the at least one candidate POI being associated with the POI feature and the WIFI list includes: the at least one candidate POI being a POI having a POI confidence in the POI feature greater than or equal to a preset threshold, where the POI confidence is used to indicate a degree of match between the POI feature and the WIFI list.

[0011] In this implementation method, at least one candidate POI in the POI feature can be determined by the difference between the BSSID in the WIFI list and the BSSID in the POI feature, or it can be understood that the candidate POI is first determined based on the strength comparison of the BSSID, so that the determined candidate POI is within a certain range from the terminal device.

[0012] Optionally, in a possible implementation of the first aspect, the above step of obtaining the POI features of the point of interest includes: sending a second request to the cloud device, where the second request is used to request the POI features of the first area; and receiving the POI features sent by the cloud device.

[0013] In this implementation, the terminal device can obtain POI features by requesting them from the cloud device. On the one hand, the cloud device has a large storage capacity and can provide a more comprehensive set of POI features for the terminal device's request. On the other hand, obtaining POI features from the cloud device can reduce the computing power consumption of the terminal device.

[0014] Optionally, in a possible implementation of the first aspect, the step of sending the first request to the cloud device includes sending the first request to the cloud device if a preset condition is met; the preset condition includes at least one of the following:

[0015] The movement distance of the terminal device is greater than or equal to a first threshold, where the movement distance is the distance between the location of the terminal device when the request was last sent to the cloud device and the current location of the terminal device;

[0016] The difference between the WiFi list and the previously acquired WiFi list is greater than or equal to a second threshold;

[0017] After neural network analysis, the conclusion is to send the first request.

[0018] In this implementation, by setting the preset conditions for triggering the request, or understanding it as setting multiple interception mechanisms, invalid requests are reduced and overall power consumption is lowered.

[0019] Optionally, in a possible implementation manner of the first aspect, the relevant information includes a statistical value of the first BSSID, the statistical value includes at least a maximum value and a minimum value, and the statistical value is used to measure strength information of the first BSSID.

[0020] In this implementation, the POI feature includes statistical values ​​related to the first BSSID strength, which can provide more information for subsequent preliminary identification of the terminal device, so that a candidate POI that is more consistent with the current location of the terminal device can be determined based on the statistical values.

[0021] Optionally, in a possible implementation of the first aspect, the above steps further include: recommending related services based on the target POI. In this implementation, after the terminal device determines the target POI, services related to the current location, such as package deals and food recommendations, can be recommended to the terminal device to enhance the user experience.

[0022] Optionally, in a possible implementation of the first aspect, the steps further include: collecting at least one data packet, each of the at least one data packet including Wi-Fi information collected by the terminal device during movement and / or information collected by the terminal device during on-site interactions; and sending at least one data packet to a cloud device, the at least one data packet being used by the cloud device to generate a database, which is used to determine the target POI. The database generation process can be either from scratch or by updating, and the specifics are not limited here.

[0023] In this implementation, the terminal device can report information collected during movement and / or on-site interactions to the cloud device, allowing the cloud device to generate or update a database based on the information reported by the terminal device. Instead of adding specialized personnel to collect data on-site, the database is built using data collected by the terminal device during movement or interaction. This not only automates Wi-Fi training but also allows for the timely identification of newly opened or recently closed stores.

[0024] The second aspect of the present application provides a resource configuration method, which can be applied to POI identification or service recommendation scenarios. The method is executed by a cloud device, or the method is executed by some components in the cloud device (such as a processor, a chip or a chip system, etc.), or the method can also be implemented by a logic module or software that can realize all or part of the cloud device functions. In the second aspect and its possible implementation, the method is described as being executed by a cloud device. In this method, the cloud device receives a first request from a terminal device, the first request carries at least one candidate POI and a WIFI list, the WIFI list includes at least one WIFI, and each WIFI in the at least one WIFI includes its own second BSSID and strength; the cloud device sends a target POI to the terminal device, the target POI is related to the database, at least one candidate POI and the WIFI list, the database stores POI information and POI fingerprints, and each POI fingerprint includes at least one WIFI fingerprint.

[0025] In the embodiments of this application, compared to existing solutions that rely entirely on the cloud for POI identification, this application performs pre-identification on the terminal before performing precise identification in the cloud. This not only improves POI identification accuracy but also reduces the computing load on the cloud. Furthermore, POI identification can be completed based on a single round of Wi-Fi list scanning, which reduces overall identification latency compared to the existing multiple rounds of Wi-Fi scanning.

[0026] Optionally, in a possible implementation manner of the second aspect, the above step: before receiving the first request from the terminal device, the method further includes: obtaining a database, the POI information includes a POI identifier and geographic information, the POI information also includes at least one of the following: name, POI type, at least one WIFI fingerprint includes at least one WIFI, and each WIFI in the at least one WIFI includes its own BSSID and strength.

[0027] In this implementation, the cloud device first obtains the database storing POI information and WIFI fingerprints, so as to facilitate the subsequent cooperation with the terminal device to complete the POI identification.

[0028] Optionally, in a possible implementation of the second aspect, the above-mentioned step of: obtaining a database includes: receiving at least one data packet reported from at least one terminal device, each of the at least one data packet including WIFI information collected by the corresponding terminal device during movement and / or information collected by the terminal device during on-site interactive behavior; aggregating at least two data packets to obtain at least two temporary POIs; associating the at least two temporary POIs with a POI library to obtain a database, the POI library including at least two POI identifiers and basic information corresponding to the at least two POI identifiers.

[0029] In this implementation, cloud devices can receive information collected by mobile devices during movement and / or on-site interactions, thereby generating or updating a database based on the information reported by the terminals. This eliminates the need for dedicated personnel to collect data on-site. Instead, the database is built using data collected by mobile devices during movement or interactions. This not only automates Wi-Fi training but also allows for the timely identification of newly opened or recently closed stores.

[0030] Optionally, in a possible implementation of the second aspect, the above steps also include: extracting a feature library from a database, the feature library including the BSSID of each POI whose parameters are greater than a threshold and corresponding statistical values, and geographic information of each POI, the parameters including: frequency and / or intensity, the feature library is used to provide POI features for the terminal device, and the POI features are related to at least one candidate POI.

[0031] In this implementation method, BSSIDs with parameters greater than a threshold can be extracted for the terminal device based on the full database, thereby providing a reference for the terminal device to determine candidate POIs, thereby improving the accuracy of the terminal device's initial recognition results.

[0032] Optionally, in a possible implementation of the second aspect, the above step: before receiving the first request from the terminal device, the method also includes: receiving a second request from the terminal device, the second request being used to request POI features of the first area, the POI features including a POI identifier, a first basic service set identifier BSSID corresponding to the POI identifier, and related information of the first BSSID; determining the POI features in the feature library based on the first area; and sending the POI features to the terminal device.

[0033] In this implementation, the cloud device can provide corresponding POI features based on requests sent by the terminal device. On the one hand, the cloud device has a large storage capacity and can provide a more comprehensive set of POI features for the terminal device's request. On the other hand, obtaining POI features through the cloud device can reduce the computing power consumption of the terminal device.

[0034] Optionally, in a possible implementation manner of the second aspect, the target POI is related to a database, at least one candidate POI, and a WIFI list, including: the database is used to determine a WIFI fingerprint related to the at least one candidate POI, and the similarity between the WIFI fingerprint and the WIFI list is related to the target POI.

[0035] In this implementation, the Wi-Fi fingerprints associated with candidate POIs are determined through a database. The target POI is then determined based on the similarity between the Wi-Fi list scanned by the terminal device and the Wi-Fi fingerprints. This allows POI identification to be completed in a single round of Wi-Fi list scanning, reducing overall identification latency compared to the multiple rounds of Wi-Fi scanning used in existing technologies.

[0036] A third aspect of an embodiment of the present application provides a terminal device, which can be applied to POI identification or service recommendation scenarios. The terminal device includes: an acquisition unit, used to obtain POI features of a first area, the POI features including a POI identifier, a first basic service set identifier BSSID corresponding to the POI identifier, and related information of the first BSSID; the acquisition unit is also used to obtain a wireless fidelity WIFI list, the WIFI list includes at least one WIFI, and each WIFI in the at least one WIFI includes its own second BSSID and strength; a transceiver unit is used to send a first request to a cloud device, the first request carries at least one candidate POI and a WIFI list, and the at least one candidate POI is related to the POI features and the WIFI list; the transceiver unit is also used to receive a target POI sent by the cloud device, and the target POI belongs to at least one candidate POI.

[0037] Optionally, in a possible implementation manner of the third aspect, the at least one candidate POI is associated with the POI feature and the WIFI list, including: at least one candidate POI is a POI in the POI feature whose POI confidence is greater than or equal to a preset threshold, and the POI confidence is used to indicate the degree of matching between the POI feature and the WIFI list.

[0038] Optionally, in a possible implementation of the third aspect, the above-mentioned acquisition unit is specifically used to send a second request to the cloud device, and the second request is used to request the POI features of the first area; the acquisition unit is specifically used to receive the POI features sent by the cloud device.

[0039] Optionally, in a possible implementation manner of the third aspect, the acquisition unit is specifically configured to send the first request to the cloud device if a preset condition is met; the preset condition includes at least one of the following:

[0040] The movement distance of the terminal device is greater than or equal to a first threshold, where the movement distance is the distance between the location of the terminal device when the request was last sent to the cloud device and the current location of the terminal device;

[0041] The difference between the WiFi list and the previously acquired WiFi list is greater than or equal to a second threshold;

[0042] After neural network analysis, the conclusion is to send the first request.

[0043] Optionally, in a possible implementation manner of the third aspect, the relevant information includes a statistical value of the first BSSID, the statistical value includes at least a maximum value and a minimum value, and the statistical value is used to measure strength information of the first BSSID.

[0044] Optionally, in a possible implementation manner of the third aspect, the terminal device further includes: a recommendation unit, configured to recommend related services based on the target POI.

[0045] Optionally, in a possible implementation of the third aspect, the above-mentioned terminal device also includes: a collection unit, used to collect at least one data packet, each of the at least one data packet includes WIFI information collected by the terminal device during movement and / or information collected by the terminal device during on-site interactive behavior; a transceiver unit, also used to send at least one data packet to a cloud device, at least one data packet is used for the cloud device to generate a database, and the database is used to determine the target POI.

[0046] A fourth aspect of an embodiment of the present application provides a terminal device, which can be applied to POI identification or service recommendation scenarios. The terminal device includes: a transceiver unit, used to receive a first request from the terminal device, the first request carrying at least one candidate POI and a WIFI list, the WIFI list including at least one WIFI, each of the at least one WIFI including its own second BSSID and strength; the transceiver unit is also used to send a target POI to the terminal device, the target POI is related to a database, at least one candidate POI and the WIFI list, the database stores POI information and POI fingerprints, and each POI fingerprint includes at least one WIFI fingerprint.

[0047] Optionally, in a possible implementation of the fourth aspect, the above-mentioned cloud device also includes: an acquisition unit, used to obtain a database, the POI information includes a POI identifier and geographic information, the POI information also includes at least one of the following: name, POI type, at least one WIFI fingerprint includes at least one WIFI, and each WIFI in the at least one WIFI includes its own BSSID and strength.

[0048] Optionally, in a possible implementation of the fourth aspect, the above-mentioned acquisition unit is specifically used to receive at least one data packet reported from at least one terminal device, each of the at least one data packet includes WIFI information collected by the corresponding terminal device during movement and / or information collected by the terminal device during on-site interactive behavior; the acquisition unit is specifically used to aggregate at least two data packets to obtain at least two temporary POIs; the acquisition unit is specifically used to associate the at least two temporary POIs with a POI library to obtain a database, and the POI library includes at least two POI identifiers and basic information corresponding to the at least two POI identifiers.

[0049] Optionally, in a possible implementation of the fourth aspect, the above-mentioned cloud device also includes: an extraction unit, used to extract a feature library from a database, the feature library including the BSSID of each POI whose parameters are greater than a threshold and the corresponding statistical values, and the geographic information of each POI, the parameters include: frequency and / or intensity, the feature library is used to provide POI features for the terminal device, and the POI features are related to at least one candidate POI.

[0050] Optionally, in a possible implementation of the fourth aspect, the above-mentioned transceiver unit is also used to receive a second request from the terminal device, the second request is used to request the POI features of the first area, the POI features including the POI identifier, the first basic service set identifier BSSID corresponding to the POI identifier, and related information of the first BSSID; the transceiver unit is also used to determine the POI features in the feature library based on the first area; the transceiver unit is also used to send the POI features to the terminal device.

[0051] Optionally, in a possible implementation manner of the fourth aspect, the above-mentioned target POI is related to a database, at least one candidate POI, and a WIFI list, including: the database is used to determine a WIFI fingerprint related to the at least one candidate POI, and the similarity between the WIFI fingerprint and the WIFI list is related to the target POI.

[0052] In a fifth aspect, the present application provides a terminal device comprising at least one processor coupled to a memory; the memory is used to store programs or instructions; and the at least one processor is used to execute the program or instructions so that the terminal device implements a method of any possible implementation of the first aspect described above.

[0053] In the sixth aspect of the present application, a cloud device is provided, comprising at least one processor, at least one processor coupled to a memory; the memory is used to store programs or instructions; the at least one processor is used to execute the program or instructions, so that the cloud device implements a method of any possible implementation method of the aforementioned second aspect.

[0054] In a seventh aspect, the present application provides a terminal device comprising at least one logic circuit and an input / output interface; the logic circuit is used to execute the method described in any possible implementation of the first aspect.

[0055] In an eighth aspect, the present application provides a cloud device comprising at least one logic circuit and an input / output interface; the logic circuit is used to execute a method as any possible implementation method in the aforementioned second aspect.

[0056] The ninth aspect of the present application provides a communication system, which includes a terminal device of any possible implementation method in the fifth aspect and a cloud device of any possible implementation method in the sixth aspect, or includes a terminal device of any possible implementation method in the seventh aspect and a cloud device of any possible implementation method in the eighth aspect.

[0057] In a tenth aspect, the present application provides a computer-readable storage medium for storing one or more computer-executable instructions. When the computer-executable instructions are executed by a processor, the processor executes the method described in any possible implementation of any of the first or second aspects above.

[0058] In an eleventh aspect, the present application provides a computer program product (or computer program). When the computer program in the computer program product is executed by the processor, the processor executes the method described in any possible implementation of any of the first or second aspects above.

[0059] The twelfth aspect of the present application provides a chip system, which includes at least one processor for supporting a terminal device / cloud device to implement the method described in any possible implementation method of any aspect of the first or second aspect above.

[0060] In one possible design, the chip system may also include a memory for storing program instructions and data necessary for the terminal device / cloud device. The chip system may consist of a chip alone or may include a chip and other discrete components. Optionally, the chip system may also include an interface circuit that provides program instructions and / or data to at least one processor.

[0061] Among them, the technical effects brought about by any design method in the third aspect to the twelfth aspect can refer to the technical effects brought about by the different design methods in the above-mentioned first aspect and second aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] FIG1 is a schematic diagram of the structure of a communication system provided in an embodiment of the present application;

[0063] FIG2 is a flow chart of a data processing method provided in an embodiment of the present application;

[0064] FIG3 is another flow chart of the data processing method provided in an embodiment of the present application;

[0065] FIG4 is another flow chart of the data processing method provided in an embodiment of the present application;

[0066] FIG5 is a schematic structural diagram of a terminal device provided in an embodiment of the present application;

[0067] FIG6 is a schematic diagram of the structure of a cloud device provided in an embodiment of the present application;

[0068] FIG7 is another schematic diagram of the structure of a terminal device provided in an embodiment of the present application;

[0069] FIG8 is another structural diagram of the cloud device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0070] To facilitate understanding, the following first introduces the relevant terms and concepts mainly involved in the embodiments of this application.

[0071] 1. Point of interest (POI)

[0072] POIs are an important component of navigational electronic maps. They generally refer to landmarks, buildings, and scenic spots on electronic maps. They are used to mark government departments, commercial establishments (gas stations, department stores, supermarkets, restaurants, hotels, convenience stores, hospitals, etc.), tourist attractions (parks, public restrooms, etc.), historical sites, and transportation facilities (various bus stations, parking lots, speed cameras, speed limit signs), etc.

[0073] POI search is a basic need of users in the mobile Internet era and has been integrated into every aspect of life, such as daily travel, tourism, and dining. In the existing technology, there are two ways to identify POIs.

[0074] One solution, based on indoor positioning, involves obtaining longitude and latitude and then matching POIs based on an indoor map. However, this method relies on an indoor map with POI annotations, which is not available in most scenarios. Furthermore, this method places very high demands on the accuracy of indoor positioning and POIs on the indoor map. The accuracy of POI matching based on longitude and latitude directly impacts the user experience of the final location-based service.

[0075] Another approach uses wireless fidelity (Wi-Fi) fingerprinting to identify the user's current point of interest (POI). The client intermittently scans surrounding Wi-Fi networks (either system- or application-initiated), and the resulting Wi-Fi list (i.e., Wi-Fi fingerprint) serves as the basis for identifying the current location. Each time the client obtains location information, it requests POI data from the server. The server then matches the data against a pre-built database, completing the POI identification process.

[0076] However, in scenarios with excessive passenger flow, such as scenic spots and entertainment venues, the large number of clients will lead to a high cloud computing load and increase the hardware cost of the server.

[0077] In order to solve the above technical problems, an embodiment of the present application provides a data processing method. Compared with the solution in the prior art in which POI identification is entirely handled by the cloud, the present application performs pre-identification through the terminal and then performs accurate identification through the cloud, which can not only improve the accuracy of POI identification, but also reduce the computing load on the cloud.

[0078] Figure 1 is a schematic diagram of a communication system provided by an embodiment of the present application. The communication system includes a terminal device 101 and a cloud device 102. The terminal device 101 can communicate with the cloud device 102 via a wired network or a wireless network.

[0079] The terminal device 101 may refer to a terminal used by a user, and the terminal device 101 is used to provide services to the user. The user can operate the terminal device 101 through voice, touch gestures, and other operations. When the user uses the terminal device 101, the terminal device 101 can independently provide services to the user, or it can support joint processing with other devices (such as other devices such as the cloud device 102) to provide services to the user.

[0080] Optionally, the terminal device 101 may be equipped with an operating system and loaded with applications according to user operations. The terminal device 101 may support at least one of the following functions: installing applications, mobilizing cloud services (such as public clouds, private clouds, etc.), built-in services, etc.

[0081] The cloud device 102 has data processing (such as storage, search, identification, etc.) functions. The cloud device 102 can receive data processing requests from the terminal device 101, process the data to obtain processing results, and return the processing results to the terminal device 101, so that the terminal device 101 can present the processing results to the user.

[0082] In the POI recognition scenario, the terminal device 101 can first perform preliminary POI recognition to obtain candidate POIs. The terminal device 101 sends a POI recognition request to the cloud device 102, and the POI recognition request carries at least the candidate POI. In this way, the cloud device 102 can perform accurate POI recognition based on the database and the candidate POIs initially recognized by the terminal device 101 to obtain the target POI, and send the target POI to the terminal device 101. The terminal device 101 can then present the target POI to the user, or recommend related services to the user based on the target POI. For example, merchant discount coupons, sign recommendations, membership card processing, etc. Compared to the existing solution in which POI recognition is entirely handled by the cloud, in this communication system, preliminary recognition is first performed by the terminal, and then accurate recognition is performed by the cloud. Since the basis for the accurate recognition of the cloud device 102 is the candidate POI identified by the terminal device 101, it can not only improve the accuracy of POI recognition, but also reduce the computing load of the cloud.

[0083] The terminal device 101 in the embodiment of the present application can be a mobile phone, a tablet computer (pad), a portable game console, a personal digital assistant (PDA), a laptop computer, an ultra mobile personal computer (UMPC), a handheld computer, a netbook, a car media player, a wearable electronic device, a virtual reality (VR) terminal device, an augmented reality (AR), a vehicle, a vehicle-mounted terminal, an aircraft terminal, an intelligent robot, and other terminal devices.

[0084] The cloud device 102 in the embodiments of the present application can be a device or server with data processing capabilities, such as a cloud server, network server, application server, or management server. The cloud device 102 receives data processing requests from terminal devices through an interactive interface, and then processes the data through a memory that stores data and a processor that processes the data. The memory in the cloud device 102 can be a general term that includes local storage and a database that stores historical data. The database can be on the cloud device or on other network servers.

[0085] In addition, the data processing method and related devices provided in the embodiments of the present application can be applied to a variety of application scenarios. The following are several common scenarios:

[0086] 1. Map navigation: By collecting POI information, you can easily find your destination in navigation modes such as driving, walking, and public transportation.

[0087] 2. Travel: Plan travel routes and find tourist resources by searching for POI information such as attractions, restaurants, and accommodation.

[0088] 3. Commercial services: Provide commercial services and convenience services by searching for POI information such as business stores, supermarkets, hotels, etc.

[0089] 4. Geographic analysis: Analyze the business district, transportation, and other aspects of a region through POI information, and provide services such as business data, traffic analysis, and urban planning.

[0090] It is understandable that the above application scenarios are just examples. In actual applications, there may be other application scenarios, which are not specifically limited here.

[0091] The data processing method provided in the embodiment of the present application is described below. The method can be executed by a data processing device, or by a component of the data processing device (such as a processor, chip, or chip system, etc.). The data processing device can be a cloud device, a terminal device, or a system consisting of a cloud device and a terminal device (as shown in Figure 1 above).

[0092] The method provided in the embodiment of the present application is mainly applicable to scenarios such as POI identification.

[0093] Please refer to Figure 2, which is a flowchart of a data processing method provided by an embodiment of the present application. The method may include steps 201 to 206. Steps 201 to 206 are described in detail below.

[0094] Step 201: The terminal device obtains POI features of a first area.

[0095] The terminal device obtains a POI feature of the first area, where the POI feature includes a first basic service set identifier (BSSID) and related information of the first BSSID. The related information of the first BSSID includes a statistical value of the first BSSID, where the statistical value is used to measure strength information of the first BSSID. The statistical value includes at least a maximum value and a minimum value, and the statistical value may also include at least one of the following: a variance, a mean, etc. It is understandable that the number of first BSSIDs may be one or more.

[0096] The BSSID in the embodiments of the present application can also be understood as the Media Access Control Address (MAC) address of the Access Point (AP), which is used to identify the Basic Service Set (BSS) of the AP. The specific representation method of the BSSID is not limited here, for example, it can be represented by a hexadecimal string or a binary string.

[0097] In the embodiment of the present application, there are many ways for the terminal device to obtain POI features, which can be selected from a local database, or received from other devices (such as cloud devices), etc., which are not limited here.

[0098] In one possible implementation, the terminal device selects POI features of the first area from a local database, which includes BSSIDs and corresponding statistical values ​​of POIs with parameters greater than a threshold, including frequency and / or intensity.

[0099] Among them, the above-mentioned local database can also be called a feature library, which can be pre-stored in the terminal device or sent from the cloud device, and the specific details are not limited here.

[0100] In another possible implementation, the terminal device obtains the POI features of the first area by receiving the POI features sent by the cloud device. The acquisition process in this case can be shown in Figure 3. The embodiment shown in Figure 3 will be described later and will not be expanded here.

[0101] The first area in the embodiment of the present application is used to express a certain geographical area. The granularity of the area can be an administrative area (such as an autonomous prefecture, county, autonomous county, city, urban district, etc.), a street area, a geographical grid (such as a five-digit Geohash), a specific area (such as a shopping mall, office building, airport, entertainment facility, hospital, etc.). In addition, the area with the terminal device as the circle point and the preset distance as the radius, the area with the terminal device as the midpoint and the preset distance as the side length, etc., are not specifically limited here. In addition, the physical shape of the first area can be a polygon or a circle, etc., which is not specifically limited here.

[0102] For example, for the convenience of description, the store name is used to represent the POI identifier, and the statistical value includes the minimum value and the maximum value. The above-mentioned first BSSID is replaced by a sequence, and the sequence can specifically be FC:83:C6:00:F0:E7, etc. For example, the first sequence and the second sequence refer to two different first BSSIDs.

[0103] An example of POI features of the first area is shown in Table 1:

[0104] Table 1

[0105] Among them, the first sequence, second sequence, third sequence and fourth sequence are only for distinguishing different BSSIDs. Assume that the first area involves 4 POIs, namely Store A, Store B, Store C and Store D. Store A has three first BSSIDs (i.e., the first sequence, second sequence and third sequence), Store B has four first BSSIDs (i.e., the first sequence, second sequence, third sequence and fourth sequence), Store C has four first BSSIDs (i.e., the first sequence, second sequence, third sequence and fourth sequence), and Store D has three first BSSIDs (i.e., the fourth sequence, third sequence and second sequence).

[0106] Step 202: The terminal device obtains a WIFI list.

[0107] The terminal device obtains a WIFI list, where the WIFI list includes at least one WIFI, and each WIFI in the at least one WIFI includes its own second BSSID and strength.

[0108] In the embodiment of the present application, there are many ways for the terminal device to obtain the WIFI list. It can be obtained by scanning the surrounding WIFI signals based on its own WIFI module, or by receiving signals sent by other devices (such as other terminal devices), etc., which are not limited here.

[0109] For example, similar to the previous example, for the convenience of description, the above BSSID is replaced by a sequence, and the sequence can specifically be FC:83:C6:00:F0:E7, etc. For example, the first sequence and the second sequence refer to two different BSSIDs.

[0110] Assume that the WIFI list scanned by the terminal device at the current location is as shown in Table 2:

[0111] Table 2

[0112] In a possible implementation manner, the terminal device scans available Wi-Fi signals in the surrounding area to obtain a Wi-Fi list.

[0113] For example, the terminal device is a mobile phone, which can scan surrounding Wi-Fi signals through its own Wi-Fi module to obtain a Wi-Fi list.

[0114] In another possible implementation, the terminal device sends a scan request to other devices. After the other devices scan the WIFI list, they feed the WIFI list back to the terminal device.

[0115] For example, the terminal device is a smart watch and the other device is a mobile phone. The mobile phone can scan the surrounding Wi-Fi signals through its own Wi-Fi module to obtain a Wi-Fi list, and send the Wi-Fi list to the smart watch, so that the smart watch obtains the Wi-Fi list.

[0116] Step 203: The terminal device determines candidate POIs based on the POI features and the WIFI list.

[0117] After the terminal device obtains the POI characteristics and the Wi-Fi list, it can determine candidate POIs based on the POI characteristics and the Wi-Fi list. Alternatively, it can be understood that the candidate POIs are related to the POI characteristics and the Wi-Fi list. The number of candidate POIs can be one or more, and the specific number is not limited here.

[0118] This step can also be understood as pre-identification, rough identification or preliminary identification of POI.

[0119] The terminal device determines a candidate POI based on the statistical values ​​of different first BSSIDs in the POI feature and the strength of the second BSSID.

[0120] Optionally, determining candidate POIs based on the statistical values ​​of different first BSSIDs in the POI feature and the strength of the second BSSID includes: determining a POI confidence based on the difference between the relevant information of each second BSSID in the WiFi list and the first BSSID in the POI feature; and identifying POIs corresponding to POI confidences greater than a preset threshold as candidate POIs. Alternatively, the correlation between candidate POIs and the POI feature and the WiFi list includes: candidate POIs are POIs whose POI confidences in the POI feature are greater than or equal to a preset threshold, and the POI confidences are used to indicate the degree of match between the POI feature and the WiFi list.

[0121] Furthermore, a first difference between the maximum and minimum strength values ​​corresponding to each first BSSID is calculated. A second difference between the strength of each second BSSID in the Wi-Fi list and the minimum strength value corresponding to the first BSSID is then calculated, and the ratio of the first and second differences is calculated. The POI confidence level of each POI is determined based on the ratios corresponding to all first BSSIDs in each POI. Finally, candidate POIs are determined based on the POI confidence level and a preset threshold.

[0122] For example, the POI confidence level is used to indicate the degree of matching between the POI feature and the WIFI list, which can be specifically expressed in the following formula 1. That is, the POI confidence level is calculated using the following formula 1:

[0123] Formula 1:

[0124] rssi j =clamp(minRssi j ,maxRssi j );

[0125] Among them, N represents the number of first BSSIDs corresponding to a POI (or a store), j represents any first BSSID, minRssi j Indicates the minimum strength value of the jth first BSSID in the POI feature corresponding to a store, maxRssi j Indicates the maximum strength of the jth first BSSID in a POI, rssi j Indicates the strength of the second BSSID in the Wi-Fi list corresponding to the j-th first BSSID. For example, in the example of Table 1 above, N of store A is 3, N of store B is 4, N of store C is 4, and N of store D is 3. clamp(minRssi j ,maxRssi j ) is used to limit rssi j The value range is minRssi j with maxRssij between.

[0126] It is understandable that the above method of calculating the POI confidence using average distribution is only an example. In practical applications, other methods may be used, such as Gaussian distribution, etc., which are not limited here.

[0127] For example, continuing with the examples in Tables 1 and 2 above, the terminal device can determine that the maximum value of the first sequence of store A is -40 and the minimum value is -70 based on the POI features; the maximum value of the second sequence is -50 and the minimum value is -80; the maximum value of the third sequence is -60 and the minimum value is -90.

[0128] The maximum value of the second sequence of Store B is -40, and the minimum value is -70; the maximum value of the first sequence is -50, and the minimum value is -80; the maximum value of the third sequence is -50, and the minimum value is -80; the maximum value of the fourth sequence is -60, and the minimum value is -90.

[0129] The maximum value of the third sequence of store C is -40 and the minimum value is -70; the maximum value of the second sequence is -50 and the minimum value is -80; the maximum value of the fourth sequence is -50 and the minimum value is -80; the maximum value of the first sequence is -60 and the minimum value is -90.

[0130] The maximum value of the fourth sequence of store D is -40 and the minimum value is -70; the maximum value of the third sequence is -50 and the minimum value is -80; the maximum value of the second sequence is -60 and the minimum value is -90.

[0131] Due to clamp(minRssi j ,maxRssi j ) For each of the following restrictions, it is equivalent to constraining the value range of each item in the following calculation formula to be between 0 and 1. During the calculation process, the values ​​in Table 2 above need to be adjusted to between the maximum and minimum values.

[0132] For Store B's POI confidence, since the strength of the first sequence of the second item is -40, the clamp can be used to adjust the strength of the first sequence of the second item to between -50 and -80. The value closest to the maximum and minimum values ​​is usually selected, which is equivalent to replacing -40 with -50. Similarly, for Store C's POI confidence, the third item is replaced by -80, while for Store D's POI confidence, the first item is replaced by -70, while the second item is replaced by -85.

[0133] The POI confidence of each store is calculated as follows:

[0134] Assuming that the preset threshold is 0.43, it is determined that the candidate POIs with a threshold greater than 0.43 include the aforementioned store A, store B, and store D.

[0135] It is understandable that the preset threshold can be set according to actual needs and is not specifically limited here.

[0136] Step 204: The terminal device sends a first request to the cloud device.

[0137] After the terminal device determines the candidate POI, it sends a first request to the cloud device. In response, the cloud device receives the first request sent by the terminal device. The first request carries at least one candidate POI and a Wi-Fi list, and at least one candidate POI is related to the POI feature and the Wi-Fi list.

[0138] In step 205 , the cloud device determines the target POI based on the database, the candidate POIs, and the WIFI list.

[0139] The cloud device stores a database containing POI information and at least one Wi-Fi fingerprint. The POI information includes a POI identifier. The at least one Wi-Fi fingerprint includes at least one Wi-Fi, and each of the at least one Wi-Fi includes its own BSSID and strength.

[0140] This step can also be understood as accurate or detailed identification of POIs.

[0141] Optionally, the POI information further includes at least one of the following: POI name, geographic information of the POI (such as latitude and longitude and address, etc.), POI type, etc.

[0142] In the embodiment of the present application, the POI type can be set according to actual needs, and specifically may include at least one of the following: catering, scenic spots, public facilities, companies and enterprises, shopping, transportation facilities services, financial insurance services, science, education and cultural services, commercial residences, life services, sports and leisure services, medical care services, government agencies and social groups, accommodation services, etc.

[0143] After receiving the first request, the cloud device determines a target POI based on the database, the candidate POIs, and the Wi-Fi list. The target POI is associated with the database, the at least one candidate POI, and the Wi-Fi list, including: the database is used to determine a Wi-Fi fingerprint associated with the at least one candidate POI, and the similarity between the Wi-Fi fingerprint and the Wi-Fi list is associated with the target POI.

[0144] For example, it is assumed that each candidate POI has the POI fingerprint shown in Table 3 found in the database:

[0145] Table 3

[0146] The number of Wi-Fi fingerprints included in each POI fingerprint can be one or more. For example, in Table 3, the POI fingerprint of Store A includes two Wi-Fi fingerprints, the POI fingerprint of Store B includes three Wi-Fi fingerprints, and the POI fingerprint of Store D includes two Wi-Fi fingerprints. Each Wi-Fi fingerprint includes multiple Wi-Fis, and each Wi-Fi includes the Wi-Fi's BSSID and BSSID strength.

[0147] Optionally, determining the target POI based on the database, candidate POIs, and Wi-Fi list includes first obtaining POI fingerprints associated with the candidate POIs in the database (each POI fingerprint includes one or more Wi-Fi fingerprints), calculating the similarity between the Wi-Fi list and each Wi-Fi fingerprint in each POI fingerprint, and for a POI fingerprint, determining the POI based on the similarity of each Wi-Fi fingerprint in the POI fingerprint (for example, summing the similarities of each Wi-Fi fingerprint in the POI fingerprint to determine the similarity of the POI fingerprint). The POI corresponding to the POI fingerprint that meets the preset conditions is thereby determined as the target POI. The process of obtaining Wi-Fi fingerprints can be understood as first determining a search range based on the candidate set, and then determining the target POI using an algorithm such as weighted k-nearest neighbor (wkNN). Specifically, the k Wi-Fi fingerprints closest to the Wi-Fi list and their corresponding similarities are first found. Finally, the similarity of the POI to which they belong is determined based on the k Wi-Fi fingerprints and their respective similarities.

[0148] For example, using the wkNN algorithm with k = 5 and the POI fingerprints shown in Table 3, the four Wi-Fi fingerprints closest to the Wi-Fi list are found, along with their corresponding similarities. Finally, the similarity of the POIs to which they belong is determined based on these four Wi-Fi fingerprints. Assume that three of the four Wi-Fi fingerprints belong to Store B, and one belongs to Store A. For example, Store B can be identified as the target POI based on the number of fingerprints. For another example, the target POI can be determined based on the similarity of the specific POI fingerprints. The specific method for determining the similarity of the POIs to which they belong based on k Wi-Fi fingerprints is not limited.

[0149] The preset condition is related to the magnitude of the similarity. For example, the preset condition is a similarity greater than or equal to a first preset threshold, or a similarity less than or equal to a second preset threshold, etc., and the specifics are not limited here. In addition, there are various methods for calculating the similarity, such as Euclidean distance or cosine similarity, and the specifics are not limited here.

[0150] Step 206: The cloud device sends the target POI to the terminal device.

[0151] After the cloud device determines the target POI, it sends the target POI to the terminal device. Correspondingly, the terminal device receives the target POI sent by the cloud device.

[0152] Optionally, after acquiring the target POI, the terminal device recommends services related to the target POI to the user. For example, these services may be services at the target POI or services at nearby POIs, thereby enhancing the user experience. These services may include map navigation, travel, business services, geographic analysis, and more.

[0153] For example, assuming that the target POI is store A, services related to store A may be pushed to the user, such as store A's recommended packages, group purchase coupons, discount coupons, etc.

[0154] In the embodiment of the present application, pre-identification is performed by the terminal and then accurate identification is performed through the cloud, which not only improves the accuracy of POI identification but also reduces the computing load of the cloud.

[0155] Furthermore, in order to reduce overall power consumption, multiple interception mechanisms can be set up to avoid most invalid requests. The following is a detailed description:

[0156] The first interception mechanism:

[0157] The first interception mechanism is to set a first preset condition for step 204 in the embodiment shown in FIG. 2 , that is, step 204 is triggered only if the first preset condition is met.

[0158] This situation can also be understood as determining whether it is necessary to perform accurate identification of the POI based on the first preset condition.

[0159] The first preset condition in the embodiment of the present application includes at least one of the following:

[0160] 1. The terminal device's movement distance is greater than or equal to a first threshold, where the movement distance is the distance between the terminal device's location when the last request was sent to the cloud device and the terminal device's current location. Alternatively, if the terminal device's movement distance is small, since the surrounding POIs have changed little, it is not necessary to accurately identify and update the target POI.

[0161] 2. The difference between the WiFi list obtained in step 202 and the previously obtained WiFi list is greater than or equal to a second threshold. Alternatively, if the difference in the WiFi list is small, it can be understood that the strength of each WiFi has not changed, and there is no need to accurately identify and update the target POI.

[0162] 3. After neural network analysis, a conclusion is reached, and the conclusion is to send the first request. Alternatively, it can be understood that the data pairs of the two POI recognition results can be used to calculate the POI candidate set similarity, estimated offset, WIFI similarity, time interval and other features between the data pairs. If the two recognition results are consistent (for example, whether there is a significant position change), it is marked as a positive sample (an invalid request that needs to be intercepted). If the two recognition results are inconsistent, it is marked as a negative sample (a valid request that does not need to be intercepted). Based on the data constructed above, a neural network is trained to determine whether the current request needs to be intercepted. Therefore, neural network analysis can be used to draw a conclusion on whether to send the first request or not, or to draw a conclusion on whether a significant position change has occurred.

[0163] 4. The terminal device is not at the preset location, which includes at least one of the following: home, work, etc. Alternatively, when the user is at home or work, there is a small probability that the Wi-Fi of a nearby POI can be scanned, triggering the subsequent precise identification process. If the user is clearly at home or work, there is no need to initiate POI precise identification. Identifying the user's home or work location can be based on connected Wi-Fi or scanned Wi-Fi fingerprints.

[0164] The second interception mechanism:

[0165] The first interception mechanism is to set a preset condition for step 203 in the embodiment shown in FIG. 2 , that is, step 203 is triggered only if the second preset condition is met.

[0166] The second preset condition in the embodiment of the present application includes at least one of the following:

[0167] 1. The terminal device is not at the preset location, which includes at least one of the following: home, work, etc. Alternatively, when the user is at home or work, there is a small probability that the Wi-Fi of the surrounding POIs can be scanned, thereby triggering the subsequent identification process. When it is clear that the user is at home or work, there is no need to initiate terminal-side POI pre-identification (and therefore no POI precise identification will be initiated). Identifying that the user is at home or work can be based on the connected Wi-Fi or the scanned Wi-Fi fingerprint.

[0168] 2. The cloud device learns the business hours of each POI and sends it to the terminal device as a feature. This allows the terminal device to intercept traffic based on business hours before performing initial recognition. For example, it can intercept traffic during non-business hours.

[0169] It is understandable that the several situations of the above-mentioned first preset condition and the second preset condition are only examples. In actual applications, there may be other situations, which are not specifically limited here.

[0170] The embodiments of the present application set up multiple interception mechanisms to avoid most invalid requests and reduce overall power consumption.

[0171] The following describes how the terminal device obtains the POI features of the first area by receiving the POI features sent by the cloud device in the aforementioned step 201.

[0172] Please refer to FIG. 3 . The process includes steps 301 to 303 , which are described in detail below.

[0173] Step 301: The terminal device sends a second request to the cloud device.

[0174] The terminal device sends a second request to the cloud device. Correspondingly, the cloud device receives the second request sent by the terminal device, the second request being used to request POI features of the first area, the POI features including the POI identifier, the first BSSDI corresponding to the POI identifier, and related information of the first BSSID.

[0175] The above-mentioned relevant information includes a statistical value of the first BSSID, the statistical value includes at least a maximum value and a minimum value, and the statistical value is used to measure the strength information of the first BSSID.

[0176] Optionally, the second request may also be used to indicate a POI type. For the POI type, reference may be made to the description in step 205 in the embodiment shown in FIG. 2 , and details thereof will not be repeated here.

[0177] In step 302 , the cloud device determines POI features in a feature library based on the first area.

[0178] The cloud device first obtains a feature library, which includes BSSIDs of POIs with parameters greater than a threshold, corresponding statistical values, and POI geographic information (such as city information, latitude and longitude, and address). Parameters include frequency and / or intensity.

[0179] In the embodiment of the present application, there are many ways for the cloud device to obtain the feature library, which can be stored in advance, extracted from a database, or received from other devices, etc., which are not limited here.

[0180] Optionally, the feature library may further include relevant information of each POI, and the relevant information includes at least one of the following: POI name, POI type, etc.

[0181] After receiving the second request sent by the terminal device, the cloud device can determine the POI features in the feature library based on the first area. Specifically, the POI features of the first area are obtained by matching the first area with the geographic information of each POI in the feature library.

[0182] Furthermore, if the feature library includes a POI type, and the second request is also used to indicate a POI type, then the type of the POI corresponding to the POI feature determined by the cloud device conforms to the POI type indicated by the second request.

[0183] Step 303: The cloud device sends the POI features to the terminal device.

[0184] After the cloud device determines the POI features of the first area, it sends the POI features to the terminal device. In response, the terminal device receives the POI features sent by the cloud device. The terminal device can then pre-identify the POI based on the POI features. For details, please refer to step 203 in the embodiment shown in FIG. 2 , and will not be repeated here.

[0185] It is understandable that FIG3 only describes one case of step 201 in the embodiment shown in FIG2 . In actual applications, there are other possibilities for step 201 , which are not specifically limited here.

[0186] In the embodiment of the present application, the cloud device receives the second request from the terminal device and provides the terminal device with a BSSID whose parameters are greater than a threshold and related information of the BSSID, thereby facilitating the terminal device to pre-identify the POI.

[0187] In addition, embodiments of the present application also provide another data processing method in which a terminal device can collect data packets while moving and / or participating in on-site interactive activities and report them to a cloud device. The cloud device can then generate a database based on the data packets reported by multiple terminal devices, facilitating subsequent accurate POI identification based on user requests. This method can generate a database for POI identification without requiring on-site data collection by specialized technicians, thereby improving database generation efficiency.

[0188] Please refer to Figure 4, which is another flowchart of the data processing method provided by an embodiment of the present application. The method may include steps 401 to 404. Steps 401 to 404 are described in detail below.

[0189] Step 401: The terminal device collects data.

[0190] There are many ways for terminal devices to collect data, which may include at least one of the following: WIFI information collected by the terminal device during movement (or called trajectory crowdsourcing data), information collected by the terminal device during on-site interactive behaviors (payment, code scanning, NFC) (or called behavior crowdsourcing data), etc.

[0191] The Wi-Fi information can also be understood as a Wi-Fi fingerprint, which includes the Wi-Fi ID and the statistical value of the Wi-Fi ID's corresponding strength. The aforementioned interaction between the terminal device and the site can include at least one of the following: payment, code scanning, near field communication (NFC), Bluetooth, etc.

[0192] Optionally, the terminal device collects Wi-Fi information while it is moving. For example, the terminal device is in a specific area (such as a shopping mall, airport, entertainment facility, etc.) and collects Wi-Fi information at intervals. Of course, data from the base station to which the terminal device belongs can also be collected.

[0193] Optionally, the terminal device collects data during on-site interactive activities. For example, when a user uses a terminal device to pay at a store, store-related information (e.g., including at least one of the following: store name, store street information, store Wi-Fi, data of the base station to which the terminal device belongs, store category, brand name, etc.) can be collected through the payment interface. For another example, when a user uses a terminal device to scan a code at a store, store-related information can be collected through the interface that pops up after scanning the code.

[0194] It is understandable that the above collection process may be triggered with the authorization or permission of the user.

[0195] Step 402: The terminal device sends a data packet to the cloud device.

[0196] After collecting data, the terminal device sends a data packet to the cloud device. The cloud device then receives the data packet sent by the terminal device. The data packet includes the data collected by the terminal device in step 401. This data packet is used by the cloud device to identify POIs. For example, the data packet is used to generate a database, which is then used to determine the target POI.

[0197] Optionally, in addition to the data collected by the terminal device in step 401, the data packet may also include corresponding longitude and latitude information of the terminal device during the collection process.

[0198] In the embodiment of the present application, the data packet can be actively reported by the terminal device, or the cloud device can issue an instruction so that the terminal device reports it according to the instruction. The specific details are not limited here.

[0199] In step 403 , the cloud device aggregates at least two data packets to obtain at least two temporary POIs.

[0200] After receiving at least two data packets sent by at least two terminal devices, the cloud device may aggregate the at least two data packets to obtain at least two temporary POIs.

[0201] It's understandable that crowdsourced behavior data includes POI descriptions. However, crowdsourced trajectory data may not include POI descriptions, necessitating the use of a Wi-Fi-POI relationship database to determine the POI descriptions for the crowdsourced trajectory data. This Wi-Fi-POI relationship database represents the mapping between Wi-Fi and POIs. This database can be pre-stored or manually annotated, and the specifics are not limited here.

[0202] After the cloud device obtains at least two data packets, it can determine the POI description information related to the Wi-Fi name from the data packets and then obtain the POI intermediate data, which includes the POI's geographic information, POI description information, and the POI's Wi-Fi list.

[0203] The cloud device determines geographic information based on at least one of the latitude and longitude information of the terminal device when collecting data or the data of the base station to which the terminal device belongs, and then clusters the data packets using the geographic information and the Wi-Fi fingerprint to obtain multiple temporary POIs.

[0204] Optionally, before clustering the data packets, the cloud device may also perform data cleansing on at least two data items, for example, deleting data that the user does not wish to disclose or redundant data, thereby improving user privacy or reducing storage consumption. In this case, the cloud device uses geographic information to cluster the cleaned data packets to obtain at least two temporary POIs.

[0205] Among them, POI description information can be understood as information related to the POI, specifically the store name corresponding to the POI, street information, store WIFI, store category, brand name, etc.

[0206] Optionally, the cloud device can filter outliers during the clustering process. Alternatively, a maturity assessment can be performed on at least two temporary POIs to filter out immature temporary POIs (e.g., POIs whose crowdsourced metrics are less than a threshold are deleted. Metrics include one or more of the following: clustering metrics, sample size, etc.).

[0207] In step 404 , the cloud device associates at least two temporary POIs with the POI library to obtain a database.

[0208] The cloud device obtains a POI library (also known as a POI parent library or map database, etc.), which can be understood as being built by a map manufacturer. The POI library includes at least two POI identifiers and basic information corresponding to at least two POI identifiers. The basic information includes at least one of the following: the POI name, the street information where the POI is located, the Wi-Fi network corresponding to the POI, the data of the base station to which the POI belongs, the POI classification, and the brand name corresponding to the POI. This step can also be understood as associating the at least two temporary POIs with the POI entity in the POI library through entity linking.

[0209] The cloud device may obtain the POI library through manual collection, receiving information sent by other devices, or selecting it from a database, etc., and the specific method is not limited here.

[0210] After the cloud device obtains the POI library and at least two temporary POIs, it associates the at least two temporary POIs with the POI library to obtain a database. The process of generating a database by the cloud device can also be a process of creating a database from scratch or a process of updating the database. The specific process is not limited here.

[0211] Optionally, the cloud device aggregates Wi-Fi fingerprints for each POI entity in the POI database to create a database. The database stores POI information and POI fingerprints, with each POI fingerprint including at least one Wi-Fi fingerprint. The POI information includes a POI identifier and geographic information, and also includes at least one of the following: a POI name and a POI type. The at least one Wi-Fi fingerprint includes at least one Wi-Fi network, and each of the at least one Wi-Fi network includes its own BSSID and strength.

[0212] Furthermore, if a temporary POI is not linked to the POI database, it indicates that a new POI entity has been added to the site or the old POI no longer exists. In this case, on-site personnel can be assigned to update the store information. Compared to the existing method of regularly maintaining the POI database, this method can promptly detect changes to POI entities and update the database.

[0213] Optionally, the cloud device can also extract a feature library from the database. The feature library includes the BSSID of each POI whose parameters are greater than a threshold and the corresponding statistical values, and the geographic information of each POI. The parameters include: frequency and / or intensity. The feature library is used to provide POI features for the terminal device. The POI features are related to at least one candidate POI.

[0214] Alternatively, it can be understood that the cloud device extracts the BSSID with higher parameters of each POI to facilitate subsequent assistance to the terminal device in the preliminary identification of the POI.

[0215] In the embodiments of this application, instead of adding specialized personnel to collect data on-site to build a database, the database is built using data collected by mobile devices or during interactive activities. This not only automates Wi-Fi training but also allows for the timely detection of newly opened or recently closed stores.

[0216] It is understood that the embodiments shown in Figures 2 to 4 can be combined with each other. For example, the embodiment shown in Figure 2 can be combined with the embodiment shown in Figure 3. For another example, the embodiment shown in Figure 2 can be combined with the embodiment shown in Figure 4. For another example, the embodiment shown in Figure 2 can be combined with the embodiments shown in Figures 3 and 4. Specific limitations are not provided herein.

[0217] The data processing method in the embodiment of the present application is described above. The relevant devices in the embodiment of the present application are described below. Please refer to Figure 5. An embodiment of the terminal device in the embodiment of the present application includes:

[0218] An acquiring unit 501 is configured to acquire a point of interest (POI) feature of a first area, where the POI feature includes a POI identifier, a first basic service set identifier (BSSID) corresponding to the POI identifier, and related information of the first BSSID.

[0219] The acquiring unit 501 is further configured to acquire a wireless fidelity WIFI list, where the WIFI list includes at least one WIFI, and each WIFI in the at least one WIFI includes its own second BSSID and strength;

[0220] The transceiver unit 502 is configured to send a first request to the cloud device, where the first request carries at least one candidate POI and a WIFI list, and the at least one candidate POI is related to the POI feature and the WIFI list;

[0221] The transceiver unit 502 is further configured to receive a target POI sent by the cloud device, where the target POI belongs to at least one candidate POI.

[0222] Optionally, the at least one candidate POI is associated with the POI feature and the WIFI list, including: the at least one candidate POI is a POI whose POI confidence in the POI feature is greater than or equal to a preset threshold, and the POI confidence is used to indicate a degree of matching between the POI feature and the WIFI list.

[0223] Optionally, the acquisition unit 501 is specifically configured to send a second request to the cloud device, where the second request is used to request the POI features of the first area; the acquisition unit 501 is specifically configured to receive the POI features sent by the cloud device.

[0224] Optionally, the acquiring unit 501 is specifically configured to send a first request to the cloud device if a preset condition is met;

[0225] The prerequisites include at least one of the following:

[0226] The movement distance of the terminal device is greater than or equal to a first threshold, where the movement distance is the distance between the location of the terminal device when the request was last sent to the cloud device and the current location of the terminal device;

[0227] The difference between the WiFi list and the previously acquired WiFi list is greater than or equal to a second threshold;

[0228] After neural network analysis, the conclusion is to send the first request.

[0229] Optionally, the relevant information includes a statistical value of the first BSSID, the statistical value includes at least a maximum value and a minimum value, and the statistical value is used to measure strength information of the first BSSID.

[0230] Optionally, the terminal device further includes: a recommendation unit 503, configured to recommend related services based on the target POI.

[0231] Optionally, the terminal device also includes: a collection unit 504, which is used to collect at least one data packet, each of the at least one data packet includes WIFI information collected by the terminal device during movement and / or information collected by the terminal device during on-site interactive behavior; a transceiver unit 502, which is also used to send at least one data packet to the cloud device, and the at least one data packet is used by the cloud device to generate a database, and the database is used to determine the target POI.

[0232] In this embodiment, the operations performed by each unit in the terminal device are similar to those described in the embodiments shown in Figures 1 to 4 above, and will not be repeated here.

[0233] In this embodiment, compared to existing solutions that rely entirely on the cloud for POI identification, this application performs pre-identification on the terminal before performing precise identification on the cloud. This not only improves POI identification accuracy but also reduces the computing load on the cloud. Furthermore, POI identification can be completed based on a single round of Wi-Fi list scanning, which reduces overall identification latency compared to the existing multiple rounds of Wi-Fi scanning.

[0234] Please refer to FIG6 , an embodiment of the cloud device in the embodiment of the present application includes:

[0235] The transceiver unit 601 is configured to receive a first request from a terminal device, where the first request carries at least one candidate POI and a WIFI list, where the WIFI list includes at least one WIFI, and each WIFI in the at least one WIFI includes its own second BSSID and strength;

[0236] The transceiver unit 601 is further configured to send a target POI to the terminal device. The target POI is associated with a database, at least one candidate POI, and a WIFI list. The database stores POI information and POI fingerprints. Each POI fingerprint includes at least one WIFI fingerprint.

[0237] Optionally, the cloud device further includes: an acquisition unit 602, configured to acquire a database, wherein the POI information includes a POI identifier and geographic information, and the POI information further includes at least one of the following: a name, a POI type, and at least one WIFI fingerprint includes at least one WIFI, and each WIFI in the at least one WIFI includes its own BSSID and strength.

[0238] Optionally, the acquisition unit 602 is specifically used to receive at least one data packet reported from at least one terminal device, each of the at least one data packet includes WIFI information collected by the corresponding terminal device during movement and / or information collected by the terminal device when participating in on-site interactive behavior; the acquisition unit 602 is specifically used to aggregate at least two data packets to obtain at least two temporary POIs; the acquisition unit 602 is specifically used to associate the at least two temporary POIs with a POI library to obtain a database, the POI library includes at least two POI identifiers and basic information corresponding to the at least two POI identifiers.

[0239] Optionally, the cloud device also includes: an extraction unit 603, which is used to extract a feature library from the database, the feature library including the BSSID of each POI with parameters greater than a threshold and corresponding statistical values, and the geographic information of each POI, the parameters including: frequency and / or intensity, the feature library is used to provide POI features for the terminal device, and the POI features are related to at least one candidate POI.

[0240] Optionally, the transceiver unit 601 is also used to receive a second request from the terminal device, the second request is used to request the POI features of the first area, the POI features include the POI identifier, the first basic service set identifier BSSID corresponding to the POI identifier, and related information of the first BSSID; the transceiver unit 601 is also used to determine the POI features in the feature library based on the first area; the transceiver unit 601 is also used to send the POI features to the terminal device.

[0241] Optionally, the target POI is associated with a database, at least one candidate POI, and a WIFI list, including: the database is used to determine a POI fingerprint associated with at least one candidate POI, and the similarity between each WIFI fingerprint in the POI fingerprint and each WIFI in the WIFI list is associated with the target POI.

[0242] In this embodiment, the operations performed by each unit in the cloud device are similar to those described in the embodiments shown in Figures 1 to 4 above, and will not be repeated here.

[0243] In this embodiment, compared to existing solutions that rely entirely on the cloud for POI identification, this application performs pre-identification on the terminal before performing precise identification on the cloud. This not only improves POI identification accuracy but also reduces the computing load on the cloud. Furthermore, POI identification can be completed based on a single round of Wi-Fi list scanning, which reduces overall identification latency compared to the existing multiple rounds of Wi-Fi scanning.

[0244] Please refer to Figure 7. This embodiment of the present application provides another terminal device. For ease of explanation, only the parts related to this embodiment of the present application are shown. For specific technical details not disclosed, please refer to the method section of this embodiment of the present application. The terminal device can be any terminal device including a mobile phone, tablet computer, personal digital assistant (PDA), point of sales (POS), car computer, etc. Taking the mobile phone as an example:

[0245] FIG7 is a block diagram showing a partial structure of a mobile phone related to a terminal device provided in an embodiment of the present application. Referring to FIG7 , the mobile phone includes components such as a radio frequency (RF) circuit 710, a memory 720, an input unit 730, a display unit 740, a sensor 750, an audio circuit 760, a wireless fidelity (WiFi) module 770, a processor 780, and a power supply 790. Those skilled in the art will appreciate that the mobile phone structure shown in FIG7 does not limit the mobile phone and may include more or fewer components than shown, or combine certain components, or arrange the components differently.

[0246] The following is a detailed introduction to the various components of the mobile phone in conjunction with Figure 7:

[0247] The RF circuit 710 can be used to receive and send signals during information transmission or calls. In particular, after receiving downlink information from the base station, it is sent to the processor 780 for processing; in addition, the designed uplink data is sent to the base station. Generally, the RF circuit 710 includes but is not limited to an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier (LNA), a duplexer, etc. In addition, the RF circuit 710 can also communicate with the network and other devices through wireless communication. The above-mentioned wireless communication can use any communication standard or protocol, including but not limited to the global system of mobile communications (GSM), general packet radio service (GPRS), code division multiple access (CDMA), wideband code division multiple access (WCDMA), long term evolution (LTE), email, short messaging service (SMS), etc.

[0248] The memory 720 can be used to store software programs and modules. The processor 780 executes the various functional applications and data processing of the mobile phone by running the software programs and modules stored in the memory 720. The memory 720 can mainly include a program storage area and a data storage area. The program storage area can store an operating system and at least one application required for a function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created based on the use of the mobile phone (such as audio data, a phone book, etc.). In addition, the memory 720 can include high-speed random access memory and non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0249] The input unit 730 can be used to receive input digital or character information, and to generate key signal input related to the user settings and function control of the mobile phone. Specifically, the input unit 730 may include a touch panel 731 and other input devices 732. The touch panel 731, also known as a touch screen, can collect user touch operations on or near it (such as operations performed by the user using any suitable object or accessory such as a finger, stylus, etc. on or near the touch panel 731) and drive the corresponding connection device according to a pre-set program. Optionally, the touch panel 731 may include two parts: a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch direction and detects the signal caused by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device and converts it into touch point coordinates, which are then sent to the processor 780. It can also receive commands sent by the processor 780 and execute them. In addition, the touch panel 731 can be implemented using various types such as resistive, capacitive, infrared and surface acoustic wave. In addition to the touch panel 731, the input unit 730 may further include other input devices 732. Specifically, the other input devices 732 may include, but are not limited to, one or more of a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, and a joystick.

[0250] The display unit 740 can be used to display information input by the user or information provided to the user and various menus of the mobile phone. The display unit 740 may include a display panel 741. Optionally, the display panel 741 may be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), etc. Further, the touch panel 731 may cover the display panel 741. When the touch panel 731 detects a touch operation on or near it, it is transmitted to the processor 780 to determine the type of touch event. Subsequently, the processor 780 provides a corresponding visual output on the display panel 741 according to the type of touch event. Although in Figure 7, the touch panel 731 and the display panel 741 are used as two independent components to implement the input and output functions of the mobile phone, in some embodiments, the touch panel 731 and the display panel 741 can be integrated to implement the input and output functions of the mobile phone.

[0251] The mobile phone may also include at least one sensor 750, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor, wherein the ambient light sensor may adjust the brightness of the display panel 741 according to the brightness of the ambient light, and the proximity sensor may turn off the display panel 741 and / or the backlight when the mobile phone is moved to the ear. As a type of motion sensor, the accelerometer sensor can detect the magnitude of acceleration in all directions (generally three axes), and can detect the magnitude and direction of gravity when stationary. It can be used for applications that identify the posture of the mobile phone (such as horizontal and vertical screen switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, tapping), etc.; as for other sensors that the mobile phone can also be configured with, such as gyroscopes, barometers, hygrometers, thermometers, infrared sensors, etc., they will not be described here.

[0252] Audio circuit 760, speaker 761, and microphone 762 provide an audio interface between the user and the phone. Audio circuit 760 converts received audio data into electrical signals and transmits them to speaker 761, which then converts them into sound signals for output. Microphone 762, on the other hand, converts collected sound signals into electrical signals, which are then received by audio circuit 760 and converted into audio data. The audio data is then processed by processor 780 and transmitted to, for example, another phone via RF circuit 710, or stored in memory 720 for further processing.

[0253] WiFi is a short-range wireless transmission technology. A mobile phone can help users send and receive emails, browse the web, and access streaming media through WiFi module 770, providing users with wireless broadband Internet access. Although FIG7 shows WiFi module 770, it is understood that it is not a required component of a mobile phone.

[0254] Processor 780 is the control center of the mobile phone, connecting all parts of the mobile phone using various interfaces and circuits. By running or executing software programs and / or modules stored in memory 720 and accessing data stored in memory 720, it performs various functions of the mobile phone and processes data, thereby providing overall monitoring of the mobile phone. Optionally, processor 780 may include one or more processing units; preferably, processor 780 may integrate an application processor and a modem processor, wherein the application processor primarily handles the operating system, user interface, and application programs, while the modem processor primarily handles wireless communications. It is understood that the modem processor may not be integrated into processor 780.

[0255] The mobile phone also includes a power supply 790 (such as a battery) for supplying power to various components. Preferably, the power supply can be logically connected to the processor 780 through a power management system, thereby managing charging, discharging, and power consumption management functions through the power management system.

[0256] Although not shown, the mobile phone may also include a camera, a Bluetooth module, etc., which will not be described in detail here.

[0257] In an embodiment of the present application, the processor 780 included in the terminal device can perform the functions in the embodiments shown in Figures 1 to 4 above, which will not be repeated here.

[0258] Referring to FIG8 , a schematic diagram of the structure of another cloud device provided herein is shown. The cloud device may include a processor 801, a memory 802, and a communication port 803. The processor 801, the memory 802, and the communication port 803 are interconnected via a line. The memory 802 stores program instructions and data.

[0259] The memory 802 stores program instructions and data corresponding to the steps executed by the cloud device in the corresponding embodiments shown in Figures 1 to 4. For example, a database is stored.

[0260] The processor 801 is configured to execute the steps performed by the cloud device as shown in any of the embodiments shown in FIG. 1 to FIG. 4 .

[0261] The communication port 803 can be used to receive and send data, and to execute the steps related to acquisition, sending, and receiving in any of the embodiments shown in FIG. 1 to FIG. 4 .

[0262] In one implementation, the cloud device may include more or fewer components than those in FIG. 8 . This application is merely an illustrative description and does not limit this.

[0263] An embodiment of the present application also provides a computer-readable storage medium, which is used to store one or more computer-executable instructions. When the computer-executable instructions are executed by a processor, the processor executes the method described in the possible implementation methods of the terminal device or cloud device in the above embodiments.

[0264] An embodiment of the present application also provides a computer program product (or computer program). When the computer program product is executed by the processor, the processor executes the method that may be implemented by the above-mentioned terminal device or cloud device.

[0265] An embodiment of the present application also provides a chip system, which includes at least one processor for supporting a communication device to implement the functions involved in the possible implementation methods of the above-mentioned communication device. Optionally, the chip system also includes an interface circuit, which provides program instructions and / or data to the at least one processor. In one possible design, the chip system may also include a memory for storing the necessary program instructions and data for the communication device. The chip system can be composed of a chip, or it can include a chip and other discrete devices, wherein the communication device can specifically be a terminal device or a cloud device in the aforementioned method embodiment.

[0266] An embodiment of the present application also provides a communication system, which includes the terminal device and cloud device in any of the above embodiments.

[0267] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0268] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0269] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in whole or in part through software, hardware, firmware, or any combination thereof.

[0270] When software is used to implement the integrated unit, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in accordance with the embodiments of the present invention are generated in whole or in part. 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 website, computer, server, or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, hard disk, tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0271] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, and this is merely a way of distinguishing the objects of the same attributes when describing them in the embodiments of the present application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, so that the process, method, system, product or equipment comprising a series of units need not be limited to those units, but may include other units that are not clearly listed or inherent to these processes, methods, products or equipment.

Claims

1. A data processing method, characterized in that: The method is applied to a terminal device, and the method comprises: Acquire a point of interest (POI) feature of the first area, the POI feature including a POI identifier, a first basic service set identifier (BSSID) corresponding to the POI identifier, and related information of the first BSSID; Obtain a wireless fidelity WIFI list, wherein the WIFI list includes at least one WIFI, and each WIFI in the at least one WIFI includes its own second BSSID and strength; Sending a first request to a cloud device, wherein the first request carries at least one candidate POI and the WIFI list, and the at least one candidate POI is related to the POI feature and the WIFI list; A target POI sent by the cloud device is received, where the target POI belongs to the at least one candidate POI.

2. The method according to claim 1, characterized in that The at least one candidate POI is associated with the POI feature and the WIFI list, including: the at least one candidate POI is a POI in the POI feature whose POI confidence is greater than or equal to a preset threshold, and the POI confidence is used to indicate the degree of matching between the POI feature and the WIFI list.

3. The method according to claim 1 or 2, characterized in that: The obtaining of the point of interest (POI) feature of the first area includes: Sending a second request to the cloud device, where the second request is used to request the POI feature of the first area; Receive the POI feature sent by the cloud device.

4. The method according to any one of claims 1 to 3, characterized in that The sending a first request to the cloud device includes: If the preset conditions are met, sending the first request to the cloud device; The preset condition includes at least one of the following: The moving distance of the terminal device is greater than or equal to a first threshold, and the moving distance is the distance between the location of the terminal device when the request was last sent to the cloud device and the current location of the terminal device; The difference between the WIFI list and the previously acquired WIFI list is greater than or equal to a second threshold; A conclusion is obtained through neural network analysis, and the conclusion is to send the first request.

5. The method according to any one of claims 1 to 4, characterized in that The relevant information includes a statistical value of the first BSSID, the statistical value includes at least a maximum value and a minimum value, and the statistical value is used to measure the strength information of the first BSSID.

6. The method according to any one of claims 1 to 5, characterized in that The method further comprises: Recommend related services based on the target POI.

7. The method according to any one of claims 1 to 6, characterized in that The method further comprises: Collecting at least one data packet, each of the at least one data packet includes WIFI information collected by the terminal device during movement and / or information collected by the terminal device during on-site interactive behavior; The at least one data packet is sent to the cloud device, where the at least one data packet is used by the cloud device to generate a database, and the database is used to determine the target POI.

8. A data processing method, characterized in that: The method is applied to a cloud device, and the method includes: Receive a first request from a terminal device, wherein the first request carries at least one candidate POI and a WIFI list, wherein the WIFI list includes at least one WIFI, and each WIFI in the at least one WIFI includes its own second BSSID and strength; A target POI is sent to the terminal device, where the target POI is related to a database, the at least one candidate POI, and the WIFI list, where the database stores POI information and POI fingerprints, and each POI fingerprint includes at least one WIFI fingerprint.

9. The method according to claim 8, characterized in that Before receiving the first request from the terminal device, the method further includes: The database is obtained, wherein the POI information includes a POI identifier and geographic information, and the POI information also includes at least one of the following: a name and a POI type; the at least one WIFI fingerprint includes at least one WIFI, and each WIFI in the at least one WIFI includes its own BSSID and strength.

10. The method according to claim 9, characterized in that The obtaining of the database comprises: Receiving at least one data packet reported from at least one terminal device, each of the at least one data packet includes WIFI information collected by the corresponding terminal device during movement and / or information collected by the terminal device during on-site interactive behavior; Aggregating at least two data packets to obtain at least two temporary POIs; The at least two temporary POIs are associated with a POI library to obtain the database, wherein the POI library includes at least two POI identifiers and basic information corresponding to the at least two POI identifiers.

11. The method according to any one of claims 8 to 10, characterized in that The method further comprises: A feature library is extracted from the database, wherein the feature library includes BSSIDs of POIs having parameters greater than a threshold value and corresponding statistical values, and geographic information of the POIs, wherein the parameters include: frequency and / or intensity. The feature library is used to provide POI features for the terminal device, and the POI features are related to the at least one candidate POI.

12. The method according to claim 11, characterized in that Before receiving the first request from the terminal device, the method further includes: receiving a second request from a terminal device, where the second request is used to request a POI feature of a first area, where the POI feature includes a POI identifier, a first basic service set identifier BSSID corresponding to the POI identifier, and related information of the first BSSID; Determine the POI feature in the feature library based on the first area; The POI feature is sent to the terminal device.

13. The method according to any one of claims 8 to 12, characterized in that The target POI is related to a database, the at least one candidate POI and the WIFI list, including: the database is used to determine a POI fingerprint related to the at least one candidate POI, and the similarity between each WIFI fingerprint in the POI fingerprint and each WIFI in the WIFI list is related to the target POI.

14. A terminal device, characterized in that: The terminal device comprises: An acquiring unit, configured to acquire a point of interest (POI) feature of a first area, wherein the POI feature includes a POI identifier, a first basic service set identifier (BSSID) corresponding to the POI identifier, and related information of the first BSSID; The acquisition unit is further used to acquire a wireless fidelity WIFI list, wherein the WIFI list includes at least one WIFI, and each WIFI in the at least one WIFI includes its own second BSSID and strength; A transceiver unit, configured to send a first request to a cloud device, wherein the first request carries at least one candidate POI and the WIFI list, and the at least one candidate POI is related to the POI feature and the WIFI list; The transceiver unit is further configured to receive a target POI sent by the cloud device, where the target POI belongs to the at least one candidate POI.

15. The device according to claim 14, characterized in that The at least one candidate POI is associated with the POI feature and the WIFI list, including: the at least one candidate POI is a POI in the POI feature whose POI confidence is greater than or equal to a preset threshold, the POI confidence is associated with a difference, and the difference is a difference between the relevant information of the first BSSID and the strength of the second BSSID in the WIFI list.

16. The device according to claim 14 or 15, characterized in that The acquisition unit is specifically configured to send a second request to a cloud device, where the second request is configured to request the POI feature of the first area; The acquisition unit is specifically configured to receive the POI feature sent by the cloud device.

17. The device according to any one of claims 14 to 16, characterized in that The acquisition unit is specifically configured to send the first request to the cloud device if a preset condition is met; The preset condition includes at least one of the following: The moving distance of the terminal device is greater than or equal to a first threshold, and the moving distance is the distance between the location of the terminal device when the request was last sent to the cloud device and the current location of the terminal device; The difference between the WIFI list and the previously acquired WIFI list is greater than or equal to a second threshold; A conclusion is obtained through neural network analysis, and the conclusion is to send the first request.

18. The device according to any one of claims 14 to 17, characterized in that The relevant information includes a statistical value of the first BSSID, the statistical value includes at least a maximum value and a minimum value, and the statistical value is used to measure the strength information of the first BSSID.

19. The device according to any one of claims 14 to 18, characterized in that The terminal device further includes: A recommendation unit is used to recommend related services based on the target POI.

20. The device according to any one of claims 14 to 19, characterized in that The terminal device further includes: A collection unit, configured to collect at least one data packet, each of the at least one data packet including WIFI information collected by the terminal device during movement and / or information collected by the terminal device during on-site interactive behavior; The transceiver unit is further configured to send the at least one data packet to the cloud device, and the at least one data packet is used for the cloud device. The terminal device generates a database, and the database is used to determine the target POI.

21. A cloud device, characterized in that: The cloud device includes: A transceiver unit, configured to receive a first request from a terminal device, wherein the first request carries at least one candidate POI and a WIFI list, wherein the WIFI list includes at least one WIFI, and each WIFI in the at least one WIFI includes its own second BSSID and strength; The transceiver unit is further used to send a target POI to the terminal device, where the target POI is related to a database, the at least one candidate POI and the WIFI list, and the database stores POI information and at least one WIFI fingerprint.

22. The device according to claim 21, characterized in that The cloud device also includes: The acquisition unit is used to acquire the database, wherein the POI information includes a POI identifier and geographic information, and the POI information also includes at least one of the following: a name and a POI type. The at least one WIFI fingerprint includes at least one WIFI, and each WIFI in the at least one WIFI includes its own BSSID and strength.

23. The device according to claim 22, characterized in that The acquisition unit is specifically configured to receive at least one data packet reported by at least one terminal device, each of the at least one data packet including WIFI information collected by the corresponding terminal device during movement and / or information collected by the terminal device during on-site interactive behavior; The acquisition unit is specifically used to aggregate at least two data packets to obtain at least two temporary POIs; The acquisition unit is specifically configured to associate the at least two temporary POIs with a POI library to obtain the database, wherein the POI library includes at least two POI identifiers and basic information corresponding to the at least two POI identifiers.

24. The device according to any one of claims 21 to 23, characterized in that The cloud device also includes: An extraction unit is used to extract a feature library from the database, wherein the feature library includes BSSIDs of POIs with parameters greater than a threshold and corresponding statistical values, and geographic information of the POIs, wherein the parameters include: frequency and / or intensity, and the feature library is used to provide POI features for the terminal device, and the POI features are related to the at least one candidate POI.

25. The device according to claim 24, characterized in that The transceiver unit is further configured to receive a second request from a terminal device, the second request being configured to request a POI feature of a first area, the POI feature comprising a POI identifier, a first basic service set identifier BSSID corresponding to the POI identifier, and related information of the first BSSID; The transceiver unit is further configured to determine the POI feature in the feature library based on the first area; The transceiver unit is further used to send the POI feature to the terminal device.

26. The device according to any one of claims 21 to 25, characterized in that The target POI is related to a database, the at least one candidate POI and the WIFI list, including: the database is used to determine a WIFI fingerprint related to the at least one candidate POI, and the similarity between the WIFI fingerprint and the WIFI list is related to the target POI.

27. A terminal device, characterized in that: The method comprises at least one processor coupled to a memory; the at least one processor is configured to execute the method according to any one of claims 1 to 7.

28. The terminal device according to claim 27, characterized in that: The terminal device is a chip.

29. A cloud device, characterized in that: The method comprises at least one processor coupled to a memory; the at least one processor is configured to execute the method according to any one of claims 8 to 13.

30. The cloud device according to claim 29, characterized in that: The cloud device is a chip.

31. A communication system, characterized in that: It includes the terminal device as described in claim 27 and the cloud device as described in claim 29, or it includes the terminal device as described in claim 28 and the cloud device as described in claim 30.

32. A readable storage medium, characterized in that: The storage medium stores a computer program or an instruction, and when the computer program or the instruction is executed by the communication device, the method according to any one of claims 1 to 13 is implemented.

33. A computer program product, characterized in that The method comprises instructions, which, when executed on a computer, cause the computer to perform the method according to any one of claims 1 to 13.

Images