A method, device and apparatus for identifying and locating a network access device

Abstract

The embodiment of the present application provides a kind of identification method, positioning method, device and equipment of network access equipment.Method includes: obtaining the positioning log and collection log of terminal equipment, network positioning data are included in positioning log;Satellite positioning data are included in collection log;Based on positioning log, obtain the subway line data of terminal equipment and the subway station corresponding to subway line data;According to subway line data, positioning log and collection log, determine the network access equipment deployed in subway station.The technical scheme provided in this embodiment, by obtaining positioning log and collection log, based on positioning log, obtain the subway line data of terminal equipment and the subway station corresponding to subway line data;According to subway line data, positioning log and collection log, determine the network access equipment deployed in the subway station, effectively realize the effective identification of network access equipment, so as to facilitate positioning operation based on network access equipment.

Description

Technical Field

[0001] This invention relates to the field of mobile communication technology, and in particular to a method, a positioning method, an apparatus, and a device for identifying network access devices. Background Technology

[0002] With the rapid development of technology, subways, as a form of public transportation, are expanding in both mileage and coverage area. However, since subways are usually located underground, when users are on the subway or after entering a subway station, their terminal devices cannot receive satellite positioning signals (such as GPS or BeiDou) and can only rely on network positioning. The accuracy of network positioning depends on the positioning fingerprint characteristics of network access devices such as Wi-Fi and base stations uploaded by the terminal device. Therefore, how to identify network access devices in the subway scenario, and ensure that these devices can guarantee the positioning accuracy of the terminal device in the subway scenario, is a problem that needs to be solved. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide a method, a method, a device, and a apparatus for identifying network access devices, which can effectively identify network access devices, thereby facilitating location operations based on network access devices and reducing location and maintenance costs.

[0004] In a first aspect, embodiments of the present invention provide a method for identifying a network access device, comprising:

[0005] Acquire the location logs and data collection logs of the terminal device. The location logs include network location data; the data collection logs include satellite location data.

[0006] Based on location logs, obtain subway line data of terminal devices and subway stations corresponding to the subway line data.

[0007] Based on subway line data, location logs, and data collection logs, the network access devices deployed in the subway stations were identified.

[0008] In a second aspect, embodiments of the present invention provide a network access device identification apparatus, comprising:

[0009] The acquisition module is used to acquire the location logs and collection logs of the terminal device. The location logs include network location data; the collection logs include satellite location data.

[0010] The processing module is used to obtain subway line data of the terminal device and the subway station corresponding to the subway line data based on the location log.

[0011] The determination module is used to determine the network access devices deployed in the subway stations based on subway line data, location logs, and collection logs.

[0012] Thirdly, embodiments of the present invention provide an electronic device including a processor and a memory. The memory stores one or more computer instructions, wherein the one or more computer instructions, when executed by the processor, implement the network access device identification method described in the first aspect. The electronic device may also include a communication interface for communicating with other devices or communication networks.

[0013] Fourthly, embodiments of the present invention provide a computer storage medium for storing a computer program that, when executed by a computer, implements the network access device identification method described in the first aspect above.

[0014] Fifthly, embodiments of the present invention provide a positioning method, wherein the positioning of a subway scene is performed based on the network access device identified by the network access device identification method described in the first aspect above.

[0015] Sixthly, embodiments of the present invention provide a positioning device, comprising: a memory and a processor; wherein,

[0016] The memory is used to store one or more computer instructions, wherein the one or more computer instructions, when executed by the processor, implement the positioning method as described in the fifth aspect above.

[0017] In a seventh aspect, embodiments of the present invention provide a computer storage medium for storing a computer program that, when executed by a computer, implements the positioning method described in the fifth aspect above.

[0018] By acquiring location logs and collection logs, subway line data and corresponding subway stations are obtained based on the location logs. Based on the subway line data, location logs, and collection logs, the network access devices deployed in the subway stations are identified, thus achieving effective identification of network access devices. This facilitates location operations based on network access devices, effectively ensuring the accuracy and reliability of processing location requests from subway passengers, thereby improving the practicality of the method. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 A flowchart of a network access device identification method provided in an embodiment of the present invention. Figure 1 ;

[0021] Figure 2 A scenario flowchart of a method for identifying a network access device provided in an embodiment of the present invention;

[0022] Figure 3 A flowchart of a network access device identification method provided in an embodiment of the present invention. Figure 2 ;

[0023] Figure 4 A flowchart of a network access device identification method provided in an embodiment of the present invention. Figure 3 ;

[0024] Figure 5 A flowchart for obtaining subway stations corresponding to the subway line data provided in this embodiment of the invention;

[0025] Figure 6 A flowchart for determining the expected running time corresponding to the subway line data is provided as an embodiment of the present invention;

[0026] Figure 7 A flowchart of a network access device identification method provided in an embodiment of the present invention. Figure 4 ;

[0027] Figure 8 A flowchart of a network access device identification method provided in an embodiment of the present invention. Figure 5 ;

[0028] Figure 9 A flowchart of a network access device identification method provided in an embodiment of the present invention. Figure 6 ;

[0029] Figure 10 A flowchart illustrating a method for identifying a network access device provided in an application embodiment of the present invention;

[0030] Figure 11 This is a schematic diagram of the structure of a network access device identification device provided in an embodiment of the present invention;

[0031] Figure 12 To and Figure 11 The illustrated embodiment provides a schematic diagram of the electronic device corresponding to the identification device for the network access device.

[0032] Figure 13 This is a schematic diagram of a positioning device provided in an embodiment of the present invention. Detailed Implementation

[0033] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0034] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “a,” “the,” and “the” used in the embodiments of this invention and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise. “Multiple” generally includes at least two, but does not exclude the inclusion of at least one.

[0035] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0036] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to identification.” Similarly, depending on the context, the phrases “if determination” or “if identification (of the condition or event of the statement)” can be interpreted as “when determination” or “in response to determination” or “when identification (of the condition or event of the statement)” or “in response to identification (of the condition or event of the statement).”

[0037] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a product or system comprising a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a product or system. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the product or system that includes said element.

[0038] Terminology Definition

[0039] Location log: The network location log generated when an object uses map positioning. In other words, the location log includes network location data. Network positioning refers to the positioning of a mobile device by scanning the surrounding WiFi and network access device signals when GPS positioning is not available.

[0040] Data collection log: When there is a Global Positioning System (GPS) signal, the object can use a map to locate itself and save all the current information. That is, the data collection log includes satellite positioning data.

[0041] Mobile WiFi: WiFi devices whose physical location changes frequently, such as mobile hotspots, 4G mobile routers, and WiFi hotspots on buses, subways, and high-speed trains.

[0042] Network access equipment: Network access equipment installed in subway stations or subway tunnels. This type of network access equipment has a different structure than network access equipment on the ground, and its coverage area is also smaller.

[0043] Hidden Markov Model: A hidden Markov model is a probabilistic model about time series. It describes the process of generating an unobservable sequence of states (hidden states) randomly from a hidden Markov chain, and then generating an observation from each state to produce a random sequence of observations (manifest states).

[0044] Location-to-collection ratio: The ratio of the number of objects located to the number of objects collected by a Wi-Fi or network access device within a certain period of time.

[0045] DBSCAN (Density-Based Spatial Clustering of Applications with Noise) is a representative density-based clustering algorithm. Unlike partitioning and hierarchical clustering methods, it defines a cluster as the largest set of density-connected points, enabling it to divide regions with sufficiently high density into clusters and discover clusters of arbitrary shapes in noisy spatial databases.

[0046] To facilitate understanding of the technical solution in this embodiment, the prior art will be described below:

[0047] Subway scenarios are typically underground, and when locating an object on a subway, GPS signals are often unavailable, necessitating the use of network positioning. Network positioning utilizes offline training data from Wi-Fi and network access devices, combining offline data with online positioning algorithms to determine the object's location. However, while some subway systems offer public Wi-Fi, this is often mobile or cloned Wi-Fi, lacking positioning capabilities. Alternatively, this approach requires strategically placing a router in a suitable location within the subway environment, relying on scanned Wi-Fi signal characteristics for location. While this method offers high accuracy, it suffers from drawbacks due to the need to consider various factors such as location selection, power, and frequency band, potentially requiring agreements with multiple map service providers, leading to high maintenance costs. Therefore, when locating an object on a subway, network access devices are the only viable option.

[0048] Furthermore, the timing of the steps in the following method embodiments is merely an example and not a strict limitation.

[0049] Figure 1 A flowchart of a network access device identification method provided in an embodiment of the present invention. Figure 1 ; Figure 2 A flowchart illustrating a method for identifying a network access device according to an embodiment of the present invention; see attached diagram. Figure 1-2 As shown, this embodiment provides a method for identifying a network access device. The main body executing this method is an identification device, which can be implemented as software or a combination of software and hardware. Specifically, the method may include:

[0050] S101: Obtain the location log and collection log of the terminal device. The location log includes network location data; the collection log includes satellite location data.

[0051] The identification device of the network access device can communicate with the terminal device, which stores location logs and collection logs. The location logs include data located via the network, and the collection logs include data located via GPS. The identification device can then obtain the location logs and collection logs from the terminal device. Specifically, this embodiment does not limit the specific implementation method for obtaining the location logs and collection logs; those skilled in the art can configure them according to specific application scenarios and requirements. For example, the identification device can send a log acquisition request to the terminal device, and after receiving the request, the terminal device can send the location logs and collection logs back to the identification device. Alternatively, the terminal device can send the location logs and collection logs to the identification device according to a preset collection period, such as 1 day, 2 days, 3 days, or 7 days, etc.

[0052] Of course, those skilled in the art can also use other methods to obtain location logs and collection logs, as long as the accuracy and reliability of obtaining location logs and collection logs can be guaranteed, which will not be elaborated here.

[0053] S102: Based on the location log, obtain the subway line data of the terminal device and the subway station corresponding to the subway line data.

[0054] After obtaining the location logs, they can be analyzed and processed to extract one or more subway line data scanned in the location logs. It should be noted that the obtained subway line data can be the trajectory information corresponding to subway stations, that is, the subway stations corresponding to the subway line data can be obtained through the location logs.

[0055] In other instances, when the subway line data does not have corresponding subway station trajectory information, in order to obtain the subway station corresponding to the subway line data, those skilled in the art can make settings according to specific application scenarios and design requirements. For example, the subway station corresponding to the subway line data can be obtained by accessing a preset database, which stores multiple subway line data and the correspondence between subway line data and subway stations.

[0056] Of course, those skilled in the art can also use other methods to obtain the subway stations corresponding to the subway line data, as long as they can ensure that the subway stations corresponding to the subway line data are obtained accurately and stably, which will not be elaborated here.

[0057] S103: Based on subway line data, location logs, and collection logs, determine the network access devices deployed in the subway stations.

[0058] After obtaining subway line data, location logs, and data collection logs, these data can be analyzed and processed to determine the network access devices deployed in the subway stations. It can be understood that the number of network access devices identified can be one or more. Specifically, based on the subway line data, location logs, and data collection logs, the network access devices deployed in the subway stations can include:

[0059] S1031: Determine all network access devices included in the location log and collection log, as well as the number of location objects and collection objects corresponding to each network access device.

[0060] After obtaining the location logs and collection logs, these logs can be analyzed to determine all network access devices included in the logs, as well as the number of location objects and collection objects corresponding to each network access device. It can be understood that all network access devices include both above-ground and underground network access devices, and each network access device has a larger number of location objects than collection objects. Specifically, determining the number of location objects and collection objects corresponding to each network access device can include:

[0061] S10311: Determine the number of location objects corresponding to each network access device based on the location log.

[0062] S10312: Determine the number of collection objects corresponding to each network access device based on the collection logs.

[0063] For each network access device, there are corresponding number of located objects and number of collected objects. The number of located objects refers to the number of objects for which a location operation is performed on the network access device, while the number of collected objects refers to the number of times a location operation is performed on the network access device and its objects. Specifically, the location log includes the number of located objects corresponding to each network access device, and the collection log includes the number of collected objects corresponding to each network access device. It can be understood that for the same network access device, the number of located objects is less than or equal to the number of collected objects.

[0064] For example, the location log may include the following location data for the network access device: location information of object A at time T1, location information of object B at time T2, location information of object A at time T3, location information of object C at time T3, etc. In this case, for the network access device, the number of located objects is the total number of objects A, B, and C, i.e., the number of located objects is 3. Similarly, the collection log may include the following location data for the network access device: location information of object A at time T1, location information of object B at time T2, location information of object A at time T3, location information of object C at time T3, etc. In this case, for the network access device, the number of collected objects is the number of times the location information at time T1, time T2, time T3, and time T3 is collected, i.e., the number of collected objects is 4.

[0065] It should be noted that the execution order of the above steps in this embodiment is not limited to the execution order represented by the above step numbers. That is, step S10312 can be executed before step S10311, or it can be executed simultaneously. Those skilled in the art can set it arbitrarily according to specific application requirements and design requirements.

[0066] In this embodiment, the number of location objects corresponding to each network access device is determined by the location log, and the number of collection objects corresponding to each network access device is determined by the collection log. This effectively ensures the accuracy and reliability of the acquisition of the number of location objects and the number of collection objects, and further improves the accuracy and reliability of identifying network access devices.

[0067] S1032: The first machine learning model is used to analyze and process the current location, the subway station, and the number of location objects and the number of collection objects corresponding to each network access device to determine the first access device deployed in the subway station among all network access devices. The first machine learning model is trained to identify the subway equipment information included in all network access devices.

[0068] The system includes a pre-trained first machine learning model (also known as a "classification model"), which is trained to identify subway equipment information included in all network access devices. Specifically, during the training of the first machine learning model, the following information can be obtained: subway line data, subway stations corresponding to the subway line data, the number of location objects and collection objects corresponding to each network access device, and the mapping relationship between the above information and the type of network access device. Specifically, the subway line data corresponding to the network access device, the subway stations corresponding to the subway line data, the number of location objects and collection objects corresponding to each network access device can be used as positive samples, and the subway line data corresponding to non-network access devices, the subway stations corresponding to the subway line data, the number of location objects and collection objects corresponding to each network access device can be used as negative samples for training, thereby obtaining the first machine learning model.

[0069] Then, after obtaining the subway line data, the subway stations corresponding to the subway line data, the number of positioning objects and the number of collection objects corresponding to each network access device, the first machine learning model can be used to analyze and process the subway line data, the subway stations corresponding to the subway line data, the number of positioning objects and the number of collection objects corresponding to each network access device, so as to determine the first access device included in all network access devices, which has the characteristic that the number of positioning objects is greater than the number of collection objects.

[0070] The network access device identification method provided in this embodiment obtains location logs and collection logs, acquires subway line data of terminal devices and subway stations corresponding to the subway line data based on the location logs, and determines the network access devices deployed in subway stations based on the subway line data, location logs and collection logs. This achieves effective identification of network access devices, thereby facilitating location operations based on network access devices, effectively ensuring the accuracy and reliability of processing location requests from subway passengers, and thus improving the practicality of the method.

[0071] Figure 3 A flowchart of a network access device identification method provided in an embodiment of the present invention. Figure 2 Based on the above embodiments, please continue to refer to the appendix. Figure 3 As shown, after obtaining subway line data based on location logs, the method in this embodiment may further include:

[0072] S301: Data quality for identifying subway line data.

[0073] S302: If the data quality does not meet the preset requirements, the subway line data will be filtered.

[0074] To accurately identify network access devices based on subway line data, after acquiring subway line data from location logs, the data can be analyzed to determine its quality. The quality of the subway line data is related to the continuity of time and trajectory. Specifically, a pre-set scanning device can be used to scan the subway line data, obtaining a first continuous feature and a second continuous feature in time. If the first continuous feature is greater than or equal to a first preset threshold, and the second continuous feature is greater than or equal to a second preset threshold, then the data quality meets the preset requirements. If the first continuous feature is less than the first preset threshold, and / or the second continuous feature is less than the second preset threshold, then the data quality does not meet the preset requirements. This allows for filtering of the subway line data, removing data that does not meet the preset requirements and retaining only the data that does, thereby improving the accuracy and reliability of network access device identification based on subway line data.

[0075] For example, consider the following subway line data: Subway Line Data A, Subway Line Data B, Subway Line Data C, and Subway Line Data D. Analysis of this data reveals that Subway Line Data A is discontinuous between time T1 and T2; Subway Line Data B is continuous in time and its trajectory is also continuous; Subway Line Data C is continuous in time, but its trajectory has gaps. For instance, Subway Line Data C is at station C1 at time T1 and at station C5 at time T2, but information for stations C2, C3, and C4 is missing between C1 and C5. In this case, the trajectory of Subway Line Data C is not continuous; Subway Line Data D is continuous in time and its trajectory is also continuous.

[0076] The above analysis and identification leads to the following conclusions: the data quality of subway line data A and subway line data C does not meet the preset requirements, while the data quality of subway line data B and subway line data D meets the preset requirements. Therefore, subway line data B and subway line data D can be retained, while subway line data A and subway line data C can be filtered to improve the accuracy and reliability of network access device identification based on subway line data.

[0077] Figure 4 A flowchart of a network access device identification method provided in an embodiment of the present invention. Figure 3 Based on the above embodiments, please continue to refer to the appendix. Figure 4 As shown, after obtaining subway line data based on location logs, the method in this embodiment may further include:

[0078] S401: Obtain standard station information corresponding to the metro line data.

[0079] S402: Based on standard station information and subway stations, detect whether subway stations are missing in the subway line data.

[0080] S403: When subway line data is missing a station, the subway line data will be divided into multiple new subway line data based on the missing station.

[0081] To accurately identify network access devices based on subway line data, after obtaining the subway line data from location logs, the data can be analyzed to determine if any subway stations are missing. Specifically, standard station information (pre-configured standard station information) corresponding to the subway line data can be obtained first. Then, the subway stations traversed by the subway line data are analyzed and compared with the standard station information to identify whether any subway stations are missing. If subway line data is missing a station, to ensure the accuracy of network access device identification based on the missing subway line data, the subway line data can be divided into multiple new subway line data sets based on the missing stations. Network access devices can then be identified based on these new subway line data sets.

[0082] For example, consider subway line data A, which passes through the following subway stations: A1, A2, A3, A5, A6, A7, A8. The corresponding standard station information is: A1, A2, A3, A4, A5, A6, A7, A8. By comparison, we can see that subway line data A omits subway station A4. Therefore, based on the omitted subway station A4, subway line data A can be divided into two new subway line data sets: A' and A''. Subway line data A' passes through subway stations A1, A2, and A3; subway line data A'' passes through subway stations A5, A6, A7, and A8. In other words, using the omitted subway station as the breakpoint, the subway line data is divided into multiple new subway line data sets. Then, network access devices can be identified based on these new subway line data sets, effectively ensuring the accuracy and reliability of network access device identification.

[0083] Figure 5 This invention provides a flowchart for obtaining subway station data corresponding to subway line data; based on the above embodiments, please refer to the appendix. Figure 5As shown, this embodiment does not limit the specific implementation method for obtaining the subway station corresponding to the subway line data. Those skilled in the art can set it according to specific application and design requirements. Preferably, obtaining the subway station corresponding to the subway line data in this embodiment may include:

[0084] S501: Obtain original station information. The original station information does not match the subway line data.

[0085] In order to obtain the subway stations corresponding to the subway line data, the original station information that does not match the subway line data can be obtained first. Specifically, the original station information can be stored in a preset database and obtained by accessing the preset database; or, the original station information can be collected manually.

[0086] S502: Determine the initial state probability information, observation probability information, and state transition probability information between stations in the metro line data corresponding to the metro line data. The initial state probability information includes the transition probability corresponding to the first station in the metro line data, and the observation probability information includes the transition probability corresponding to each station in the metro line data.

[0087] For subway line data, since the data contains input-output relationships at various locations, the initial state probability information, observation probability information, and state transition probability information between stations can be determined based on these relationships. The initial state probability information and observation probability information conform to a Gaussian distribution. Specifically, determining the initial state probability information corresponding to the subway line data can include:

[0088] S5021: Obtain the first station included in the metro line data.

[0089] S5022: Determine the latitude and longitude of the first station and the trajectory latitude and longitude corresponding to the subway line data.

[0090] S5023: Determine the initial state probability information corresponding to the subway line data based on the station latitude and longitude and the trajectory latitude and longitude.

[0091] After acquiring the subway line data, a direction of travel can be set for the subway line data, thereby determining the first station included in the subway line data. The first station can refer to the starting station in a certain subway line data. Specifically, the latitude and longitude of the first station and the trajectory latitude and longitude of the corresponding subway line data can be obtained. Then, the latitude and longitude of the station and the trajectory latitude and longitude are analyzed and processed to determine the initial state probability information corresponding to the subway line data. This initial state probability information includes the transition probability corresponding to the first station in the subway line data.

[0092] In addition, determining the state transition probability information between stations in the subway line data can include:

[0093] S5024: Obtain the actual running time of the terminal device based on subway line data.

[0094] S5025: Determine the expected travel time corresponding to the metro line data.

[0095] S5026: Determine the state transition probability information corresponding to the metro line data based on the actual operating time and the expected operating time.

[0096] After obtaining the subway line data from the terminal device, the actual running time of the terminal device on the subway line data can be obtained based on the subway line data. Then, the expected running time corresponding to the subway line data can be determined. It can be understood that this expected running time is a pre-configured theoretical running time corresponding to the subway line data, and this expected running time may be the same as or different from the actual running time. After obtaining the actual running time and the expected running time, the actual running time and the expected running time can be analyzed and processed to determine the state transition probability information corresponding to the subway line data. Specifically, determining the state transition probability information corresponding to the subway line data based on the actual running time and the expected running time can include:

[0097] S50261: When the actual running time is the same as the expected running time, the state transition probability information corresponding to the subway line data is determined to be 1. Alternatively,

[0098] S50262: When the actual running time is less than the expected running time, the state transition probability information corresponding to the subway line data is determined to satisfy the first Gaussian distribution. Alternatively,

[0099] S50263: When the actual running time is longer than the expected running time, the state transition probability information corresponding to the subway line data is determined to satisfy the second Gaussian distribution. The decay characteristic of the second Gaussian distribution is slower than that of the first Gaussian distribution.

[0100] Specifically, after obtaining the actual running time and the expected running time, these two times can be analyzed and compared. If the actual running time is the same as the expected running time, it indicates that the prediction of the running time for the subject's subway ride data is relatively accurate, and the state transition probability information corresponding to the subway ride data can be determined to be 1. If the actual running time is less than the expected running time, it indicates that there is an error in the prediction of the running time for the subject's subway ride data, and the state transition probability information corresponding to the subway ride data can be determined to satisfy a first Gaussian distribution. If the actual running time is greater than the expected running time, it indicates that other factors may have prolonged the running time for the subject's subway ride data, and the state transition probability information corresponding to the subway ride data can be determined to satisfy a second Gaussian distribution. It should be noted that the decay characteristic of the second Gaussian distribution is slower than that of the first Gaussian distribution.

[0101] It should be noted that the execution order of the above steps in this embodiment is not limited to the execution order represented by the above step numbers. That is, steps S5024-S5026 can be executed before steps S5021-S5023, or they can be executed simultaneously. Those skilled in the art can make arbitrary settings according to specific application requirements and design requirements.

[0102] In this embodiment, the state transition probability information corresponding to the subway line data can be accurately determined by the actual running time and the expected running time. This facilitates the determination of the subway station corresponding to the subway line data based on the state transition probability information, effectively ensuring the accuracy and reliability of the method.

[0103] S503: The Viterbi algorithm is used to analyze and process the original station information, initial state probability information, observation probability information and state transition probability information to determine the subway station corresponding to the subway line data.

[0104] The Viterbi algorithm is a dynamic programming algorithm used to find the Viterbi path—the sequence of hidden states—that is most likely to produce the sequence of observed events. After obtaining the original station information, initial state probability information, observation probability information, and state transition probability information, the Viterbi algorithm can be used to analyze and process these information, thereby accurately and effectively determining the subway stations corresponding to the subway line data.

[0105] Of course, those skilled in the art can also use other methods or algorithms to determine the subway stations corresponding to the subway line data, as long as the accuracy and reliability of determining the subway stations corresponding to the subway line data can be guaranteed, which will not be elaborated here.

[0106] Figure 6 A flowchart for determining the expected travel time corresponding to subway line data is provided as an embodiment of the present invention; based on the above embodiments, please continue to refer to the appendix. Figure 6 As shown, this embodiment does not limit the specific implementation method for determining the expected running time corresponding to the subway line data. Those skilled in the art can set it according to specific application and design requirements. Preferably, the determination of the expected running time corresponding to the subway line data in this embodiment may include:

[0107] S601: Determine the distance between stations and the subway operating speed based on the subway line data.

[0108] S602: Determine the expected travel time corresponding to the subway line data based on the distance between stations and the subway operating speed.

[0109] After obtaining the subway line data, the distances between stations and the subway's operating speed can be determined. It's understood that these distances and speeds can be pre-configured. In practice, these distances and speeds can be stored in a pre-defined database, which can be accessed to obtain the corresponding distances and speeds. After obtaining these distances and speeds, they can be analyzed to determine the expected travel time corresponding to the subway line data. Specifically, determining the expected travel time of an object on the subway line based on the distances and speeds can include using the ratio of the distance to the speed as the expected travel time.

[0110] It is understood that those skilled in the art can also use other methods to obtain the expected running time corresponding to the subway line data, as long as the accuracy and reliability of the determination of the expected running time corresponding to the subway line data can be guaranteed, which will not be elaborated here.

[0111] Figure 7 A flowchart of a network access device identification method provided in an embodiment of the present invention. Figure 4 Based on the above embodiments, please continue to refer to the appendix. Figure 7 As shown, after determining the expected travel time corresponding to the subway line data, the method in this embodiment may further include:

[0112] S701: Detect whether the subway line data has changed.

[0113] S702: When the subway line data changes, the expected travel time will be increased by the preset transfer time.

[0114] The subway line data can include multiple different subway line data points. When a user takes the subway, they can transfer between different subway line data points. In this application scenario where the user is transferring between subway line data points, the expected travel time can be adjusted accordingly. Therefore, to ensure the accuracy and reliability of the expected travel time acquisition, after determining the expected travel time of the user on the subway line data, it is possible to detect whether the subway line data the user is taking has changed. Specifically, it is possible to detect whether the subway line data corresponding to the terminal device at time t1 and the subway line data corresponding to the terminal device at time t2 are the same subway line data. If the subway line data corresponding to the terminal device at time t1 and the subway line data corresponding to the terminal device at time t2 are different, it can be determined that the corresponding subway line data has changed. When the subway line data the user is taking changes, the expected travel time is increased by a preset transfer time. For example, when the user transfers to a different subway line data point, the expected travel time can be increased by 180 seconds; when the user transfers to the opposite direction of the same subway line data point, the expected travel time can be increased by 120 seconds.

[0115] In this embodiment, by detecting whether the data of the subway line the object is taking has changed, if the data of the subway line the object is taking changes, the expected travel time is increased by a preset transfer time. This effectively enables the accurate acquisition of the expected travel time in application scenarios where the object is transferring subway lines or changing the direction of travel, further improving the accuracy and reliability of the method.

[0116] Figure 8 A flowchart of a network access device identification method provided in an embodiment of the present invention. Figure 5 Based on any of the above embodiments, refer to the appendix. Figure 8 As shown, after determining all network access devices included in the location logs and collection logs, as well as the number of location objects and collection objects corresponding to each network access device, the method in this embodiment may further include:

[0117] S801: Identifies all network access devices, including neighboring devices and their location information.

[0118] To improve the accuracy and reliability of network access device identification, after obtaining all network access devices included in the location logs and collection logs, it is possible to identify neighboring devices among all network access devices and their location information. Specifically, one method for identifying neighboring devices among all network access devices includes:

[0119] S8011: Obtain the first network location request.

[0120] S8012: Based on the first network location request, perform a scan and identify all network access devices scanned as the first neighboring devices.

[0121] When an object requires location tracking, a first network location request can be sent from the terminal device to the identification device. This first network location request is used to locate the object's current position. Specifically, after the identification device receives the first network location request, it can perform a scan based on the request and identify all network access devices detected as first nearby devices.

[0122] For example, after obtaining the first network location request, a scan can be performed based on the first network location request. Suppose that network access device a, network access device b, network access device c, and network access device d are scanned. At this time, all the scanned network access devices can be identified as the first neighboring devices.

[0123] In addition, another method for identifying neighboring devices included in all network access devices includes:

[0124] S8013: Obtain the second network location request. The request times for the first network location request and the second network location request are different.

[0125] S8014: Perform a scan based on the second network location request, and identify all the scanned second access devices and all network access devices as second neighboring devices.

[0126] For example: after obtaining the first network location request at time T1, a scan can be performed based on the first network location request, such as scanning network access device a, network access device b, network access device c, and network access device d; after obtaining the second network location request at time T2, a scan can be performed based on the second network location request, such as scanning second access device a, second access device b, second access device c, and second access device d, and then all the scanned network access devices and all the second access devices can be identified as second neighboring devices.

[0127] In addition, another method for identifying neighboring devices included in all network access devices includes:

[0128] S8015: Obtain the overlapping device between the network access device and the second access device.

[0129] S8016: Determine the third network access device (excluding overlapping devices) and the fourth network access device (excluding overlapping devices) in the second access device.

[0130] S8017: The third network access device and the fourth network access device are identified as third neighboring devices.

[0131] For example: After obtaining the first network location request at time T1, a scan can be performed based on the first network location request to obtain all network access devices. Assume all network access devices include: network access device A, network access device B, network access device C, and network access device D. After obtaining the second network location request at time T2, a scan can be performed based on the second network location request to obtain all second access devices. Assume all second access devices include: network access device C, network access device D, network access device E, and network access device F. Analyzing and identifying the aforementioned network access devices and second access devices, overlapping devices between network access devices and second access devices are determined to include network access devices C and D. Then, the third network access devices (excluding overlapping devices) are determined to include network access devices A and B. The fourth network access devices (excluding overlapping devices) are determined to include network access devices E and F. The third and fourth network access devices can then be identified as the third neighboring devices.

[0132] In some instances, the priority of the first neighboring device is higher than that of the second neighboring device, and the priority of the second neighboring device is higher than that of the third neighboring device.

[0133] When determining neighboring devices among all network access devices, a network access device can be one or more of the aforementioned neighboring device types. That is, a network access device can be a first neighboring device, or both a first neighboring device and a second neighboring device. To ensure the accuracy and reliability of determining the neighboring device type of a network access device, the neighboring device type can be determined based on the priority corresponding to that type. For example, network access device A can be either a first neighboring device or a second neighboring device. In this case, since the priority of the first neighboring device is higher than that of the second neighboring device, network access device A is determined to be a first neighboring device. Network access device A can also be either a second neighboring device or a third neighboring device. In this case, since the priority of the second neighboring device is higher than that of the third neighboring device, network access device A is determined to be a second neighboring device.

[0134] It is understood that the types of proximity devices are not limited to the examples described above. Those skilled in the art can also set up other types of proximity devices according to specific application and design requirements, which will not be elaborated here.

[0135] After identifying neighboring devices among all network access devices, these neighboring devices can be analyzed and identified to obtain their location information. Specifically, identifying the location information of neighboring devices can include:

[0136] S8018: Obtain the network access device type and weight information for each neighboring device.

[0137] S8019: Use a clustering algorithm to cluster neighboring devices and their corresponding weight information to obtain the location information of neighboring devices.

[0138] The network access device types of neighboring devices can include at least one of the following: a first neighboring device, a second neighboring device, and a third neighboring device. Different weight information is pre-configured for each network access device type, with the weight of the first neighboring device being greater than that of the second neighboring device, and the weight of the second neighboring device being greater than that of the third neighboring device. After determining the neighboring devices included in all network access devices, the network access device type of each neighboring device can be determined. Then, the weight information corresponding to that neighboring device can be determined based on its network access device type. A clustering algorithm is then used to cluster the neighboring devices and their corresponding weight information, thereby obtaining the location information of the neighboring devices.

[0139] In this embodiment, by obtaining the network access device type and weight information of each neighboring device, and using a clustering algorithm to cluster the neighboring devices and their corresponding weight information, the location information of the neighboring devices can be accurately obtained.

[0140] S802: Utilize a second machine learning model to analyze and process the location information of neighboring devices, the number of located objects, and the number of collected objects to determine the second access devices included in all network access devices that correspond to the location logs and collection logs. The second access devices are deployed in subway stations. The second machine learning model is trained to identify the subway devices included in all network access devices.

[0141] The system includes a pre-trained second machine learning model (also known as a "classification model"), which is trained to identify subway equipment included in all network access devices. Specifically, during the training of the second machine learning model, the following information can be obtained: neighboring devices, the location information of neighboring devices, the number of location objects and the number of collection objects corresponding to each network access device, and the mapping relationship between the above information and the type of network access device. Specifically, the neighboring devices corresponding to the network access devices, their location information, the number of location objects and the number of collection objects corresponding to each network access device can be used as positive samples, while the neighboring devices not corresponding to the network access devices, their location information, the number of location objects and the number of collection objects corresponding to each network access device can be used as negative samples for training, thereby obtaining the second machine learning model.

[0142] Then, after obtaining the location information of neighboring devices, the number of location objects, and the number of collection objects, the second machine learning model can be used to analyze and process the aforementioned location information of neighboring devices, the number of location objects, and the number of collection objects, thereby determining the second access device included in all network access devices, which has the characteristic that the number of location objects is greater than the number of collection objects.

[0143] S803: Determine the target network access device corresponding to the current location based on the network access device and the second access device.

[0144] After acquiring the network access device and the second access device, these devices can be analyzed to determine the target network access device corresponding to the current location. Specifically, determining the target network access device corresponding to the current location based on the network access device and the second access device can include:

[0145] S8031: When the network access device range of the network access device is greater than the network access device range of the second access device, the network access device is determined as the target network access device corresponding to the current location.

[0146] or,

[0147] S8032: When the network access device range of the network access device differs from that of the second access device, the sum of the network access device ranges formed by the network access device and the second access device is determined as the target network access device corresponding to the current location. Alternatively,

[0148] S8033: When the network access device range of the network access device is smaller than the network access device range of the second access device, the second access device is determined as the target network access device corresponding to the current location.

[0149] Specifically, after acquiring the network access device and the second access device, the network access device range of the first access device can be analyzed and compared with that of the second access device. If the network access device's network access device range is greater than that of the second access device, then the first access device is identified as the target network access device corresponding to the current location. For example, suppose the network access device's network access device range includes network access devices A, B, C, D, and E, and the second access device's network access device range includes network access devices B, C, and D. In this case, the network access device's network access device range is greater than that of the second access device, and therefore, the first access device can be identified as the target network access device.

[0150] When the network access device range of the network access device differs from or is partially different from the network access device range of the second access device, the sum of the network access device ranges formed by the network access device and the second access device is determined as the target network access device corresponding to the current location. For example, suppose the network access device range of the network access device includes network access devices A, B, C, D, and E, and the network access device range of the second access device includes network access devices F, G, and H; or, the network access device range of the second access device includes network access devices B, C, F, G, and H. In this case, the network access device range of the network access device differs from or is partially different from the network access device range of the second access device. Therefore, the sum of the network access device ranges formed by the network access device and the second access device can be obtained as including: network access devices A, B, C, D, E, F, G, and H. Then, the sum of the above network access device ranges is determined as the target network access device.

[0151] When the network access device range of the first network access device is smaller than that of the second network access device, the second network access device is identified as the target network access device corresponding to the current location. For example, suppose the network access device range of the first network access device includes network access devices A, B, and C, and the network access device range of the second network access device includes network access devices A, B, C, and D. In this case, the network access device range of the first network access device is smaller than that of the second network access device, and therefore the second network access device can be identified as the target network access device.

[0152] In this embodiment, by identifying the neighboring devices and their location information among all network access devices, a second machine learning model is used to analyze and process the neighboring devices, their location information, the number of location objects, and the number of collection objects. This determines the second access device among all network access devices that corresponds to the location logs and collection logs. Then, based on the network access device and the second access device, the target network access device corresponding to the current location can be determined, thereby effectively improving the accuracy and reliability of identifying the target network access device.

[0153] Figure 9 A flowchart of a network access device identification method provided in an embodiment of the present invention. Figure 6 Based on any of the above embodiments, please continue to refer to the appendix. Figure 9 As shown, after determining the network access device corresponding to the current location, the method in this embodiment may further include:

[0154] S901: Identifies the number of network access devices.

[0155] S902: When the number of network access devices exceeds a preset threshold, the terminal device is determined to be located inside the subway station.

[0156] Specifically, after acquiring network access devices, the number of network access devices can be obtained. Then, the number of network access devices can be analyzed and compared with a preset threshold. When the number of network access devices is greater than the preset threshold, it can be determined that the terminal device is located in the subway station, that is, the object corresponding to the terminal device is taking the subway, thus realizing stable and effective identification of the scene of the object taking the subway.

[0157] In some instances, after obtaining the network access device, the current location of the object can be located based on the first access device.

[0158] In this embodiment, by identifying the number of network access devices, if the number of network access devices exceeds a preset threshold, it is determined that the object is riding the subway. This effectively realizes the identification of whether the object is riding the subway in the application scenario, thereby effectively improving the practicality of the method.

[0159] For specific applications, please refer to the appendix. Figure 10 As shown in the illustration, this application embodiment provides a method for identifying network access devices. This method can identify network access devices to perform subway scene identification based on the network access devices, and can also perform positioning operations based on the identified network access devices. Specifically, the method can include two parts: the first part is the active identification and location training of network access devices, including: iterative location association of network access devices, location acquisition ratio of network access devices, number of location objects, and number of acquisition objects, as well as the identification of network access devices; the second part is the location mining of network access devices based on subway line data, including: extraction of subway line data, location matching between network access devices and subway stations, and identification of network access devices. Finally, the identification results of network access devices obtained from the above two parts are merged to determine the final result of the network access devices.

[0160] I. Active Identification and Location Training of Network Access Devices

[0161] 1.1 Obtain characteristics such as the location acquisition ratio, the number of location objects, and the number of acquisition objects of network access devices.

[0162] Location logs and data collection logs are obtained from the terminal device. The location logs include data located via the network; the data collection logs include data located via GPS. Specifically, location logs and data collection logs can be obtained from the terminal device according to a preset collection period (e.g., 14 days, 15 days, 20 days, etc.). The location logs and data collection logs are then analyzed to obtain all network access devices scanned by the location logs and data collection logs. These network access devices can include both terrestrial network access devices and other similar devices. The number of located objects and the number of collected objects corresponding to all network access devices can then be obtained. Specifically, the number of located objects can be obtained based on the location logs, and the number of collected objects can be obtained based on the data collection logs. Then, the location acquisition ratio can be determined based on the number of location objects and the number of acquisition objects. After obtaining the number of location objects, the number of acquisition objects, and the location acquisition ratio, the parameters such as the number of location objects, the number of acquisition objects, and the location acquisition ratio can be analyzed and processed to determine the underground network access devices included in all network access devices. Among them, for underground network access devices, due to the application scenario of underground network access devices being located underground, underground network access devices have the characteristic that the number of location objects is greater than the number of acquisition objects.

[0163] 1.2 Identify nearby devices and their location information.

[0164] When a terminal device sends a location request to an identification device, it can typically scan multiple network access devices simultaneously for a single location request. These network access devices are generally spatially close, so the neighboring devices of the network access devices can be identified, and their location information can be determined.

[0165] Specifically, the implementation methods for determining neighboring devices may include:

[0166] (1) Directly nearby devices, obtain network location requests, and determine the network access devices that appear in the network location requests.

[0167] (2) Time proximity devices, obtain the first network location request and the second network location request entered in different time periods, and determine the network access device appearing in the first network location request and the second network location request.

[0168] (3) Indirectly adjacent equipment, that is, the direct neighbor of the direct neighbor.

[0169] It is important to note that directly adjacent devices have a higher priority than time-adjacent devices, and time-adjacent devices have a higher priority than indirect adjacent devices. Then, different weights are assigned to these three types of adjacent devices, with directly adjacent devices having a higher weight than time-adjacent devices, and time-adjacent devices having a higher weight than indirect adjacent devices.

[0170] Then, the DBSCAN clustering algorithm is used to cluster the network access device type and the weight information corresponding to the network access device type. Multiple iterations can be performed on the network access device type and the weight information corresponding to the network access device type to obtain the iteration position of the network access device.

[0171] 1.3. Determine the network access equipment.

[0172] By using a machine learning model to analyze and process the number of nearby devices, the number of located objects, and the number of collected objects, the network access devices included in all network access devices that correspond to the location logs and collection logs are identified. The machine learning model is trained to identify the network access devices included in all network access devices, and these network access devices can be identified as network access device results.

[0173] II. Location mining of network access devices based on subway line data

[0174] 2.1 Extraction, filtering, and segmentation of subway line data.

[0175] By obtaining subway line data from the location logs, if the quality of the subway line data does not meet the preset requirements, the subway line data can be filtered. If the subway line data omits subway stations, the subway line data can be segmented based on the omitted subway stations.

[0176] 2.2 Identification of network access devices.

[0177] The Hidden Markov Model (HMM) for subway station matching is a probabilistic model concerning time series. It describes the process of generating an unobservable sequence of states (latent states) randomly from a hidden Markov chain, and then generating an observation from each state, thus producing a random sequence of observations (manifest states). The sequence generated from the latent states is called the state sequence, and each state generates an observation; the resulting sequence of observations is called the observation sequence. Each position in the sequence can be considered as a time point. Taking the current position of the terminal device as the manifest-observation sequence, both the initial state probability vector pi and the observation probability matrix B can be defined as Gaussian distributions.

[0178] Specifically, the location of the terminal device at a subway station can be considered as a hidden state. The state transition probability matrix A between stations can be designed and modeled using the expected and actual running times of the terminal device. The solution is to determine which subway station the terminal device is at, which can be solved using the Viterbi algorithm.

[0179] The initial state probability vector pi and the observation probability matrix B can be expressed by a Gaussian distribution. The parameters in the Gaussian distribution can be determined by preset conditions. For example, the preset conditions may include: 95% of the positioning results fall within 500m of the true value result (correct subway station). The unique Gaussian distribution parameters can be determined by the above preset conditions, and the unique Gaussian distribution function can be determined by the Gaussian distribution parameters.

[0180] In addition, the probability transition matrix is ​​related to the expected running time. Specifically, the expected running time and the probability transition information included in the probability transition matrix can be determined according to the following rules:

[0181] (1) Expected travel time: The expected travel time between different stations on the same metro line can be obtained by length / speed. For application scenarios involving transfers between different metro lines, the expected travel time can be increased by a preset 180s; for application scenarios involving transfers in the opposite direction on the same metro line, the expected travel time can be increased by 120s, that is, the expected travel time should be increased to account for the actual walking or waiting time in the middle.

[0182] (2) Determine the transition probability matrix (here, a piecewise probability distribution function) based on the actual running time and the expected running time:

[0183] a. If the actual running time is equal to the expected running time, or within a certain range of the expected running time, then the transition probability information in the transition probability matrix is ​​set to 1;

[0184] b. If the actual running time is less than the expected running time, the transition probability information in the transition probability matrix will be determined as a Gaussian distribution;

[0185] c. If the actual running time is longer than the expected running time, the transition probability information in the transition probability matrix will be determined as a Gaussian distribution. However, the decay of this Gaussian distribution is relatively slow because the terminal equipment may be delayed in the middle.

[0186] After obtaining the aforementioned preset original station information, initial state probability vector pi, state transition probability matrix A, and observation probability matrix B, the Viterbi algorithm can be used to analyze and process the above information, thereby determining the subway station corresponding to the subway line data.

[0187] 2.3 Identification of Network Access Devices

[0188] By using subway line data, all network access devices scanned by terminal devices can be identified. These network access devices can include primary network access devices. Specifically, when each terminal device makes a location request, a primary network access device can be scanned based on that request. For example, a location request from a mobile terminal device can scan a primary network access device for China Mobile, a location request from a China Unicom terminal device can scan a primary network access device for China Unicom, and a location request from a China Telecom terminal device can scan a primary network access device for China Telecom. After obtaining the primary network access device, its location can be scanned, and the location of the subway station can be determined based on the location of the primary network access device.

[0189] Furthermore, the total number of network access devices includes not only underground network access devices but also above-ground network access devices. This is because during continuous iteration, if the network access devices on the terminal device haven't been updated, the scanned network access devices might actually be above-ground network access devices scanned before entering the subway. In other words, the total number of network access devices at this point could include above-ground network access devices. Additionally, subway line data doesn't entirely represent the terminal device's trajectory within the subway. Due to incomplete trajectory segmentation, parts of the trajectory might be located above ground, or even entirely outside the subway. For example, the presence of some above-ground network access devices means that a terminal device on the subway can scan network access devices within the station, and people outside the subway can also scan these devices. In short, these non-subway network access devices cannot be ignored. If a terminal device isn't actually inside the subway but is located near a subway station, the user experience is poor. Therefore, it's necessary to filter out these non-underground network access devices.

[0190] Specifically, supervised learning algorithms can be used to filter out non-underground network access devices. This involves using pre-configured ground truth samples (network access devices) within the subway station as positive samples, and then extracting a portion of the data collection logs from the ground near the subway station as negative samples. Features are then trained using parameters such as positive samples, negative samples, the location-to-collection ratio of network access devices, the number of located objects, the number of collected objects, and the type of network access device (above-ground or underground). This results in a classification model that can identify all network access devices, and this portion of network access device information can then be identified as the second access device result.

[0191] Of course, in addition to obtaining a classification model based on the above features, some artificial rules can be added. For example, the number of located objects and the number of collected objects for a network access device must reach a certain value within a week before it can be identified. Alternatively, network access device identification can also be achieved through other classification models. Besides features composed of information such as the location-to-collection ratio, the number of located objects, and the number of collected objects, more features of network access devices can be obtained. Furthermore, in addition to the DBSCAN clustering algorithm for iterative association of network access device locations, other clustering methods can be used to achieve iterative association of network access device locations.

[0192] Finally, after obtaining the network access device result and the second access device result, the target network access device corresponding to the current location can be determined based on the network access device result and the second access device result. Specifically, if the range of the network access device in the network access device result is greater than the range of the network access device in the second access device result, then the network access device result is determined as the target network access device corresponding to the current location; or, if the range of the network access device in the network access device result is partially different from the range of the network access device in the second access device result, then the sum of the ranges of the network access device in the network access device result and the second access device result is determined as the target network access device corresponding to the current location; or, if the range of the network access device in the network access device result is less than the range of the network access device in the second access device result, then the second access device result is determined as the target network access device corresponding to the current location.

[0193] The network access device identification method provided in this application embodiment does not rely on manually deployed related equipment. All data sources can be collected through terminal devices (or clients). It can not only effectively identify network access devices, but also has the advantages of low cost and wide coverage. In addition, after using this method, accurate and effective positioning operations can be performed based on the identified network access devices, thereby effectively improving the practicality of the method.

[0194] Furthermore, this embodiment provides a positioning method, wherein the positioning method can be based on the above. Figures 1-10 The network access device identification method in the illustrated embodiment identifies the network access devices deployed in the subway station and performs subway scene localization.

[0195] Specifically, through the above Figures 1-10 The network access device identification method shown in the embodiment can identify network access devices deployed in subway stations. After obtaining the network access device, the positioning operation in the subway scene can be realized based on the obtained network access device, thereby effectively realizing accurate and effective positioning operation of terminal devices located in the subway scene, and further improving the practicality of the positioning method.

[0196] Figure 11 This is a schematic diagram of the structure of a network access device identification device provided in an embodiment of the present invention; see attached diagram. Figure 11 As shown, this embodiment provides a network access device identification device, which can perform the above-described... Figure 1 The method for identifying network access devices is shown. Specifically, the identification device may include:

[0197] The acquisition module 11 is used to acquire the location log and collection log of the terminal device. The location log includes network location data; the collection log includes satellite location data.

[0198] Processing module 12 is used to obtain subway line data of terminal devices and subway stations corresponding to the subway line data based on location logs.

[0199] Module 13 is used to determine the network access devices deployed in the subway station based on subway line data, location logs, and collection logs.

[0200] In some instances, after obtaining the subway line data corresponding to the terminal device, the processing module 12 in this embodiment is also used to perform: obtaining standard station information corresponding to the subway line data; based on the standard station information and the subway station, detecting whether the subway line data is missing a subway station; if the subway line data is missing a subway station, then dividing the subway line data into multiple new subway line data based on the missing subway station.

[0201] In some instances, when determining the network access devices deployed in the subway station based on the subway line data, location logs, and collection logs, the determining module 13 can perform the following: determine all network access devices included in the location logs and collection logs, as well as the number of location objects and collection objects corresponding to each network access device; and use a first machine learning model to analyze and process the subway line data, subway station, and the number of location objects and collection objects corresponding to each network access device to determine the first access device deployed in the subway station included in all network access devices. The first machine learning model is trained to identify the subway equipment information included in all network access devices.

[0202] In some instances, when determining the number of location objects and the number of collection objects corresponding to each network access device, the determining module 13 may perform the following: determining the number of location objects corresponding to each network access device based on the location log; and determining the number of collection objects corresponding to each network access device based on the collection log.

[0203] In some instances, the number of objects located by the network access device is greater than the number of objects collected.

[0204] In some instances, when processing module 12 acquires the subway station corresponding to the subway line data, it can perform the following: acquire the original station information, which does not match the subway line data; determine the initial state probability information, observation probability information, and state transition probability information between stations in the subway line data corresponding to the subway line data, wherein the initial state probability information includes the transition probability corresponding to the first station in the subway line data, and the observation probability information includes the transition probability corresponding to each station in the subway line data; and analyze and process the original station information, initial state probability information, observation probability information, and state transition probability information using the Viterbi algorithm to determine the subway station corresponding to the subway line data.

[0205] In some instances, the initial state probability information and the observation probability information conform to a Gaussian distribution.

[0206] In some instances, when processing module 12 determines the initial state probability information corresponding to the metro line data, the processing module 12 may perform the following: obtain the first station included in the metro line data; determine the station latitude and longitude of the first station and the trajectory latitude and longitude of the metro line data; and determine the initial state probability information corresponding to the metro line data based on the station latitude and longitude and the trajectory latitude and longitude.

[0207] In some instances, when processing module 12 determines the state transition probability information between stations in the metro line data, processing module 12 can perform the following: obtain the actual running time of the terminal device based on the metro line data; determine the expected running time corresponding to the metro line data; and determine the state transition probability information corresponding to the metro line data based on the actual running time and the expected running time.

[0208] In some instances, when processing module 12 determines the state transition probability information corresponding to the subway line data based on the actual running time and the expected running time, processing module 12 can perform the following: if the actual running time is the same as the expected running time, then determine that the state transition probability information corresponding to the subway line data is 1; or, if the actual running time is less than the expected running time, then determine that the state transition probability information corresponding to the subway line data satisfies a first Gaussian distribution; or, if the actual running time is greater than the expected running time, then determine that the state transition probability information corresponding to the subway line data satisfies a second Gaussian distribution, wherein the decay characteristic of the second Gaussian distribution is slower than that of the first Gaussian distribution.

[0209] In some instances, when processing module 12 determines the expected running time corresponding to the metro line data, it may perform the following: determine the inter-station distance and metro running speed in the metro line data; and determine the ratio of the inter-station distance to the metro running speed as the expected running time corresponding to the metro line data.

[0210] In some instances, after determining all network access devices included in the location logs and collection logs, as well as the number of location objects and collection objects corresponding to each network access device, the processing module 12 in this embodiment can be used to perform the following: identify the neighboring devices included in all network access devices and their location information; analyze and process the neighboring devices, their location information, the number of location objects, and the number of collection objects using a second machine learning model to determine the second access device included in all network access devices that corresponds to the location logs and collection logs, wherein the second access device is deployed in the subway station, and the second machine learning model is trained to identify the subway equipment included in all network access devices; and determine the target access device deployed in the subway station based on the first access device and the second access device.

[0211] In some instances, when the processing module 12 identifies neighboring devices among all network access devices, the processing module 12 performs the following actions: obtaining a first network location request; scanning based on the first network location request, and identifying all scanned network access devices as first neighboring devices.

[0212] In some instances, when processing module 12 identifies neighboring devices among all network access devices, it performs the following actions: obtaining a second network location request, wherein the request times of the first network location request and the second network location request are different; and performing a scan based on the second network location request to identify all scanned second access devices and all network access devices as second neighboring devices.

[0213] In some instances, when processing module 12 identifies neighboring devices included in all network access devices, processing module 12 performs the following actions: acquiring overlapping devices between the first device and the second device; identifying a third device in the first device after removing overlapping devices and a fourth device in the second device after removing overlapping devices; and identifying the third device and the fourth device as third neighboring devices.

[0214] In some instances, the first neighboring device has a higher priority than the second neighboring device, and the second neighboring device has a higher priority than the third neighboring device.

[0215] In some instances, when processing module 12 identifies the location information of neighboring devices, it performs the following actions: obtaining the network access device type and weight information of each neighboring device; and using a clustering algorithm to cluster the neighboring devices and their corresponding weight information to obtain the location information of the neighboring devices.

[0216] In some instances, the network access device types of neighboring devices include first neighboring devices, second neighboring devices, and third neighboring devices; the weight of the first neighboring device is greater than the weight of the second neighboring device, and the weight of the second neighboring device is greater than the weight of the third neighboring device.

[0217] In some instances, when processing module 12 determines the target access device to be deployed in the subway station based on the first access device and the second access device, processing module 12 can perform the following: if the network access device range of the first access device is greater than the network access device range of the second access device, then the first access device is determined as the target access device to be deployed in the subway station; or, if the network access device range of the first access device is partially different from the network access device range of the second access device, then the sum of the network access device ranges formed by the first access device and the second access device is determined as the target access device to be deployed in the subway station; or, if the network access device range of the first access device is less than the network access device range of the second access device, then the second access device is determined as the target access device to be deployed in the subway station.

[0218] In some instances, after identifying the target access devices deployed in the subway station, the processing module 12 in this embodiment can be used to perform: identifying the number of target access devices; and if the number of target access devices is greater than a preset threshold, determining that the terminal device is located inside the subway station.

[0219] Figure 11 The device shown can perform Figures 1 to 10 For the methods in the embodiments shown, the parts not described in detail in this embodiment can be referred to the [examples / descriptions]. Figures 1 to 10 The embodiments shown are described in detail below. For the implementation process and technical effects of this technical solution, please refer to... Figures 1 to 10 The descriptions in the illustrated embodiments will not be repeated here.

[0220] In one possible design, Figure 11 The identification device for the network access device shown can be implemented as an electronic device, which can be various devices such as mobile phones, tablets, and servers. Figure 12 As shown, the electronic device may include a first processor 21 and a first memory 22. The first memory 22 is used to store data supporting the electronic device in performing the above-described actions. Figures 1-10In at least some of the embodiments shown, the program for identifying a network access device is provided, wherein a first processor 21 is configured to execute a program stored in a first memory 22.

[0221] The program includes one or more computer instructions, wherein when executed by the first processor 21, the one or more computer instructions can perform the following steps:

[0222] Acquire the location logs and data collection logs of the terminal device. The location logs include network location data; the data collection logs include satellite location data.

[0223] Based on location logs, obtain subway line data of terminal devices and subway stations corresponding to the subway line data;

[0224] Based on subway line data, location logs, and data collection logs, the network access devices deployed in the subway stations were identified.

[0225] Optionally, the first processor 21 is also used to perform the aforementioned Figures 1-10 All or part of the steps in at least some of the embodiments shown.

[0226] The structure of the electronic device may also include a first communication interface 23 for communication between the electronic device and other devices or communication networks.

[0227] In addition, embodiments of the present invention provide a computer storage medium for storing computer software instructions used by an electronic device, which includes instructions for executing the above-described... Figures 1-10 The procedures involved in the network access device identification method in at least some of the embodiments shown.

[0228] Figure 13 This is a schematic diagram of a positioning device provided in an embodiment of the present invention, with reference to the attached diagram. Figure 13 As shown, the positioning device may include a second processor 31 and a second memory 32. The second memory 32 stores a program that supports the positioning device in executing the positioning method shown in the above embodiments, and the second processor 31 is configured to execute the program stored in the second memory 32.

[0229] The program includes one or more computer instructions, wherein when one or more computer instructions are executed by the second processor 31, they can achieve the following: determine the network access devices deployed in the subway station and perform subway scene positioning.

[0230] Optionally, the second processor 31 is also used to perform all or part of the steps shown in the foregoing embodiments.

[0231] The structure of the electronic device may also include a second communication interface 33 for communication between the electronic device and other devices or communication networks.

[0232] In addition, embodiments of the present invention provide a computer storage medium for storing computer software instructions used by an electronic device, which includes a program for executing the positioning method shown in the above embodiments.

[0233] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. 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 the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0234] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of a necessary general-purpose hardware platform, or by a combination of hardware and software. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a computer product. The present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0235] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0236] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0237] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0238] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0239] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0240] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0241] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for identifying a network access device, wherein, Used to identify base stations deployed in subway stations, including: The system acquires the location logs and data collection logs of the terminal device, wherein the location logs include network location data and the data collection logs include satellite location data. Based on the location log, obtain the subway line data of the terminal device and the subway station corresponding to the subway line data; Identify all network access devices included in the location logs and collection logs, as well as the number of location objects and collection objects corresponding to each network access device; use a first machine learning model to analyze and process the subway line data, subway stations, and the number of location objects and collection objects corresponding to each network access device, and identify the first access devices deployed in the subway stations included in all network access devices. The first machine learning model is trained to identify subway equipment information included in all network access devices.

2. The method according to claim 1, wherein, After obtaining the subway line data corresponding to the terminal device based on the location log, the method further includes: Obtain standard station information corresponding to the subway line data; Based on the standard station information and the subway station, detect whether any subway stations are missing from the subway line data; When the subway line data is missing a station, the subway line data is divided into multiple new subway line data based on the missing station.

3. The method according to claim 2, wherein, Determine the number of location objects and the number of data collection objects corresponding to each network access device, including: Based on the location logs, determine the number of location objects corresponding to each network access device; The number of objects to be collected for each network access device is determined based on the collected logs.

4. The method according to claim 1, wherein, The number of objects located by the first access device is greater than the number of objects collected.

5. The method according to claim 1, wherein, Obtaining the subway station corresponding to the subway line data includes: Obtain the original station information, which does not match the subway line data; Determine the initial state probability information, observation probability information, and state transition probability information between stations in the metro line data corresponding to the metro line data. The initial state probability information includes the transition probability corresponding to the first station in the metro line data, and the observation probability information includes the transition probabilities corresponding to each station in the metro line data. The Viterbi algorithm is used to analyze and process the original station information, initial state probability information, observation probability information, and state transition probability information to determine the subway station corresponding to the subway line data.

6. The method according to claim 5, wherein, The initial state probability information and the observation probability information conform to a Gaussian distribution.

7. The method according to claim 5, wherein, Determining the initial state probability information corresponding to the subway line data includes: Obtain the first station included in the subway line data; Determine the latitude and longitude of the first station and the trajectory latitude and longitude corresponding to the subway line data; Based on the latitude and longitude of the station and the latitude and longitude of the trajectory, the initial state probability information corresponding to the subway line data is determined.

8. The method according to claim 5, wherein, Determining the state transition probability information between stations in the subway line data includes: Obtain the actual running time of the terminal device based on the subway line data; Determine the expected travel time corresponding to the subway line data; Based on the actual running time and the expected running time, determine the state transition probability information corresponding to the subway line data.

9. The method according to claim 8, wherein, Based on the actual operating time and the expected operating time, determine the state transition probability information corresponding to the subway line data, including: When the actual running time is the same as the expected running time, the state transition probability information corresponding to the subway line data is determined to be 1; or, When the actual running time is less than the expected running time, the state transition probability information corresponding to the subway line data is determined to satisfy a first Gaussian distribution; or, When the actual running time is greater than the expected running time, the state transition probability information corresponding to the subway line data is determined to satisfy a second Gaussian distribution, and the decay characteristic of the second Gaussian distribution is slower than that of the first Gaussian distribution.

10. The method according to claim 8, wherein, Determining the expected travel time corresponding to the subway line data includes: Determine the distances between stations and the subway operating speed in the subway line data; The ratio of the distance between stations to the subway operating speed is determined as the expected travel time corresponding to the subway line data.

11. The method according to claim 1, wherein, After determining all network access devices included in the location logs and collection logs, as well as the number of location objects and collection objects corresponding to each network access device, the method further includes: Identify all network access devices, including neighboring devices and their location information; The second machine learning model is used to analyze and process the nearby devices, their location information, the number of location objects, and the number of collection objects to determine the second access devices included in all network access devices that correspond to the location logs and collection logs. The second access devices are deployed in the subway station. The second machine learning model is trained to identify the subway devices included in all network access devices. Based on the first access device and the second access device, the target access device deployed in the subway station is determined.

12. The method according to claim 11, wherein, Identify neighboring devices included in all network access devices, including: Obtain the first network location request; Based on the first network location request, a scan is performed, and all the first devices scanned are identified as first neighboring devices.

13. The method according to claim 12, wherein, Identify neighboring devices included in all network access devices, including: Obtain a second network location request, wherein the request times of the first network location request and the second network location request are different; Based on the second network location request, a scan is performed, and all the second devices and all the first devices detected are identified as second neighboring devices.

14. The method according to claim 13, wherein, Identify neighboring devices included in all network access devices, including: Identify overlapping devices between the first device and the second device; Identify the third device in the first device that removes the overlapping device and the fourth device in the second device that removes the overlapping device; The third device and the fourth device are identified as third neighboring devices.

15. The method according to claim 14, wherein, The priority of the first neighboring device is greater than that of the second neighboring device, and the priority of the second neighboring device is greater than that of the third neighboring device.

16. The method according to claim 11, wherein, Identifying the location information of the nearby devices includes: Obtain the network access device type and weight information for each neighboring device; Clustering algorithms are used to cluster the network access device types and the weight information corresponding to neighboring devices to obtain the location information of the neighboring devices.

17. The method according to claim 16, wherein, The network access device type of the neighboring device includes at least one of the following: a first neighboring device, a second neighboring device, and a third neighboring device; the weight of the first neighboring device is greater than the weight of the second neighboring device, and the weight of the second neighboring device is greater than the weight of the third neighboring device.

18. The method according to claim 11, wherein, Based on the first access device and the second access device, the target access device deployed in the subway station is determined, including: When the network access device range of the first access device is greater than the network access device range of the second access device, then the first access device is determined as the target access device deployed in the subway station; or, When the network access device range of the first access device differs from that of the second access device, the sum of the network access device ranges of the first access device and the second access device is determined as the target access device deployed in the subway station; or, If the network access device range of the first access device is smaller than that of the second access device, then the second access device is determined as the target access device deployed in the subway station.

19. The method according to claim 11, wherein, After identifying the target access devices to be deployed in the subway station, the method further includes: Identify the number of the target access devices; When the number of target access devices exceeds a preset threshold, it is determined that the terminal device is located inside the subway station.

20. A device for identifying a network access device, wherein, include: The acquisition module is used to acquire the location logs and collection logs of the terminal device, wherein the location logs include network location data; The collection log includes satellite positioning data; The processing module is used to obtain the subway line data corresponding to the terminal device based on the positioning log; The determination module is used to determine all network access devices included in the location logs and collection logs, as well as the number of location objects and collection objects corresponding to each network access device; and to use a first machine learning model to analyze and process the subway line data, subway stations, and the number of location objects and collection objects corresponding to each network access device to determine the first access devices deployed in the subway stations included in all network access devices. The first machine learning model is trained to identify subway equipment information included in all network access devices.

21. An electronic device, wherein, include: Memory, processor; among which, The memory is used to store one or more computer instructions, wherein the one or more computer instructions, when executed by the processor, implement the identification method of the network access device as described in any one of claims 1 to 19.

22. A positioning method, wherein, Based on the network access devices deployed in the subway station as determined by the method described in any one of claims 1-19, the subway scene is located.

23. A positioning device, wherein, include: Memory, processor; among which, The memory is used to store one or more computer instructions, wherein the one or more computer instructions, when executed by the processor, implement the positioning method as described in claim 22.

Images