WO2021190145A1 - 站点识别方法、装置、终端及存储介质 - Google Patents

站点识别方法、装置、终端及存储介质 Download PDF

Info

Publication number
WO2021190145A1
WO2021190145A1 PCT/CN2021/074680 CN2021074680W WO2021190145A1 WO 2021190145 A1 WO2021190145 A1 WO 2021190145A1 CN 2021074680 W CN2021074680 W CN 2021074680W WO 2021190145 A1 WO2021190145 A1 WO 2021190145A1
Authority
WO
WIPO (PCT)
Prior art keywords
energy
site
state
response
station
Prior art date
Application number
PCT/CN2021/074680
Other languages
English (en)
French (fr)
Inventor
黄粟
Original Assignee
Oppo广东移动通信有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Oppo广东移动通信有限公司 filed Critical Oppo广东移动通信有限公司
Publication of WO2021190145A1 publication Critical patent/WO2021190145A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/123—Traffic control systems for road vehicles indicating the position of vehicles, e.g. scheduled vehicles; Managing passenger vehicles circulating according to a fixed timetable, e.g. buses, trains, trams
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Definitions

  • the embodiments of the present application relate to the field of artificial intelligence technology, and in particular to a method, device, terminal, and storage medium for site identification.
  • the arrival reminder function is a function that reminds passengers to get off the bus when they arrive at the target stop.
  • the terminal usually uses data collected by sensors (such as acceleration sensors, gravity sensors, and magnetic sensors) to calculate whether a vehicle enters or exits the station through acceleration and deceleration, and combines the map to predict the station, or recognize the traffic through voice
  • sensors such as acceleration sensors, gravity sensors, and magnetic sensors
  • the embodiments of the present application provide a site identification method, device, terminal, and storage medium.
  • the technical solution is as follows:
  • an embodiment of the present application provides a method for identifying a site, and the method includes:
  • the operating state includes at least one of an inbound state, a stopped state, an outbound state, and an inter-station driving state;
  • the current site is determined according to the currently registered base station.
  • an embodiment of the present application provides a site identification device, and the device includes:
  • the collection module is used to collect ambient sound through a microphone in response to being in the subway mode
  • the feature extraction module is configured to perform feature extraction on the environmental sound to obtain the energy feature of the environmental sound
  • the first determining module is configured to determine the operating state of the subway according to the energy characteristics, where the operating state includes at least one of an inbound state, a stopped state, an outbound state, and an inter-station driving state;
  • the second determining module is configured to determine the current site according to the currently registered base station in response to the operating state being the stopped state.
  • an embodiment of the present application provides a terminal, the terminal includes a processor and a memory; the memory stores at least one instruction, and the at least one instruction is used to be executed by the processor to implement the foregoing aspects.
  • a computer program product or computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium.
  • the processor of the terminal reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the terminal executes the site identification method provided in the various optional implementation manners of the foregoing aspects.
  • Fig. 1 is a flow chart showing a method for site identification according to an exemplary embodiment
  • Fig. 2 is a schematic diagram showing the distribution of subway stations and base stations around the station according to an exemplary embodiment
  • Fig. 3 is a flow chart showing a method for site identification according to another exemplary embodiment
  • Fig. 4 is a diagram showing an audio signal and a frequency spectrum of an environmental sound according to an exemplary embodiment
  • Fig. 5 is a schematic diagram showing the relationship between the length of a first timer and the length of travel between stations according to an exemplary embodiment
  • Fig. 6 is a subway line diagram according to an exemplary embodiment
  • Fig. 7 is a structural block diagram of a site identification device according to an exemplary embodiment
  • Fig. 8 is a structural block diagram of a terminal according to an exemplary embodiment.
  • the "plurality” mentioned herein means two or more.
  • “And/or” describes the association relationship of the associated objects, indicating that there can be three types of relationships, for example, A and/or B, which can mean: A alone exists, A and B exist at the same time, and B exists alone.
  • the character “/” generally indicates that the associated objects before and after are in an "or” relationship.
  • the terminal usually uses data collected by sensors (such as acceleration sensors, gravity sensors, and magnetic sensors, etc.) to calculate whether the subway enters or exits the station by accelerating and decelerating, so as to determine whether the current station of the terminal is the passenger's target.
  • sensors such as acceleration sensors, gravity sensors, and magnetic sensors, etc.
  • the terminal usually uses data collected by sensors (such as acceleration sensors, gravity sensors, and magnetic sensors, etc.) to calculate whether the subway enters or exits the station by accelerating and decelerating, so as to determine whether the current station of the terminal is the passenger's target.
  • sensors such as acceleration sensors, gravity sensors, and magnetic sensors, etc.
  • the subway does not always travel at a constant speed during driving, but has a certain oscillation phenomenon.
  • the posture of the user holding the terminal will affect the acceleration direction recorded by the acceleration sensor, and if the user is inside the subway
  • the acceleration value recorded by the terminal includes the acceleration when the user is walking, and it will also have a certain impact on the terminal's sensor. It is difficult to judge whether the vehicle is in an accelerating state or a decelerating state. These factors will cause the terminal's station prediction to be inaccurate;
  • the voice extraction method of site information is very noisy in the subway environment, and the terminal cannot accurately recognize the content of the voice broadcast using noise reduction technology. For the site information displayed on the screen, it needs to be photographed by a camera, which is not practical.
  • the embodiments of the present application provide a site identification method, which is used in a terminal with audio collection and processing functions.
  • the terminal may be a smart phone, a tablet computer, an e-book reader, a personal portable computer, and the like.
  • the site identification method provided in the embodiment of the present application may be implemented as an application program or a part of an application program and installed in a terminal.
  • the application can be manually opened (or the application is automatically opened), so that the application can prompt the user of the site where the user is currently located.
  • the operating state includes at least one of the inbound state, the stopped state, the outbound state, and the inter-station driving state;
  • the current site is determined according to the currently registered base station.
  • determining the operating state of the subway according to the energy characteristics includes:
  • the operating state is a driving state between stations.
  • determining that the running state is the stopped state includes:
  • the environmental sound is divided into frames to obtain at least two audio frames.
  • the first energy mean value is the energy mean value of the environmental sound in the full frequency band, and the preset energy
  • the range is the energy range corresponding to the ambient sound when the subway stops;
  • determining that the operating state is the inbound state or the outbound state including:
  • the third energy mean value in response to the i-th environmental sound belongs to the preset energy range, and the third energy mean value of the i+1th environmental sound and the i+2th environmental sound is greater than the third energy mean value of the i-th environmental sound , It is determined that the operating state is the outbound state, the preset energy range is the energy range corresponding to the ambient sound when the subway stops, and i is an integer greater than or equal to 1.
  • determining that the operating state is the inbound state or the outbound state further includes:
  • the third energy mean value in response to the i+2th environmental sound belongs to the preset energy range, and the third energy mean value of the i-th environmental sound and the i+1th environmental sound is greater than the third energy of the i+2th environmental sound
  • the average value of energy is used to determine the operating state as the inbound state.
  • the method further includes:
  • the first timer In response to the running state being the outbound state, the first timer is started, and the first timer duration of the first timer is the estimated travel time between stations;
  • the current site is determined according to the currently registered base station, including:
  • the current station is determined according to the currently registered base station.
  • the current site is determined according to the currently registered base station, including:
  • the mapping table contains the corresponding relationship between the site and the base station around the site;
  • the site found is determined as the current site
  • the neighboring site of the previous site is acquired; the intersection site of the found site and the neighboring site is determined as the current site.
  • the method also includes:
  • mapping table In response to the mapping table does not include the site corresponding to the current registered base station, or the number of intersection sites is at least two, obtain the number of steps and historical sites of the pedometer between the previous site and the current site, and the historical site is before the current site At least two stations passed by;
  • the subway line and the driving direction are determined according to the historical station, and the current station is determined according to the subway line and the driving direction.
  • the method further includes:
  • a second timer is set, and the timer duration of the second timer is less than the estimated travel time between stations;
  • an arrival reminder is performed in a predetermined manner.
  • FIG. 1 shows a flowchart of a site identification method shown in an embodiment of the present application.
  • the site identification method is used in a terminal with audio collection and processing functions as an example for description.
  • the method includes:
  • Step 101 In response to being in the subway mode, collect ambient sound through a microphone.
  • the terminal When in subway mode, the terminal turns on the station recognition function and collects ambient sound through the microphone.
  • the terminal when the site identification method is applied to map navigation applications, the terminal obtains the user's location information in real time. When it is determined that the user enters a vehicle according to the user's location information, the terminal turns on the subway mode; when the user uses the payment type When the app uses the card to take the subway, the terminal confirms to enter the subway according to the user interface of the successful entry or the successful ticket payment, and the subway mode is turned on.
  • the terminal may use a low-power microphone to collect environmental sounds in real time, or collect environmental sounds for a period of time at predetermined intervals, for example, environmental sounds with a duration of 20s every 15s. .
  • Step 102 Perform feature extraction on the environmental sound to obtain the energy feature of the environmental sound.
  • the terminal cannot directly recognize the sound changes during subway operation from the environmental sound, it is necessary to preprocess the collected environmental sound, convert the environmental sound collected by the microphone into audio data, and perform environmental sound on the audio data. Feature extraction to obtain digital features that can be recognized by the terminal.
  • Step 103 Determine the operating state of the subway according to the energy characteristics.
  • the operating state includes at least one of an inbound state, a stopped state, an outbound state, and an inter-station driving state.
  • the terminal can determine the corresponding operating state of the subway through the energy characteristics of the ambient sound. For example, when the subway is in the state of pitting, the speed will eventually stop moving from high to low, and the energy of the noise generated when the subway is running also decreases from high to low.
  • the terminal pre-stores various operating states of the subway and the energy characteristics of the sounds corresponding to the different operating states.
  • the terminal determines the operating state of the subway according to the energy characteristics of the current ambient sound .
  • Step 104 in response to the running state being the stopped state, determine the current site according to the currently registered base station.
  • the terminal when the terminal determines that the subway is in a stopped state or in a station state, it indicates that the subway has arrived at the subway station, and the current station needs to be updated at this time. Since the base stations around the subway station are relatively fixed and usually do not move or change, the terminal can determine the site corresponding to the currently registered base station as the current site. Schematically, please refer to Figure 2, which shows the distribution intention of stations in a subway line and surrounding base stations. Among them, there is usually only one subway station in the coverage area of a base station. Similarly, there is usually only one subway station nearby. One base station, for example, base station 202 covers subway station B, base station 203 covers subway station C, and base station 204 covers subway station D. Therefore, the terminal can determine the current site according to the correspondence between the subway station and the base station and the currently registered base station.
  • the different energy characteristics of the sound of the subway under different operating conditions are used, the ambient sound is collected through the microphone in the subway mode, and the current operating status of the subway is determined according to the energy characteristics of the ambient sound.
  • the subway is in a stopped state, confirm that the subway arrives at the station, and use the current registered base station to identify the current station and update it.
  • the current registered base station is used to determine the current station. Low consumption and high accuracy rate.
  • FIG. 3 shows a flowchart of a site identification method shown in another embodiment of the present application.
  • the site identification method is used in a terminal with audio collection and processing functions as an example for description.
  • the method includes:
  • Step 301 In response to being in the subway mode, collect ambient sound through a microphone.
  • Step 302 Perform feature extraction on the environmental sound to obtain the energy feature of the environmental sound.
  • step 301 and step 302 For the implementation manner of step 301 and step 302, reference may be made to step 101 and step 102 described above, and details are not described herein again in this embodiment.
  • Step 303 In response to the energy characteristic meeting the energy average condition, it is determined that the running state is a stopped state.
  • the terminal pre-stores the energy average condition corresponding to the stop state of the subway, and when the terminal recognizes that the energy feature of the current environmental sound meets the energy average condition, it determines that the subway is in the stop state.
  • step 303 includes the following steps one to three:
  • the environmental sound is divided into frames to obtain at least two audio frames.
  • the first energy mean value is the energy mean value of the environmental sound in the entire frequency band.
  • Let the energy range be the energy range corresponding to the ambient sound when the subway stops.
  • FIG. 4 shows a schematic diagram of the audio signal and frequency spectrum of the environmental sound inside the subway, the upper part is the time domain signal, and the lower part is the spectrogram.
  • the audio signal of ambient sound changes with the operating state of the subway.
  • the audio signal gradually increases, when the subway decelerates in the station, the audio signal gradually weakens, and when the subway stops, the audio signal is weaker and changes in magnitude Smaller.
  • the energy changes in different operating states during subway operation mainly occur in the low-frequency part below 1KHz. In the stopped state, the energy of the medium-low frequency part is relatively low and does not change much.
  • the bright spot in the figure is The alarm bell for the subway to open or close.
  • the first energy mean value of the ambient sound belongs to the energy range corresponding to the ambient sound when the subway stops, it indicates that the subway may be in a stopped state at this time, and it is necessary to identify whether there is a subway opening or closing in the ambient sound.
  • the alarm bell to further determine whether the subway is in a stopped state.
  • the terminal collects environmental sound through a microphone at a sampling rate of 16KHz, and uses 5s as one input to calculate the first energy average value of the environmental sound in the full frequency band.
  • the energy average value belongs to 3.5 ⁇ 10 7 J to At 7 ⁇ 10 7 J
  • the terminal needs to convert the audio data of the environmental sound into an energy distribution in the frequency domain, so the environmental sound is first divided into frames to obtain audio frames.
  • the first frequency band is the frequency band corresponding to the alarm bell when the subway door is opened or closed.
  • the frequency band of the alarm bells is usually between 2.5KHz and 3.5KHz. Therefore, the terminal uses 2.5KHz to 3.5KHz as the first frequency band to obtain the second energy mean value of the environmental sound in this frequency band. .
  • the terminal uses a certain number of Fourier transform points (for example, 512 points) to Fourier transform the audio data after the framing process to obtain the energy distribution of the audio data in the frequency domain. Then intercept the audio data between 2.5KHz and 3.5KHz, and calculate the second energy mean value.
  • the alarm bell of subway door opening or closing has significantly higher energy and is easier to distinguish.
  • the developer presets the energy threshold to distinguish the alarm bell from other environmental sounds.
  • the terminal only needs to determine the first frequency band. Second, if the average energy value is higher than the energy threshold, it can be determined whether the environmental sound contains an alarm bell. In a possible implementation manner, if the second energy average value is higher than the energy threshold, there is an alarm bell in the segment of ambient sound, and it can be determined that the operating state of the subway at this time is a stopped state.
  • Step 304 In response to the energy characteristic meeting the energy change condition, it is determined that the operating state is the inbound state or the outbound state.
  • the audio signal also has obvious regularity when the subway decelerates into the station and accelerates out of the station.
  • the energy of the low- and medium-frequency part below 1KHz gradually increases from the energy when it stops. ;
  • the energy of the low frequency part below 1KHz changes from large to small until it decreases to the energy at stop.
  • the terminal determines that the energy feature of the environmental sound meets the energy change condition, it is determined that the subway is in the inbound state or the outbound state.
  • step 304 includes the following steps one to three:
  • the environmental sound is processed in segments.
  • the terminal Since it is necessary to obtain the energy change of the environmental sound, the terminal performs segmentation processing on the environmental sound and compares the energy of several consecutive environmental sounds. In a possible implementation manner, the terminal divides the environmental sounds with a certain duration, and obtains multiple pieces of audio data of the environmental sounds. For example, the terminal takes an environmental sound with a duration of 15s as one input, and divides the environmental sound into 3 segments, each with a duration of 5s.
  • the terminal analyzes the energy change of the environmental sound, it also needs to perform Fourier transform on the environmental sound to obtain the energy distribution of the environmental sound in the frequency domain.
  • the terminal performs framing processing on each segment of the environmental sound, and then performs Fourier transform on the environmental sound after the framing processing with 512 transformation points, and obtains the first environmental sound in the second frequency band.
  • the terminal respectively performs Fourier transform on three continuous environmental sounds with a duration of 5s, and calculates the third energy mean values E1, E2, and E3 of each environmental sound from 0 Hz to 600 Hz.
  • the third energy mean value in response to the i-th environmental sound belongs to the preset energy range, and the third energy mean of the i+1th environmental sound and the i+2th environmental sound is greater than the third energy of the i-th environmental sound
  • the energy mean value, the operating state is determined to be the outbound state
  • the preset energy range is the energy range corresponding to the ambient sound when the subway stops
  • i is an integer greater than or equal to 1.
  • step two above if E1 belongs to the preset energy range of 3.5 ⁇ 10 7 J to 7 ⁇ 10 7 J, and the ratio of E2 to E1 and the ratio of E3 to E1 are greater than 1, it can be determined that the operating status of the subway is Outbound status. In order to improve the accuracy of the recognition result, an energy ratio is preset in the terminal. If E2/E1>1.2 and E3/E1 is greater than 1.45, it is determined that the operating state is the outbound state.
  • the site identification method provided in the embodiment of the present application further includes the following steps:
  • the third energy mean value in response to the i+2th environmental sound belongs to the preset energy range, and the third energy mean value of the i+1th environmental sound and the i-th environmental sound is greater than the third energy value of the i+2th environmental sound Energy average, confirm the running state is the inbound state. For example, if E1/E3 is greater than 1.45, E2/E3 is greater than 1.2, and E3 belongs to 3.5 ⁇ 10 7 J to 7 ⁇ 10 7 J, it is determined that the subway is in the station state.
  • the terminal determines that the subway arrives at the station when the operating state of the subway satisfies the station first and then the stop state; accordingly, the terminal is in the operating state of the subway When it is satisfied that it is in the stopped state and then in the outbound state, it is determined that the subway starts to run.
  • Step 305 In response to the energy feature not meeting the energy average condition and the energy change condition, it is determined that the operating state is the inter-station driving state.
  • the subway does not always run at a constant speed during the running process between stations, as shown in Figure 4, there may be acceleration and deceleration, so it is impossible to distinguish the running state between stations through specific energy characteristics.
  • the energy characteristics of the ambient sound do not meet the above-mentioned energy average condition and energy change condition, it means that the subway is not in any one of the stopped state, the inbound state, or the outbound state, that is, The subway is running between stations.
  • the terminal In order to improve the accuracy of station recognition and avoid the deceleration in the process of driving between subway stations, the terminal is mistakenly recognized as an inbound state, and a timer is preset in the terminal.
  • the travel time between each station is basically fixed. When the travel time is not met, the subway will not reach the next station. Therefore, the developer collects the travel time between all subway stations in advance, and controls the terminal by using a timer. Site identification to avoid errors.
  • the first timer duration may be a fixed duration, and the fixed duration may be set as the shortest duration of travel between subway stations; or, the first timer duration is obtained by querying the current station to the next station.
  • the average duration of a site is not limited in this embodiment of the application.
  • FIG. 5 shows a schematic diagram of a terminal starting a timer during subway driving.
  • the terminal recognizes that the subway is out of the station, it immediately starts the first timer, and the first timer duration of the first timer is the estimated travel time between stations.
  • Step 307 In response to reaching the first timer duration and the running state is the stop state, determine the current site according to the currently registered base station.
  • the terminal obtains the ambient sound through the microphone in real time, and judges the operating status of the subway.
  • the terminal queries whether the timer has expired, that is, whether the first timer duration has been reached. For the first timer duration, continue to judge the operating status according to the environmental sound. If the timer duration is reached, it is determined that the subway arrives at the station, and the current station is determined according to the currently registered base station.
  • the terminal always determines the current station according to the currently registered base station in the subway mode. When it is determined that the subway is in a stopped state, it queries whether the timer has expired. If it does not expire, the current station is not updated. , The current site is updated.
  • Step 308 Determine neighboring sites of the current site.
  • the subway mode of the terminal includes an arrival reminder function. Every time it arrives at a station, the terminal obtains the neighboring stations of the current station, so that when it is determined that it is about to arrive at the station, it will remind the user of the station arrival, so that the user is ready to get off the train in advance.
  • the neighboring station may be the next station determined according to the current station and the current subway driving direction.
  • Step 309 In response to the neighboring station being the target station, a second timer is set, and the timer duration of the second timer is less than the estimated travel time between stations.
  • the target site is a site set by the user in advance that requires the arrival reminder service; or the terminal may default to the arrival reminder before arriving at a site, and the target site is the next site of the current site.
  • the second timer is started when the subway is in the outbound state, and the duration of the second timer is less than the estimated travel time between stations, for example, ,
  • the duration of the second timer is one-half of the estimated travel time between stations.
  • the terminal recognizes that the current station is Donglu Road, and the adjacent station is the target station Jufeng Road.
  • the estimated travel time between Donglu Road and Jufeng Road is 6 minutes, and the terminal starts the second station when the subway is out of the station. Timer, the duration of the second timer is 3 minutes.
  • the terminal obtains the interface information by way of system embedding, and automatically turns on the subway mode when it obtains the interface of a successful entry or a successful ticket payment.
  • the target station input interface is displayed.
  • the user enters the target station by voice or manually.
  • the arrival reminder function is turned on; or the terminal automatically based on the user's historical travel records Filter the target site for users to choose.
  • the user may choose to manually turn on the subway mode, and when the terminal receives an instruction to turn on the subway mode, the target station input interface is displayed, or the default target station is displayed according to the historical travel records.
  • step 310 in response to reaching the second timer duration, an arrival reminder is performed in a predetermined manner.
  • the terminal reminds the user to arrive at the destination site through voice, prompt messages, etc., get off the car in time, and add special reminders such as text messages and vibrations when necessary to prevent users from missing messages.
  • the operating state of the subway is determined by analyzing the energy characteristics of the ambient sound, and the timer is started when the station is out of the station, and when the timer expires, the subway is determined to arrive at the station according to the static state, which prevents the subway from being between stations.
  • the deceleration and acceleration in the driving state affect the recognition result of the terminal, which improves the accuracy and timeliness of station recognition; in addition, when the terminal determines that the neighboring station of the current station is the target station, the opening time is less than the expected driving time between stations When the second timer expires, the user will be reminded of the arrival of the station, so that the user can prepare for getting off the bus in advance and avoid sitting over the station.
  • step 307 further includes the following steps 1 to 3:
  • the mapping table contains the corresponding relationship between the site and the base stations around the site.
  • the terminal When the terminal detects that the subway is in a stopped state, the current station needs to be updated. In a possible implementation manner, the terminal uses a base station to locate the station to determine the current station. Due to the limited coverage of base stations, usually covering a distance of 2 to 5 kilometers, and because the signal quality in the subway is poor, major operators will deploy more base stations in the subway line to ensure the signal strength in the subway. Station, the terminal will be registered to different base stations.
  • the terminal obtains the base station information of the currently registered base station, and queries the corresponding base station in the mapping table to obtain the corresponding site, which is the current site.
  • the currently registered base station of the terminal is mcc-460-mnc-00-ci-25935874-pci-435-tac-6270, and the current station is determined to be Shanghai Metro_Line 12_Longhua Middle Road according to the mapping table.
  • the site found is determined as the current site.
  • the site corresponding to the currently registered base station in the mapping table is unique, the site can be determined as the current site.
  • base station 201 covers subway station A and subway station B; similarly, a few subway stations are located in the overlapping area of coverage of multiple base stations, such as subway stations. B is both within the coverage area of the base station 201 and also within the coverage area of the base station 202.
  • the current site cannot be directly determined. Considering that the proximity relationship of each station in a subway line is fixed, and before the terminal determines the current station, the displayed station is the previous station, so it can be determined by obtaining the intersection of the station corresponding to the current base station and the adjacent station of the previous station The current site.
  • the terminal stores information about each site of the current line, including the neighboring sites corresponding to each site.
  • the terminal obtains An adjacent station of a station (that is, the station displayed by the current terminal).
  • the database of the back-end server stores the subway lines of each city, and the terminal can upload the name of the previous site to the server, and the server queries the neighboring sites of the previous site from the database and feeds it back to the corresponding terminal.
  • the subway line where the terminal is currently located there are subway station A and subway station B in the coverage area of base station 201.
  • the subway where the user is traveling is from subway station A to subway station B, and the current terminal displays The station of is subway station A.
  • the stations obtained by the current registered base station 201 are subway station A and subway station B.
  • the current station cannot be determined, so the terminal obtains the neighboring stations of subway station A. It is obtained that the neighboring site is the subway station B, and the current site is the subway station B by taking the intersection of the neighboring site B and the subway station A and the subway station B corresponding to the currently registered base station 201.
  • the terminal cannot find the current registered base station from the mapping table, or there are multiple intersection sites between the current registered base station and the neighboring site of the previous site, and the terminal cannot determine the current site based on the current registered base station. It is necessary to use historical stations and subway lines to perform station estimation to obtain the current station.
  • the station identification method also includes the following steps 4 and 5:
  • step number threshold determine the subway line and driving direction according to historical stations, and determine the current station according to the subway line and driving direction.
  • the terminal obtains that the historical sites are Donglu Road and Jufeng Road, it can be inferred that the user took Line 12, but Jufeng Road is a transfer station, and the user may transfer to Line 6 to reach Wulian Road. Or Dongjing Road, so the terminal needs to obtain the number of steps of the pedometer between the previous station and the current station. If the number of steps is less than the threshold, it means that the user has not got off and transferred, and it can be inferred that the current station is Line 12 Yanggao North Road.
  • FIG. 7 shows a structural block diagram of a site identification device provided by an exemplary embodiment of the present application.
  • the device can be implemented as all or a part of the terminal through software, hardware or a combination of the two.
  • the device includes:
  • the collection module 701 is configured to collect ambient sound through a microphone in response to being in the subway mode;
  • the feature extraction module 702 is configured to perform feature extraction on the environmental sound to obtain the energy feature of the environmental sound;
  • the first determining module 703 is configured to determine the operating state of the subway according to the energy characteristics, where the operating state includes at least one of an inbound state, a stopped state, an outbound state, and an inter-station driving state;
  • the second determining module 704 is configured to determine the current site according to the currently registered base station in response to the operating state being the stopped state.
  • the first determining module 703 includes:
  • the first determining unit is configured to determine that the operating state is the stopped state in response to the energy characteristic meeting the energy average condition
  • the second determining unit is configured to determine that the operating state is the inbound state or the outbound state in response to the energy characteristic meeting the energy change condition;
  • the third determining unit is configured to determine that the operating state is the inter-station driving state in response to the energy feature not meeting the energy average condition and the energy change condition.
  • the first determining unit is further configured to:
  • the environmental sound In response to the energy feature indicating that the first energy mean value of the environmental sound belongs to a preset energy range, the environmental sound is framed to obtain at least two audio frames, and the first energy mean value is the entire frequency band.
  • the energy average value of the environmental sound, and the preset energy range is the energy range corresponding to the environmental sound when the subway stops;
  • the second determining unit is further configured to:
  • the third energy mean value in response to the i-th environmental sound belongs to a preset energy range, and the third energy mean values of the i+1-th environmental sound and the i+2th environmental sound are greater than the i-th environmental sound
  • the third energy mean value of the sound determines that the operating state is the outbound state
  • the preset energy range is the energy range corresponding to the ambient sound when the subway stops
  • i is an integer greater than or equal to 1.
  • the second determining unit is further configured to:
  • the third energy mean value in response to the i+2th environmental sound belongs to the preset energy range, and the third energy of the i-th environmental sound and the i+1th environmental sound If the average value is greater than the third energy average value of the i+2th environmental sound, it is determined that the operating state is the inbound state.
  • the device further includes:
  • the first timing module is configured to start a first timer in response to the operating state being the outbound state, and the first timer duration of the first timer is the estimated travel time between stations;
  • the second determining module 704 includes:
  • the fourth determining unit is configured to determine the current site according to the currently registered base station in response to the first timer duration being reached and the running state is the stopped state.
  • the second determining module 704 further includes:
  • An acquiring unit configured to acquire the currently registered base station and a mapping table, where the mapping table contains the corresponding relationship between the site and the base stations around the site;
  • a fifth determining unit configured to respond to the mapping table containing the site corresponding to the currently registered base station, and the number of sites is one, determining the site found as the current site;
  • the sixth determining unit is configured to respond to the mapping table containing the site corresponding to the currently registered base station, and the number of sites is at least two, to obtain the neighboring sites of the previous site; The intersection site of neighboring sites is determined to be the current site.
  • the device further includes:
  • the obtaining module is configured to obtain a pedometer between the previous station and the current station in response to the fact that the station corresponding to the currently registered base station is not included in the mapping table, or the number of the intersection stations is at least two The number of steps and the historical site, where the historical site is at least two sites that the current site has passed before;
  • the third determining module is configured to determine a subway line and a driving direction according to the historical station in response to the number of steps being less than a threshold of the number of steps, and determine the current station according to the subway line and the driving direction.
  • the device further includes:
  • the fourth determining module is used to determine the neighboring sites of the current site
  • the second timing module is configured to set a second timer in response to the neighboring station being the target station, and the timer duration of the second timer is less than the estimated travel time between stations;
  • the arrival reminder module is used for reminding the arrival of the station in a predetermined manner in response to reaching the second timer duration.
  • FIG. 8 shows a structural block diagram of a terminal 800 provided by an exemplary embodiment of the present application.
  • the terminal 800 may be an electronic device with an application program installed and running, such as a smart phone, a tablet computer, an e-book, a portable personal computer, and the like.
  • the terminal 800 in this application may include one or more of the following components: a processor 820, a memory 810, a screen 830, and a microphone 840.
  • the processor 820 may include one or more processing cores.
  • the processor 820 uses various interfaces and lines to connect various parts of the entire terminal 800, and executes the terminal by running or executing instructions, programs, code sets, or instruction sets stored in the memory 810, and calling data stored in the memory 810. 800 various functions and processing data.
  • the processor 820 may use at least one of digital signal processing (Digital Signal Processing, DSP), Field-Programmable Gate Array (Field-Programmable Gate Array, FPGA), and Programmable Logic Array (Programmable Logic Array, PLA).
  • DSP Digital Signal Processing
  • FPGA Field-Programmable Gate Array
  • PLA Programmable Logic Array
  • the processor 820 may be integrated with one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), a modem, and the like.
  • the CPU mainly processes the operating system, user interface, and application programs; the GPU is used to render and draw the content that needs to be displayed on the screen 830; and the modem is used to process wireless communication. It is understandable that the above-mentioned modem may not be integrated into the processor 820, but may be implemented by a communication chip alone.
  • the memory 810 may include random access memory (RAM) or read-only memory (ROM).
  • the memory 810 includes a non-transitory computer-readable storage medium.
  • the memory 810 may be used to store instructions, programs, codes, code sets or instruction sets.
  • the memory 810 may include a storage program area and a storage data area, where the storage program area may store instructions for implementing the operating system and instructions for implementing at least one function (such as touch function, sound playback function, image playback function, etc.) ,
  • the instructions used to implement the foregoing various method embodiments, etc., the operating system may be the Android system (including the system based on the in-depth development of the Android system), the IOS system developed by Apple (including the system based on the in-depth development of the IOS system) Or other systems.
  • the data storage area can also store data created during use of the terminal 800 (such as phone book, audio and video data, chat record data) and the like.
  • the screen 830 may be a capacitive touch display screen, which is used to receive a user's touch operation on or near any suitable object such as a finger, a touch pen, etc., and display the user interface of each application program.
  • the touch screen is usually set on the front panel of the terminal 800.
  • the touch screen can be designed as a full screen, curved screen or special-shaped screen.
  • the touch display screen can also be designed as a combination of a full screen and a curved screen, or a combination of a special-shaped screen and a curved screen, which is not limited in the embodiments of the present application.
  • the microphone 840 may be a low-power microphone.
  • the microphone 840 is used to collect environmental sounds when the terminal enables the station entry and exit prediction function, and can also be used to collect environmental sounds during a voice call.
  • the microphone 840 is usually arranged at an edge part (the following edge) on one side of the terminal display screen, which is not limited in the embodiment of the present application.
  • the structure of the terminal 800 shown in the above drawings does not constitute a limitation on the terminal 800, and the terminal may include more or less components than those shown in the figure, or a combination of certain components. Components, or different component arrangements.
  • the terminal 800 also includes components such as a radio frequency circuit, a photographing component, a sensor, an audio circuit, a WiFi component, a power supply, and a Bluetooth component, which will not be repeated here.
  • the embodiments of the present application also provide a computer-readable storage medium that stores at least one instruction, and the at least one instruction is loaded and executed by the processor to implement the site described in each of the above embodiments. recognition methods.
  • a computer program product or computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium.
  • the processor of the terminal reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the terminal executes the site identification method provided in the various optional implementation manners of the foregoing aspects.
  • the functions described in the embodiments of the present application may be implemented by hardware, software, firmware, or any combination thereof. When implemented by software, these functions can be stored in a computer-readable storage medium or transmitted as one or more instructions or codes on the computer-readable storage medium.
  • the computer-readable storage medium includes a computer storage medium and a communication medium, where the communication medium includes any medium that facilitates the transfer of a computer program from one place to another.
  • the storage medium may be any available medium that can be accessed by a general-purpose or special-purpose computer.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Signal Processing (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Remote Sensing (AREA)
  • General Physics & Mathematics (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Telephone Function (AREA)
  • Train Traffic Observation, Control, And Security (AREA)

Abstract

提供了一种站点识别方法、站点识别装置、终端及计算机可读存储介质，属于人工智能领域。该方法包括：响应于处于地铁模式，通过麦克风采集环境音（101）；对环境音进行特征提取，得到环境音的能量特征（102）；根据能量特征确定地铁的运行状态，运行状态包括进站状态、停止状态、出站状态和站间行驶状态中的至少一种（103）；响应于运行状态为停止状态，根据当前注册基站确定当前站点（104）。本方法利用地铁在不同运行状态下声音的能量特征不同的特点，判断地铁的运行状态，当地铁处于停止状态时，利用当前注册基站识别当前站点并更新，无需通过复杂的模型获取报站语音或依据第三方数据确定站点，功耗低且准确率高。

Description

站点识别方法、装置、终端及存储介质
本申请要求于2020年03月25日提交的申请号为202010217221.X、发明名称为“站点识别方法、装置、终端及存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请实施例涉及人工智能技术领域，特别涉及一种站点识别方法、装置、终端及存储介质。
背景技术
人们在乘坐地铁等公共交通工具出行时，需要时刻注意当前停靠站点是否为自己的目标站点，而到站提醒功能则是一种提醒乘客在到达目标站时及时下车的功能。
相关技术中，终端通常利用传感器(例如加速度传感器、重力传感器和磁力传感器等)采集的数据，通过加速与减速计算交通工具是否进站或出站，并结合地图进行站点预测，或者通过语音识别交通工具的报站信息，识别当前所在的站点。
发明内容
本申请实施例提供了一种站点识别方法、装置、终端及存储介质。所述技术方案如下：
一方面，本申请实施例提供了一种站点识别方法，所述方法包括：
响应于处于地铁模式，通过麦克风采集环境音；
对所述环境音进行特征提取，得到所述环境音的能量特征；
根据所述能量特征确定地铁的运行状态，所述运行状态包括进站状态、停止状态、出站状态和站间行驶状态中的至少一种；
响应于所述运行状态为所述停止状态，根据当前注册基站确定当前站点。
另一方面，本申请实施例提供了一种站点识别装置，所述装置包括：
采集模块，用于响应于处于地铁模式，通过麦克风采集环境音；
特征提取模块，用于对所述环境音进行特征提取，得到所述环境音的能量特征；
第一确定模块，用于根据所述能量特征确定地铁的运行状态，所述运行状态包括进站状态、停止状态、出站状态和站间行驶状态中的至少一种；
第二确定模块，用于响应于所述运行状态为所述停止状态，根据当前注册基站确定当前站点。
另一方面，本申请实施例提供了一种终端，所述终端包括处理器和存储器； 所述存储器存储有至少一条指令，所述至少一条指令用于被所述处理器执行以实现上述方面所述的站点识别方法。
根据本申请的一个方面，提供了一种计算机程序产品或计算机程序，该计算机程序产品或计算机程序包括计算机指令，该计算机指令存储在计算机可读存储介质中。终端的处理器从计算机可读存储介质读取该计算机指令，处理器执行该计算机指令，使得该终端执行上述方面的各种可选实现方式中提供的站点识别方法。
附图说明
图1是根据一示例性实施例示出的站点识别方法的流程图；
图2是根据一示例性实施例示出的地铁站及站点周侧基站分布示意图；
图3是根据另一示例性实施例示出的站点识别方法的流程图；
图4是根据一示例性实施例示出的环境音的音频信号和频谱图；
图5是是根据一示例性实施例示出的第一定时器时长与站间行驶时长的关系示意图；
图6是是根据一示例性实施例示出的地铁线路图；
图7是根据一示例性实施例示出的站点识别装置的结构框图；
图8是根据一示例性实施例示出的终端的结构框图。
具体实施方式
为使本申请的目的、技术方案和优点更加清楚，下面将结合附图对本申请实施方式作进一步地详细描述。
在本文中提及的“多个”是指两个或两个以上。“和/或”，描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。字符“/”一般表示前后关联对象是一种“或”的关系。
相关技术中，终端通常利用传感器(例如加速度传感器、重力传感器和磁力传感器等)采集的数据，通过加速与减速计算地铁是否进站或出站，从而判断终端当前所处的站点是否为乘客的目标站点；或者通过麦克风获取地铁的报站语音，从报站语音中提取站点信息，将站点信息与预先获取的目的站点信息进行对比，若该站点信息与目的站点信息一致，则对用户进行到站提醒。
然而，采用传感器数据识别站点时，地铁在行驶过程中并非始终匀速行驶，而是具有一定的振荡现象，用户握持终端的姿态会对加速度传感器记录的加速度方向产生影响，并且如果用户在地铁内部行走，终端记录的加速度值包含用户行走时的加速度，也会对终端的传感器产生一定影响，难以判断交通工具处于加速状态还是减速状态，这些因素会导致终端的站点预测不准确；对于识别报站语音提取站点信息的方式，地铁内环境噪声很大，终端利用降噪技术也无法准确识别语音播报内容，对于利用屏幕显示的站点信息，则需要摄像头拍摄， 不具备实际可操作性。
为了解决上述问题，本申请实施例提供了一种站点识别方法，该方法用于具备音频采集和处理功能的终端，该终端可以是智能手机、平板电脑、电子书阅读器、个人便携式计算机等。在一种可能的实施方式中，本申请实施例提供的站点识别方法可以实现成为应用程序或者应用程序的一部分，并安装在终端中。当用户乘坐交通工具时，可以手动开启该应用程序(或应用程序自动开启)，从而通过应用程序，提示用户当前所在站点。
本申请实施例提供的站点识别方法包括：
响应于处于地铁模式，通过麦克风采集环境音；
对环境音进行特征提取，得到环境音的能量特征；
根据能量特征确定地铁的运行状态，运行状态包括进站状态、停止状态、出站状态和站间行驶状态中的至少一种；
响应于运行状态为停止状态，根据当前注册基站确定当前站点。
可选的，根据所述能量特征确定地铁的运行状态，包括：
响应于能量特征符合能量均值条件，确定运行状态为停止状态；
响应于能量特征符合能量变化条件，确定运行状态为进站状态或出站状态；
响应于能量特征不符合能量均值条件和能量变化条件，确定运行状态为站间行驶状态。
可选的，响应于能量特征符合能量均值条件，确定运行状态为停止状态，包括：
响应于能量特征指示环境音的第一能量均值属于预设能量范围，对环境音进行分帧处理，得到至少两个音频帧，第一能量均值是全频段内环境音的能量均值，预设能量范围是地铁停止时环境音对应的能量范围；
对所述音频帧进行傅里叶变换，得到第一频段内环境音的第二能量均值，第一频段是地铁开门或关门的警铃声对应的频段；
响应于第二能量均值高于能量阈值，确定运行状态为停止状态。
可选的，响应于能量特征符合能量变化条件，确定运行状态为进站状态或出站状态，包括：
对环境音进行分段处理；
对各段环境音进行傅里叶变换，得到第二频段内环境音的第三能量均值，第二频段为低于预设频率的低频频段；
响应于第i段环境音的第三能量均值属于预设能量范围，且第i+1段环境音和第i+2段环境音的第三能量均值大于第i段环境音的第三能量均值，确定运行状态为出站状态，预设能量范围是地铁停止时环境音对应的能量范围，i为大于等于1的整数。
可选的，响应于能量特征符合能量变化条件，确定运行状态为进站状态或出站状态，还包括：
响应于第i+2段环境音的第三能量均值属于预设能量范围，且第i段环境音 和第i+1段环境音的第三能量均值大于第i+2段环境音的第三能量均值，确定运行状态为进站状态。
可选的，响应于运行状态为停止状态，根据当前注册基站确定当前站点之前，方法还包括：
响应于运行状态为出站状态，启动第一定时器，第一定时器的第一定时器时长为站间预计行驶时长；
响应于运行状态为停止状态，根据当前注册基站确定当前站点，包括：
响应于达到第一定时器时长，且运行状态为停止状态，根据当前注册基站确定当前站点。
可选的，根据当前注册基站确定当前站点，包括：
获取当前注册基站和映射表，映射表中包含站点与站点周侧基站之间的对应关系；
响应于映射表中包含当前注册基站对应的站点，且站点数量为一个，将查找到的站点确定为当前站点；
响应于映射表中包含当前注册基站对应的站点，且站点数量为至少两个，获取上一站点的相邻站点；将查找到的站点与相邻站点的交集站点确定为当前站点。
可选的，方法还包括：
响应于映射表中不包含当前注册基站对应的站点，或，交集站点的数量为至少两个，获取上一站点与当前站点之间计步器的步数和历史站点，历史站点为当前站点之前经过的至少两个站点；
响应于所述步数小于步数阈值，根据历史站点确定地铁线路和行驶方向，并根据地铁线路和行驶方向确定当前站点。
可选的，响应于运行状态为停止状态，根据当前注册基站确定当前站点之后，方法还包括：
确定当前站点的相邻站点；
响应于相邻站点为目标站点，设置第二定时器，第二定时器的定时器时长小于站间预计行驶时长；
响应于达到第二定时器时长，通过预定方式进行到站提醒。
请参考图1，其示出了本申请的一个实施例示出的站点识别方法的流程图。本实施例以站点识别方法用于具备音频采集和处理功能的终端为例进行说明，该方法包括：
步骤101，响应于处于地铁模式，通过麦克风采集环境音。
当处于地铁模式时，终端开启站点识别功能，并通过麦克风采集环境音。
在一种可能的实施方式中，站点识别方法应用于地图导航类应用程序时，终端实时获取用户位置信息，当根据用户位置信息确定用户进入交通工具时，终端开启地铁模式；当用户使用支付类应用程序进行刷卡乘坐地铁时，终端根据进站成功或车票支付成功的用户界面确认进入地铁，开启地铁模式。
在一种可能的实施方式中，为了降低功耗，终端可使用低功耗麦克风实时采集环境音，或者每隔预定时间间隔采集一段时间的环境音，例如每隔15s采集时长为20s的环境音。
步骤102，对环境音进行特征提取，得到环境音的能量特征。
由于终端无法直接从环境音中识别出地铁运行时的声音变化情况，因此，需要对采集到的环境音进行预处理，将通过麦克风采集的环境音转换为音频数据，并对音频数据进行环境音特征提取，得到终端能够识别的数字特征。
地铁在运行过程中，进站刹车时，存在声音的能量由大到小的渐变过程，同时不同声音的信号频率也存在明显区别；同样地，交通工具出站加速时，存在声音的能量由小到大的渐变过程。因此，在一种可能的实施方式中，终端采集环境音后，对环境音的能量特征进行提取。
步骤103，根据能量特征确定地铁的运行状态，运行状态包括进站状态、停止状态、出站状态和站间行驶状态中的至少一种。
由于地铁在不同运行状态下环境音的能量特征不同，因此终端可以通过环境音的能量特征确定地铁对应的运行状态。例如，地铁处于进站状态时，速度由大到小最终停止行驶，地铁运行时产生的噪音的能量也随着由大变小。
在一种可能的实施方式中，终端预先存储有地铁的各种运行状态，以及不同运行状态对应的声音的能量特征，当处于地铁模式时，终端根据当前环境音的能量特征确定地铁的运行状态。
步骤104，响应于运行状态为停止状态，根据当前注册基站确定当前站点。
在一种可能的实施方式中，当终端确定地铁处于停止状态或者进站状态时，说明地铁到达地铁站，此时需要更新当前站点。由于地铁站周围的基站比较固定，通常不会移动或更换，因此终端可以将当前注册基站对应的站点确定为当前站点。示意性的，请参考图2，其示出了一条地铁线路中的站点及周围基站的分布意图，其中，一个基站的覆盖范围内通常只存在一个地铁站点，同样地，一个地铁站附近通常只有一个基站，例如基站202覆盖地铁站B，基站203覆盖地铁站C，基站204覆盖地铁站D。因此终端可以根据地铁站与基站的对应关系，以及当前注册基站确定出当前站点，例如终端检测到当前注册基站为基站203，则可以确定当前站点为地铁站C。
综上所述，本申请实施例中，利用地铁在不同运行状态下声音的能量特征不同的特点，在地铁模式中通过麦克风采集环境音，并根据环境音的能量特征确定当前地铁的运行状态，当地铁处于停止状态时，确定地铁到达站点，利用当前注册基站识别当前站点并更新，其中，利用当前注册基站确定当前站点，无需通过复杂的模型获取报站语音或依据第三方数据确定站点，功耗低且准确率高。
请参考图3，其示出了本申请的另一个实施例示出的站点识别方法的流程图。本实施例以站点识别方法用于具备音频采集和处理功能的终端为例进行说明，该方法包括：
步骤301，响应于处于地铁模式，通过麦克风采集环境音。
步骤302，对环境音进行特征提取，得到环境音的能量特征。
步骤301和步骤302的实施方式可以参考上述步骤101和步骤102，本实施例在此不再赘述。
步骤303，响应于能量特征符合能量均值条件，确定运行状态为停止状态。
地铁处于停止状态时，环境音中包含乘客行走、说话产生的声音，以及开门或关门时几秒钟的警铃声，因此环境音的能量变化不大，能量均值处于固定的范围内。在一种可能的实施方式中，终端预先存储有地铁停止状态对应的能量均值条件，当终端识别出当前环境音的能量特征符合能量均值条件时，确定地铁处于停止状态。
在一种可能的实施方式中，步骤303包括如下步骤一至三：
一、响应于能量特征指示环境音的第一能量均值属于预设能量范围，对环境音进行分帧处理，得到至少两个音频帧，第一能量均值是全频段内环境音的能量均值，预设能量范围是地铁停止时环境音对应的能量范围。
请参考图4，其示出了一种地铁内部环境音的音频信号和频谱示意图，上半部分为时域信号，下半部分为频谱图。从时域上看，环境音的音频信号随地铁运行状态变化，地铁出站加速时，音频信号逐渐增强，地铁进站减速时，音频信号逐渐减弱，地铁停止时，音频信号较弱且变化幅度较小。从频谱图上看，地铁运行过程中不同运行状态的能量变化主要发生在1KHz以下的中低频部分，停止状态时，中低频部分的能量相对较低且变化不大，图中圈出的亮点为地铁开门或关门的警铃声。在一种可能的实施方式中，当环境音的第一能量均值属于地铁停止时环境音对应的能量范围，说明此时地铁可能处于停止状态，需要通过识别环境音中是否存在地铁开门或关门时的警铃声，进一步确定地铁是否处于停止状态。
在一种可能的实施方式中，终端以16KHz的采样率通过麦克风采集环境音，并以5s为一次输入，计算环境音在全频段的第一能量均值，当能量均值属于3.5×10 7J至7×10 7J时，对环境音进行警铃声识别，终端需要将环境音的音频数据转换为在频域上的能量分布，因此首先对环境音进行分帧处理，得到音频帧。
二、对音频帧进行傅里叶变换，得到第一频段内环境音的第二能量均值，第一频段是地铁开门或关门的警铃声对应的频段。
根据事先采集的警铃声的音频数据，得到警铃声的频段通常属于2.5KHz至3.5KHz之间，因此终端以2.5KHz至3.5KHz作为第一频段，获取环境音在该频段内的第二能量均值。在一种可能的实施方式中，终端以一定的傅里叶变换点数(例如512点)对分帧处理后的音频数据进行傅里叶变换，得到该段音频数据在频域上的能量分布，然后截取2.5KHz至3.5KHz之间的音频数据，计算其第二能量均值。
三、响应于第二能量均值高于能量阈值，确定运行状态为停止状态。
地铁开门或关门的警铃声与其余环境音相比，能量明显偏高，比较容易分 辨，开发人员预先设定能量阈值，用于区分警铃声与其余环境音，终端只需判断第一频段的第二能量均值是否高于能量阈值，就可以确定环境音中是否包含警铃声。在一种可能的实施方式中，若第二能量均值高于能量阈值，则该段环境音中存在警铃声，可以确定此时地铁的运行状态为停止状态。
步骤304，响应于能量特征符合能量变化条件，确定运行状态为进站状态或出站状态。
同样地，如图4所示，地铁减速进站和加速出站的过程中，音频信号也存在明显的规律性，加速出站时，1KHz以下中低频部分的能量由停止时的能量开始逐渐增加；减速进站时，1KHz以下中低频部分的能量由大变小直至减小为停止时的能量。在一种可能的实施方式中，当终端判断环境音的能量特征符合能量变化条件时，确定地铁处于进站状态或出站状态。
在一种可能的实施方式中，步骤304包括如下步骤一至三：
一、对环境音进行分段处理。
由于需要获取环境音的能量变化情况，因此终端对环境音进行分段处理，并对连续的几段环境音进行能量比较。在一种可能的实施方式中，终端以一定的时长划分环境音，并获取多段环境音的音频数据。例如，终端以时长为15s的环境音作为一次输入，并将该段环境音分为3段，每段时长为5s。
二、对各段环境音进行傅里叶变换，得到第二频段内环境音的第三能量均值，第二频段为低于预设频率的低频频段。
终端对环境音的能量变化进行分析之前，同样需要对环境音进行傅里叶变换，得到环境音在频域上的能量分布。
在一种可能的实施方式中，终端对各段环境音进行分帧处理，然后以512个变换点对分帧处理后的环境音进行傅里叶变换，并得到第二频段内环境音的第三能量均值，其中，第二频段为地铁运行时的声音所属的低频频段，低于预设频率，例如0Hz至600Hz。
对于上述步骤一中的示例，终端分别对三段时长为5s的连续环境音进行傅里叶变换，并计算得到各段环境音在0Hz至600Hz的第三能量均值E1、E2和E3。
三、响应于第i段环境音的第三能量均值属于预设能量范围，且第i+1段环境音和第i+2段环境音的第三能量均值大于第i段环境音的第三能量均值，确定运行状态为出站状态，预设能量范围是地铁停止时环境音对应的能量范围，i为大于等于1的整数。
对于上述步骤二中的示例，若E1属于预设能量范围3.5×10 7J至7×10 7J，且E2与E1的比值和E3与E1的比值大于1，则可以确定地铁的运行状态为出站状态。为了提高识别结果的准确性，终端内预先设置有能量比值，若E2/E1＞1.2，且E3/E1大于1.45，则确定运行状态为出站状态。
与出站状态相反，地铁处于进站状态时的能量变化条件为中低频部分的能量由大到小变化，降低至停止状态时的能量范围。在一种可能的实施方式中，上述步骤二之后，本申请实施例提供的站点识别方法方法还包括如下步骤：
响应于第i+2段环境音的第三能量均值属于预设能量范围，且第i+1段环境音和第i段环境音的第三能量均值大于第i+2段环境音的第三能量均值，确定运行状态为进站状态。例如，E1/E3大于1.45，E2/E3大于1.2，且E3属于3.5×10 7J至7×10 7J，则确定地铁处于进站状态。在另一种可能的实施方式中，为了进一步确定地铁是否到达站点，终端在地铁的运行状态满足先处于进站状态后处于停止状态时，确定地铁到达站点；相应地，终端在地铁的运行状态满足先处于停止状态后处于出站状态时，确定地铁开始运行。
步骤305，响应于能量特征不符合能量均值条件和能量变化条件，确定运行状态为站间行驶状态。
由于地铁在站间行驶过程中并非始终匀速行驶，如图4所示，可能存在加速和减速的情况，因此无法通过特定的能量特征辨别站间行驶状态。在一种可能的实施方式中，若环境音的能量特征不符合上述能量均值条件和能量变化条件，则说明地铁不处于停止状态、进站状态或出站状态中的任何一种运行状态，即地铁处于站间行驶状态。
步骤306，响应于运行状态为出站状态，启动第一定时器，第一定时器的第一定时器时长为站间预计行驶时长。
为了提高站点识别的准确性，避免地铁站间行驶过程中的减速导致终端误识别为进站状态，终端内预先设置有定时器。各个站点之间的行驶时长基本是固定的，在未满足行驶时长时，地铁不会到达下一个站点，因此开发人员预先采集所有地铁站之间的行驶时长，通过采用定时器的方式控制终端进行站点识别，避免发生错误。
在一种可能的实施方式中，第一定时器时长可以是固定时长，该固定时长可以设定为地铁站间行驶的最短时长；或者，第一定时器时长是通过查询得到的当前站点到下一站点的平均时长，本申请实施例对此不作限定。
请参考图5，其示出了一种地铁行驶过程中终端启动定时器的示意图。当终端识别出地铁处于出站状态时，立即启动第一定时器，第一定时器的第一定时器时长为站间预计行驶时长。
步骤307，响应于达到第一定时器时长，且运行状态为停止状态，根据当前注册基站确定当前站点。
在一种可能的实施方式中，终端实时通过麦克风获取环境音，并判断地铁的运行状态，当确定地铁处于停止状态时，查询定时器是否超时，即是否达到第一定时器时长，若未达到第一定时器时长，则继续根据环境音判断运行状态，若达到定时器时长，则确定地铁到站，并根据当前注册基站确定当前站点。
在另一种可能的实施方式中，终端在地铁模式中始终根据当前注册基站确定当前站点，当确定地铁处于停止状态时，查询定时器是否超时，若未超时，则不更新当前站点，若超时，则更新当前站点。
步骤308，确定当前站点的相邻站点。
在一种可能的实施方式中，终端的地铁模式包括到站提醒功能。每到达一站，终端获取一次当前站点的相邻站点，以便在确定即将到达下车站时，对用 户进行到站提醒，使得用户提前做好下车准备。其中，相邻站点可以是根据当前站点和当前地铁行驶方向确定出的下一站点。
步骤309，响应于相邻站点为目标站点，设置第二定时器，第二定时器的定时器时长小于站间预计行驶时长。
在一种可能的实施方式中，目标站点是用户事先设置的需要到站提醒服务的站点；或者终端可以默认每到达一个站点之前都进行到站提醒，则目标站点为当前站点的下一站点。
在一种可能的实施方式中，当终端确定出当前站点的相邻站点为目标站点时，在地铁处于出站状态时启动第二定时器，第二定时器时长小于站间预计行驶时长，例如，第二定时器时长为站间预计行驶时长的二分之一。示意性的，终端识别到当前站点为东陆路，相邻站点为目标站点巨峰路，从东陆路到巨峰路的站间预计行驶时长为6分钟，则终端在地铁处于出站状态时启动第二定时器，第二定时器时长为3分钟。在一种可能的实施方式中，终端通过系统埋点的方式获取界面信息，当获取到进站成功或车票支付成功的界面时，自动开启地铁模式。终端进入地铁模式后，显示目标站点输入界面，用户通过语音或手动输入目标站点，当终端获取到用户输入的至少一个目标站点时，开启到站提醒功能；或者，终端根据用户的历史出行记录自动筛选目标站点以便用户选择。
在另一种可能的实施方式中，用户可以选择手动开启地铁模式，当终端接收到地铁模式的开启指令时，显示目标站点输入界面，或根据历史出行记录显示默认的目标站点。
步骤310，响应于达到第二定时器时长，通过预定方式进行到站提醒。
当达到第二定时器时长时，终端通过语音、提示消息等方式提醒用户到达目的站点，及时下车，必要时可以添加短信、振动等特别提醒，防止用户遗漏消息。
本申请实施例中，通过对环境音的能量特征进行分析确定地铁的运行状态，在出站状态时启动定时器，并在定时器超时时根据静止状态确定地铁到站，避免了地铁在站间行驶状态下的减速和加速对终端的识别结果造成影响，提高了站点识别的准确率和时效性；此外，终端确定出当前站点的相邻站点为目标站点时，开启时长小于站间预计行驶时长的第二定时器，并在第二定时器超时时对用户进行到站提醒，以便用户能够提前为下车做好准备，避免坐过站。
如图2所示，少数基站可能覆盖多个地铁站，此时终端无法直接根据当前注册基站确定当前站点，在一种可能的实施方式中，上述步骤307还包括如下步骤一至三：
一、获取当前注册基站和映射表，映射表中包含站点与站点周侧基站之间的对应关系。
当终端检测到地铁处于停止状态时，需要更新当前站点，在一种可能的实施方式中，终端采用基站定位站点的方式确定当前站点。由于基站的覆盖范围有限，通常覆盖距离在2至5公里，并且由于地铁内信号质量较差，各大运营 商会在地铁线路中部署更多的基站，确保地铁内的信号强度，因此在不同的站点，终端会注册到不同的基站。
在一种可能的实施方式中，终端内存储有映射表，如表1所示，该映射表中包含各个站点与站点周侧基站间的对应关系。
Figure PCTCN2021074680-appb-000001
表1
在一种可能的实施方式中，终端获取当前注册基站的基站信息，在映射表中查询对应的基站，从而获得对应的站点，该站点为当前站点。例如，终端当前注册基站为mcc-460-mnc-00-ci-25935874-pci-435-tac-6270，根据映射表确定当前站点为上海地铁_12号线_龙华中路。
可选的，该映射表存储在后台服务器中，当终端检测到进站时，将当前注册基站的基站信息发送至后台服务器，并根据后台服务器反馈的站点信息确定当前站点。
二、响应于映射表中包含当前注册基站对应的站点，且站点数量为一个，将查找到的站点确定为当前站点。
若映射表中当前注册基站对应的站点唯一，则该站点可以确定为当前站点。
三、响应于映射表中包含当前注册基站对应的站点，且站点数量为至少两个，获取上一站点的相邻站点；将查找到的站点与相邻站点的交集站点确定为当前站点。
地铁行驶过程中可能存在少数基站同时覆盖多个站点，例如图2中，基站201覆盖了地铁站A和地铁站B；同样地，少数地铁站位于多个基站覆盖范围的重叠区域，例如地铁站B既在基站201的覆盖范围内，也在基站202的覆盖范围内。
若映射表中当前注册基站对应的站点数大于1，则无法直接确定当前站点。考虑到一条地铁线路中各个站点的邻近关系是固定的，并且终端确定当前站点之前，显示的站点为上一站点，因此可以通过获取当前基站对应的站点与上一站点的相邻站点的交集确定当前站点。
在一种可能的实施方式中，终端内存储有当前线路各个站点的信息，包括各站点对应的相邻站点，当终端从映射表中获取的当前注册基站对应的站点数量大于1时，获取上一站点(即当前终端所显示的站点)的相邻站点。
可选的，后台服务器的数据库中存储有各个城市的地铁线路，终端可以将上一站点的名称上传至服务器，由服务器从数据库中查询上一站点的相邻站点，并反馈至对应终端。
示意性的，请参考图2，终端当前所在的地铁线路中，基站201的覆盖范围内对应有地铁站A和地铁站B，用户所在地铁正在由地铁站A驶往地铁站B，当前终端显示的站点为地铁站A，当终端检测到地铁处于停止状态时，根据当前注册基站201获得的站点为地铁站A和地铁站B，无法确定当前站点，因此终端获取地铁站A的相邻站点，得到相邻站点为地铁站B，通过对相邻站点B与当前注册基站201对应的地铁站A和地铁站B取交集，得到当前站点为地铁站B。
在一种可能的实施方式中，终端无法从映射表中查询到当前注册基站，或者当前注册基站与上一站点的相邻站点的交集站点有多个，终端无法根据当前注册基站确定当前站点，需要利用历史站点和地铁线路进行站点推测，得到当前站点，则站点识别方法还包括如下步骤四和五：
四、响应于映射表中不包含当前注册基站对应的站点，或，交集站点的数量为至少两个，获取上一站点与当前站点之间计步器的步数和历史站点，历史站点为当前站点之前经过的至少两个站点。
若终端无法根据当前注册基站确定当前站点，则获取历史站点，根据历史站点推测当前站点。终端进行站点推测之前，需要判断用户在上一站点是否换乘其他线路，否则可能导致推测结果错误，因此终端在进入地铁模式时开启计步器，实时记录用户的步数，终端进行站点推测前，获取上一站点与当前站点之间计步器更新的步数，或者，终端在判断出当前站点或下一站点为可以换乘线路的地铁站时，开启计步器，并在确定地铁驶离该站点后关闭计步器。
五、响应于步数小于步数阈值，根据历史站点确定地铁线路和行驶方向，并根据地铁线路和行驶方向确定当前站点。
若步数小于步数阈值(例如步数阈值为50步)，则说明用户在上一站点没有换乘其他线路，终端可以根据历史站点确定地铁线路和行驶方向，再根据地铁线路和行驶方向确定当前站点。
如图6所示，假如终端获取到历史站点为东陆路和巨峰路，则可以推测出用户乘坐了12号线，但巨峰路为换乘站，用户可能换乘至6号线到达五莲路或东靖路，因此终端需要获取上一站点与当前站点之间计步器的步数，若该步数小于阈值，则说明用户并未下车换乘，可以推测出当前站点为12号线的杨高北路。
本申请实施例中，终端通过获取当前注册基站以及该基站对应的站点确定当前站点，无需通过复杂的模型获取报站语音或依据第三方数确定站点，功耗低且准确率高；终端利用历史站点和计步器步数进一步推测当前站点，避免了无法查询到当前注册基站，或当前注册基站同时覆盖多个站点导致的站点识别结果错误，提高了站点识别的准确率。
请参考图7，其示出了本申请一个示例性实施例提供的站点识别装置的结构框图。该装置可以通过软件、硬件或者两者的结合实现成为终端的全部或一部分。该装置包括：
采集模块701，用于响应于处于地铁模式，通过麦克风采集环境音；
特征提取模块702，用于对所述环境音进行特征提取，得到所述环境音的能量特征；
第一确定模块703，用于根据所述能量特征确定地铁的运行状态，所述运行状态包括进站状态、停止状态、出站状态和站间行驶状态中的至少一种；
第二确定模块704，用于响应于所述运行状态为所述停止状态，根据当前注册基站确定当前站点。
可选的，所述第一确定模块703，包括：
第一确定单元，用于响应于所述能量特征符合能量均值条件，确定所述运行状态为所述停止状态；
第二确定单元，用于响应于所述能量特征符合能量变化条件，确定所述运行状态为所述进站状态或所述出站状态；
第三确定单元，用于响应于所述能量特征不符合所述能量均值条件和所述能量变化条件，确定所述运行状态为所述站间行驶状态。
可选的，所述第一确定单元，还用于：
响应于所述能量特征指示所述环境音的第一能量均值属于预设能量范围，对所述环境音进行分帧处理，得到至少两个音频帧，所述第一能量均值是全频段内所述环境音的能量均值，所述预设能量范围是地铁停止时环境音对应的能量范围；
对所述音频帧进行傅里叶变换，得到第一频段内所述环境音的第二能量均值，所述第一频段是地铁开门或关门的警铃声对应的频段；
响应于所述第二能量均值高于能量阈值，确定所述运行状态为所述停止状态。
可选的，所述第二确定单元，还用于：
对所述环境音进行分段处理；
对各段环境音进行傅里叶变换，得到第二频段内所述环境音的第三能量均值，所述第二频段为低于预设频率的低频频段；
响应于第i段环境音的所述第三能量均值属于预设能量范围，且第i+1段环境音和第i+2段环境音的所述第三能量均值大于所述第i段环境音的所述第三能量均值，确定所述运行状态为所述出站状态，所述预设能量范围是地铁停止时环境音对应的能量范围，i为大于等于1的整数。
可选的，所述第二确定单元，还用于：
响应于所述第i+2段环境音的所述第三能量均值属于所述预设能量范围，且所述第i段环境音和所述第i+1段环境音的所述第三能量均值大于所述第i+2段环境音的所述第三能量均值，确定所述运行状态为所述进站状态。
可选的，所述装置还包括：
第一定时模块，用于响应于所述运行状态为所述出站状态，启动第一定时器，所述第一定时器的第一定时器时长为站间预计行驶时长；
所述第二确定模块704，包括：
第四确定单元，用于响应于达到所述第一定时器时长，且所述运行状态为所述停止状态，根据所述当前注册基站确定所述当前站点。
可选的，所述第二确定模块704，还包括：
获取单元，用于获取所述当前注册基站和映射表，所述映射表中包含站点与站点周侧基站之间的对应关系；
第五确定单元，用于响应于所述映射表中包含所述当前注册基站对应的站点，且站点数量为一个，将查找到的站点确定为所述当前站点；
第六确定单元，用于响应于所述映射表中包含所述当前注册基站对应的站点，且站点数量为至少两个，获取上一站点的相邻站点；将查找到的站点与所述相邻站点的交集站点确定为所述当前站点。
可选的，所述装置还包括：
获取模块，用于响应于所述映射表中不包含所述当前注册基站对应的站点，或，所述交集站点的数量为至少两个，获取上一站点与所述当前站点之间计步器的步数和历史站点，所述历史站点为所述当前站点之前经过的至少两个站点；
第三确定模块，用于响应于所述步数小于步数阈值，根据所述历史站点确定地铁线路和行驶方向，并根据所述地铁线路和所述行驶方向确定所述当前站点。
可选的，所述装置还包括：
第四确定模块，用于确定所述当前站点的相邻站点；
第二定时模块，用于响应于所述相邻站点为目标站点，设置第二定时器，所述第二定时器的定时器时长小于站间预计行驶时长；
到站提醒模块，用于响应于达到所述第二定时器时长，通过预定方式进行到站提醒。
请参考图8，其示出了本申请一个示例性实施例提供的终端800的结构方框图。该终端800可以是智能手机、平板电脑、电子书、便携式个人计算机等安装并运行有应用程序的电子设备。本申请中的终端800可以包括一个或多个如下部件：处理器820、存储器810、屏幕830和麦克风840。
处理器820可以包括一个或者多个处理核心。处理器820利用各种接口和线路连接整个终端800内的各个部分，通过运行或执行存储在存储器810内的指令、程序、代码集或指令集，以及调用存储在存储器810内的数据，执行终端800的各种功能和处理数据。可选地，处理器820可以采用数字信号处理(Digital Signal Processing，DSP)、现场可编程门阵列(Field－Programmable Gate Array，FPGA)、可编程逻辑阵列(Programmable Logic Array，PLA)中的至少一种硬件形式来实现。处理器820可集成中央处理器(Central Processing Unit，CPU)、图像处理器(Graphics Processing Unit，GPU)和调制解调器等中的一种或几种的组合。其中，CPU主要处理操作系统、用户界面和应用程序等；GPU用于负责屏幕830所需要显示的内容的渲染和绘制；调制解调器用于处理无线通信。可以理解的是，上述调制解调器也可以不集成到处理器820中，单独通 过一块通信芯片进行实现。
存储器810可以包括随机存储器(Random Access Memory，RAM)，也可以包括只读存储器(Read-Only Memory，ROM)。可选地，该存储器810包括非瞬时性计算机可读介质(non-transitory computer-readable storage medium)。存储器810可用于存储指令、程序、代码、代码集或指令集。存储器810可包括存储程序区和存储数据区，其中，存储程序区可存储用于实现操作系统的指令、用于实现至少一个功能的指令(比如触控功能、声音播放功能、图像播放功能等)、用于实现上述各个方法实施例的指令等，该操作系统可以是安卓(Android)系统(包括基于Android系统深度开发的系统)、苹果公司开发的IOS系统(包括基于IOS系统深度开发的系统)或其它系统。存储数据区还可以存储终端800在使用中所创建的数据(比如电话本、音视频数据、聊天记录数据)等。
屏幕830可以为电容式触摸显示屏，该电容式触摸显示屏用于接收用户使用手指、触摸笔等任何适合的物体在其上或附近的触摸操作，以及显示各个应用程序的用户界面。触摸显示屏通常设置在终端800的前面板。触摸显示屏可被设计成为全面屏、曲面屏或异型屏。触摸显示屏还可被设计成为全面屏与曲面屏的结合，异型屏与曲面屏的结合，本申请实施例对此不加以限定。
麦克风840可以为低功耗麦克风，该麦克风840用于终端开启进出站预测功能时采集环境音，也可以用于语音通话时采集环境音。麦克风840通常设置在终端显示屏一侧的边缘部分(如下边缘)，本申请实施例对此不加限定。
除此之外，本领域技术人员可以理解，上述附图所示出的终端800的结构并不构成对终端800的限定，终端可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。比如，终端800中还包括射频电路、拍摄组件、传感器、音频电路、WiFi组件、电源、蓝牙组件等部件，在此不再赘述。
本申请实施例还提供了一种计算机可读存储介质，该计算机可读存储介质存储有至少一条指令，所述至少一条指令由所述处理器加载并执行以实现如上各个实施例所述的站点识别方法。
根据本申请的一个方面，提供了一种计算机程序产品或计算机程序，该计算机程序产品或计算机程序包括计算机指令，该计算机指令存储在计算机可读存储介质中。终端的处理器从计算机可读存储介质读取该计算机指令，处理器执行该计算机指令，使得该终端执行上述方面的各种可选实现方式中提供的站点识别方法。本领域技术人员应该可以意识到，在上述一个或多个示例中，本申请实施例所描述的功能可以用硬件、软件、固件或它们的任意组合来实现。当使用软件实现时，可以将这些功能存储在计算机可读存储介质中或者作为计算机可读存储介质上的一个或多个指令或代码进行传输。计算机可读存储介质包括计算机存储介质和通信介质，其中通信介质包括便于从一个地方向另一个地方传送计算机程序的任何介质。存储介质可以是通用或专用计算机能够存取的任何可用介质。
以上所述仅为本申请的可选实施例，并不用以限制本申请，凡在本申请的 精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本申请的保护范围之内。

Claims (20)

  1. 一种站点识别方法，其中，所述方法包括：
    响应于处于地铁模式，通过麦克风采集环境音；
    对所述环境音进行特征提取，得到所述环境音的能量特征；
    根据所述能量特征确定地铁的运行状态，所述运行状态包括进站状态、停止状态、出站状态和站间行驶状态中的至少一种；
    响应于所述运行状态为所述停止状态，根据当前注册基站确定当前站点。
  2. 根据权利要求1所述的方法，其中，所述根据所述能量特征确定地铁的运行状态，包括：
    响应于所述能量特征符合能量均值条件，确定所述运行状态为所述停止状态；
    响应于所述能量特征符合能量变化条件，确定所述运行状态为所述进站状态或所述出站状态；
    响应于所述能量特征不符合所述能量均值条件和所述能量变化条件，确定所述运行状态为所述站间行驶状态。
  3. 根据权利要求2所述的方法，其中，所述响应于所述能量特征符合能量均值条件，确定所述运行状态为所述停止状态，包括：
    响应于所述能量特征指示所述环境音的第一能量均值属于预设能量范围，对所述环境音进行分帧处理，得到至少两个音频帧，所述第一能量均值是全频段内所述环境音的能量均值，所述预设能量范围是地铁停止时环境音对应的能量范围；
    对所述音频帧进行傅里叶变换，得到第一频段内所述环境音的第二能量均值，所述第一频段是地铁开门或关门的警铃声对应的频段；
    响应于所述第二能量均值高于能量阈值，确定所述运行状态为所述停止状态。
  4. 根据权利要求2所述的方法，其中，所述响应于所述能量特征符合能量变化条件，确定所述运行状态为所述进站状态或所述出站状态，包括：
    对所述环境音进行分段处理；
    对各段环境音进行傅里叶变换，得到第二频段内所述环境音的第三能量均值，所述第二频段为低于预设频率的低频频段；
    响应于第i段环境音的所述第三能量均值属于预设能量范围，且第i+1段环境音和第i+2段环境音的所述第三能量均值大于所述第i段环境音的所述第三能量均值，确定所述运行状态为所述出站状态，所述预设能量范围是地铁停止时环境音对应的能量范围，i为大于等于1的整数。
  5. 根据权利要求4所述的方法，其中，所述响应于所述能量特征符合能量变化条件，确定所述运行状态为所述进站状态或所述出站状态，还包括：
    响应于所述第i+2段环境音的所述第三能量均值属于所述预设能量范围，且所述第i段环境音和所述第i+1段环境音的所述第三能量均值大于所述第i+2段环境音的所述第三能量均值，确定所述运行状态为所述进站状态。
  6. 根据权利要求1至5任一所述的方法，其中，所述响应于所述运行状态为所述停止状态，根据当前注册基站确定当前站点之前，所述方法还包括：
    响应于所述运行状态为所述出站状态，启动第一定时器，所述第一定时器的第一定时器时长为站间预计行驶时长；
    所述响应于所述运行状态为所述停止状态，根据当前注册基站确定当前站点，包括：
    响应于达到所述第一定时器时长，且所述运行状态为所述停止状态，根据所述当前注册基站确定所述当前站点。
  7. 根据权利要求1至5任一所述的方法，其中，所述根据当前注册基站确定当前站点，包括：
    获取所述当前注册基站和映射表，所述映射表中包含站点与站点周侧基站之间的对应关系；
    响应于所述映射表中包含所述当前注册基站对应的站点，且站点数量为一个，将查找到的站点确定为所述当前站点；
    响应于所述映射表中包含所述当前注册基站对应的站点，且站点数量为至少两个，获取上一站点的相邻站点；将查找到的站点与所述相邻站点的交集站点确定为所述当前站点。
  8. 根据权利要求7所述的方法，其中，所述方法，还包括：
    响应于所述映射表中不包含所述当前注册基站对应的站点，或，所述交集站点的数量为至少两个，获取上一站点与所述当前站点之间计步器的步数和历史站点，所述历史站点为所述当前站点之前经过的至少两个站点；
    响应于所述步数小于步数阈值，根据所述历史站点确定地铁线路和行驶方向，并根据所述地铁线路和所述行驶方向确定所述当前站点。
  9. 根据权利要求1至5任一所述的方法，其中，所述响应于所述运行状态为所述停止状态，根据当前注册基站确定当前站点之后，所述方法还包括：
    确定所述当前站点的相邻站点；
    响应于所述相邻站点为目标站点，设置第二定时器，所述第二定时器的定时器时长小于站间预计行驶时长；
    响应于达到所述第二定时器时长，通过预定方式进行到站提醒。
  10. 一种站点识别装置，所述装置包括：
    采集模块，用于响应于处于地铁模式，通过麦克风采集环境音；
    特征提取模块，用于对所述环境音进行特征提取，得到所述环境音的能量特征；
    第一确定模块，用于根据所述能量特征确定地铁的运行状态，所述运行状态包括进站状态、停止状态、出站状态和站间行驶状态中的至少一种；
    第二确定模块，用于响应于所述运行状态为所述停止状态，根据当前注册基站确定当前站点。
  11. 根据权利要求10所述的装置，其中，所述第一确定模块，包括：
    第一确定单元，用于响应于所述能量特征符合能量均值条件，确定所述运行状态为所述停止状态；
    第二确定单元，用于响应于所述能量特征符合能量变化条件，确定所述运行状态为所述进站状态或所述出站状态；
    第三确定单元，用于响应于所述能量特征不符合所述能量均值条件和所述能量变化条件，确定所述运行状态为所述站间行驶状态。
  12. 根据权利要求11所述的装置，其中，所述第一确定单元，还用于：
    响应于所述能量特征指示所述环境音的第一能量均值属于预设能量范围，对所述环境音进行分帧处理，得到至少两个音频帧，所述第一能量均值是全频段内所述环境音的能量均值，所述预设能量范围是地铁停止时环境音对应的能量范围；
    对所述音频帧进行傅里叶变换，得到第一频段内所述环境音的第二能量均值，所述第一频段是地铁开门或关门的警铃声对应的频段；
    响应于所述第二能量均值高于能量阈值，确定所述运行状态为所述停止状态。
  13. 根据权利要求11所述的装置，其中，所述第二确定单元，还用于：
    对所述环境音进行分段处理；
    对各段环境音进行傅里叶变换，得到第二频段内所述环境音的第三能量均值，所述第二频段为低于预设频率的低频频段；
    响应于第i段环境音的所述第三能量均值属于预设能量范围，且第i+1段环境音和第i+2段环境音的所述第三能量均值大于所述第i段环境音的所述第三能量均值，确定所述运行状态为所述出站状态，所述预设能量范围是地铁停止时环境音对应的能量范围，i为大于等于1的整数。
  14. 根据权利要求13所述的装置，其中，所述第二确定单元，还用于：
    响应于所述第i+2段环境音的所述第三能量均值属于所述预设能量范围，且所述第i段环境音和所述第i+1段环境音的所述第三能量均值大于所述第i+2段 环境音的所述第三能量均值，确定所述运行状态为所述进站状态。
  15. 根据权利要求10至14任一所述的装置，其中，所述装置还包括：
    第一定时模块，用于响应于所述运行状态为所述出站状态，启动第一定时器，所述第一定时器的第一定时器时长为站间预计行驶时长；
    所述第二确定模块，包括：
    第四确定单元，用于响应于达到所述第一定时器时长，且所述运行状态为所述停止状态，根据所述当前注册基站确定所述当前站点。
  16. 根据权利要求10至14任一所述的装置，其中，所述第二确定模块，还包括：
    获取单元，用于获取所述当前注册基站和映射表，所述映射表中包含站点与站点周侧基站之间的对应关系；
    第五确定单元，用于响应于所述映射表中包含所述当前注册基站对应的站点，且站点数量为一个，将查找到的站点确定为所述当前站点；
    第六确定单元，用于响应于所述映射表中包含所述当前注册基站对应的站点，且站点数量为至少两个，获取上一站点的相邻站点；将查找到的站点与所述相邻站点的交集站点确定为所述当前站点。
  17. 根据权利要求16所述的装置，其中，所述装置还包括：
    获取模块，用于响应于所述映射表中不包含所述当前注册基站对应的站点，或，所述交集站点的数量为至少两个，获取上一站点与所述当前站点之间计步器的步数和历史站点，所述历史站点为所述当前站点之前经过的至少两个站点；
    第三确定模块，用于响应于所述步数小于步数阈值，根据所述历史站点确定地铁线路和行驶方向，并根据所述地铁线路和所述行驶方向确定所述当前站点。
  18. 根据权利要求10至14任一所述的装置，其中，所述装置还包括：
    第四确定模块，用于确定所述当前站点的相邻站点；
    第二定时模块，用于响应于所述相邻站点为目标站点，设置第二定时器，所述第二定时器的定时器时长小于站间预计行驶时长；
    到站提醒模块，用于响应于达到所述第二定时器时长，通过预定方式进行到站提醒。
  19. 一种终端，所述终端包括处理器和存储器；所述存储器存储有至少一条指令，所述至少一条指令用于被所述处理器执行以实现如权利要求1至9任一所述的站点识别方法。
  20. 一种计算机可读存储介质，所述存储介质存储有至少一条指令，所述 至少一条指令用于被处理器执行以实现如权利要求1至9任一所述的站点识别方法。
PCT/CN2021/074680 2020-03-25 2021-02-01 站点识别方法、装置、终端及存储介质 WO2021190145A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010217221.XA CN111415679B (zh) 2020-03-25 2020-03-25 站点识别方法、装置、终端及存储介质
CN202010217221.X 2020-03-25

Publications (1)

Publication Number Publication Date
WO2021190145A1 true WO2021190145A1 (zh) 2021-09-30

Family

ID=71493273

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/074680 WO2021190145A1 (zh) 2020-03-25 2021-02-01 站点识别方法、装置、终端及存储介质

Country Status (2)

Country Link
CN (1) CN111415679B (zh)
WO (1) WO2021190145A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114090696A (zh) * 2021-10-13 2022-02-25 桂林理工大学 一种环境音大数据可视化系统及方法

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111415679B (zh) * 2020-03-25 2023-02-28 Oppo广东移动通信有限公司 站点识别方法、装置、终端及存储介质
CN113114752B (zh) * 2021-04-07 2023-02-24 Oppo广东移动通信有限公司 基于公共交通场景的数据获取方法、装置、终端及服务器

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN2896395Y (zh) * 2006-03-28 2007-05-02 宇龙计算机通信科技(深圳)有限公司 地铁到站提醒装置
CN103167410A (zh) * 2012-07-18 2013-06-19 深圳市金立通信设备有限公司 基于地铁基站信号实现手机到站提醒的系统及方法
CN105142112A (zh) * 2015-09-24 2015-12-09 广东欧珀移动通信有限公司 移动终端自动检测地铁环境并自动报站提示的方法及装置
US20160091593A1 (en) * 2014-09-30 2016-03-31 Apple Inc. Location fingerprinting for transit systems
CN107545763A (zh) * 2016-06-28 2018-01-05 高德信息技术有限公司 一种车辆定位方法、终端、服务器及系统
WO2019226114A1 (en) * 2018-05-24 2019-11-28 Icomera Ab System and apparatus for determining the position of railbound vehicles on a railway system
CN110660201A (zh) * 2019-09-23 2020-01-07 Oppo广东移动通信有限公司 到站提醒方法、装置、终端及存储介质
CN111325386A (zh) * 2020-02-11 2020-06-23 Oppo广东移动通信有限公司 交通工具运行状态的预测方法、装置、终端及存储介质
CN111354371A (zh) * 2020-02-26 2020-06-30 Oppo广东移动通信有限公司 交通工具运行状态的预测方法、装置、终端及存储介质
CN111415679A (zh) * 2020-03-25 2020-07-14 Oppo广东移动通信有限公司 站点识别方法、装置、终端及存储介质

Family Cites Families (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6804605B2 (en) * 2000-05-17 2004-10-12 Omega Patents, L.L.C. Vehicle tracker with user registration reminder and related methods
US11008029B2 (en) * 2016-01-21 2021-05-18 Transportation Ip Holdings, Llc Vehicle control system
WO2014031563A2 (en) * 2012-08-20 2014-02-27 Jonathan Strimling System and method for neighborhood-scale vehicle monitoring
CN104092654B (zh) * 2014-01-22 2016-03-02 腾讯科技（深圳）有限公司 媒体播放方法、客户端及系统
WO2016183718A1 (zh) * 2015-05-15 2016-11-24 冯旋宇 一种车站信息反馈系统及方法
CN106558232A (zh) * 2015-09-30 2017-04-05 中国电信股份有限公司 一种用户到站提醒方法、系统和到站提醒服务器
CN105235716B (zh) * 2015-11-03 2017-03-08 株洲南车时代电气股份有限公司 一种列车全自动报站方法
WO2017101067A1 (zh) * 2015-12-17 2017-06-22 华为技术有限公司 一种对周围环境音的处理方法及设备
CN105425115B (zh) * 2016-01-25 2018-04-13 成都国铁电气设备有限公司 多种定位方式的接触网定位方法及系统
CN105810212B (zh) * 2016-03-07 2019-04-23 合肥工业大学 一种复杂噪声环境下的列车鸣笛识别方法
JP2018100936A (ja) * 2016-12-21 2018-06-28 トヨタ自動車株式会社 車載装置及び経路情報提示システム
JP7163035B2 (ja) * 2018-02-19 2022-10-31 株式会社東芝 音響出力システム、音響出力方法及びプログラム
CN109151168B (zh) * 2018-07-20 2020-08-18 阿里巴巴集团控股有限公司 乘车码的切换方法、装置、移动终端及可读存储介质
CN109696609A (zh) * 2019-01-25 2019-04-30 西南交通大学 一种新型弓网受流质量的获取方法及其获取系统
CN110035379B (zh) * 2019-03-28 2020-08-25 维沃移动通信有限公司 一种定位方法及终端设备
CN110245377B (zh) * 2019-05-08 2023-08-04 暨南大学 一种出行方案推荐方法及推荐系统

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN2896395Y (zh) * 2006-03-28 2007-05-02 宇龙计算机通信科技(深圳)有限公司 地铁到站提醒装置
CN103167410A (zh) * 2012-07-18 2013-06-19 深圳市金立通信设备有限公司 基于地铁基站信号实现手机到站提醒的系统及方法
US20160091593A1 (en) * 2014-09-30 2016-03-31 Apple Inc. Location fingerprinting for transit systems
CN105142112A (zh) * 2015-09-24 2015-12-09 广东欧珀移动通信有限公司 移动终端自动检测地铁环境并自动报站提示的方法及装置
CN107545763A (zh) * 2016-06-28 2018-01-05 高德信息技术有限公司 一种车辆定位方法、终端、服务器及系统
WO2019226114A1 (en) * 2018-05-24 2019-11-28 Icomera Ab System and apparatus for determining the position of railbound vehicles on a railway system
CN110660201A (zh) * 2019-09-23 2020-01-07 Oppo广东移动通信有限公司 到站提醒方法、装置、终端及存储介质
CN111325386A (zh) * 2020-02-11 2020-06-23 Oppo广东移动通信有限公司 交通工具运行状态的预测方法、装置、终端及存储介质
CN111354371A (zh) * 2020-02-26 2020-06-30 Oppo广东移动通信有限公司 交通工具运行状态的预测方法、装置、终端及存储介质
CN111415679A (zh) * 2020-03-25 2020-07-14 Oppo广东移动通信有限公司 站点识别方法、装置、终端及存储介质

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114090696A (zh) * 2021-10-13 2022-02-25 桂林理工大学 一种环境音大数据可视化系统及方法
CN114090696B (zh) * 2021-10-13 2024-03-29 桂林理工大学 一种环境音大数据可视化系统及方法

Also Published As

Publication number Publication date
CN111415679B (zh) 2023-02-28
CN111415679A (zh) 2020-07-14

Similar Documents

Publication Publication Date Title
WO2021190145A1 (zh) 站点识别方法、装置、终端及存储介质
WO2021175062A1 (zh) 服务提供方法、装置、终端及存储介质
CN110660201B (zh) 到站提醒方法、装置、终端及存储介质
WO2021184985A1 (zh) 站点识别方法、到站提醒方法、装置、终端及存储介质
CN109792577B (zh) 信息处理设备、信息处理方法和计算机可读存储介质
CN103918247B (zh) 基于背景环境的智能手机传感器逻辑
WO2021179849A1 (zh) 站点预测方法、装置、终端及存储介质
WO2021169742A1 (zh) 交通工具运行状态的预测方法、装置、终端及存储介质
CN111325386B (zh) 交通工具运行状态的预测方法、装置、终端及存储介质
WO2021115232A1 (zh) 到站提醒方法、装置、终端及存储介质
WO2021232962A1 (zh) 目的站点的预测方法、装置、电子设备及存储介质
CN107545763B (zh) 一种车辆定位方法、终端、服务器及系统
CN110971763B (zh) 到站提醒方法、装置、存储介质及电子设备
US11438029B2 (en) Screen transmission method, vehicle mount, and storage medium
CN110972112B (zh) 地铁运行方向的确定方法、装置、终端及存储介质
CN107452221A (zh) 到站提醒方法及装置
CN106713633A (zh) 一种聋人提示系统、方法及智能手机
CN110110026A (zh) 一种智能提示出行帮助信息的方法、装置及介质
CN102779426B (zh) 语音提示系统及方法
CN112216140A (zh) 交通工具到站确认方法、电子设备及计算机可读存储介质
CN109451385A (zh) 一种基于使用耳机时的提醒方法以及装置
CN110880328A (zh) 到站提醒方法、装置、终端及存储介质
CN106156207A (zh) 提醒时间修改方法及装置
CN113984078A (zh) 到站提醒方法、装置、终端及存储介质
CN111422150B (zh) 车辆语音播报方法及车载终端

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21775309

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21775309

Country of ref document: EP

Kind code of ref document: A1