WO2021169757A1

WO2021169757A1 - Method and apparatus for giving reminder of arrival at station, storage medium and electronic device

Info

Publication number: WO2021169757A1
Application number: PCT/CN2021/074954
Authority: WO
Inventors: 陈喆
Original assignee: Oppo广东移动通信有限公司
Priority date: 2020-02-27
Filing date: 2021-02-03
Publication date: 2021-09-02
Also published as: CN111311889A

Abstract

A method and apparatus for giving a reminder of arrival at a station, a storage medium and an electronic device. The method for giving a reminder of arrival at a station comprises: receiving, by means of a processor, a request for giving a reminder of arrival at a station, and according to the request for giving a reminder of arrival at a station, determining a target public transport station for which a reminder of arrival at a station needs to be given (101); acquiring, by means of the processor, the number of target stations, which an electronic device needs to pass to arrive at the target public transport station, from among public transport stations (102); by means of a special voice recognition chip, controlling a microphone to collect an external audio signal (103); recognizing the audio signal by means of the special voice recognition chip and the processor to obtain the number of stations, which the electronic device has passed, from among the public transport stations (104); and when the number of stations is consistent with the number of target stations, executing, by means of the processor, a preset operation of giving a reminder of arrival at a station (105).

Description

Arrival reminder method, device, storage medium and electronic equipment

This application claims the priority of a Chinese patent application filed with the Chinese Patent Office on February 27, 2020, the application number is 202010125355.9, and the invention title is "arrival reminder method, device, storage medium and electronic equipment", the entire content of which is incorporated by reference Incorporated in this application.

Technical field

This application relates to the technical field of audio recognition, and in particular to a method, device, storage medium, and electronic equipment for reminding station arrival.

Background technique

At present, electronic devices such as smart phones and tablet computers have entered people's daily lives. People can install various applications on electronic devices to expand the functions of electronic devices, such as games, social networking, shopping, etc. When people take public transportation, they may ride over stations due to the use of electronic devices. For this reason, satellite positioning is used in related technologies to determine whether to arrive at the station, and to remind when the station arrives.

Summary of the invention

The embodiments of the present application provide an arrival reminding method, device, storage medium, and electronic equipment, which can reduce the power consumption of the electronic equipment to realize arrival reminding.

In the first aspect, an embodiment of the present application provides an arrival reminder method, which is applied to an electronic device, the electronic device includes a microphone, a processor, and a dedicated voice recognition chip, and the arrival reminder method includes:

Receiving the station reminding request through the processor, and determining the target public transportation station that needs to be reminded according to the station reminding request;

Acquiring, by the processor, the target number of public transportation stations that the electronic device needs to pass through to reach the target public transportation station;

Controlling the microphone to collect external audio signals through the dedicated voice recognition chip;

Recognizing the audio signal through the dedicated voice recognition chip and the processor to obtain the number of stations where the electronic device has passed public transportation stations;

When the number of sites is consistent with the number of target sites, the processor executes a preset arrival reminder operation.

In the second aspect, an embodiment of the present application provides an arrival reminder device, which is applied to an electronic device, the electronic device includes a microphone, a processor, and a dedicated voice recognition chip, and the arrival reminder device includes:

The request receiving module is configured to receive the station reminder request through the processor, and determine the target public transportation station that needs to be reminded according to the station reminder request;

A quantity determining module, configured to obtain, through the processor, the target number of public transportation stations that the electronic device needs to pass through to reach the target public transportation station;

An audio collection module, configured to control the microphone to collect external audio signals through the dedicated voice recognition chip;

An audio recognition module, configured to recognize the audio signal through the dedicated voice recognition chip and the processor, and obtain the number of stations where the electronic device has passed the public transportation station;

The arrival reminder module is configured to execute a preset arrival reminder operation through the processor when the number of stations is consistent with the number of target stations.

In the third aspect, the embodiments of the present application provide a storage medium on which a computer program is stored. When the computer program runs on an electronic device including a microphone, a processor, and a dedicated voice recognition chip, the electronic device executes The steps in the arrival reminding method provided in the embodiment of this application.

In a fourth aspect, an embodiment of the present application also provides an electronic device, the electronic device including a microphone, a processor, and a dedicated voice recognition chip with lower power consumption than the processor, wherein:

The processor is configured to receive the arrival reminder request, and determine the target public transportation station that needs arrival reminder according to the arrival reminder request; and

Obtain the target number of public transportation stations that the electronic device needs to pass through to reach the target public transportation station:

The dedicated voice recognition chip is used to control the microphone to collect external audio signals; and

Identify the audio signal in cooperation with the processor to obtain the number of stations where the electronic device has passed public transportation stations;

The processor is further configured to perform a preset arrival reminder operation when the number of sites is consistent with the number of target sites.

Description of the drawings

In order to more clearly describe the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings that need to be used in the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

FIG. 1 is a schematic flow chart of the arrival reminding method provided by an embodiment of the present application.

Fig. 2 is an example diagram of an arrival reminder interface in an embodiment of the present application.

Fig. 3 is a spectrogram of the prompt sound when the subway door is opened and closed in the embodiment of the present application.

FIG. 4 is a schematic diagram of non-overlapping framing of an audio signal in an embodiment of the present application.

FIG. 5 is a schematic diagram of another flow chart of the arrival reminding method provided by an embodiment of the present application.

Fig. 6 is a schematic structural diagram of an arrival reminding device provided by an embodiment of the present application.

Fig. 7 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.

Detailed ways

Please refer to the drawings, where the same component symbols represent the same components, and the principle of the present application is implemented in an appropriate computing environment for illustration. The following description is based on the exemplified specific embodiments of the application, which should not be regarded as limiting other specific embodiments of the application that are not described in detail herein.

The embodiments of the present application provide an arrival reminding method, an arrival reminding device, a storage medium, and electronic equipment. Wherein, the execution subject of the arrival reminding method may be the arrival reminding device provided in the embodiment of the present application, or an electronic device integrated with the arrival reminding device, wherein the arrival reminding device can be implemented in hardware or software. The electronic device can be a computing device such as a laptop computer, a computer monitor containing an embedded computer, a tablet computer, a cellular phone, a media player, or other handheld or portable electronic devices, smaller devices (such as wrist watch devices, Hanging devices, earphones or earpiece devices, devices embedded in glasses or other devices worn on the user’s head, or other wearable or micro devices), gaming devices, navigation devices, embedded systems, etc.

The present application provides an arrival reminder method, which is applied to an electronic device, the electronic device includes a microphone, a processor, and a dedicated voice recognition chip, and the arrival reminder method includes:

Optionally, in an embodiment, the recognition of the audio signal through the dedicated voice recognition chip and the processor to obtain the number of stations where the electronic device has passed public transportation stations includes:

Recognizing whether the audio signal includes the frequency component corresponding to the public transportation station through the dedicated voice recognition chip;

When it is recognized that the audio signal includes the frequency component, it is recognized by the processor whether the audio signal is a preset audio signal corresponding to the public transportation station;

The number of stations is obtained according to the number of recognition times that the processor recognizes that the result is yes.

Optionally, in an embodiment, the identifying whether the audio signal includes a frequency component corresponding to the public transportation station through the dedicated voice recognition chip includes:

The dedicated voice recognition chip is used to identify whether the duration of the frequency component in the audio signal reaches a preset duration, and if yes, it is determined that the audio signal includes the frequency component.

Optionally, in an embodiment, the identifying whether the duration of the frequency component in the audio signal reaches a preset duration through the dedicated voice recognition chip includes:

Performing non-overlapping framing processing on the audio signal by the dedicated speech recognition chip to obtain multiple audio frames;

Perform Fourier transform on the audio frame through the dedicated speech recognition chip, and identify whether the amplitude of the frequency component in the continuous audio frame within the preset time period reaches a preset value according to the Fourier transform result Amplitude, it is determined that the duration of the frequency component in the audio signal reaches the preset duration.

Optionally, in an embodiment, the identifying by the processor whether the audio signal is a preset audio signal corresponding to the public transportation station includes:

Calling the pre-trained audio recognition model corresponding to the preset audio signal through the processor;

Identify whether the audio signal is a preset audio signal corresponding to the public transportation station according to the audio recognition model.

Optionally, in an embodiment, before identifying whether the audio signal includes a frequency component corresponding to the public transportation station through the dedicated voice recognition chip, the method further includes:

The human voice frequency components in the audio signal are filtered out through the dedicated speech recognition chip.

Optionally, in an embodiment, the receiving a station reminder request through the processor includes:

Detect trigger information generated by the public transportation application through the processor, and provide an arrival reminder interface based on the trigger information;

The arrival reminder request is received through the arrival reminder interface.

Optionally, in an embodiment, when the number of sites is the same as the number of target sites, executing a preset arrival reminder operation by the processor includes:

When the number of sites is the same as the number of target sites, obtaining the base station identifier of the base station that establishes a mobile communication connection with the electronic device through the processor;

According to the preset correspondence between the base station identifier and the public transportation station, determine the public transportation station corresponding to the base station identifier through the processor;

When the public transportation station is the target public transportation station, the processor executes a preset arrival reminder operation.

Optionally, in an embodiment, the determining the target public transportation station that needs to be reminded according to the arrival reminder request includes:

The processor parses out the site identification carried in the arrival reminder request, and sets the public transportation site corresponding to the site identification as the target public transportation site.

Please refer to FIG. 1, which is a schematic flowchart of the arrival reminding method provided by an embodiment of the application. The arrival reminding method is applied to the electronic device provided in this application, and the electronic device includes a processor, a dedicated voice recognition chip, and a microphone. As shown in FIG. 1, the flow of the arrival reminding method provided in this embodiment of the application may be as follows:

In 101, the processor receives the station reminder request, and determines the target public transportation station that needs to be reminded according to the station reminder request.

It should be noted that the types of public transportation involved in the following embodiments include, but are not limited to, subways, buses, and so on.

In the embodiments of the present application, the processor is a processor suitable for general processing tasks, such as an ARM architecture processor. Dedicated speech recognition chips are dedicated chips designed for speech recognition, such as digital signal processing chips designed for speech recognition, dedicated integrated circuit chips designed for speech recognition, etc., which are compared with general-purpose chips. The processor has lower power consumption and is suitable for processing speech recognition tasks. Among them, the dedicated speech recognition chip, the processor, and the microphone establish a communication connection through a communication bus (such as an I2C bus) to realize data interaction. Specifically, those of ordinary skill in the art can select the model of the processor and the model of the dedicated voice recognition chip according to actual needs. For example, the processor models that can be selected include, but are not limited to, Snapdragon 855+, Snapdragon 845, Snapdragon 820, Snapdragon 810, and Snapdragon 710.

In addition, the microphone included in the electronic device may be a built-in microphone or an external microphone (which may be a wired microphone or a wireless microphone).

When the electronic device is in the on-screen state, the processor receives the arrival reminder request input by the user. For example, the processor receives the arrival reminder request input by the user through the arrival reminder interface provided by the public transportation application running in the foreground.

Exemplarily, please refer to Fig. 2. The arrival reminder interface shown in Fig. 2 includes all public transportation stations passed by a public transportation route, that is, public transportation station 1 to public transportation station 9 shown in the figure, and the processor can be based on The user receives an arrival reminder request corresponding to the public transportation site for the "alarm clock" control associated with any public transportation site, and the arrival reminder request carries the site identifier of the corresponding public transportation site (for example, the site name of the site).

After receiving the input arrival reminder request, the processor parses out the site identifier carried in the arrival reminder request, and sets the public transportation station corresponding to the site identifier as the target public transportation station that requires arrival reminder.

In 102, the processor obtains the target number of public transportation stations that the electronic device needs to pass through to reach the target public transportation station.

After determining the target public transportation station that needs to be reminded of arrival, the processor further obtains the number of target public transportation stations that the electronic device needs to pass through to reach the target public transportation station.

Among them, the processor first obtains the base station identifier of the current base station that is currently establishing a mobile communication connection with the electronic device, and determines the public transportation station corresponding to the aforementioned current base station according to the preset correspondence between the base station identifier and the public transportation station, and records it as the current public transportation station. Traffic site.

It should be noted that a base station provides network access services for electronic devices, and its location is usually fixed. When the electronic device establishes a mobile communication connection with a certain base station, the location of the electronic device can be determined. Based on this, in the embodiment of the present application, the base station is previously associated with the nearest public transportation station, and the corresponding relationship between the base station identifier and the public transportation station is further established. Among them, the base station identifier is used to uniquely identify the base station, and can be selected as a parameter of the base station identifier by a person of ordinary skill in the art according to actual needs. For example, in the embodiment of the present application, a cell identifier combined with a location area code is used as the base station identifier.

After determining the current public transportation station, the processor obtains the pre-stored route information from the current public transportation station to the target public transportation station, and determines that the electronic device is used by the current public transportation station according to the route information, the current public transportation station, and the target public transportation station. The target number of public transportation stations that the station needs to pass through to reach the target public transportation station.

For example, for the public transportation route from public transportation station 1 to public transportation station 9 shown in Figure 2, assuming that the target public transportation station is public transportation station 9, if the determined current public transportation station is public transportation station 3, the processor may It is determined that the number of public transportation stations that the electronic device needs to pass through to reach the target public transportation station is 6.

In 103, the microphone is controlled by a dedicated voice recognition chip to collect external audio signals.

After determining the number of target stations of public transportation stations that the electronic device needs to pass through to reach the target public transportation station, the processor instructs the dedicated voice recognition chip to start passing station detection, that is, to detect whether it passes the public transportation station.

Correspondingly, the dedicated voice recognition chip controls the microphone to collect external audio signals according to the instructions of the processor for passing station detection.

In 104, the audio signal is recognized through a dedicated voice recognition chip and a processor, and the number of stations where the electronic device has passed the public transportation station is obtained.

Among them, the dedicated voice recognition chip and processor perform passing detection based on the collected audio signal, that is, to identify whether the collected audio signal is an audio signal passing through a public transportation station, and if it is, it is determined that the electronic device passes through a public transportation station. Thus, the number of stations where the electronic equipment has passed the public transportation station can be obtained.

Exemplarily, the dedicated voice recognition chip first recognizes whether the audio signal is an audio signal passing through a public transportation station, and when it recognizes that the audio signal is an audio signal passing through a public transportation station, the audio signal is provided to the processor, and the processor again Identify whether the audio signal is an audio signal passing through a public transportation station, and if yes, it is determined that the electronic device passes through a public transportation station.

For example, a dedicated speech recognition chip can determine whether the audio signal includes the audio characteristics of a public transportation station, and if it is, it is determined that the aforementioned audio signal is an audio signal passing through a public transportation station; and the processor can directly combine the audio signal provided by the microphone with the pre-collected path The audio signal of the public transportation station is compared, and when the two comparisons are consistent, it is determined that the audio signal is the audio signal passing through the public transportation station.

In 105, when the aforementioned number of stations is consistent with the number of target stations, the processor executes a preset arrival reminder operation.

Among them, the processor determines in real time whether the number of stations where the electronic equipment has passed the public transportation station is consistent with the number of the target station. When the number of stations where the electronic equipment has passed the public transportation station is consistent with the number of the target station, it means that the electronic equipment has arrived at this time and needs to be performed. At the target public transportation station of the arrival reminder, the processor executes the preset arrival reminder operation at this time. The type of arrival reminding operation is not specifically limited in the embodiments of this application, and can be set by a person of ordinary skill in the art according to actual needs, including but not limited to audio, video, image, text and other arrival reminding methods. For example, the processor can play a preset arrival reminder alarm tone, and use the arrival reminder alarm tone to remind the user that the station has arrived currently.

It can be seen from the above that this application receives the station reminder request through the processor, and according to the arrival reminder request, determines the target public transportation station that needs to be reminded, and obtains the information of the public transportation station that the electronic device needs to pass through to reach the target public transportation station. The number of target sites, and then use a dedicated voice recognition chip to control the microphone to collect external audio signals, and the dedicated voice recognition chip co-processor recognizes the collected audio signals to obtain the number of sites where the electronic equipment has passed the public transportation site, and finally when it has passed When the number of sites is the same as the number of target sites, the processor executes the preset arrival reminder operation. Compared with related technologies, the arrival reminder can be realized without satellite positioning, which can effectively reduce the power consumption of the electronic device to realize the arrival reminder.

In one embodiment, the audio signal is recognized by a dedicated voice recognition chip and a processor to obtain the number of stations where the electronic device has passed the public transportation station, including:

(1) Identify whether the audio signal includes frequency components corresponding to public transportation stations through a dedicated voice recognition chip;

(2) When it is recognized that the audio signal includes the aforementioned frequency components, the processor recognizes whether the audio signal is a preset audio signal corresponding to a public transportation station;

(3) Obtain the number of sites according to the number of recognition times that the processor recognition result is yes.

It should be noted that there are specific sound characteristics for different types of public transportation stations.

For example, for a bus station, when the bus passes by the bus station, there is the sound feature of the bus opening/closing (that is, the door opens at the station, and the door closes when the station leaves the station); while for the subway station, when the subway passes the subway station, Then there is the sound characteristic of the prompt sound of subway opening/closing (also opening the door when arriving at the station and closing the door when leaving the station).

Exemplarily, taking a subway station as an example, please refer to Figure 3, which is a spectrogram of the prompt sound when the subway door is opened and closed. According to the spectrogram, it can be seen that the prompt sound of the subway door opening and closing consists of multiple frequency components. Correspondingly, the correspondence between subway stations and corresponding frequency components can be established in advance. In the same way, the correspondence between public transportation stations and corresponding frequency components can be established.

Therefore, when the audio signal is recognized, the dedicated voice recognition chip can recognize whether the audio signal includes the frequency component corresponding to the public transportation station. If it is, it can be preliminarily determined that the electronic device has passed a public transportation station, and the audio signal is provided to the processor for further identification. Wherein, the processor recognizes whether the audio signal is a preset audio signal corresponding to a public transportation station, and if yes, it can be determined that the electronic device has passed a public transportation station.

Therefore, the processor can obtain the number of stations where the electronic device has passed the public transportation station according to the number of identifications whose identification result is yes, where the processor can directly use the number of identifications whose identification result is yes as the number of identifications that the electronic device has passed the public transportation station. The number of sites.

For example, the processor recognizes multiple audio signals provided by a dedicated voice recognition chip at different times. If the number of times the recognition result is yes is N, it means that the number of stations where the electronic device has passed the public transportation station is also N.

In an embodiment, before recognizing whether the audio signal includes the frequency component corresponding to the public transportation station through the dedicated voice recognition chip, the method further includes:

The human voice frequency components in the audio signal are filtered through a dedicated speech recognition chip.

Among them, before the audio signal is recognized, the human voice frequency components in the audio signal can be extracted and filtered to reduce the interference caused by the human voice frequency components on the recognition.

In an embodiment, identifying whether the aforementioned audio signal includes frequency components corresponding to public transportation stations through a dedicated voice recognition chip includes:

A dedicated voice recognition chip is used to identify whether the duration of the frequency component in the audio signal reaches a preset duration, and if yes, it is determined that the audio signal includes the frequency component.

In the embodiment of the present application, when the dedicated voice recognition chip recognizes whether the audio signal provided by the microphone includes the frequency component corresponding to the public transportation station, it can recognize whether the frequency component of the corresponding public transportation station in the audio signal lasts for a preset duration Time length, when it is recognized that the aforementioned frequency component in the audio signal lasts for a preset time length, it is determined that the audio signal includes the frequency component corresponding to the public transportation station.

It should be noted that different types of public transportation stations have different corresponding frequency components.

For example, taking a subway station as an example, it corresponds to 7 different frequency components, and these 7 different frequency components correspond to the corresponding preset durations, and the preset durations corresponding to different frequency components are different, and the dedicated voice recognition chip recognizes them separately Whether the duration of the 7 frequency components corresponding to the subway station in the audio signal provided by the microphone reaches their respective preset durations, if they are all reached, it can be determined that the audio signal includes the frequency components corresponding to the subway station, and then it can be determined that the electronic device passes by A subway station.

In an embodiment, identifying whether the duration of the aforementioned frequency component in the audio signal reaches a preset duration through a dedicated voice recognition chip includes:

(1) Perform non-overlapping framing processing of the aforementioned audio signal through a dedicated speech recognition chip to obtain multiple audio frames;

(2) Perform Fourier transform on the audio frame through a dedicated speech recognition chip, and identify whether the amplitude of the aforementioned frequency component in the continuous audio frame within the preset time length reaches the preset amplitude according to the Fourier transform result, yes It is determined that the duration of the aforementioned frequency component in the aforementioned audio signal reaches the preset duration.

In the embodiment of the present application, when identifying whether the duration of the aforementioned frequency components in the audio signal reaches a preset duration, the dedicated voice recognition chip first performs non-overlapping frame division processing on the audio signal provided by the microphone to obtain multiple audio frames.

For example, referring to Figure 4, the dedicated speech recognition chip performs non-overlapping framing for the audio signal x(n) provided by the microphone, and each frame is of length N. A total of m audio frames are obtained by framing, and each audio frame can be expressed as x _m (n). Among them, non-overlapping framing can be generally understood as framing to obtain no overlap between two adjacent audio frames.

After multiple audio frames are obtained by framing, the dedicated speech recognition chip further performs Fourier transform on each audio frame obtained by framing, and recognizes that the frequency component of the corresponding public transportation station is within the preset time according to the result of Fourier transform Whether the amplitudes in the consecutive audio frames all reach the preset amplitude, it is determined that the duration of the frequency component in the audio signal reaches the preset duration. Among them, the preset duration can be set by a person of ordinary skill in the art according to actual needs, and is not specifically limited in the embodiment of the present application.

For example, fast Fourier transform is performed on the audio frame x _m (n) to obtain the corresponding Fourier transform result X _m (n)=FFT[x _m (n)], then the frequency resolution of the Fourier transform is f _s /N, where f _s is the sampling frequency of the audio signal, and N is the length of the audio frame. For any frequency component f, its position in the Fourier transform result X _m (n) is i=Nf/f _s , which can be expressed as X _m (i). Then, for the frequency component f'of the corresponding public transportation station, in each audio frame, the amplitude of the frequency component f'is

Among them, abs[] means to obtain the absolute value. For the frequency component f', if the frequency component f'is within the preset duration t, the amplitude of each continuous audio frame

When both reach the preset amplitude α, it is determined that the duration of the frequency component f'in the audio signal reaches the preset duration t.

In an embodiment, identifying whether the audio signal is a preset audio signal corresponding to a public transportation station by the processor includes:

(1) Call the pre-trained audio recognition model corresponding to the preset audio signal through the processor;

(2) Identify whether the audio signal is a preset audio signal corresponding to the public transportation station according to the audio recognition model.

It should be noted that, in the embodiment of the present application, the audio recognition model corresponding to the preset audio signal is pre-trained, and it is configured to classify the input audio signal to be recognized to obtain the classification of the audio signal to be recognized as the preset audio signal As a result, or obtain the classification result that the audio signal to be identified is not a preset audio signal.

Exemplarily, a preset audio signal corresponding to a public transportation station may be collected in advance, and its spectrogram may be extracted as a training sample, and a convolutional neural network may be used for training according to the training sample to obtain an audio recognition model.

Correspondingly, when the processor recognizes whether the audio signal is the preset audio signal corresponding to the public transportation station, the processor can call the pre-trained audio recognition model corresponding to the preset audio signal, and use the audio provided by the dedicated voice recognition chip The signal is input into the audio recognition model for classification, and the recognition result that the audio signal is the aforementioned preset audio signal is obtained, or the recognition result that the audio signal is not the aforementioned preset audio signal is obtained.

In an embodiment, the station reminding request received by the processor includes:

(1) The processor detects the trigger information generated by the public transportation application, and provides an arrival reminder interface based on the trigger information;

(2) Receive the arrival reminder request through the arrival reminder interface.

It should be noted that when a public transportation application is running in the foreground, the processor can receive a display request for indicating the display of the bus code through the public transportation application, and display the bus code according to the display request, so that the user can quickly pass through the subway gate Machine, or enter the bus, etc. Correspondingly, after the displayed travel code is scanned, the public transportation application will generate trigger information to indicate that the travel code has been scanned.

Correspondingly, the processor can detect the trigger information generated by the public transportation application. If the trigger information is detected, it can determine the electronic device to follow the user into the subway station or board the bus, and provide an arrival reminder interface at this time , Through the arrival reminder interface to receive the arrival reminder request.

In one embodiment, in order to ensure the accuracy of the arrival reminder, when the number of sites is consistent with the number of target sites, the processor executes the preset arrival reminder operation, including:

(1) When the number of sites where the electronic device has passed public transportation sites is the same as the number of target sites, obtain the base station identifier of the base station that establishes a mobile communication connection with the electronic device through the processor;

(2) According to the preset correspondence between the base station identifier and the public transportation station, the processor determines the public transportation station corresponding to the base station identifier;

(3) When the aforementioned public transportation station is the target public transportation station, the processor executes the preset arrival reminder operation.

In the embodiment of the present application, when the processor recognizes that the number of stations of the public transportation station that the electronic device has passed is the same as the number of the target station, it does not immediately perform the preset arrival reminder operation, but first informs the public that the electronic device has actually arrived. The traffic station is identified, and the preset arrival reminder operation is performed only when the public transportation station actually reached by the electronic device is consistent with the target public transportation station.

Among them, when it is recognized that the number of sites where the electronic device has passed the public transportation site is consistent with the number of target sites, the processor first obtains the base station identifier of the base station that establishes a mobile communication connection with the electronic device, that is, obtains the network that provides the electronic device. The base station ID of the base station accessing the service.

Then, the processor determines the public transportation station corresponding to the acquired base station identifier according to the preset correspondence between the base station identifier and the public transportation station, as the public transportation station actually reached by the electronic device.

When determining the public transportation station actually reached by the electronic device, the processor further identifies whether the public transportation station actually reached by the electronic device is the target public transportation station. When the public transportation station actually reached by the electronic device is the target public transportation station, the processor executes For the preset arrival reminder operation, please refer to the related description in the above embodiment for details, which will not be repeated here.

FIG. 5 is a schematic diagram of another flow of the arrival reminding method provided by an embodiment of the application. The arrival reminding method is applied to the electronic device provided in this application, and the electronic device includes a processor, a dedicated voice recognition chip, and a microphone. As shown in FIG. 5, the flow of the arrival reminding method provided in this embodiment of the application may be as follows:

In 201, the processor detects the trigger information generated by the public transportation application, and provides an arrival reminder interface based on the trigger information.

Correspondingly, the processor can detect the trigger information generated by the public transportation application. If the trigger information is detected, it can determine the electronic device to follow the user into the subway station or board the bus, and provide an arrival reminder interface at this time , To receive the arrival reminder request through the arrival reminder interface.

In 202, the processor receives the arrival reminder request through the arrival reminder interface, and according to the arrival reminder request, determines the target public transportation station that needs to be reminded.

In 203, the processor obtains the target number of public transportation stations that the electronic device needs to pass through to reach the target public transportation station.

In 204, a dedicated voice recognition chip controls the microphone to collect external audio signals.

In 205, the dedicated voice recognition chip co-processor recognizes the audio signal, and obtains the number of stations where the electronic device has passed the public transportation station.

In 206, when the number of sites is consistent with the number of target sites, the processor obtains the base station identifier of the base station that establishes a mobile communication connection with the electronic device.

In 207, the processor determines the public transportation station corresponding to the base station identifier according to the preset correspondence between the base station identifier and the public transportation station.

In 208, when the public transportation station is the target public transportation station, the processor executes a preset arrival reminder operation.

When determining the public transportation station actually reached by the electronic device, the processor further identifies whether the public transportation station actually reached by the electronic device is the target public transportation station. When the public transportation station actually reached by the electronic device is the target public transportation station, the processor executes The preset arrival reminder operation.

Among them, the type of arrival reminding operation is not specifically limited in the embodiments of this application, and can be set by a person of ordinary skill in the art according to actual needs, including but not limited to audio, video, image, text, etc. arrival reminding methods. For example, the processor can play a preset arrival reminder alarm tone, and use the arrival reminder alarm tone to remind the user that the station has arrived currently.

Please refer to FIG. 6, which is a schematic structural diagram of the arrival reminding device provided by an embodiment of the application. The arrival reminder device can be applied to electronic equipment, which includes a processor, a dedicated voice recognition chip and a microphone. The arrival reminder device may include a request receiving module 301, a quantity determination module 302, an audio collection module 303, an audio recognition module 304, and an arrival reminder module 305, where:

The request receiving module 301 is configured to receive the stop reminder request through the processor, and determine the target public transportation station that needs to be reminded according to the stop reminder request;

The quantity determining module 302 is configured to obtain the target station quantity of public transportation stations that the electronic device needs to pass through to reach the target public transportation station through the processor;

The audio collection module 303 is used to control the microphone to collect external audio signals through a dedicated voice recognition chip;

The audio recognition module 304 is used to recognize the audio signal through a dedicated voice recognition chip and a processor, and obtain the number of stations where the electronic device has passed the public transportation station;

The arrival reminder module 305 is configured to execute a preset arrival reminder operation through the processor when the number of the aforementioned stations is consistent with the number of target stations.

In one embodiment, when the audio signal is recognized by a dedicated voice recognition chip and a processor to obtain the number of stations where the electronic device has passed the public transportation station, the audio recognition module 304 is used to:

Recognize whether the audio signal includes frequency components corresponding to public transportation stations through a dedicated voice recognition chip;

When it is recognized that the audio signal includes the aforementioned frequency components, the processor recognizes whether the audio signal is a preset audio signal corresponding to a public transportation station;

According to the number of recognition times that the processor recognition result is yes, the aforementioned number of sites is obtained.

In an embodiment, when recognizing whether the aforementioned audio signal includes frequency components corresponding to public transportation stations through a dedicated voice recognition chip, the audio recognition module 304 is used to:

In an embodiment, when identifying whether the duration of the aforementioned frequency components in the audio signal reaches a preset duration through a dedicated voice recognition chip, the audio recognition module 304 is used to:

Perform non-overlapping framing processing of the aforementioned audio signal through a dedicated speech recognition chip to obtain multiple audio frames;

The audio frame is Fourier-transformed through a dedicated speech recognition chip, and according to the Fourier-transform result, it is recognized whether the amplitudes of the aforementioned frequency components in the continuous audio frames within the preset time period all reach the preset amplitudes, and if yes, the foregoing is determined The duration of the frequency component in the aforementioned audio signal reaches the preset duration.

In an embodiment, when the processor recognizes whether the audio signal is a preset audio signal corresponding to a public transportation station, the audio recognition module 304 is configured to:

Call the pre-trained audio recognition model corresponding to the preset audio signal through the processor;

According to the audio recognition model, it is recognized whether the audio signal is a preset audio signal corresponding to the public transportation station.

In an embodiment, when a station reminder request is received through the processor, the request receiving module 301 is configured to:

The processor detects the trigger information generated by the public transportation application, and provides an arrival reminder interface based on the trigger information;

Receive the arrival reminder request through the arrival reminder interface.

In one embodiment, when the number of sites is the same as the number of target sites, and the preset arrival reminder operation is executed by the processor, the arrival reminder module 305 is used to:

When the number of sites where the electronic device has passed public transportation sites is the same as the number of target sites, obtain the base station identifier of the base station that establishes a mobile communication connection with the electronic device through the processor;

According to the preset correspondence between the base station identifier and the public transportation station, the processor determines the public transportation station corresponding to the base station identifier;

When the aforementioned public transportation station is the target public transportation station, the processor executes a preset arrival reminder operation.

It should be noted that the arrival reminding device provided in the embodiment of this application belongs to the same concept as the arrival reminding method in the above embodiment, and any method provided in the embodiment of the arrival reminding method can be run on the arrival reminding device. For the specific implementation process, please refer to the above embodiment, which will not be repeated here.

The embodiment of the present application provides a storage medium on which a computer program for arrival reminder is stored. When the stored computer program for the arrival reminder is executed on the electronic device provided in the embodiment of the application, the electronic device Perform the steps in the arrival reminding method provided in the embodiment of this application. Among them, the storage medium may be a magnetic disk, an optical disc, a read only memory (Read Only Memory, ROM), or a random access device (Random Access Memory, RAM), etc.

The embodiment of the present application also provides an electronic device. Please refer to FIG. The dedicated voice recognition chip 402 and the processor 401 establish a communication connection through a communication bus (such as an I2C bus) to realize data interaction.

It should be noted that the processor in the embodiment of the present application is a general-purpose processor, and a person of ordinary skill in the art can select the processor model according to actual needs. For example, the processor models that can be selected include but are not limited to Snapdragon 855+, Snapdragon 845, Snapdragon 820, Snapdragon 810, Snapdragon 710, etc.

The dedicated voice recognition chip 402 is a dedicated chip designed for voice recognition, such as a digital signal processing chip designed for voice recognition, a dedicated integrated circuit chip designed for voice recognition, etc., compared to general-purpose chips The processor has lower power consumption and is suitable for processing speech recognition tasks.

The memory 404 stores a computer program for arrival reminder, which may be a high-speed random access memory, or a non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device, etc. . Correspondingly, the memory 404 may also include a memory controller to provide the processor 401 and the dedicated voice recognition chip 402 to access the memory 404, so as to realize the following functions:

The processor 401 is configured to receive the arrival reminder request, and according to the arrival reminder request, determine the target public transportation station that needs the arrival reminder; and

Obtain the target number of public transportation stations that the electronic device needs to pass through to reach the target public transportation station;

The dedicated voice recognition chip 402 is used to control the microphone to collect external audio signals; and

The co-processor 401 recognizes the audio signal, and obtains the number of stations where the electronic device has passed the public transportation station;

The processor 401 is further configured to perform a preset arrival reminder operation through the processor when the number of the aforementioned sites is consistent with the number of the target sites.

In one embodiment, when the co-processor 401 recognizes the audio signal and obtains the number of stations where the electronic device has passed the public transportation station, the dedicated voice recognition chip 402 is used to:

Identify whether the audio signal includes the frequency component of the corresponding public transportation station;

When the dedicated voice recognition chip 402 recognizes that the audio signal includes the aforementioned frequency components, the processor 401 is used to recognize whether the audio signal is a preset audio signal corresponding to a public transportation station; and

According to the number of recognitions whose recognition result is yes, the aforementioned number of sites is obtained.

In one embodiment, when recognizing whether the aforementioned audio signal includes frequency components corresponding to public transportation stations, the dedicated voice recognition chip 402 is used to:

Identify whether the duration of the frequency component in the audio signal reaches the preset duration, and if yes, it is determined that the audio signal includes the frequency component.

In an embodiment, when identifying whether the duration of the aforementioned frequency component in the audio signal reaches a preset duration, the dedicated voice recognition chip 402 is used to:

Perform non-overlapping framing processing on the aforementioned audio signal to obtain multiple audio frames;

Perform Fourier transform on the audio frame, and identify whether the amplitude of the aforementioned frequency component in the continuous audio frame within the preset time length reaches the preset amplitude according to the Fourier transform result. If yes, it is determined that the aforementioned frequency component is in the aforementioned audio The duration of the signal reaches the preset duration.

In an embodiment, when identifying whether the audio signal is a preset audio signal corresponding to a public transportation station, the processor 401 is configured to:

Call the pre-trained audio recognition model corresponding to the preset audio signal;

In an embodiment, when a station reminder request is received, the processor 401 is configured to:

Detect trigger information generated by public transportation applications, and provide an arrival reminder interface based on the trigger information;

Receive the arrival reminder request through the arrival reminder interface.

In an embodiment, when the number of sites is the same as the number of target sites and the preset arrival reminder operation is performed, the processor 401 is configured to:

When the number of sites where the electronic device has passed the public transportation site is the same as the number of target sites, acquiring the base station identifier of the base station that establishes a mobile communication connection with the electronic device;

According to the preset correspondence between the base station identifier and the public transportation station, determine the public transportation station corresponding to the base station identifier;

When the aforementioned public transportation station is the target public transportation station, the preset arrival reminder operation is performed.

Optionally, in an embodiment, the dedicated speech recognition chip 402 is also used to filter out the human voice frequency components in the aforementioned audio signal.

Optionally, in an embodiment, the processor 401 is configured to parse out the site identifier carried in the arrival reminder request, and set the public transportation site corresponding to the site identifier as the target public transportation site.

It should be noted that the electronic device provided in the embodiment of this application belongs to the same concept as the arrival reminding method in the above embodiment. Any method provided in the embodiment of the arrival reminding method can be run on the electronic device, and its specific implementation For details of the process, refer to the embodiment of the feature extraction method, which will not be repeated here.

It should be noted that for the arrival reminding method of the embodiment of the application, ordinary testers in the field can understand all or part of the process of implementing the arrival reminding method of the embodiment of the application, and the relevant hardware can be controlled by a computer program. To complete, the computer program can be stored in a computer readable storage medium, such as stored in the memory of an electronic device, and executed by a processor and a dedicated voice recognition chip in the electronic device, and may include Such as the flow of the embodiment of the arrival reminding method. Wherein, the storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, etc.

The above provides a detailed introduction to the arrival reminder method, storage medium and electronic equipment provided by the embodiments of the present application. Specific examples are used in this article to illustrate the principles and implementation of the present application. The description of the above embodiments is only used To help understand the methods and core ideas of this application; at the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation and scope of application. In summary, the content of this specification It should not be construed as a limitation on this application.

Claims

An arrival reminding method applied to an electronic device, wherein the electronic device includes a microphone, a processor, and a dedicated voice recognition chip, and the arrival reminding method includes:

Receiving the station reminding request through the processor, and determining the target public transportation station that needs to be reminded according to the station reminding request;

Acquiring, by the processor, the target number of public transportation stations that the electronic device needs to pass through to reach the target public transportation station;

Controlling the microphone to collect external audio signals through the dedicated voice recognition chip;

Recognizing the audio signal through the dedicated voice recognition chip and the processor to obtain the number of stations where the electronic device has passed public transportation stations;

When the number of sites is consistent with the number of target sites, the processor executes a preset arrival reminder operation.
The arrival reminding method according to claim 1, wherein said recognizing said audio signal through said dedicated voice recognition chip and said processor to obtain the number of stations where said electronic device has passed public transportation stations comprises:

Recognizing whether the audio signal includes the frequency component corresponding to the public transportation station through the dedicated voice recognition chip;

When it is recognized that the audio signal includes the frequency component, it is recognized by the processor whether the audio signal is a preset audio signal corresponding to the public transportation station;

The number of stations is obtained according to the number of recognition times that the processor recognizes that the result is yes.
The arrival reminding method according to claim 2, wherein the identifying whether the audio signal includes a frequency component corresponding to the public transportation station through the dedicated voice recognition chip comprises:

The dedicated voice recognition chip is used to identify whether the duration of the frequency component in the audio signal reaches a preset duration, and if yes, it is determined that the audio signal includes the frequency component.
The arrival reminding method according to claim 3, wherein the identifying whether the duration of the frequency component in the audio signal reaches a preset duration through the dedicated voice recognition chip comprises:

Performing non-overlapping framing processing on the audio signal by the dedicated speech recognition chip to obtain multiple audio frames;

Perform Fourier transform on the audio frame through the dedicated speech recognition chip, and identify whether the amplitude of the frequency component in the continuous audio frame within the preset time period reaches a preset value according to the Fourier transform result Amplitude, it is determined that the duration of the frequency component in the audio signal reaches the preset duration.
The arrival reminding method according to claim 2, wherein the identifying by the processor whether the audio signal is a preset audio signal corresponding to the public transportation station comprises:

Calling the pre-trained audio recognition model corresponding to the preset audio signal through the processor;

Identify whether the audio signal is a preset audio signal corresponding to the public transportation station according to the audio recognition model.
The arrival reminding method according to claim 2, wherein before said identifying whether said audio signal includes frequency components corresponding to said public transportation station through said dedicated voice recognition chip, the method further comprises:

The human voice frequency components in the audio signal are filtered out through the dedicated speech recognition chip.
The station reminding method according to any one of claims 1 to 6, wherein the receiving station reminding request through the processor comprises:

Detect trigger information generated by the public transportation application through the processor, and provide an arrival reminder interface based on the trigger information;

The arrival reminder request is received through the arrival reminder interface.
The arrival reminding method according to any one of claims 1 to 6, wherein when the number of sites is the same as the number of target sites, executing a preset arrival reminding operation by the processor comprises:

When the number of sites is the same as the number of target sites, obtaining the base station identifier of the base station that establishes a mobile communication connection with the electronic device through the processor;

According to the preset correspondence between the base station identifier and the public transportation station, determine the public transportation station corresponding to the base station identifier through the processor;

When the public transportation station is the target public transportation station, the processor executes a preset arrival reminder operation.
The arrival reminder method according to any one of claims 1 to 6, wherein the determining the target public transportation station that needs arrival reminder according to the arrival reminder request comprises:

The processor parses out the site identification carried in the arrival reminder request, and sets the public transportation site corresponding to the site identification as the target public transportation site.
An arrival reminding device applied to electronic equipment, wherein the electronic equipment includes a microphone, a processor and a dedicated voice recognition chip, and the arrival reminding device includes:

The request receiving module is configured to receive the station reminder request through the processor, and determine the target public transportation station that needs to be reminded according to the station reminder request;

A quantity determining module, configured to obtain, through the processor, the target number of public transportation stations that the electronic device needs to pass through to reach the target public transportation station;

An audio collection module, configured to control the microphone to collect external audio signals through the dedicated voice recognition chip;

An audio recognition module, configured to recognize the audio signal through the dedicated voice recognition chip and the processor, and obtain the number of stations where the electronic device has passed public transportation stations;

The arrival reminder module is configured to execute a preset arrival reminder operation through the processor when the number of stations is consistent with the number of target stations.
A storage medium, wherein, when a computer program stored in the storage medium runs on an electronic device including a microphone, a processor, and a dedicated voice recognition chip, the processor and the dedicated voice recognition chip are caused to execute:

The processor receives the station reminder request, and according to the station reminder request, determines the target public transportation station that needs to be reminded; and obtains the public transportation station that the electronic device needs to pass through to reach the target public transportation station Number of target sites:

The dedicated voice recognition chip is used to control the microphone to collect external audio signals; and cooperate with the processor to recognize the audio signals to obtain the number of stations where the electronic device has passed public transportation stations;

The processor is further configured to perform a preset arrival reminder operation when the number of sites is consistent with the number of target sites.
An electronic device, wherein the electronic device includes a microphone, a processor, and a dedicated voice recognition chip, wherein,

The processor is configured to receive the arrival reminder request, and determine the target public transportation station that needs arrival reminder according to the arrival reminder request; and

Obtain the target number of public transportation stations that the electronic device needs to pass through to reach the target public transportation station:

The dedicated voice recognition chip is used to control the microphone to collect external audio signals; and

Identify the audio signal in cooperation with the processor to obtain the number of stations where the electronic device has passed public transportation stations;

The processor is further configured to perform a preset arrival reminder operation when the number of sites is consistent with the number of target sites.
The electronic device according to claim 12, wherein the dedicated voice recognition chip is used to identify whether the audio signal includes a frequency component corresponding to the public transportation station;

When it is recognized that the audio signal includes the frequency component, the processor is used to recognize whether the audio signal is a preset audio signal corresponding to the public transportation station; and according to the number of recognition times the recognition result is yes, obtain The number of said sites.
The electronic device according to claim 13, wherein the dedicated speech recognition chip is used to identify whether the duration of the frequency component in the audio signal reaches a preset duration, and if yes, it is determined that the audio signal includes all The frequency components.
The electronic device according to claim 14, wherein the dedicated speech recognition chip is used to perform non-overlapping framing processing on the audio signal through the dedicated speech recognition chip to obtain multiple audio frames; and The audio frame is subjected to Fourier transform, and according to the Fourier transform result, it is identified whether the amplitude of the frequency component in the continuous audio frame within the preset time period all reaches the preset amplitude, and if yes, the frequency is determined The duration of the component in the audio signal reaches the preset duration.
The electronic device according to claim 13, wherein the processor is configured to call a pre-trained audio recognition model corresponding to the preset audio signal through the processor; and recognize the audio signal according to the audio recognition model Whether it is a preset audio signal corresponding to the public transportation station.
The electronic device according to claim 13, wherein the dedicated voice recognition chip is further used to filter out human voice frequency components in the audio signal through the dedicated voice recognition chip.
The electronic device according to any one of claims 12-17, wherein the processor is configured to detect trigger information generated by a public transportation application, and provide an arrival reminder interface based on the trigger information; and through the arrival The reminder interface receives the arrival reminder request.
The electronic device according to claims 12-17, wherein the processor is configured to obtain a base station identifier of a base station that establishes a mobile communication connection with the electronic device when the number of sites is the same as the number of target sites; and According to the preset correspondence between the base station identifier and the public transportation station, determine the public transportation station corresponding to the base station identifier; and when the public transportation station is the target public transportation station, perform a preset arrival reminder operation.
The electronic device according to claims 12-17, wherein the processor is configured to parse out the site identification carried in the arrival reminder request, and set the public transportation site corresponding to the site identification as the target public Traffic site.