A station arrival prompting method and device, electronic equipment and storage medium

Abstract

Embodiments of the present application disclose a station arrival prompting method and device, electronic equipment and a storage medium. The method comprises: acquiring audio data collected by a voice collection unit; performing voice recognition on the audio data based on a first voice detection model to obtain a first voice recognition result; determining a station arrival point of the first electronic device based on the first voice recognition result; generating station prompting information based on the station arrival point, and controlling a user output unit to output the station prompting information. In this way, when a user boards a vehicle, the station arrival point is determined by performing voice recognition on the audio data of the current environment, station prompting information (such as voice prompts, pop-up prompts, vibration prompts, etc.) is generated to remind the user, avoiding missing the station due to the user wearing noise reduction earphones or being absent-minded, and improving the user travel experience.

Description

Technical Field

[0001] This application relates to control technology for electronic devices, and more particularly to an arrival notification method, apparatus, electronic device, and storage medium. Background Technology

[0002] Currently, more and more users are choosing to use active noise-canceling (ANC) headphones during their commutes or travels to listen to audio or isolate themselves from noise to ensure quality rest. However, this also brings an obvious problem: when the noise cancellation effect is good enough, users may not receive announcements about stops on public transport, causing them to miss their stop or requiring them to actively seek out stop information. This negatively impacts the user experience of noise-canceling headphones and hinders their widespread adoption. Summary of the Invention

[0003] To address the aforementioned technical problems, embodiments of this application aim to provide an arrival notification method, apparatus, electronic device, and storage medium.

[0004] The technical solution of this application is implemented as follows:

[0005] Firstly, an arrival notification method is provided, applied to a first electronic device, including:

[0006] Acquire audio data collected by the voice acquisition unit;

[0007] The audio data is used to perform speech recognition based on the first speech detection model to obtain the first speech recognition result.

[0008] The arrival station of the first electronic device is determined based on the first speech recognition result;

[0009] Based on the arrival at the station, a station prompt message is generated, and the user output unit is controlled to output the station prompt message.

[0010] Secondly, an arrival notification device is provided, applied to a first electronic device, comprising:

[0011] The acquisition unit is used to acquire audio data collected by the voice acquisition unit;

[0012] The processing unit is configured to perform speech recognition on the audio data based on a first speech detection model to obtain a first speech recognition result; determine the arrival station of the first electronic device based on the speech recognition result; and generate station prompt information based on the arrival station.

[0013] The control unit is used to control the user output unit to output the station prompt information.

[0014] Thirdly, an electronic device is provided, comprising: a processor and a memory configured to store a computer program capable of running on the processor.

[0015] Wherein, the processor is configured to execute the steps of the aforementioned method when running the computer program.

[0016] Fourthly, a computer-readable storage medium is provided having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the aforementioned method.

[0017] This application provides an arrival notification method, device, electronic device, and storage medium. The method includes: acquiring audio data collected by a voice acquisition unit; performing voice recognition on the audio data based on a first voice detection model to obtain a first voice recognition result; determining the arrival station of the first electronic device based on the first voice recognition result; generating station notification information based on the arrival station; and controlling a user output unit to output the station notification information. In this way, when a user arrives at a transportation vehicle, the arrival station is determined by performing voice recognition on the audio data of the current environment, and station notification information (such as voice prompts, pop-up prompts, vibration prompts, etc.) is generated to remind the user, preventing them from missing their stop due to wearing noise-canceling headphones or being distracted, thus improving the user's travel experience. Attached Figure Description

[0018] Figure 1 This is a first flowchart illustrating the arrival notification method in this application embodiment;

[0019] Figure 2 This is a second flowchart illustrating the arrival notification method in this application embodiment;

[0020] Figure 3 This is a schematic diagram of the first component structure of the sub-road network information in the embodiments of this application;

[0021] Figure 4 This is a schematic diagram of the second component structure of the sub-road network information in the embodiments of this application;

[0022] Figure 5 This is a schematic diagram of the third process of the arrival notification method in the embodiments of this application;

[0023] Figure 6 This is a schematic diagram of the composition structure of the arrival notification system in the embodiments of this application;

[0024] Figure 7 This is a schematic diagram of the composition of the arrival notification device in the embodiments of this application;

[0025] Figure 8 This is a schematic diagram of the composition structure of the electronic device in the embodiments of this application. Detailed Implementation

[0026] In order to gain a more detailed understanding of the features and technical content of the embodiments of this application, the implementation of the embodiments of this application will be described in detail below with reference to the accompanying drawings. The accompanying drawings are for reference and illustration only and are not intended to limit the embodiments of this application.

[0027] This application provides an arrival notification method applied to a first electronic device. The first electronic device uses a configured first speech detection model to perform speech recognition on the audio data of the current environment, determines the arrival station, and reminds the user.

[0028] The first electronic device may include mobile devices such as mobile phones, wearable devices, tablets, laptops, PDAs, personal digital assistants (PDAs), and portable media players (PMPs). When a user carries the first electronic device on public transportation, the first electronic device can provide the user with an arrival reminder service.

[0029] Figure 1 This is a schematic diagram of the first process of the arrival notification method in the embodiments of this application, such as... Figure 1 As shown, the method may specifically include:

[0030] Step 101: Acquire audio data collected by the voice acquisition unit;

[0031] Here, the voice acquisition unit is used to acquire audio data of the current environment, and the voice acquisition unit can be a microphone configured on the first electronic device.

[0032] Step 102: Perform speech recognition on the audio data based on the first speech detection model to obtain the first speech recognition result;

[0033] Here, the first speech detection model is used to identify whether the audio data contains a preset keyword. For example, the first speech detection model first extracts audio features from the audio data, and then matches the audio features with the audio features of the preset keyword to determine whether the audio data contains the preset keyword.

[0034] For example, in some embodiments, the first speech recognition result includes the predicted probability of a keyword detected by the first speech detection model. Further, the audio data is judged based on the predicted probability of the keyword. The higher the predicted probability, the higher the probability that the audio data contains the preset keyword, and vice versa.

[0035] Step 103: Determine the arrival station of the first electronic device based on the first speech recognition result;

[0036] Here, the arrival station can be the station a user is about to reach or the current station when taking a certain type of public transportation. The public transportation system sets station prompt sounds for each line and each station. By collecting and analyzing the station prompt sounds, the system determines whether the vehicle is about to arrive at or is currently at a station, and then reminds the user. For example, "Next station XXX" determines whether the next station is the destination station by extracting keywords from the ambient sound, and "XXX station arrived" determines whether the current station is the destination station by extracting keywords from the ambient sound.

[0037] For example, in some embodiments, the first speech recognition result includes the predicted probability of a keyword, and determining the arrival station of the first electronic device based on the first speech recognition result includes: obtaining the predicted probability of a first keyword from the first speech recognition result; wherein the first keyword is one of the at least one station keyword; when the predicted probability of the first keyword is greater than or equal to a decision threshold of the first keyword, the station referred to by the first keyword is determined to be an arrival station; when the predicted probability of the first keyword is less than the decision threshold of the first keyword, the station referred to by the first keyword is determined not to be an arrival station.

[0038] In other words, the probability threshold of the keyword is compared with the decision threshold to determine whether the audio data contains the keyword. If it is contained, the site referred to by the keyword is the destination site; if it is not contained, the site referred to by the keyword is not the destination site, which can also be understood as the site referred to by the keyword not being reached.

[0039] For example, in some embodiments, the method further includes: obtaining a pre-trained initial speech detection model; determining a destination site; configuring model parameters in the initial speech detection model based on keywords of the destination site to obtain a first speech detection model; wherein the first speech detection model is used to identify keywords of the destination site.

[0040] In practical applications, the initial speech detection model can be a neural network model. After training, this model possesses speech recognition capabilities. Once the destination station is determined, only the keywords of the destination station need to be used to configure the model parameters of the initial speech model; no model training is required. The predicted probability of the destination station keywords in the first speech recognition result is obtained. If the predicted probability of the destination station keywords is greater than a decision threshold, it indicates that the current ambient sound contains the destination station keywords, and a prompt message is generated to remind the user that the destination station has been reached.

[0041] In practical applications, considering the timeliness of reminders, the first voice detection model can also be used to identify keywords of neighboring stations of the destination station, and start reminding the user one or two stations before the destination station. In practice, whether the station reminder function is enabled can be selected by the user, and the specific reminder method can be the system default method or set by the user.

[0042] Step 104: Generate station prompt information based on the arrived station, and control the user output unit to output the station prompt information.

[0043] For example, in some embodiments, the method further includes: obtaining the first speech detection model generated and sent by the second electronic device. That is, the second electronic device generates the first speech detection model and sends it to the first electronic device for use.

[0044] For example, the processing and storage resources of the second electronic device are superior to those of the first electronic device. The first electronic device can be a wearable device, while the second electronic device can be a mobile device such as a mobile phone, tablet, laptop, or PDA, whose processing and storage resources are superior to those of a wearable device. The second electronic device generates a first speech detection model based on the user's destination site, which is easy to deploy on a wearable device, thus narrowing the scope of speech detection and limiting the model size.

[0045] Recognizing keywords (such as station names, voice assistant commands, etc.) from sound requires prior keyword modeling, and the size of such models increases rapidly with the number and length of keywords. This solution uses only keywords from the destination station, or keywords from some stations near the destination station, to build a first speech detection model. The smaller size of the first speech detection model allows it to be applied to wearable devices with limited processing and storage resources, avoiding the problem of excessively large models being unsuitable for deployment on wearable devices.

[0046] In scenarios with poor location signals, such as subways, or where users are unwilling to enable location information, systems utilizing geolocation information will be completely unable to provide normal service. If a user's mobile phone runs out of battery and shuts down during their commute, the phone's location function will be completely ineffective. Therefore, users may choose to pause using their phones to avoid draining the battery or may miss their stop while resting, which will greatly affect the user experience. This application applies the aforementioned arrival notification method to wearable devices, which can effectively solve these problems. When the wearable device is an earphone, the microphone on the earphone end is not easily blocked by the user and can collect high-quality environmental audio data, thereby accurately identifying the arrival station.

[0047] For example, the first electronic device can be a mobile device, and the second electronic device can be a fixed device. The first electronic device and the second electronic device can communicate wirelessly. The first electronic device sends a model request (including a destination site), and the second electronic device responds to the model request, generates a first speech detection model, and sends it to the first electronic device.

[0048] By adopting the above technical solution, when a user arrives at a transportation vehicle, the system uses voice recognition based on the audio data of the current environment to determine the arrival station and generates station prompts (such as voice prompts, pop-up prompts, vibration prompts, etc.) to remind the user, thus preventing the user from missing the station due to wearing noise-canceling headphones or being distracted, and improving the user's travel experience.

[0049] To better illustrate the purpose of this application, further examples are provided based on the above embodiments. Figure 2 This is a schematic diagram of the second process of the arrival notification method in the embodiments of this application, such as... Figure 2 As shown, the method may specifically include:

[0050] Step 201: Obtain the pre-trained initial speech detection model;

[0051] Step 202: Determine the destination station; based on the destination station, determine the sub-road network information related to the destination station from the current urban road network information;

[0052] Here, the current city road network information is the road network information of the city where the first electronic device is located. The current city road network information will be updated when the road network information is updated or when the user moves to a new city.

[0053] Here, sub-route network information refers to the portion of the current city's road network information related to the destination station. For example, sub-route network information includes the topological relationship between the destination station and its surrounding related stations. Sub-route network information can include information on all stations along a preset arrival path, such as all stations on Metro Line 1 in a city. Sub-route network information can also include the destination station and preceding stations along a preset arrival path, such as... Figure 3 As shown, sub-route information includes the destination station and information on several preceding stations along a travel route. Sub-route information may also include information on the destination station and surrounding stations, such as... Figure 4 As shown, if there are 3 routes passing through the destination station, then obtain the sub-network information of the stations before and after the destination station on each path.

[0054] Step 203: Configure the model parameters in the initial speech detection model based on the keywords of each station in the sub-road network information to obtain the first speech detection model;

[0055] In practical applications, the initial speech detection model can be a neural network model. The trained initial speech detection model has speech recognition capabilities. After determining the sub-road network information of the destination station, it is only necessary to use the keywords of each station in the sub-road network information and configure the model parameters of the initial speech model without model training. The resulting first speech detection model not only has the ability to detect the destination station, but also has the ability to detect other related stations.

[0056] Step 204: Acquire audio data collected by the voice acquisition unit;

[0057] Step 205: Perform speech recognition on the audio data based on the first speech detection model to obtain the first speech recognition result;

[0058] Step 206: Determine the arrival station of the first electronic device based on the first speech recognition result;

[0059] For example, the speech recognition result includes the predicted probability of each site keyword. When the predicted probability of a keyword is greater than or equal to a decision threshold for the keyword, the site referred to by the keyword is determined to be the destination site. That is, when the first speech detection model is used to detect multiple sites, it outputs the predicted probabilities of multiple keywords, and the site keywords contained in the speech data are determined by the magnitude of the predicted probabilities.

[0060] In practical applications, the decision thresholds for each keyword may be equal or unequal. A higher decision threshold indicates stricter detection conditions for the keyword, while a lower threshold indicates more lenient detection conditions. Furthermore, the decision threshold can be flexibly configured based on the probability of a user reaching the site; a higher probability of reaching the site results in a lower decision threshold, and vice versa.

[0061] For example, in some embodiments, the method further includes: acquiring location information and motion information of the first electronic device; predicting a first station that the first electronic device is about to arrive at based on the location information and motion information of the first electronic device; and lowering the decision threshold corresponding to the keyword of the first station.

[0062] Here, location information can be obtained through a positioning unit or determined based on the location of a base station communicating with the first electronic device. Motion information includes the direction and speed of movement of the first electronic device. This information can be detected by sensor units on the first or second electronic device, such as gyroscopes and accelerometers.

[0063] For example, in some embodiments, the method further includes: determining a second station that the first electronic device has passed through; and increasing the decision threshold corresponding to the keyword of the second station.

[0064] For example, in some embodiments, the method further includes: obtaining the first speech detection model generated and sent by the second electronic device. That is, the second electronic device generates the first speech detection model and sends it to the first electronic device for use.

[0065] Step 207: Generate station prompt information based on the arrived station, and control the user output unit to output the station prompt information.

[0066] For example, the first voice detection model is used to identify keywords for each station in the sub-road network information. The step of generating station prompt information based on the arrival station includes: when the arrival station of the first electronic device is the destination station, generating the station prompt information to indicate arrival at the destination station.

[0067] In other words, when the first speech detection model can identify the destination station and intermediate stations, it only generates a prompt message to remind the user when an intermediate station is identified. When an intermediate station is identified, it can assist in the decision of the destination station, for example, by lowering the decision threshold for the destination station.

[0068] For example, generating site notification information based on the arrival station includes generating site notification information for all identified stations. In practical applications, considering the timeliness of reminders, the first voice detection model can also be used to identify keywords of neighboring stations of the destination station, and start reminding the user at the station one or two stations before the destination station. In practical applications, whether the site reminder function is enabled can be selected by the user, and the specific reminder method can be the system default method or set by the user.

[0069] To better illustrate the purpose of this application, based on the above embodiments, the arrival notification method is further illustrated with examples. Figure 5 This is a schematic diagram of the third process of the arrival notification method in the embodiments of this application, such as... Figure 5 As shown, the method may specifically include:

[0070] Step 501: Acquire audio data collected by the voice acquisition unit;

[0071] Step 502: Perform speech recognition on the audio data based on the first speech detection model to obtain the first speech recognition result;

[0072] Step 503: Determine the arrival station of the first electronic device based on the first speech recognition result;

[0073] Step 504: Generate station prompt information based on the arrived station, and control the user output unit to output the station prompt information.

[0074] Step 505: Perform speech recognition on the audio data based on the second speech detection model to obtain the second speech recognition result;

[0075] Step 506: Determine a voice wake-up command or a voice control command based on the second speech recognition result.

[0076] Here, the second speech detection model can be understood as a voice assistant in existing electronic devices. If the audio data contains wake-up keywords (i.e., voice wake-up commands), the speech detection function of the second speech detection model is activated, and control keywords (i.e., voice control commands) are detected in the audio data.

[0077] For example, the first and second voice detection models can be implemented by different hardware modules. For instance, a new KWS module can be added to the existing Keyword Spotting (KWS) module used by voice assistants. This makes the two voice detection methods independent, preventing the arrival reminder function from affecting the voice assistant's functionality. On the software side, the stations to be detected are determined based on the current urban road network information. Keywords from the arrival broadcast information of these stations are added to the voice detection model, reducing the number of keywords and limiting the model size. Simultaneously, information collected by the positioning unit and sensor unit can be used for joint auxiliary decision-making, improving the accuracy of the decision.

[0078] Based on the above embodiments, we will further illustrate this by taking the first electronic device as an earphone and the second electronic device as a mobile phone. Figure 6 This is a schematic diagram of the composition structure of the arrival notification system in the embodiments of this application, such as... Figure 6 As shown, the arrival notification system includes: headset 601, mobile phone 602, and cloud 603.

[0079] Among them, the cloud-based 603 stores the city's road network information database;

[0080] Mobile phone 602 obtains the current city road network information from the city road network information database in the cloud 603 based on the current city, and determines the sub-road network information of the destination from the current city road network information based on the user's destination information; generates a first voice detection model based on the sub-road network information and sends it to the first voice detection module of the headset to perform station detection, and obtains location information and motion information and sends them to the main controller of headset 601 for auxiliary judgment;

[0081] The hardware of the earphone 601 includes an additional data path that passes through the first voice detection module for site detection. The basic structure of the first voice detection module is basically the same as that of the second voice detection module in the voice assistant, but because the voice detection model used is smaller, the computing power and the number of storage units can be appropriately reduced.

[0082] The earphone 601 receives the first voice detection model from the mobile phone 602. The first voice detection module performs station detection on the audio data collected by the microphone based on the first voice detection model, obtaining a first voice recognition result. The second voice detection module performs voice recognition on the audio data collected by the microphone based on a pre-existing second voice detection model, obtaining a second voice recognition result. The main controller further judges the two voice recognition results to ultimately determine the keywords contained in the audio data and executes the corresponding control operations. It should be noted that, to improve accuracy during station recognition, the main controller also uses location and motion information sent by the mobile phone 602 for auxiliary judgment. If the vehicle has already reached the current station, the probability of the next station name appearing is appropriately increased, i.e., the judgment threshold for the next station is lowered.

[0083] For example, based on the sub-network information of the destination, the range of base stations in the sub-network information is determined, and the range of base stations is used for judgment. If the mobile phone is connected to a base station within the range of the base station, it is determined that the user has entered a certain range of the destination. Then, the headset is notified to appropriately lower the judgment threshold for the appearance of certain station names, thereby dynamically assisting the final judgment.

[0084] Motion information can be the acceleration of the mobile phone. When the acceleration decreases, it is determined that the train is decelerating to enter the station, and when the acceleration increases, it is determined that the train is accelerating to leave the station, which is used to provide auxiliary judgment information.

[0085] The headphone 601 main controller primarily utilizes the voice recognition results from the first voice detection module, combined with location and motion information transmitted from the mobile phone 602, to determine which station the user has reached and whether they have arrived at their destination. If it is determined that the user has arrived at their destination, a notification is sent to the user (either by playing a sound or through a pop-up window on the phone). This frees up the user's attention during travel, allowing them to focus on other things and greatly improving the user's travel experience. Even in cities or stations the user has never been to before, it can still prevent them from missing their stop and wasting time.

[0086] The aforementioned headphones can be any type of headphone, such as in-ear headphones, over-ear headphones, wired headphones, or wireless headphones.

[0087] To implement the method of the embodiments of this application, based on the same inventive concept, the embodiments of this application also provide an arrival notification device, applied to a first electronic device, such as... Figure 7 As shown, the device 70 includes:

[0088] Acquisition unit 701 is used to acquire audio data collected by the voice acquisition unit;

[0089] Processing unit 702 is configured to perform speech recognition on the audio data based on a first speech detection model to obtain a first speech recognition result; determine the arrival station of the first electronic device based on the speech recognition result; and generate station prompt information based on the arrival station.

[0090] The control unit 703 is used to control the user output unit to output the station prompt information.

[0091] For example, in some embodiments, the device further includes a configuration unit ( Figure 7 (Not shown in the image) is used to obtain a pre-trained initial speech detection model; determine the destination site; configure the model parameters in the initial speech detection model based on the keywords of the destination site to obtain the first speech detection model; wherein, the first speech detection model is used to identify the keywords of the destination site.

[0092] For example, in some embodiments, the device further includes a configuration unit, specifically configured to determine sub-road network information related to the destination station from the current urban road network information based on the destination station; wherein the sub-road network information includes the destination station and intermediate stations of the destination station on a preset arrival path; and configure model parameters in the initial speech detection model based on the keywords of each station in the sub-road network information to obtain the first speech detection model;

[0093] The first speech detection model is used to identify keywords for each station in the sub-network information.

[0094] For example, in some embodiments, the control unit 703 is configured to generate station prompt information when the arrival station of the first electronic device is the destination station, to prompt that the destination station has been reached.

[0095] For example, in some embodiments, the acquisition unit 701 is used to acquire the first speech detection model generated and sent by the second electronic device.

[0096] For example, the processing and storage resources of the second electronic device are superior to those of the first electronic device. The first electronic device can be a wearable device, while the second electronic device can be a mobile terminal such as a mobile phone, tablet, laptop, or PDA, whose processing and storage resources are superior to those of a wearable device. The second electronic device generates a first speech detection model based on the user's destination site, which is easy to deploy on a wearable device, thus narrowing the scope of speech detection and limiting the model size.

[0097] For example, in some embodiments, the first speech recognition result includes the predicted probability of at least one site keyword;

[0098] Processing unit 702 is configured to obtain the predicted probability of a first keyword from the first speech recognition result; wherein the first keyword is one of the at least one site keyword; when the predicted probability of the first keyword is greater than or equal to the decision threshold of the first keyword, the site referred to by the first keyword is determined to be an arrival site; when the predicted probability of the first keyword is less than the decision threshold of the first keyword, the site referred to by the first keyword is determined not to be an arrival site.

[0099] For example, in some embodiments, the processing unit 702 is configured to acquire the location information and motion information of the first electronic device; predict the first station that the first electronic device is about to arrive at based on the location information and motion information of the first electronic device; and lower the decision threshold corresponding to the keyword of the first station.

[0100] For example, in some embodiments, the processing unit 702 is used to determine a second station that the first electronic device has passed through; and increase the decision threshold corresponding to the keyword of the second station.

[0101] For example, in some embodiments, the processing unit 702 is further configured to perform speech recognition on the audio data based on the second speech detection model to obtain a second speech recognition result; and determine a voice wake-up command or a voice control command based on the second speech recognition result.

[0102] In practical applications, the aforementioned device can be a first electronic device or a chip applied within the first electronic device. In this application, the device can implement the functions of multiple units through software, hardware, or a combination of both, enabling the device to execute the arrival notification method provided in any of the above embodiments. Furthermore, the technical effects of each technical solution of the device can be referenced to the technical effects of the corresponding technical solutions in the arrival notification method, and will not be elaborated upon further in this application.

[0103] Based on the hardware implementation of each unit in the aforementioned arrival notification device, this application embodiment also provides an electronic device, which is a mobile device, such as... Figure 8 As shown, the electronic device 80 includes: a processor 801 and a memory 802 configured to store computer programs capable of running on the processor;

[0104] When the processor 801 is configured to run a computer program, it executes the method steps described in the foregoing embodiments.

[0105] Of course, in practical applications, such as Figure 8As shown, the various components in the electronic device 80 are coupled together via a bus system 803. It can be understood that the bus system 803 is used to enable communication between these components. In addition to a data bus, the bus system 803 also includes a power bus, a control bus, and a status signal bus. However, for clarity, all buses are labeled as bus system 803 in the figure.

[0106] In practical applications, the aforementioned processor can be at least one of the following: Application-Specific Integrated Circuit (ASIC), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field-Programmable Gate Array (FPGA), controller, microcontroller, and microprocessor. It is understood that, for different devices, the electronic devices used to implement the functions of the aforementioned processor can also be other types, and the embodiments of this application do not specifically limit this.

[0107] The aforementioned memory can be volatile memory, such as random-access memory (RAM); or non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid-state drive (SSD); or a combination of the above types of memory, and provides instructions and data to the processor.

[0108] In an exemplary embodiment, this application also provides a computer-readable storage medium, such as a memory including a computer program, which can be executed by a processor of an electronic device to perform the steps of the aforementioned method.

[0109] This application also provides a computer program product, including computer program instructions.

[0110] Optionally, the computer program product can be applied to the electronic device in the embodiments of this application, and the computer program instructions cause the computer to execute the corresponding processes implemented by the electronic device in the various methods of the embodiments of this application. For the sake of brevity, they will not be described in detail here.

[0111] This application also provides a computer program.

[0112] Optionally, the computer program can be applied to the electronic device in the embodiments of this application. When the computer program is run on a computer, it causes the computer to execute the corresponding processes implemented by the electronic device in the various methods of the embodiments of this application. For the sake of brevity, it will not be described in detail here.

[0113] It should be understood that the terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items. The expressions “having,” “may have,” “comprising,” and “including,” or “may include” and “may contain” used herein may be used to indicate the presence of a corresponding feature (e.g., an element such as a number, function, operation, or component), but do not exclude the presence of additional features.

[0114] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another, and are not necessarily used to describe a specific order or sequence. For example, without departing from the scope of this invention, first information may also be referred to as second information, and similarly, second information may also be referred to as first information.

[0115] The technical solutions described in the embodiments of this application can be combined arbitrarily without conflict.

[0116] In the several embodiments provided in this application, it should be understood that the disclosed methods, apparatus, and devices can be implemented in other ways. The embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical, or other forms.

[0117] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0118] In addition, each functional unit in the various embodiments of this application can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0119] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. An arrival notification method, applied to a first electronic device, characterized in that, The method includes: Acquire audio data collected by the voice acquisition unit; The audio data is subjected to speech recognition based on the first speech detection model to obtain the first speech recognition result; wherein, the first speech detection model is obtained by configuring the model parameters in the pre-trained initial speech detection model based on the keywords of the destination station and the keywords of the intermediate stations on the preset arrival path of the destination station, and is used to identify the keywords of the arrival station. The arrival station of the first electronic device is determined based on the first speech recognition result; Based on the arrival at the station, generate station prompt information and control the user output unit to output the station prompt information; The method further includes: Obtain the location and motion information of the first electronic device; Based on the location and motion information of the first electronic device, determine the first station that the first electronic device is about to arrive at, and determine the second station that the first electronic device has already passed; Lower the decision threshold for the keywords of the first site, and increase the decision threshold for the keywords of the second site.

2. The method according to claim 1, characterized in that, The method further includes: Obtain a pre-trained initial speech detection model; Determine the destination station; The first speech detection model is obtained by configuring the model parameters in the initial speech detection model based on the keywords of the destination site. The first speech detection model is used to identify keywords of the destination site.

3. The method according to claim 2, characterized in that, The step of configuring the model parameters in the initial speech detection model based on the keywords of the destination site to obtain the first speech detection model includes: Based on the destination station, sub-road network information related to the destination station is determined from the current urban road network information; wherein, the sub-road network information includes the destination station and intermediate stations of the destination station on the preset arrival path; The first speech detection model is obtained by configuring the model parameters in the initial speech detection model based on the keywords of each station in the sub-network information; The first speech detection model is used to identify keywords for each station in the sub-network information.

4. The method according to claim 3, characterized in that, The generation of station prompt information based on the arrived station includes: When the arrival station of the first electronic device is the destination station, the station prompt information is generated to indicate that the destination station has been reached.

5. The method according to any one of claims 1-4, characterized in that, The method further includes: acquiring the first speech detection model generated and sent by the second electronic device.

6. The method according to claim 1, characterized in that, The first speech recognition result includes the predicted probability of at least one site keyword; Determining the arrival station of the first electronic device based on the first speech recognition result includes: The predicted probability of a first keyword is obtained from the first speech recognition result; wherein the first keyword is one of the at least one site keyword; When the predicted probability of the first keyword is greater than or equal to the decision threshold of the first keyword, the station referred to by the first keyword is determined to be the destination station. If the predicted probability of the first keyword is less than the decision threshold of the first keyword, it is determined that the site referred to by the first keyword is not the destination site.

7. The method according to claim 1, characterized in that, The method further includes: The audio data is used to perform speech recognition based on the second speech detection model to obtain the second speech recognition result. Based on the second speech recognition result, a voice wake-up command or a voice control command is determined.

8. An arrival notification device, applied to a first electronic device, characterized in that, The device includes: The acquisition unit is used to acquire audio data collected by the voice acquisition unit; The processing unit is configured to perform speech recognition on the audio data based on a first speech detection model to obtain a first speech recognition result; determine the arrival station of the first electronic device based on the speech recognition result; and generate station prompt information based on the arrival station; wherein, the first speech detection model is obtained by configuring model parameters in a pre-trained initial speech detection model based on the keywords of the destination station and the keywords of intermediate stations on the preset arrival path of the destination station, and is used to identify the keywords of the arrival station. The control unit is used to control the user output unit to output the station prompt information; The processing unit is further configured to acquire the location information and motion information of the first electronic device; based on the location information and motion information of the first electronic device, determine the first station that the first electronic device is about to arrive at, and determine the second station that the first electronic device has already passed through; lower the decision threshold corresponding to the keyword of the first station, and increase the decision threshold corresponding to the keyword of the second station.

9. An electronic device, characterized in that, The electronic device includes: a processor and a memory configured to store computer programs capable of running on the processor. Wherein, when the processor is configured to run the computer program, it performs the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images