Voice rescue method and system applied to vehicle and vehicle-mounted terminal

Abstract

The application discloses a voice rescue method and system applied to a vehicle and a vehicle terminal. The voice rescue method comprises the following steps: when a voice rescue trigger instruction is detected in the vehicle, collecting voice information is triggered; voice features of the voice information are extracted; it is judged whether the voice features satisfy a voice rescue trigger condition; if yes, a vehicle rescue request is triggered. The application triggers the vehicle rescue request based on voice recognition, so that manual triggering of an in-vehicle calling button by an in-vehicle staff is not needed, and automatic triggering of an in-vehicle electronic collision sensing unit is not needed. Therefore, on one hand, the application overcomes the inherent defects of the prior art rescue scheme based on hardware triggering, improves rescue reliability, and on the other hand, the application overcomes the dependence on the in-vehicle staff's body behavior, so that the vehicle rescue request can be triggered when the in-vehicle staff cannot move.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, in particular to a voice rescue method and system applied to a vehicle and a vehicle terminal. BACKGROUND

[0002] Currently, vehicle contact rescue center rescue is usually implemented in two ways, one is that the user can trigger through the call button in the vehicle, and the other is that the vehicle triggers automatically when an emergency collision occurs. The above two rescue schemes based on hardware triggering have poor reliability, for example, the call button and the electronic collision sensing unit will gradually age with the increase of the service life of the vehicle, which may cause the call button to fail to respond or the electronic collision sensing unit to malfunction, for example, the call button or the electronic collision sensing unit may be damaged due to an accident, for example, the call button cannot be triggered and the rescue center cannot be contacted because the vehicle occupants cannot move due to an accident or some diseases. SUMMARY

[0003] The present application aims to solve the technical problem of poor reliability of the rescue scheme based on hardware triggering in the prior art, and provides a voice rescue method and system applied to a vehicle and a vehicle terminal.

[0004] The present application solves the above technical problem by the following technical scheme:

[0005] A voice rescue method applied to a vehicle, comprising the following steps:

[0006] When a voice rescue triggering instruction is detected in the vehicle, collecting voice information is triggered;

[0007] Extracting voice features of the voice information;

[0008] Determining whether the voice features meet a voice rescue triggering condition;

[0009] If yes, triggering a vehicle rescue request.

[0010] A voice rescue system applied to a vehicle, comprising:

[0011] A collecting module for triggering the collection of voice information when a voice rescue triggering instruction is detected in the vehicle;

[0012] An extracting module for extracting voice features of the voice information;

[0013] A determining module for determining whether the voice features meet a voice rescue triggering condition;

[0014] If yes, a request module is called, which is used to trigger a vehicle rescue request.

[0015] A vehicle-mounted terminal comprising the voice rescue system for vehicles as described above.

[0016] A computer readable storage medium having stored thereon a computer program, which, when executed by a processor, implements the steps of the voice rescue method for vehicles as described above.

[0017] The positive progress effect of the present application is that the present application triggers the vehicle rescue request based on voice recognition, so that neither manual triggering of the in-vehicle calling button by the in-vehicle personnel nor automatic triggering of the in-vehicle electronic collision sensing unit is needed. Based on this, on the one hand, the inherent defects of the prior art rescue triggering scheme based on hardware are overcome, and the rescue reliability is improved. On the other hand, the dependence on the in-vehicle personnel's body behavior is overcome, so that the vehicle rescue request can be triggered even when the in-vehicle personnel cannot move. BRIEF DESCRIPTION OF DRAWINGS

[0018] Figure 1 A flowchart of the voice rescue method for vehicles according to Embodiment 1 of the present application.

[0019] Figure 2 A partial flowchart of step S103 in the voice rescue method for vehicles according to Embodiment 1 of the present application.

[0020] Figure 3 Another partial flowchart of step S103 in the voice rescue method for vehicles according to Embodiment 1 of the present application.

[0021] Figure 4 A module schematic diagram of the voice rescue system for vehicles according to Embodiment 2 of the present application. DETAILED DESCRIPTION

[0022] The present application will be further described below by way of examples, but the present application is not limited in the scope of the examples.

[0023] Embodiment 1

[0024] Currently, vehicles often trigger a request for rescue from a rescue center based on hardware, specifically, one is manually realized through an in-vehicle calling button, and the other is automatically realized through an in-vehicle electronic collision sensing unit. However, in the case that the in-vehicle personnel cannot move, the rescue cannot be triggered based on the in-vehicle calling button. In addition, in the case that the in-vehicle calling button fails or the in-vehicle electronic collision sensing unit fails, the rescue cannot be triggered either. Therefore, the current rescue triggering scheme based on hardware has poor reliability. In view of this, the present embodiment provides a voice rescue method for vehicles, which will be described with reference toFigure 1 The voice rescue method of the embodiment comprises the following steps:

[0025] S101, triggering collection of voice information when a voice rescue trigger instruction is detected in the vehicle;

[0026] S102, extracting voice features of the voice information;

[0027] S103, determining whether the voice features meet a voice rescue trigger condition;

[0028] If yes, step S104 is executed;

[0029] S104, triggering a vehicle rescue request.

[0030] In the embodiment, the voice trigger instruction can be customized according to actual application, for example, it can be set as “calling the rescue center”, “calling 110”, “calling 120” and the like, and used as the trigger condition for voice information collection. Specifically, in the embodiment, a microphone or the like hardware module in the vehicle can be used to receive voice signals to realize detection of the voice rescue trigger instruction and collection of the voice information.

[0031] In step S102, voice features are extracted from the collected voice information, wherein the extracted voice features can be customized according to actual application, and in the embodiment, the voice features preferably include at least one of sound size feature and speech rate feature. Further, in the embodiment, the collection of voice information is continuous, and the extraction of voice features is repeated, and as the collected voice information increases, the extracted voice features are more accurate.

[0032] In the embodiment, the voice rescue trigger condition can be customized according to actual application, and specifically, when the vehicle needs rescue, a traffic accident often occurs, in which case the voice features of the vehicle occupants can reflect the severity of the traffic accident, the injury degree of the vehicle occupants and the like to a great extent, for example, for the sound size feature, too large or too small sound is mostly abnormal, and for example, for the speech rate feature, too fast or too slow speech rate is mostly abnormal.

[0033] When the voice features include the sound size feature, reference is made to Figure 2 Specifically, step S103 can comprise the following steps:

[0034] S1031, determining whether the sound size feature falls within a first preset range;

[0035] If no, step S1033 is executed;

[0036] S1033, determining that the voice rescue trigger condition is met.

[0037] In this embodiment, the first preset range is used to represent the range in which the sound size usually falls, which can be customized according to actual application. For example, the first preset range can be set to 35-85 decibels. When the sound size is lower than 35 decibels, the sound is abnormally weak, which can be inferred that the person in the vehicle is in an abnormal weak state. When the sound size is higher than 85 decibels, the sound is abnormally loud, which can be inferred that the person in the vehicle is in an abnormal panic state. In addition, the person in the vehicle is most likely to be in an abnormal weak state (for example, the person in the vehicle is seriously injured and is on the verge of coma) or an abnormal panic state (for example, the person in the vehicle has a stress reaction to the traffic accident) when a serious traffic accident occurs, thereby meeting the voice rescue triggering condition.

[0038] When the voice feature includes the speech rate feature, referring to Figure 3 , step S103 can specifically include the following steps:

[0039] S1032, determining whether the speech rate feature falls within a second preset range;

[0040] If not, step S1033 is performed;

[0041] S1033, determining that the voice rescue triggering condition is met.

[0042] In this embodiment, the second preset range is used to represent the range in which the speech rate usually falls, which can be customized according to actual application. For example, the second preset range can be set to 150-300 words per minute. When the speech rate is lower than 150 words per minute, the speech rate is abnormally slow or the speech is abnormally intermittent, which can be inferred that the person in the vehicle is in an abnormal weak state. When the speech rate is higher than 300 words per minute, the speech rate is abnormally urgent, which can be inferred that the person in the vehicle is in an abnormal panic state. In addition, the person in the vehicle is most likely to be in an abnormal weak state (for example, the person in the vehicle is seriously injured and is on the verge of coma) or an abnormal panic state (for example, the person in the vehicle has a stress reaction to the traffic accident) when a serious traffic accident occurs, thereby meeting the voice rescue triggering condition.

[0043] In the embodiment, the voice features preferably include both the sound volume feature and the speech rate feature, and in this case, step S103 can specifically include a step of determining that the voice rescue triggering condition is met when the sound volume feature does not fall within the first preset range and the speech rate feature does not fall within the second preset range. For example, in the case where the voice information is "I can't go on… Help… Help…", when the sound volume is lower than 35 decibels and the speech rate is lower than 150 words per minute, it can be inferred that the person in the vehicle is in an abnormally weak state, and the voice rescue triggering condition is met. For another example, in the case where the voice information is "I can't go on! Help! Help!", when the sound volume is higher than 85 decibels and the speech rate is higher than 300 words per minute, it can be inferred that the person in the vehicle is in an abnormally frightened state, and the voice rescue triggering condition is met.

[0044] The embodiment determines whether the voice rescue triggering condition is met based on the voice features, which can avoid the situation that the person in the vehicle cannot manually trigger the in-vehicle call button to request for rescue due to being unable to move, and can also avoid the situation that the in-vehicle call button fails or the in-vehicle electronic collision sensing unit fails to trigger a request for rescue when a traffic accident occurs, thereby improving the reliability of vehicle rescue.

[0045] Reference Figure 1 The voice rescue method of the embodiment can further include the following steps when the determination in step S103 is negative:

[0046] S105, triggering voice confirmation information;

[0047] S106, determining whether the voice confirmation instruction is received;

[0048] If yes, step S104 is performed.

[0049] In the embodiment, when it is determined that the voice features do not meet the voice rescue triggering condition, voice confirmation information is triggered, wherein the voice confirmation information is used to confirm with the person in the vehicle whether to trigger a request for vehicle rescue, and the person in the vehicle can confirm to trigger the request for vehicle rescue through a voice confirmation instruction (which can be customized according to actual application) to avoid missing other situations that exactly need to trigger the request for vehicle rescue, thereby improving the reliability of the voice rescue method of the embodiment.

[0050] Further, the voice rescue method of the embodiment can further include a step of obtaining a vehicle position of the vehicle and a step of determining a vehicle rescue center with the shortest time required to reach the vehicle position before the step S104, so as to realize the positioning of the vehicle when the vehicle rescue request is triggered, and based on this, the vehicle rescue center with the shortest time required to reach the vehicle position is determined, wherein the required time can be determined based on the driving distance from the vehicle rescue center to the vehicle position and the real-time road conditions, so as to ensure the timely rescue of the vehicle rescue center to the vehicle, improve the rescue efficiency, strive for more effective rescue time, and reduce the loss.

[0051] In the embodiment, the step S104 can be implemented as a step of sending a vehicle rescue request to the determined vehicle rescue center, and the step S104 can include a step of dialing a rescue phone of the determined vehicle rescue center and / or a step of sending the vehicle position and rescue reference information to the determined vehicle rescue center. In the embodiment, the step S104 preferably includes both steps at the same time, and the two steps can be performed simultaneously or sequentially, for example, the step of dialing the rescue phone of the determined vehicle rescue center can be performed first, and then the step of sending the vehicle position and rescue reference information to the determined vehicle rescue center can be performed after the rescue phone is connected.

[0052] Specifically, the conversation with the vehicle rescue center is conducive to the staff of the vehicle rescue center to understand the real-time situation of the vehicle waiting for rescue and the personnel in the vehicle, so as to facilitate the formulation of rescue strategies and promote the successful implementation of rescue actions, and the staff can also comfort the emotions of the personnel in the vehicle and guide self-rescue. Further, sending the vehicle position and rescue reference information to the vehicle rescue center can avoid the rescue difficulty caused by the fact that the personnel in the vehicle are difficult to speak and make the conversation ineffective. Further, the rescue reference information can be collected by various standard electric door sensors installed in the vehicle, wherein the electric door sensors can include industry standard airbag sensors, collision sensors, seat sensors, GSP signal sensors, etc. The rescue reference information can include at least one of collision information (such as whether a collision occurs, whether an airbag is ejected, collision level, etc.), personnel information (such as the number of people in the vehicle, etc.), temperature information, driving information (such as driving type, etc.), driving trajectory (such as driving trajectory within 10 minutes before the collision), vehicle heading, door information, window information, and engine information corresponding to the vehicle, so as to facilitate the formulation of rescue strategies and promote the successful implementation of rescue actions.

[0053] Specifically, according to different settings of the vehicle, the voice rescue function can be started manually, or the voice rescue function can be automatically started when the driving state of the vehicle meets the voice rescue triggering scenario, so as to trigger the implementation of the voice rescue method of the embodiment.

[0054] When the voice rescue function of the vehicle is in an open state, the step of determining whether the voice rescue trigger instruction is detected in the vehicle can be performed, and the step of triggering the collection of voice information is triggered when it is determined to be yes. Further, when the voice rescue function of the vehicle is in a closed state, if the voice rescue trigger instruction is detected in the vehicle, the voice reminder information is triggered without performing the step of triggering the collection of voice information to remind that the voice rescue function is in a closed state, and the vehicle personnel can determine whether to manually or through a voice instruction to open the voice rescue function according to the voice reminder information. Based on this, the false wake-up of the voice rescue trigger instruction can be avoided, for example, when the vehicle personnel includes a child, the voice rescue function can be selected to be closed.

[0055] When the driving state of the vehicle meets the voice rescue trigger scene, the step of determining whether the voice rescue trigger instruction is detected in the vehicle can be performed, and the step of triggering the collection of voice information is triggered when it is determined to be yes. Further, the scene elements of the voice rescue trigger scene can be customized according to actual application, for example, can include at least one of the following: there is a driver in the vehicle, the vehicle is in a starting state, the speed of the vehicle reaches a speed threshold (which can be customized according to actual application, for example, 30km / h), the engine speed of the vehicle reaches a speed threshold (which can be customized according to actual application, for example, 2000r / min), the voice rescue wake-up word is detected in the vehicle (which can be customized according to actual application), and the current driving time of the vehicle meets a preset driving time.

[0056] The embodiment based on voice recognition triggers the vehicle rescue request, so that neither manual triggering of the in-vehicle call button nor automatic triggering of the in-vehicle electronic collision sensing unit is needed. Therefore, on the one hand, the inherent defects of the prior art rescue scheme based on hardware triggering are overcome, and the rescue reliability is improved. On the other hand, the dependence on the in-vehicle personnel's body behavior is overcome, so that the vehicle rescue request can be triggered when the in-vehicle personnel cannot move.

[0057] Embodiment 2

[0058] Currently, the vehicle often triggers the contact rescue center to request rescue based on hardware, specifically, one is manually realized through the in-vehicle call button, and the other is automatically realized through the in-vehicle electronic collision sensing unit. However, in the case that the in-vehicle personnel cannot move, the rescue cannot be triggered based on the in-vehicle call button. In addition, in the case that the in-vehicle call button fails or the in-vehicle electronic collision sensing unit fails, the rescue cannot be triggered. Therefore, the current rescue scheme based on hardware triggering has poor reliability. In view of this, the embodiment provides a voice rescue system applied to a vehicle, with reference to Figure 4 The voice rescue system of the embodiment includes:

[0059] The collection module 201 is configured to trigger collection of the voice information when the voice rescue trigger instruction is detected in the vehicle.

[0060] The extraction module 202 is configured to extract voice features of the voice information.

[0061] The first judgment module 203 is configured to judge whether the voice features satisfy the voice rescue trigger condition.

[0062] If yes, the rescue request module 204 is called, and the rescue request module 204 is configured to trigger a vehicle rescue request.

[0063] In the embodiment, the voice trigger instruction can be set according to actual application, for example, can be set as “call the rescue center”, “call 110”, “call 120” and the like, and is taken as the trigger condition of the voice information collection. Specifically, in the embodiment, the collection module 201 can receive voice signals based on a microphone and the like in the vehicle to realize detection of the voice rescue trigger instruction and collection of the voice information.

[0064] The extraction module 202 is configured to extract voice features of the voice information, wherein the extracted voice features can be set according to actual application, and in the embodiment, the voice features preferably include at least one of a sound size feature and a speech rate feature. Further, in the embodiment, the collection of the voice information is continuously performed, and the extraction of the voice features is repeatedly performed, and with the increase of the collected voice information, the extracted voice features are more accurate.

[0065] In the embodiment, the voice rescue trigger condition can be set according to actual application, and specifically, when the vehicle needs rescue, a traffic accident often occurs, in this case, the voice features of the vehicle personnel can reflect the severity of the traffic accident, the injury degree of the vehicle personnel and the like to a great extent, for example, for the sound size feature, too large or too small sound is mostly abnormal, and for example, for the speech rate feature, too fast or too slow speech rate is mostly abnormal.

[0066] When the voice features include the sound size feature, the sound size feature is compared with the first preset range. Figure 4 The first judgment module 203 specifically can include:

[0067] The first judgment unit 2031 is configured to judge whether the sound size feature falls into the first preset range.

[0068] If no, the determination unit 2033 is called, and the determination unit 2033 is configured to determine that the voice rescue trigger condition is satisfied.

[0069] In this embodiment, the first preset range is used to represent a range in which the sound size usually falls, which can be customized according to actual application. For example, the first preset range can be set as 35-85 decibels. When the sound size is lower than 35 decibels, the sound is abnormally weak, which can be inferred that the person in the vehicle is in an abnormal weak state. When the sound size is higher than 85 decibels, the sound is abnormally loud, which can be inferred that the person in the vehicle is in an abnormal panic state. In addition, the person in the vehicle is most likely to be in an abnormal weak state (for example, the person in the vehicle is seriously injured and is on the verge of coma) or an abnormal panic state (for example, the person in the vehicle has a stress reaction to the traffic accident) when a serious traffic accident occurs, thereby meeting the voice rescue triggering condition.

[0070] In this embodiment, the voice feature includes the sound size feature and the speech rate feature. Figure 4 The first determining module 203 can specifically include:

[0071] The second determining unit 2032 is configured to determine whether the speech rate feature falls within a second preset range.

[0072] If not, the determining unit 2033 is called, and the determining unit 2033 is configured to determine that the voice rescue triggering condition is met.

[0073] In this embodiment, the second preset range is used to represent a range in which the speech rate usually falls, which can be customized according to actual application. For example, the second preset range can be set as 150-300 words per minute. When the speech rate is lower than 150 words per minute, the speech rate is abnormally slow or the speech is abnormally intermittent, which can be inferred that the person in the vehicle is in an abnormal weak state. When the speech rate is higher than 300 words per minute, the speech rate is abnormally urgent, which can be inferred that the person in the vehicle is in an abnormal panic state. In addition, the person in the vehicle is most likely to be in an abnormal weak state (for example, the person in the vehicle is seriously injured and is on the verge of coma) or an abnormal panic state (for example, the person in the vehicle has a stress reaction to the traffic accident) when a serious traffic accident occurs, thereby meeting the voice rescue triggering condition.

[0074] In this embodiment, the voice feature preferably includes both the sound size feature and the speech rate feature, with reference to Figure 4At this time, the first determining module 203 can be specifically used for determining that the voice rescue triggering condition is met when it is determined that the sound size feature does not fall within the first preset range and the speech speed feature does not fall within the second preset range. For example, in the case of the voice information being "I can't …… help …… help ……", when the sound size is lower than 35 decibels and the speech speed is lower than 150 words per minute, it can be inferred that the person in the vehicle is in an abnormal weak state, and the voice rescue triggering condition is met; for another example, in the case of the voice information being "I can't! Help! Help!", when the sound size is higher than 85 decibels and the speech speed is higher than 300 words per minute, it can be inferred that the person in the vehicle is in an abnormal panic state, and the voice rescue triggering condition is met.

[0075] The embodiment determines whether the voice rescue triggering condition is met based on the voice feature, which can avoid the situation that the person in the vehicle cannot manually trigger the in-vehicle call button to request for help due to being unable to move, and can also avoid the situation that the in-vehicle call button fails or the in-vehicle electronic collision sensing unit fails, resulting in the inability to trigger a request for help when a traffic accident occurs, thereby improving the reliability of vehicle rescue.

[0076] Reference Figure 4 The voice rescue system of the embodiment can further include:

[0077] The confirmation request module 205 is configured to trigger voice confirmation information.

[0078] The second determining module 206 is configured to determine whether a voice confirmation instruction is received.

[0079] If yes, the rescue request module 204 is called.

[0080] In the embodiment, when it is determined that the voice feature does not meet the voice rescue triggering condition, the voice confirmation information is triggered, wherein the voice confirmation information is used to confirm with the person in the vehicle whether to trigger the vehicle rescue request, and the person in the vehicle can confirm to trigger the vehicle rescue request through the voice confirmation instruction (which can be customized according to actual application) to avoid missing other situations that exactly need to trigger the vehicle rescue request, thereby improving the reliability of the voice rescue system of the embodiment.

[0081] Further, the voice rescue system of the embodiment can further include a positioning module configured to acquire a vehicle position of the vehicle and a determining module configured to determine a vehicle rescue center with the shortest time required to reach the vehicle position, so as to realize positioning of the vehicle when the vehicle rescue request is triggered, and based on this, to determine the vehicle rescue center with the shortest time required to reach the vehicle position, wherein the required time can be determined based on the driving distance from the vehicle rescue center to the vehicle position and the real-time road conditions, so as to ensure timely rescue of the vehicle by the vehicle rescue center, improve rescue efficiency, strive for more effective rescue time, and reduce losses.

[0082] In the embodiment, the rescue request module 204 can be implemented to send a vehicle rescue request to the determined vehicle rescue center, and the rescue request module 204 can include a dialing unit for dialing the rescue phone of the determined vehicle rescue center and / or a sending unit for sending the vehicle position and rescue reference information to the determined vehicle rescue center. In the embodiment, the rescue request module 204 preferably includes both the dialing unit and the sending unit, and the dialing unit and the sending unit can be called simultaneously or sequentially, for example, the dialing unit can be called first to dial the rescue phone of the determined vehicle rescue center, and after the rescue phone is connected, the sending unit can be called to send the vehicle position and rescue reference information to the determined vehicle rescue center.

[0083] Specifically, the communication with the vehicle rescue center is beneficial for the staff of the vehicle rescue center to understand the real-time situation of the vehicle waiting for rescue and the personnel in the vehicle, so as to facilitate the formulation of rescue strategies and promote the successful implementation of rescue actions, and the staff can also comfort the emotions of the personnel in the vehicle and guide self-rescue, and sending the vehicle position and rescue reference information to the vehicle rescue center can avoid the rescue difficulty caused by the fact that the personnel in the vehicle are difficult to speak and make the communication ineffective. Further, the rescue reference information can be collected by various standard electric door sensors installed in the vehicle, wherein the electric door sensors can include industry standard airbag sensors, collision sensors, seat sensors, GSP signal sensors, etc., and the rescue reference information can include at least one of collision information (such as whether a collision occurs, whether an airbag is ejected, collision level, etc.), personnel information (such as the number of people in the vehicle, etc.), temperature information, driving information (such as driving type, etc.), driving trajectory (such as driving trajectory within 10 minutes before the collision occurs), vehicle heading, door information, window information, and engine information corresponding to the vehicle, so as to facilitate the formulation of rescue strategies and promote the successful implementation of rescue actions.

[0084] Specifically, according to different settings of the vehicle, the voice rescue function can be started manually, or the voice rescue function can be automatically started when the driving state of the vehicle meets the voice rescue triggering scenario, so as to trigger the voice rescue system of the embodiment.

[0085] When the voice rescue function of the vehicle is in an open state, for example, the voice rescue function button is triggered, the collection module 201 can be called, and the collection of voice information is triggered when the voice rescue trigger instruction is detected in the vehicle. Further, when the voice rescue function of the vehicle is in a closed state, if the voice rescue trigger instruction is detected in the vehicle, the voice reminder module is called to trigger the voice reminder information without triggering the collection of voice information, so as to remind that the voice rescue function is in a closed state, and the vehicle personnel can determine whether to manually or through a voice instruction to open the voice rescue function according to the voice reminder information. Based on this, the false wake-up of the voice rescue trigger instruction can be avoided, for example, when the vehicle personnel includes a child, the voice rescue function can be selected to be closed.

[0086] When the driving state of the vehicle meets the voice rescue trigger scene, the collection module 201 can be called, and the collection of voice information is triggered when the voice rescue trigger instruction is detected in the vehicle. Further, the scene elements of the voice rescue trigger scene can be customized according to actual application, for example, at least one of the following conditions can be included: the presence of a driver in the vehicle, the vehicle is in a starting state, the speed of the vehicle reaches a speed threshold (which can be customized according to actual application, for example, 30km / h), the engine speed of the vehicle reaches a speed threshold (which can be customized according to actual application, for example, 2000r / min), the voice rescue wake-up word is detected in the vehicle (which can be customized according to actual application), and the current driving time of the vehicle meets a preset driving time.

[0087] The embodiment based on voice recognition triggers the vehicle rescue request, so that the vehicle personnel does not need to manually trigger the in-vehicle call button, and does not need to rely on the automatic trigger of the in-vehicle electronic collision sensing unit. Based on this, on the one hand, the inherent defects of the existing technology based on hardware triggered rescue scheme are overcome, and the rescue reliability is improved. On the other hand, the dependence on the body behavior of the vehicle personnel is overcome, so that the vehicle rescue request can be triggered when the vehicle personnel cannot move.

[0088] Embodiment 3

[0089] The embodiment provides a vehicle terminal. Specifically, the vehicle terminal of the embodiment includes the voice rescue system for a vehicle provided in the embodiment 2, so that the voice recognition based triggering of the vehicle rescue request is realized. In this way, the vehicle personnel does not need to manually trigger the in-vehicle call button, and does not need to rely on the automatic trigger of the in-vehicle electronic collision sensing unit. Based on this, on the one hand, the inherent defects of the existing technology based on hardware triggered rescue scheme are overcome, and the rescue reliability is improved. On the other hand, the dependence on the body behavior of the vehicle personnel is overcome, so that the vehicle rescue request can be triggered when the vehicle personnel cannot move.

[0090] Embodiment 4

[0091] The embodiment provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement steps of the voice rescue method for a vehicle provided in the embodiment 1.

[0092] More specifically, the readable storage medium can include, but is not limited to, a portable disc, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device or any suitable combination of the above.

[0093] In possible implementation manners, the present application can also be implemented in the form of a program product, which includes program codes for causing a terminal device to execute steps of the voice rescue method for a vehicle described in the embodiment 1 when the program product is run on the terminal device.

[0094] The program codes for executing the present application can be written in any combination of one or more programming languages, and can be executed completely on a user device, partially on a user device, as a separate software package, partially on a user device and partially on a remote device, or completely on a remote device.

[0095] Although the specific implementation manners of the present application are described above, those skilled in the art should understand that this is only an example, and the protection scope of the present application is defined by the appended claims. Those skilled in the art can make various changes or modifications to these implementation manners without departing from the principles and essence of the present application, and these changes and modifications all fall within the protection scope of the present application.

Claims

1. A voice-based emergency response method for vehicles, characterized in that, Includes the following steps: When a voice emergency call is detected inside the vehicle, the collection of voice information is triggered. Extract the speech features of the speech information; Determine whether the voice features meet the voice assistance triggering conditions; If so, a vehicle rescue request will be triggered; If the step of determining whether the voice feature meets the voice assistance triggering condition is negative, the voice assistance method further includes the following steps: A voice confirmation message is triggered, which is used to confirm whether the vehicle rescue request has been triggered. Determine whether a voice confirmation command has been received; If so, then proceed with the step of triggering a vehicle rescue request.

2. A voice-based emergency response method for vehicles, characterized in that, Includes the following steps: When a voice emergency call is detected inside the vehicle, the collection of voice information is triggered. Extract the speech features of the speech information; Determine whether the voice features meet the voice assistance triggering conditions; If so, a vehicle rescue request will be triggered; The voice-based emergency response method also includes the following steps: When the vehicle's voice assistance function is enabled, determine whether the voice assistance trigger command is detected inside the vehicle. If so, then proceed with the step of triggering the collection of voice information; When the voice assistance function is turned off and the voice assistance trigger command is detected in the vehicle, a voice reminder message is triggered to remind that the voice assistance function is turned off.

3. A voice-based emergency response method for vehicles, characterized in that, Includes the following steps: When a voice emergency call is detected inside the vehicle, the collection of voice information is triggered. Extract the speech features of the speech information; Determine whether the voice features meet the voice assistance triggering conditions; If so, a vehicle rescue request will be triggered; The voice-based emergency response method also includes the following steps: When the driving state of the vehicle meets the voice assistance trigger scenario, determine whether the voice assistance trigger command is detected in the vehicle; If so, then proceed with the step of triggering the collection of voice information; The voice-activated emergency response scenario includes at least one of the following elements: There is a driver inside the vehicle; The vehicle is in the running state; The vehicle's speed reached the vehicle speed threshold; The vehicle's engine speed reached the speed threshold. A voice emergency wake-up word was detected inside the vehicle. The current driving time of the vehicle meets the preset driving time.

4. The voice emergency response method for vehicles as described in any one of claims 1-3, wherein the voice features include volume features; The step of determining whether the voice feature meets the voice assistance triggering condition includes: Determine whether the sound volume feature falls within a first preset range; If not, then the conditions for triggering voice assistance are met.

5. The voice assistance method for vehicles as described in any one of claims 1-3, wherein the voice features include speech rate features; The step of determining whether the voice feature meets the voice assistance triggering condition includes: Determine whether the speech rate feature falls within the second preset range; If not, then the conditions for triggering voice assistance are met.

6. The voice-activated emergency response method for a vehicle as described in any one of claims 1-3, wherein prior to the step of triggering the vehicle emergency response request, the voice-activated emergency response method further comprises the following steps: Obtain the vehicle's location; Determine the vehicle rescue center that will take the shortest time to reach the vehicle's location; The steps for triggering a vehicle rescue request include: Send a vehicle rescue request to the designated vehicle rescue center.

7. The voice-based emergency assistance method for vehicles as described in claim 6, wherein the step of sending a vehicle assistance request to the determined vehicle assistance center includes at least one of the following steps: Call the designated vehicle rescue center's emergency number; The vehicle location and rescue reference information are sent to the designated vehicle rescue center. The rescue reference information includes at least one of the following: collision information, personnel information, temperature information, driving information, driving trajectory, vehicle orientation, door information, window information, and engine information.

8. A voice-activated emergency response system for vehicles, characterized in that, include: The collection module is used to trigger the collection of voice information when a voice assistance trigger command is detected inside the vehicle; The extraction module is used to extract the speech features of the speech information; The first judgment module is used to determine whether the voice features meet the voice rescue triggering conditions; If so, the rescue request module is invoked, which is used to trigger a vehicle rescue request; The voice-assisted system also includes: The confirmation request module is used to trigger a voice confirmation message, which is used to confirm whether the vehicle rescue request has been triggered. The second judgment module is used to determine whether a voice confirmation command has been received; if so, the rescue request module is invoked.

9. A voice-activated emergency response system for vehicles, characterized in that, include: The collection module is used to trigger the collection of voice information when a voice assistance trigger command is detected inside the vehicle; The extraction module is used to extract the speech features of the speech information; The first judgment module is used to determine whether the voice features meet the voice rescue triggering conditions; If so, the rescue request module is invoked, which is used to trigger a vehicle rescue request; The collection module is specifically used to determine whether the voice assistance trigger command is detected in the vehicle when the vehicle's voice assistance function is enabled. If so, then proceed with the step of triggering the collection of voice information; The voice-assisted system also includes: The voice reminder module is used to trigger a voice reminder message when the voice assistance function is in a turned-off state and the voice assistance trigger command is detected in the vehicle. The voice reminder message is used to remind that the voice assistance function is in a turned-off state.

10. A voice-activated emergency response system for vehicles, characterized in that, include: The collection module is used to trigger the collection of voice information when a voice assistance trigger command is detected inside the vehicle; The extraction module is used to extract the speech features of the speech information; The first judgment module is used to determine whether the voice features meet the voice rescue triggering conditions; If so, the rescue request module is invoked, which is used to trigger a vehicle rescue request; The collection module is specifically used to determine whether the voice assistance trigger command is detected in the vehicle when the vehicle's driving state meets the voice assistance trigger scenario; if so, the step of triggering the collection of voice information is executed. The voice-activated emergency response scenario includes at least one of the following elements: There is a driver inside the vehicle; The vehicle is in the running state; The vehicle's speed reached the vehicle speed threshold; The vehicle's engine speed reached the speed threshold. A voice emergency wake-up word was detected inside the vehicle. The current driving time of the vehicle meets the preset driving time.

11. A vehicle-mounted terminal, characterized in that, Includes the voice assistance system applied to a vehicle as described in any one of claims 8-10.

Images