Exterior speech recognition method, vehicle, device and product

Abstract

The invention provides an out-of-vehicle voice recognition method, a vehicle, equipment and a product, and the method comprises the steps: enabling the voice recognition functions of two adjacent first out-of-vehicle pickup equipment corresponding to the initiation position of an out-of-vehicle voice wake-up instruction in response to the received out-of-vehicle voice wake-up instruction; performing out-vehicle voice recognition through two first out-vehicle pickup devices, and detecting the moving direction of a user outside the vehicle; according to the first voice recognition results and the moving directions of the two pieces of first out-of-vehicle pickup equipment, predicting a target position where the user is about to arrive, and starting voice recognition functions of two pieces of adjacent second out-of-vehicle pickup equipment corresponding to the target position; and obtaining a second voice recognition result of the two pieces of second out-of-vehicle pickup equipment for out-of-vehicle voice recognition. Therefore, in consideration of the fact that the user outside the vehicle is always in a moving state when using the voice function outside the vehicle, the voice pickup outside the vehicle can be carried out in advance, the accurate voice recognition of the user outside the vehicle is ensured, and the voice interaction experience of the user is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of vehicle technology, and in particular to an off-vehicle voice recognition method, vehicle, device, and product. Background Art

[0002] With the continuous development of smart car technology, vehicles are becoming more and more intelligent. Among them, voice interaction between users and vehicles is an important manifestation of vehicle intelligence. Users can control vehicles through voice, for example, users can play music, open windows, turn off air conditioning, etc.

[0003] When performing voice recognition, the sound zone and the corresponding sound pickup device will be locked to eliminate sound interference from other locations, such as locking the sound pickup device at the front of the car for subsequent voice recognition. However, for the use scenario outside the car, since the user outside the car can walk around the vehicle, unlike the user inside the car who sits in a fixed seat, the awakened sound pickup device may not be able to perform accurate voice recognition due to the slight movement of the user outside the car, affecting the user's voice interaction experience. Summary of the invention

[0004] The embodiments of the present disclosure at least provide a method, vehicle, device, and product for off-vehicle speech recognition.

[0005] The present disclosure provides a method for external speech recognition, the method comprising:

[0006] In response to receiving an external voice wake-up command, enabling the voice recognition functions of two adjacent first external sound pickup devices corresponding to the initiation position of the external voice wake-up command; the voice recognition function refers to a function of performing voice recognition on external voice data other than the external voice wake-up command;

[0007] Performing voice recognition outside the vehicle through the two first sound pickup devices outside the vehicle, and detecting the moving direction of the user outside the vehicle;

[0008] Predicting a target location that the user will reach based on the first voice recognition results of the two first external sound pickup devices and the moving direction, and enabling voice recognition functions of two adjacent second external sound pickup devices corresponding to the target location;

[0009] Obtain target speech recognition results of the two off-vehicle sound pickup devices for off-vehicle recognition.

[0010] In the embodiment of the present disclosure, based on the outside-vehicle wake-up voice command, the voice recognition function can be enabled simultaneously for two adjacent first outside-vehicle sound pickup devices corresponding to the location where the outside-vehicle voice wake-up command is initiated, and the outside-vehicle voice recognition is performed through the two first outside-vehicle sound pickup devices, and the voice direction of the user outside the vehicle is detected, and then according to the first voice recognition result and the moving direction, the target location that the user is about to reach is predicted, so that the voice recognition function can be enabled simultaneously for two adjacent second outside-vehicle sound pickup devices corresponding to the target location to obtain the second voice recognition result of the two second outside-vehicle sound pickup devices performing the outside-vehicle voice recognition. In this way, considering that the outside-vehicle user is often in a moving state when using the outside-vehicle voice function, When performing outside-vehicle voice recognition through two first outside-vehicle sound pickup devices, the user's moving direction outside the vehicle can also be detected, and the target position that the user will reach can be predicted based on the first voice results and the moving direction of the two first outside-vehicle sound pickup devices, so that the voice recognition function of the two second outside-vehicle sound pickup devices corresponding to the target position can be enabled in advance, so that outside-vehicle sound pickup can be performed in advance, ensuring accurate voice recognition for users outside the vehicle and improving the user's voice interaction experience; in addition, since only two adjacent outside-vehicle sound pickup devices are enabled, filtering of the opposite sound zone is guaranteed, avoiding interference of other sounds generated in the opposite sound zone with the outside-vehicle voice recognition, and reducing the load of the outside-vehicle voice recognition.

[0011] In an optional implementation, predicting the target location that the user is about to reach based on the first voice recognition results of the two first external sound pickup devices and the moving direction includes:

[0012] If the first voice recognition result is empty, determine the next sound zone adjacent to the current sound zone of the user according to the moving direction, and determine the next sound zone as the target position that the user will reach.

[0013] In the embodiment of the present disclosure, when the first voice recognition result is empty, the next sound zone adjacent to the user's current sound zone and located in the moving direction can be determined as the target position based on the moving direction, which helps to ensure the matching of the determined target position and the moving direction.

[0014] In an optional implementation, predicting the target location that the user is about to reach based on the first voice recognition results of the two first external sound pickup devices and the moving direction includes:

[0015] If the first speech recognition result is not empty, the target position is determined according to at least one candidate position indicated by the first speech recognition result and the moving direction; the target position belongs to the candidate position.

[0016] In the embodiment of the present disclosure, when the first speech recognition result is not empty, at least one candidate position indicated by the first speech recognition result can be obtained. On this basis, combined with the moving direction, the candidate position in the at least one candidate position located in the moving direction can be determined as the target position, which helps to ensure the matching of the determined target position with the first speech structure and the moving direction.

[0017] In an optional implementation manner, the detecting the moving direction of the user outside the vehicle includes:

[0018] Determine the moving direction of the user outside the vehicle based on multiple continuous images taken by a camera device on the vehicle; or,

[0019] The user's moving direction outside the car is determined based on the Bluetooth signal broadcast by the Bluetooth key carried by the user.

[0020] In the disclosed embodiment, the moving direction can be determined by taking multiple consecutive images or by broadcasting a Bluetooth signal. In this way, the moving direction can be determined by relying on a camera installed in the vehicle itself or by relying on a Bluetooth key carried by the user, thereby improving the convenience and speed of determining the moving direction.

[0021] In an optional implementation manner, voice recognition is performed on the vehicle exterior voice data by two vehicle exterior sound pickup devices according to the following steps, wherein the two vehicle exterior sound pickup devices are the two first vehicle exterior sound pickup devices or the two second vehicle exterior sound pickup devices:

[0022] When the voice recognition results provided by the two external sound pickup devices are not empty, comparing whether the text information indicated by the two voice recognition results are consistent; if they are consistent, taking the consistent text information as the target voice recognition result;

[0023] If there is inconsistency, determine whether the two text messages match the instruction information in a preset text information set, and the preset text information set includes multiple commonly used instruction information in off-vehicle usage scenarios; if one of the two text messages matches the instruction information in the preset text information set, the text information that successfully matches will be determined as the target speech recognition result.

[0024] In the embodiment of the present disclosure, if both voice recognition results are not empty, the two text messages are compared to see if they are consistent. If they are consistent, the consistent text messages are directly used as the target voice recognition result; if they are inconsistent, the two text messages are respectively matched with the instruction information in the preset text information set. If only one text message matches, the successfully matched text information is used as the target voice recognition result. The above method helps to improve the accuracy of off-vehicle voice recognition.

[0025] In an optional implementation, the speech recognition result also carries the confidence level of the recognized text information;

[0026] The method further comprises:

[0027] If it is determined that both of the text information matches the instruction information in the preset text information set, or if both of the text information does not match the instruction information in the preset text information set, the corresponding text information with a higher confidence level is determined as the target speech recognition result.

[0028] In the disclosed embodiment, if both text messages match the instruction information or neither match the instruction information, the confidence levels of the two text messages are compared, and the text message with higher confidence level is used as the target speech recognition result, which helps to improve the accuracy of off-vehicle speech recognition.

[0029] In an optional implementation manner, the method further includes:

[0030] When the speech recognition result provided by one of the two external sound pickup devices is empty, the speech recognition result provided by the other external sound pickup device is used as the target speech recognition result;

[0031] When the voice recognition results provided by the two external sound pickup devices are both empty, it is determined that the target voice recognition result is empty.

[0032] In the embodiment of the present disclosure, if the voice recognition result of one of the external sound pickup devices is empty, the other voice recognition result that is not empty is used as the target voice recognition result; if both voice recognition results are empty, the target voice recognition result is determined to be empty, which helps to improve the accuracy of external voice recognition.

[0033] In an optional implementation, in response to receiving an external voice wake-up instruction, enabling the voice recognition functions of two adjacent first external sound pickup devices corresponding to the initiation position of the external voice wake-up instruction includes:

[0034] In response to multiple external sound pickup devices of the target vehicle receiving the external voice wake-up instruction, determining a target sound zone corresponding to the initiation position of the external voice wake-up instruction; the target sound zone is one of multiple external sound zones corresponding to the target vehicle, and each of the multiple external sound zones corresponds to two adjacent external sound pickup devices;

[0035] The voice recognition functions of two adjacent first external vehicle sound pickup devices corresponding to the target sound zone are enabled.

[0036] In the disclosed embodiment, multiple external sound pickup devices jointly receive the external voice wake-up command, and through the positioning capability of the external sound pickup devices themselves, determine the target sound zone corresponding to the location where the external voice wake-up command is initiated, and enable the voice recognition functions of two adjacent first external sound pickup devices corresponding to the target sound zone, thereby ensuring the filtering of the opposite sound zone and avoiding interference of other sounds generated in the opposite sound zone with the external voice recognition. There is no need to enable the voice recognition functions of multiple external sound pickup devices, thereby reducing the load of the external voice recognition.

[0037] In an optional implementation, the multiple vehicle exterior sound zones include a vehicle left front sound zone, a vehicle right front sound zone, a vehicle left front sound zone, a vehicle right front sound zone, a vehicle left rear sound zone, a vehicle right rear sound zone, a vehicle left rear sound zone, and a vehicle right rear sound zone.

[0038] In the embodiment of the present disclosure, compared with the four-zone division in the related art, the embodiment of the present disclosure further subdivides the sound zones outside the vehicle into eight zones, which helps to improve the accuracy of the recognition of voice outside the vehicle.

[0039] In an optional implementation, the target vehicle is provided with a plurality of external sound pickup devices, and the plurality of external sound pickup devices include a front sound pickup device, a left sound pickup device, a right sound pickup device, and a rear sound pickup device;

[0040] In the case where the target sound zone is the left front sound zone of the vehicle or the left front sound zone of the vehicle, the two adjacent first external vehicle sound pickup devices corresponding to the target sound zone include the front vehicle sound pickup device and the left vehicle sound pickup device;

[0041] In the case where the target sound zone is the right front sound zone of the vehicle or the right front sound zone of the vehicle, the two adjacent first external vehicle sound pickup devices corresponding to the target sound zone include the front vehicle sound pickup device and the right vehicle sound pickup device;

[0042] In the case where the target sound zone is the left rear sound zone of the vehicle or the left rear sound zone of the vehicle, the two adjacent first external vehicle sound pickup devices corresponding to the target sound zone include the left vehicle sound pickup device and the rear vehicle sound pickup device;

[0043] In the case where the target sound zone is the vehicle right rear sound zone or the vehicle rear right sound zone, the two adjacent first vehicle exterior sound pickup devices corresponding to the target sound zone include the vehicle right sound pickup device and the vehicle rear sound pickup device.

[0044] In the disclosed embodiment, by setting the correspondence between the external sound zone and the external sound pickup device, it is helpful to locate the two adjacent first external sound pickup devices that are adapted when receiving the external voice wake-up command, enable the voice recognition function, and help improve the success rate of external voice recognition.

[0045] The present disclosure also provides a vehicle, including a controller, wherein the controller includes:

[0046] a memory for storing machine-readable instructions; and

[0047] A processor is used to call and execute the machine-readable instructions stored in the memory to implement the steps in any possible implementation of the above-mentioned external vehicle speech recognition method.

[0048] An embodiment of the present disclosure also provides an electronic device, including: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps in any possible implementation of the above-mentioned external vehicle voice recognition method are performed.

[0049] The embodiments of the present disclosure also provide a computer program product, on which a computer program is stored. When the computer program is executed by a processor, the steps in any possible implementation of the above-mentioned method for external speech recognition are executed.

[0050] For a description of the effects of the above-mentioned vehicle, electronic device and computer program product, please refer to the description of the above-mentioned external vehicle voice recognition method, which will not be repeated here.

[0051] It should be understood that the above general description and the following detailed description are merely exemplary and explanatory, and are not intended to limit the technical solutions of the present disclosure.

[0052] In order to make the above-mentioned objectives, features and advantages of the present disclosure more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following is a brief introduction to the drawings required for use in the embodiments. The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and are used together with the specification to illustrate the technical solutions of the present disclosure. It should be understood that the following drawings only illustrate certain embodiments of the present disclosure and should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can also be obtained based on these drawings without creative work.

[0054] Figure 1 A flow chart of an off-vehicle speech recognition method provided by an embodiment of the present disclosure is shown;

[0055] Figure 2 A schematic diagram of the distribution of traditional sound zones outside a vehicle is shown;

[0056] Figure 3 A schematic diagram of the distribution of sound zones outside a vehicle provided by an embodiment of the present disclosure is shown;

[0057] Figure 4 A schematic diagram of a process of off-vehicle speech recognition provided by an embodiment of the present disclosure is shown;

[0058] Figure 5 A schematic diagram of an off-vehicle voice recognition device provided by an embodiment of the present disclosure is shown;

[0059] Figure 6 A schematic structural diagram of an electronic device provided by an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0060] In order to make the purpose, technical scheme and advantages of the embodiments of the present disclosure clearer, the technical scheme in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of the embodiments. The components of the embodiments of the present disclosure generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present disclosure provided in the drawings is not intended to limit the scope of the present disclosure for protection, but merely represents the selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present disclosure.

[0061] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0062] The term "and / or" herein only describes an association relationship, indicating that three relationships may exist. For example, A and / or B may represent the following three situations: A exists alone, A and B exist at the same time, and B exists alone. In addition, the term "at least one" herein represents any combination of at least two of any one or more of a plurality of. For example, including at least one of A, B, and C may represent including any one or more elements selected from the set consisting of A, B, and C.

[0063] Research has found that when performing voice recognition, the sound zone and the corresponding sound pickup device will be locked to eliminate sound interference from other locations. This method works better when performing in-car voice recognition. For example, after the main driver's voice zone is awakened, the sound zone will be locked on the main driver's side, and the microphone will only recognize the main driver's speech content, eliminating interference from other locations, and at the same time realize personalized processing based on sound zone positioning. For example, if the main driver says to open the window, only the window corresponding to the main driver's position will be opened. In addition, since the in-car environment is relatively stable, there is no need to consider outputting multiple recognition results, and the microphone closest to the user's position can be used directly to collect the sound.

[0064] However, the use scenarios outside the car are different from the environment for voice recognition inside the car. The position of the user outside the car for voice interaction is often not fixed. The user outside the car can move around the car a little, unlike the user inside the car who often sits in a fixed seat. At this time, due to the mobile state of the user outside the car, this method of locking a certain pickup device may result in the inability to recognize the voice outside the car.

[0065] In general related technologies, a microphone device is set at the front, rear, left and right positions of the vehicle. When performing voice recognition outside the vehicle, the area around the vehicle is divided into four sound zones: front, rear, left and right. Each sound zone corresponds to a microphone device. After the sound zone is locked according to the user's voice position, the microphone in the corresponding sound zone will perform subsequent voice recognition. For example, if the user first says the wake-up word at the front of the vehicle, the sound zone is locked in the front sound zone of the vehicle, and then if the user walks a few steps and says further instructions after reaching the right front position, because the sound zone is locked, only the microphone at the front of the vehicle performs voice recognition, which may cause the microphone to be unable to accurately recognize the user's voice command due to its distance from the user.

[0066] In addition, if the user stands at the junction of two sound zones, it is easy to cause misjudgment of the wake-up sound zone. For example, when waking up, the sound position may be located in front of the vehicle, but the actual user is between the front of the vehicle and the left side of the vehicle, or walking back and forth between the two positions. Because the wake-up positioning drifts at the junction, it is also possible that the user's command cannot be recognized due to the sound zone locking error.

[0067] In addition, there are often other noise interferences in the outside car environment, which often leads to poor outside car voice recognition effect and affects the user's voice interaction experience.

[0068] For example, the microphone at the front of the car is close to the air-conditioning compressor. When the air-conditioning is turned on, the noise is loud, which may cause the microphone recognition at the front of the car to fail. If the user wakes up near the front of the car at this time and only turns on the microphone at the front of the car, the user's commands may not be recognized.

[0069] If it is a basement scenario, when the vehicle is parked in the garage, the microphone at the rear of the vehicle is very close to the wall, making it difficult for the microphone to pick up the voice data of the user outside the vehicle. In addition, due to the closed physical space, the reverberation of the sound is also very large, resulting in poor recognition effect even if the user is awakened near the rear of the vehicle and the microphone at the rear of the vehicle is turned on.

[0070] However, it is not appropriate to turn on all microphones in all sound zones in the scenario of voice interaction outside the car, because: if the user wakes up on the left side, if all microphones are turned on, the sound on the right side of the car may also be picked up, causing interference. In addition, if all microphones are turned on at the same time for voice recognition, the load on the vehicle is relatively large.

[0071] Based on the above research, the present disclosure provides an outdoor voice recognition method. Considering that the outdoor user is often in a moving state when using the outdoor voice function, when performing outdoor voice recognition through two first outdoor sound pickup devices, the user's moving direction outside the vehicle can also be detected, and the target position that the user is about to reach is predicted according to the first voice results and the moving direction of the two first outdoor sound pickup devices, so that the voice recognition function of the two second outdoor sound pickup devices corresponding to the target position can be enabled in advance, so that outdoor sound pickup can be performed in advance, ensuring accurate voice recognition for the outdoor user and improving the user's voice interaction experience.

[0072] To facilitate understanding of this embodiment, a method for out-of-vehicle speech recognition disclosed in an embodiment of the present disclosure is first introduced in detail. The execution subject of the out-of-vehicle speech recognition method provided in the embodiment of the present disclosure is generally a vehicle, and the vehicle includes but is not limited to cars, buses, trucks, and tractors, etc., which are not limited here. The vehicle may include various controllers. For example, the controller may be a vehicle controller, a body domain controller, a cockpit domain controller, an intelligent driving domain controller, etc., which are not specifically limited. Among them, the controller may include a processor and a memory, the memory is used to store machine-readable instructions, and the processor is used to call and execute the machine-readable instructions stored in the memory, so as to implement the out-of-vehicle speech recognition method described in each embodiment of the present disclosure.

[0073] In other embodiments, the execution subject may also be a vehicle-mounted device, and the vehicle-mounted device may be a device including a processor and a memory. The off-vehicle speech recognition method may be implemented by the processor calling computer-readable instructions stored in the memory, which is not limited here. In some embodiments, the method may also be applied to an implementation environment consisting of a vehicle and a server, or to an implementation environment consisting of a vehicle-mounted device and a server. Among them, the server may be an independent physical server, or a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud storage, big data, and artificial intelligence platforms.

[0074] A method for external speech recognition provided by an embodiment of the present disclosure is described below in conjunction with the accompanying drawings.

[0075] See also Figure 1 As shown, it is a flow chart of a method for external speech recognition provided by an embodiment of the present disclosure, such as Figure 1 As shown in , the method for external speech recognition provided by the embodiment of the present disclosure includes steps S101 to S103, wherein:

[0076] S101: In response to receiving an external voice wake-up command, enabling voice recognition functions of two adjacent first external sound pickup devices corresponding to the initiation position of the external voice wake-up command; the voice recognition function refers to a function of performing voice recognition on external voice data other than the external voice wake-up command.

[0077] In this step, the user's outside-vehicle voice wake-up command is first received, and the outside-vehicle voice wake-up command carries a voice wake-up word. The vehicle is provided with multiple outside-vehicle sound pickup devices, and each of the outside-vehicle sound pickup devices is always working to detect whether there is a voice wake-up word, that is, each of the outside-vehicle sound pickup devices can always collect voice, but if it is not awakened (no command to wake up the corresponding sound zone is received), the voice recognition function will not be started.

[0078] After receiving the voice wake-up word and determining that the corresponding external sound zone of the vehicle is awakened, the external sound pickup device will automatically enable the voice recognition function to further recognize the received external voice data.

[0079] Among them, the external sound pickup device can specifically be a microphone, a voice collection array, etc.

[0080] In this way, compared with the method of locating a single sound pickup device, the embodiment of the present disclosure helps to reduce the probability of misjudgment of the sound zone by simultaneously activating two adjacent sound pickup devices outside the vehicle. It also solves the problem of unrecognition caused by noisy environment outside the vehicle, poor parking position, etc., further improves the success rate of outside vehicle voice recognition, and enhances the voice interaction experience of users outside the vehicle.

[0081] Specifically, in response to multiple external sound pickup devices of the target vehicle receiving the external voice wake-up command, a target sound zone corresponding to the location where the external voice wake-up command is initiated is determined; the target sound zone is one of the multiple external sound zones corresponding to the target vehicle, and each of the multiple external sound zones corresponds to two adjacent external sound pickup devices; and the voice recognition function of the two adjacent first external sound pickup devices corresponding to the target sound zone is enabled.

[0082] In the above steps, multiple external sound pickup devices have been collecting sound, so the multiple external sound pickup devices have all received the external voice wake-up command, detected that the external voice wake-up command carries a voice wake-up word, and then based on the voice wake-up word, through the positioning capability of the external sound pickup device itself, directionally identified the target sound zone corresponding to the initiation position of the external voice wake-up command, and the two adjacent first external sound pickup devices corresponding to the target sound zone can automatically enable the voice recognition function.

[0083] When determining the target sound zone corresponding to the initiation position of the vehicle-external voice wake-up command, optionally, the amplitude of the vehicle-external voice wake-up command acquired by each vehicle-external sound pickup device can be determined, and the target sound zone can be determined according to each amplitude. For example: the vehicle-external sound zone corresponding to the vehicle-external sound pickup device with the largest corresponding amplitude is determined as the target sound zone. It can be understood that the larger the corresponding amplitude, the closer the vehicle-external sound zone is to the user.

[0084] Optionally, the transmission time for each of the external sound pickup devices to obtain the external voice wake-up command can be determined, and the target sound zone can be determined according to each of the transmission time. For example, the external sound zone corresponding to the external sound pickup device with the smallest corresponding transmission time is determined as the target sound zone. It can be understood that the smaller the corresponding transmission time, the closer the external sound zone is to the user.

[0085] In this way, multiple external sound pickup devices jointly receive the external voice wake-up command, and through the positioning capability of the external sound pickup device itself, determine the target sound zone corresponding to the location where the external voice wake-up command is initiated, and enable the voice recognition functions of the two adjacent first external sound pickup devices corresponding to the target sound zone, thereby ensuring the filtering of the opposite sound zone and avoiding interference of other sounds generated in the opposite sound zone with the external voice recognition. There is no need to enable the voice recognition functions of multiple external sound pickup devices, thereby reducing the load of the external voice recognition.

[0086] In the related art, most vehicles are provided with four external sound zones, each of which corresponds to an external sound pickup device. Figure 2 , Figure 2 FIG. 1 shows a schematic diagram of a traditional vehicle exterior sound zone distribution. Figure 2 As shown in , a conventional vehicle is provided with a front sound zone, a left sound zone, a right sound zone and a rear sound zone. The front sound zone corresponds to the front sound pickup device, the left sound zone corresponds to the left sound pickup device, the right sound zone corresponds to the right sound pickup device, and the rear sound zone corresponds to the rear sound pickup device.

[0087] In the embodiment of the present disclosure, the sound zone can be further subdivided into eight external sound zones based on the existing four external sound pickup devices.

[0088] For example, please refer to Figure 3 , Figure 3 This is a schematic diagram of the distribution of the external sound zones of a vehicle provided by an embodiment of the present disclosure. Figure 3 As shown in , the multiple exterior sound zones include a left front sound zone, a right front sound zone, a left front sound zone, a right front sound zone, a left rear sound zone, a right rear sound zone, a left rear sound zone, and a right rear sound zone.

[0089] In this way, compared with the four-zone division in the related art, the embodiment of the present disclosure further subdivides the eight external sound zones, which helps to improve the accuracy of external voice recognition.

[0090] See again Figure 3 The target vehicle is provided with a plurality of external sound pickup devices, and the plurality of external sound pickup devices include a front sound pickup device, a left sound pickup device, a right sound pickup device and a rear sound pickup device.

[0091] In actual application, the front sound pickup device shown can be set at the front of the vehicle, the left sound pickup device can be set at the left rearview mirror of the vehicle, the right sound pickup device can be set at the right rearview mirror of the vehicle, and the rear sound pickup device is set on the rear bumper of the vehicle.

[0092] In the case where the target sound zone is the left front sound zone of the vehicle or the left front sound zone of the vehicle, the two adjacent first external vehicle sound pickup devices corresponding to the target sound zone include the front vehicle sound pickup device and the left vehicle sound pickup device;

[0093] In the case where the target sound zone is the right front sound zone of the vehicle or the right front sound zone of the vehicle, the two adjacent first external vehicle sound pickup devices corresponding to the target sound zone include the front vehicle sound pickup device and the right vehicle sound pickup device;

[0094] In the case where the target sound zone is the left rear sound zone of the vehicle or the left rear sound zone of the vehicle, the two adjacent first external vehicle sound pickup devices corresponding to the target sound zone include the left vehicle sound pickup device and the rear vehicle sound pickup device;

[0095] In the case where the target sound zone is the vehicle right rear sound zone or the vehicle rear right sound zone, the two adjacent first vehicle exterior sound pickup devices corresponding to the target sound zone include the vehicle right sound pickup device and the vehicle rear sound pickup device.

[0096] In this way, by setting the correspondence between the external sound zone and the external sound pickup device, it is helpful to locate two adjacent external sound pickup devices that are adapted when an external voice wake-up command is received, enable the voice recognition function, and help improve the success rate of external voice recognition.

[0097] S102: Performing voice recognition outside the vehicle through the two first sound pickup devices outside the vehicle, and detecting the moving direction of the user outside the vehicle.

[0098] In the above steps, the two first external sound pickup devices may receive the external voice data, and perform external voice recognition on the external voice data to obtain the first voice recognition results of the two first external sound pickup devices.

[0099] In this way, the first voice recognition result is determined according to the voice recognition results of the two first external sound pickup devices, which effectively reduces the information interference caused by multi-path recognition and improves the accuracy of external voice recognition.

[0100] Specifically, when performing speech recognition, the external voice data may be recognized by using Automatic Speech Recognition (ASR) technology, thereby obtaining a speech recognition result that matches the external voice data.

[0101] Here, the process of the two first external sound pickup devices performing external voice recognition is similar to the process of the subsequent two second external sound pickup devices performing external voice recognition. Specifically, the first voice recognition result is determined according to the voice recognition results of the two first external sound pickup devices.

[0102] In this step, the speech recognition results of the two first external sound pickup devices may be compared comprehensively from multiple aspects to determine the first target speech recognition result.

[0103] In some possible implementations, voice recognition is performed on the vehicle exterior voice data by using two vehicle exterior sound pickup devices according to the following steps, where the two vehicle exterior sound pickup devices are the two first vehicle exterior sound pickup devices or the two second vehicle exterior sound pickup devices:

[0104] When the voice recognition results provided by the two external sound pickup devices are not empty, comparing whether the text information indicated by the two voice recognition results are consistent; if they are consistent, taking the consistent text information as the target voice recognition result;

[0105] If there is inconsistency, determine whether the two text messages match the instruction information in a preset text information set, and the preset text information set includes multiple commonly used instruction information in off-vehicle usage scenarios; if one of the two text messages matches the instruction information in the preset text information set, the text information that successfully matches will be determined as the target speech recognition result.

[0106] Among them, when the two external sound pickup devices are the two first external sound pickup devices, the target voice recognition result is the first voice recognition result; when the two external sound pickup devices are the two second external sound pickup devices, the target voice recognition result is the second voice recognition result.

[0107] In the above steps, it is first determined whether the voice recognition results provided by the two external sound pickup devices are empty. If the voice recognition results provided by the two external sound pickup devices are not empty, then both voice recognition results indicate that there is recognized text information.

[0108] Then, the text information indicated by the two speech recognition results is compared to see whether they are consistent; if they are consistent, the consistent text information is directly used as the target speech recognition result.

[0109] If they are inconsistent, the two text messages are matched with the instruction information in the preset text message set respectively to determine whether the two text messages match the instruction information in the preset text message set.

[0110] Here, the preset text information set includes a plurality of commonly used command information in the scenario of use outside the vehicle. For example, command information such as "open the window" and "open the door" are command information in the scenario of use outside the vehicle, and therefore are included in the preset text information set. However, command information such as "adjust the steering wheel height" and "play a video" are not command information in the scenario of use outside the vehicle, and therefore are not included in the preset text information set.

[0111] If one of the two text messages matches the instruction information in the preset text information set, and the other text message does not match the instruction information in the preset text information set, the text message that successfully matches is determined as the target speech recognition result.

[0112] It can be understood that since this solution is aimed at out-of-vehicle usage scenarios, it is believed that the credibility of command information in out-of-vehicle usage scenarios is relatively high, that is, the priority of command information in out-of-vehicle usage scenarios is higher than the priority of command information in other usage scenarios, so the text information that is successfully matched is determined as the target voice recognition result.

[0113] In this way, if both voice recognition results are not empty, compare whether the two text information are consistent. If they are consistent, directly use the consistent text information as the target voice recognition result; if they are inconsistent, match the two text information with the instruction information in the preset text information set respectively. If only one text information matches, use the successfully matched text information as the target voice recognition result. The above method helps to improve the accuracy of off-vehicle voice recognition.

[0114] In some other possible implementations, the speech recognition result also carries the confidence level of the recognized text information.

[0115] Here, the confidence level is used to indicate the quality of recognizing the text information. For example, if the confidence level is low, such as 30%, it means that the recognition of the external voice data is relatively vague and can be considered as noise such as ambient sound; if the confidence level is high, such as 95%, it means that the recognition of the external voice data is relatively clear.

[0116] Specifically, if it is determined that both of the text information match the instruction information in the preset text information set, or if both of the text information do not match the instruction information in the preset text information set, the corresponding text information with a higher confidence level will be determined as the target speech recognition result.

[0117] In this step, when it is determined that both of the text messages match the instruction information in the preset text information set, or do not match, considering that the corresponding external vehicle voice data with a higher confidence level is recognized more clearly, the corresponding text information with a higher confidence level is determined as the target voice recognition result.

[0118] In this way, if both text messages match the instruction information or neither matches, the confidence of the two text messages is compared, and the text message with higher confidence is used as the target speech recognition result, which helps to improve the accuracy of off-vehicle speech recognition.

[0119] In other possible implementations, when the speech recognition result provided by one of the two external sound pickup devices is empty, the speech recognition result provided by the other external sound pickup device is used as the target speech recognition result;

[0120] When the voice recognition results provided by the two external sound pickup devices are both empty, it is determined that the target voice recognition result is empty.

[0121] In this way, if the voice recognition result of one of the external sound pickup devices is empty, the other non-empty voice recognition result is used as the target voice recognition result; if both voice recognition results are empty, determining that the target voice recognition result is empty helps to improve the accuracy of external voice recognition.

[0122] When the two first outside-vehicle sound pickup devices are used to perform outside-vehicle voice recognition, the moving direction of the user outside the vehicle can also be detected.

[0123] Optionally, the moving direction of the user outside the vehicle may be determined based on a plurality of continuous images captured by a camera device on the vehicle.

[0124] In this step, multiple images can be continuously captured by a camera device installed on the vehicle, such as a vehicle-mounted camera; then, for each of the multiple continuous images, the user in the image is identified and located by means of a detection algorithm, etc., to determine the position of the user in the image, thereby converting the position of the user in the real scene; then, according to the shooting order of the multiple continuous images, the positions of the user in the real scene corresponding to the two consecutive images are compared respectively, so as to determine the moving direction of the user outside the vehicle.

[0125] The number of images and the shooting frequency of the plurality of continuous images can be set according to actual needs and are not specifically limited here.

[0126] Alternatively, the direction in which the user is moving outside the vehicle may be determined based on a Bluetooth signal broadcast by a Bluetooth key carried by the user.

[0127] In this step, the Bluetooth receiver on the vehicle can measure the signal strength (Received Signal Strength Indicator, RSSI) of the Bluetooth signal broadcast by the Bluetooth key carried by the user; since the Bluetooth key can continuously broadcast the Bluetooth signal, the change trend of the RSSI value over time can be obtained; if the RSSI value increases over time, it usually means that the Bluetooth receiver is approaching the Bluetooth key; if the RSSI value decreases, it means that the Bluetooth receiver is moving away from the Bluetooth key, so that the user's moving direction outside the vehicle can be determined based on the change trend.

[0128] In this way, the direction of movement can be determined by taking multiple consecutive images or by broadcasting Bluetooth signals. In this way, the direction of movement can be determined by relying on the camera equipment installed in the vehicle itself or by relying on the Bluetooth key carried by the user, thereby improving the convenience and speed of determining the direction of movement.

[0129] In other implementations, the moving direction of the user outside the vehicle may also be determined based on a plurality of continuous infrared images collected by an infrared recognition device on the vehicle.

[0130] In this step, since the user radiates heat outward, it can be captured by the infrared recognition device such as an infrared detector. Therefore, each infrared image includes the infrared thermal imaging corresponding to the user, and then the position of the user in each infrared image can be determined, so as to obtain the position of the user in the real scene; then, according to the shooting order of the multiple consecutive infrared images, the positions of the user in the real scene corresponding to the two consecutive infrared images are compared respectively, and the moving direction of the user outside the car can be determined.

[0131] S103: predicting a target location that the user will reach based on the first voice recognition results of the two first external sound pickup devices and the moving direction, and enabling voice recognition functions of two adjacent second external sound pickup devices corresponding to the target location.

[0132] According to the foregoing content, when the voice recognition results provided by the two first external sound pickup devices are both empty, the first voice recognition result is empty; when any of the voice recognition results provided by the two first external sound pickup devices is not empty, the first voice recognition result is not empty.

[0133] Correspondingly, when the first voice recognition result is empty, the target location that the user will reach is predicted mainly based on the moving direction.

[0134] Specifically, if the first voice recognition result is empty, the next sound zone adjacent to the sound zone where the user is currently located is determined according to the moving direction, and the next sound zone is determined as the target position that the user is about to reach.

[0135] Exemplarily, the first voice recognition result is empty. If the sound zone currently located by the user is the right front sound zone of the vehicle, and the moving direction indicates that the user is moving from the position directly in front of the vehicle toward the right front, it can be determined that the next sound zone adjacent to the current sound zone of the user in the moving direction is the right front sound zone of the vehicle, thereby determining the right front sound zone of the vehicle as the target position that the user will reach.

[0136] In this way, when the first voice recognition result is empty, the next sound zone adjacent to the user's current sound zone and located in the moving direction can be determined as the target position according to the moving direction, which helps to ensure the matching of the determined target position and the moving direction.

[0137] Correspondingly, when the first speech recognition result is empty, the moving direction is mainly used. Specifically, if the first speech recognition result is not empty, the target position is determined according to at least one candidate position indicated by the first speech recognition result and the moving direction; the target position belongs to the candidate position.

[0138] Exemplarily, if the first voice recognition result is “open the front door of the car”, the first voice recognition result indicates two candidate positions, namely the left front door position and the right front door position of the car, and the moving direction indicates that the user moves from the position directly in front of the car to the right front, so that the target position can be determined to be the right front door position of the car.

[0139] In this way, when the first speech recognition result is not empty, at least one candidate position indicated by the first speech recognition result can be obtained. On this basis, combined with the moving direction, the candidate position in the at least one candidate position located in the moving direction can be determined as the target position, which helps to ensure the matching of the determined target position with the first speech structure and the moving direction.

[0140] When the target position is determined, the voice recognition functions of two adjacent second external sound pickup devices corresponding to the target position may be enabled.

[0141] Here, the two second exterior sound pickup devices may include the same exterior sound pickup devices as the two first exterior sound pickup devices, or may not include the same exterior sound pickup devices as the two first exterior sound pickup devices.

[0142] Exemplarily, if the target sound zone corresponding to the initiation position of the outside-vehicle voice wake-up command is the right rear sound zone of the vehicle, and the target position is the right rear sound zone of the vehicle, then the right rear sound zone of the vehicle or the two adjacent outside-vehicle sound pickup devices corresponding to the right rear sound zone of the vehicle are the same, that is, the two second outside-vehicle sound pickup identifications are the same as the two first outside-vehicle sound pickup devices, both of which are the right rear sound pickup device and the rear sound pickup device of the vehicle.

[0143] S104: Obtaining second voice recognition results of the two second external-vehicle sound pickup devices performing external-vehicle voice recognition.

[0144] Here, the step of determining the second voice result is similar to the step of determining the first voice result mentioned above. The specific description refers to the above embodiment and will not be repeated here.

[0145] Exemplarily, the first voice recognition result is "open the front door of the car", and the moving direction indicates that the user is moving from the position directly in front of the car to the right front, then the target position can be determined to be the position of the right front door of the car, thereby enabling the voice recognition function of the two adjacent second external sound pickup devices corresponding to the right front sound zone of the car. After the user moves to the right front sound zone of the car, he says "turn on the air conditioner", and the external voice data is picked up by the two adjacent second external sound pickup devices corresponding to the right front sound zone of the car, thereby determining the second voice recognition result.

[0146] In order to clearly illustrate the process of performing vehicle-external voice recognition by two vehicle-external voice pickup devices (the two first vehicle-external voice pickup devices or the two second vehicle-external voice pickup devices) and obtaining the target voice recognition results (the first voice recognition results or the second voice recognition results) of the two vehicle-external voice pickup devices, reference may be made to Figure 4 , Figure 4 A schematic diagram of a process for determining a target speech recognition result provided by an embodiment of the present disclosure. Figure 4 As shown in , the two external sound pickup devices receive the external voice data, and perform voice recognition on the external voice data to obtain the voice recognition results of the two external sound pickup devices.

[0147] First, determine whether the voice recognition results provided by the two external sound pickup devices are empty. In the case that the voice recognition result provided by one of the two external sound pickup devices is empty, the voice recognition result provided by the other external sound pickup device is used as the target voice recognition result. In the case that the voice recognition results provided by the two external sound pickup devices are both empty, determine that the target voice recognition result is empty. If the voice recognition results provided by the two external sound pickup devices are not empty, compare whether the text information indicated by the two voice recognition results is consistent.

[0148] If they are consistent, the consistent text information is directly used as the target speech recognition result. If they are inconsistent, it is determined whether the two text information match the instruction information in the preset text information set.

[0149] If only one text message matches, the successfully matched text message is used as the target speech recognition result. If both text messages match the instruction information or neither of them matches, the corresponding text message with a higher confidence level is determined as the target speech recognition result. The description of the specific steps can be found in the above embodiments, which will not be repeated here.

[0150] In some possible implementations, the target speech recognition result is given to a natural language understanding module and a dialogue management module on the target vehicle for execution.

[0151] Specifically, after determining the target speech recognition result (the first speech recognition result or the second speech recognition result), the method further includes:

[0152] Processing the target speech recognition result through a natural language understanding module to obtain semantic information corresponding to the target speech recognition result;

[0153] Processing the semantic information through a dialogue management module to obtain a vehicle control strategy, wherein the vehicle control strategy is used to provide feedback on the external voice data;

[0154] The vehicle control strategy is executed.

[0155] Among them, the natural language understanding (NLU) module is used to perform speech understanding on the target speech recognition result, convert the text information indicated by the target speech recognition result into a semantic representation that can be understood by the target vehicle, and obtain semantic information corresponding to the target speech recognition result.

[0156] The Dialogue Management (DM) module is used to determine what action should be taken to provide feedback on the external voice data based on the semantic information, thereby obtaining a vehicle control strategy.

[0157] For example, if the text information indicated by the target voice recognition result is "open the window", the vehicle control strategy is to open the window. If the target voice recognition result is empty, the vehicle control strategy is to play a prompt voice outside the vehicle, such as "I'm sorry I didn't hear it clearly, please say it again" to prompt the user to give the command again.

[0158] Optionally, the dialogue management module may also determine the vehicle control strategy based on the semantic information and the confidence level of the text information indicated by the target speech recognition result.

[0159] For example, a confidence threshold can be obtained and compared with the confidence threshold and the confidence carried by the target speech recognition result; if the confidence carried by the target speech recognition result is greater than or equal to the confidence threshold, the corresponding vehicle control strategy is generated according to the semantic information; if the confidence carried by the target speech recognition result is less than the confidence threshold, the vehicle control strategy is generated according to the situation where the target speech recognition result is empty.

[0160] Here, when the confidence level carried by the target speech recognition result is greater than or equal to the confidence threshold, it means that the target speech recognition result has a high credibility, and therefore it can be executed according to the semantic information; when the confidence level carried by the target speech recognition result is less than the confidence threshold, it means that the target speech recognition result has a low credibility, and therefore it is not executed according to the semantic information.

[0161] The method for external voice recognition provided by the embodiment of the present disclosure can, based on the external voice wake-up command, enable the voice recognition function for two adjacent first external voice pickup devices corresponding to the location where the external voice wake-up command is initiated at the same time, perform external voice recognition through the two first external voice pickup devices, detect the voice direction of the user outside the vehicle, and then predict the target location that the user is about to reach based on the first voice recognition result and the moving direction, thereby enabling the voice recognition function for two adjacent second external voice pickup devices corresponding to the target location at the same time, so as to obtain the second voice recognition result of the external voice recognition performed by the two second external voice pickup devices. In this way, considering that the external user is often in a moving state when using the external voice function Therefore, when performing outside-vehicle voice recognition through the two first outside-vehicle sound pickup devices, the user's moving direction outside the vehicle can also be detected, and the target position that the user will reach can be predicted according to the first voice results and the moving direction of the two first outside-vehicle sound pickup devices, so that the voice recognition function of the two second outside-vehicle sound pickup devices corresponding to the target position can be enabled in advance, so that the outside-vehicle sound pickup can be performed in advance, and accurate voice recognition for the user outside the vehicle is guaranteed, thereby improving the user's voice interaction experience; in addition, since only two adjacent outside-vehicle sound pickup devices are enabled, filtering of the opposite sound zone is guaranteed, avoiding interference of other sounds generated in the opposite sound zone with the outside-vehicle voice recognition, and reducing the load of the outside-vehicle voice recognition.

[0162] Those skilled in the art will appreciate that, in the above method of specific implementation, the order in which the steps are written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of the steps should be determined by their functions and possible internal logic.

[0163] Based on the same inventive concept, an out-of-vehicle voice recognition device corresponding to the out-of-vehicle voice recognition method is also provided in the embodiment of the present disclosure. Since the principle of solving the problem by the out-of-vehicle voice recognition device in the embodiment of the present disclosure is similar to the above-mentioned out-of-vehicle voice recognition method in the embodiment of the present disclosure, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0164] See also Figure 5 , Figure 5 Schematic diagram of an off-vehicle voice recognition device provided by an embodiment of the present disclosure. Figure 5 As shown in , the vehicle exterior speech recognition device 500 provided by the embodiment of the present disclosure includes:

[0165] The first device positioning module 510 is used to enable the voice recognition function of two adjacent first external sound pickup devices corresponding to the initiation position of the external voice wake-up command in response to receiving the external voice wake-up command; the voice recognition function refers to the function of performing voice recognition on external voice data other than the external voice wake-up command;

[0166] A direction detection module 520, configured to perform voice recognition outside the vehicle through the two first sound pickup devices outside the vehicle, and detect the moving direction of the user outside the vehicle;

[0167] The second device positioning module 530 is used to predict the target location that the user will reach based on the first voice recognition results of the two first external sound pickup devices and the moving direction, and enable the voice recognition functions of the two adjacent second external sound pickup devices corresponding to the target location;

[0168] The recognition result determination module 540 is used to obtain the second speech recognition results of the two second external-vehicle sound pickup devices performing external-vehicle speech recognition.

[0169] In an optional implementation manner, when the second device positioning module 530 is used to predict the target location that the user will reach based on the first voice recognition results of the two first external sound pickup devices and the moving direction, it is specifically used to:

[0170] If the first voice recognition result is empty, determine the next sound zone adjacent to the current sound zone of the user according to the moving direction, and determine the next sound zone as the target position that the user will reach.

[0171] In an optional implementation manner, when the second device positioning module 530 is used to predict the target location that the user will reach based on the first voice recognition results of the two first external sound pickup devices and the moving direction, it is specifically used to:

[0172] If the first speech recognition result is not empty, the target position is determined according to at least one candidate position indicated by the first speech recognition result and the moving direction; the target position belongs to the candidate position.

[0173] In an optional implementation manner, when the direction detection module 520 is used to detect the moving direction of the user outside the vehicle, it is specifically used to:

[0174] Determine the moving direction of the user outside the vehicle based on multiple continuous images taken by a camera device on the vehicle; or,

[0175] The user's moving direction outside the car is determined based on the Bluetooth signal broadcast by the Bluetooth key carried by the user.

[0176] In an optional implementation manner, the direction detection module 520 or the recognition result determination module 540 performs voice recognition on the vehicle exterior voice data through two vehicle exterior sound pickup devices according to the following steps, where the two vehicle exterior sound pickup devices are the two first vehicle exterior sound pickup devices or the two second vehicle exterior sound pickup devices:

[0177] When the voice recognition results provided by the two external sound pickup devices are not empty, comparing whether the text information indicated by the two voice recognition results are consistent; if they are consistent, taking the consistent text information as the target voice recognition result;

[0178] If there is inconsistency, determine whether the two text messages match the instruction information in a preset text information set, and the preset text information set includes multiple commonly used instruction information in off-vehicle usage scenarios; if one of the two text messages matches the instruction information in the preset text information set, the text information that successfully matches will be determined as the target speech recognition result.

[0179] In an optional implementation, the speech recognition result also carries the confidence level of the recognized text information;

[0180] The direction detection module 520 or the recognition result determination module 540 is further used for:

[0181] If it is determined that both of the text information matches the instruction information in the preset text information set, or if both of the text information does not match the instruction information in the preset text information set, the corresponding text information with a higher confidence level is determined as the target speech recognition result.

[0182] In an optional implementation manner, the direction detection module 520 or the recognition result determination module 540 is further configured to:

[0183] When the speech recognition result provided by one of the two external sound pickup devices is empty, the speech recognition result provided by the other external sound pickup device is used as the target speech recognition result;

[0184] When the voice recognition results provided by the two external sound pickup devices are both empty, it is determined that the target voice recognition result is empty.

[0185] In an optional implementation manner, the first sound pickup device positioning module 510 is specifically used to:

[0186] In response to multiple external sound pickup devices of the target vehicle receiving the external voice wake-up instruction, determining a target sound zone corresponding to the initiation position of the external voice wake-up instruction; the target sound zone is one of multiple external sound zones corresponding to the target vehicle, and each of the multiple external sound zones corresponds to two adjacent external sound pickup devices;

[0187] The voice recognition functions of two adjacent first external vehicle sound pickup devices corresponding to the target sound zone are enabled.

[0188] In an optional implementation, the multiple vehicle exterior sound zones include a vehicle left front sound zone, a vehicle right front sound zone, a vehicle left front sound zone, a vehicle right front sound zone, a vehicle left rear sound zone, a vehicle right rear sound zone, a vehicle left rear sound zone, and a vehicle right rear sound zone.

[0189] In an optional implementation, the target vehicle is provided with a plurality of external sound pickup devices, and the plurality of external sound pickup devices include a front sound pickup device, a left sound pickup device, a right sound pickup device, and a rear sound pickup device;

[0190] In the case where the target sound zone is the left front sound zone of the vehicle or the left front sound zone of the vehicle, the two adjacent first external vehicle sound pickup devices corresponding to the target sound zone include the front vehicle sound pickup device and the left vehicle sound pickup device;

[0191] In the case where the target sound zone is the right front sound zone of the vehicle or the right front sound zone of the vehicle, the two adjacent first external vehicle sound pickup devices corresponding to the target sound zone include the front vehicle sound pickup device and the right vehicle sound pickup device;

[0192] In the case where the target sound zone is the left rear sound zone of the vehicle or the left rear sound zone of the vehicle, the two adjacent first external vehicle sound pickup devices corresponding to the target sound zone include the left vehicle sound pickup device and the rear vehicle sound pickup device;

[0193] In the case where the target sound zone is the vehicle right rear sound zone or the vehicle rear right sound zone, the two adjacent first vehicle exterior sound pickup devices corresponding to the target sound zone include the vehicle right sound pickup device and the vehicle rear sound pickup device.

[0194] For descriptions of the processing flow of each module in the device and the interaction flow between each module, reference may be made to the relevant descriptions in the above method embodiment, which will not be described in detail here.

[0195] The vehicle-external voice recognition device provided by the embodiment of the present disclosure can, based on the vehicle-external wake-up voice command, simultaneously enable the voice recognition function for two adjacent first vehicle-external sound pickup devices corresponding to the location where the vehicle-external voice wake-up command is initiated, perform vehicle-external voice recognition through the two first vehicle-external sound pickup devices, and detect the voice direction of the user outside the vehicle, and then predict the target location that the user is about to reach based on the first voice recognition result and the moving direction, thereby simultaneously enabling the voice recognition function for two adjacent second vehicle-external sound pickup devices corresponding to the target location, so as to obtain the second voice recognition result of the two second vehicle-external sound pickup devices performing vehicle-external voice recognition. In this way, considering that the vehicle-external user is often in a moving state when using the vehicle-external voice function Therefore, when performing outside-vehicle voice recognition through the two first outside-vehicle sound pickup devices, the user's moving direction outside the vehicle can also be detected, and the target position that the user will reach can be predicted according to the first voice results and the moving direction of the two first outside-vehicle sound pickup devices, so that the voice recognition function of the two second outside-vehicle sound pickup devices corresponding to the target position can be enabled in advance, so that the outside-vehicle sound pickup can be performed in advance, and accurate voice recognition for the user outside the vehicle is guaranteed, thereby improving the user's voice interaction experience; in addition, since only two adjacent outside-vehicle sound pickup devices are enabled, filtering of the opposite sound zone is guaranteed, avoiding interference of other sounds generated in the opposite sound zone with the outside-vehicle voice recognition, and reducing the load of the outside-vehicle voice recognition.

[0196] The embodiment of the present disclosure also provides a vehicle, including a controller, the controller including: a memory for storing machine-readable instructions; and a processor for calling and executing the machine-readable instructions stored in the memory to implement the steps of the vehicle-external voice recognition method as described in the above method embodiment. The vehicle may be a vehicle provided with multiple vehicle-external sound zones and multiple vehicle-external sound pickup devices.

[0197] Corresponds to Figure 1 The embodiment of the present disclosure also provides an electronic device 600, such as Figure 6FIG. 6 is a schematic diagram of the structure of an electronic device 600 provided in an embodiment of the present disclosure, including:

[0198] Processor 610, memory 620, and bus 630. The memory 620 is used to store execution instructions, including internal memory 621 and external memory 622; the internal memory 621 is also called internal memory, which is used to temporarily store the operation data in the processor 610 and the data exchanged with the external memory 622 such as a hard disk. The processor 610 exchanges data with the external memory 622 through the internal memory 621.

[0199] In the embodiment of the present application, the memory 620 is specifically used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 610. That is, when the electronic device 600 is running, the processor 610 communicates with the memory 620 through the bus 630, so that the processor 1010 executes the application code stored in the memory 620, and then executes the steps of the vehicle-external voice recognition method described in any of the aforementioned embodiments.

[0200] Among them, the memory 620 can be, but is not limited to, random access memory (Random Access Memory, RAM), read only memory (Read Only Memory, ROM), programmable read-only memory (Programmable Read-Only Memory, PROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, EPROM), electrically erasable read-only memory (Electric Erasable Programmable Read-Only Memory, EEPROM), etc.

[0201] The processor 610 may be an integrated circuit chip with signal processing capabilities. The above-mentioned processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The disclosed methods, steps and logic block diagrams in the embodiments of the present invention may be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0202] It is to be understood that the structure illustrated in the embodiment of the present application does not constitute a specific limitation on the electronic device 600. In other embodiments of the present application, the electronic device 600 may include more or fewer components than shown in the figure, or combine some components, or split some components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0203] The embodiment of the present disclosure also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the vehicle-external speech recognition method described in the above method embodiment are executed. The storage medium can be a volatile or non-volatile computer-readable storage medium.

[0204] In addition, an embodiment of the present disclosure also provides a computer program product, which stores a computer program. When the computer program is executed by a processor, the steps of the outdoor speech recognition method provided by any of the above embodiments of the present disclosure are executed. For details, please refer to the above method embodiments, which will not be repeated here.

[0205] The computer program product may be implemented in hardware, software or a combination thereof. In an optional embodiment, the computer program product is embodied as a computer storage medium, which may be a volatile or non-volatile computer-readable storage medium. In another optional embodiment, the computer program product is embodied as a software product, such as a software development kit (SDK) and the like.

[0206] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the above-described equipment and devices can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. In the several embodiments provided in the present disclosure, it should be understood that the disclosed equipment, devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0207] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0208] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0209] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present disclosure, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0210] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present disclosure, which are used to illustrate the technical solutions of the present disclosure, rather than to limit them. The protection scope of the present disclosure is not limited thereto. Although the present disclosure is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed in the present disclosure, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A method for external speech recognition, characterized in that: The method comprises: In response to receiving an external voice wake-up command, enabling the voice recognition functions of two adjacent first external sound pickup devices corresponding to the initiation position of the external voice wake-up command; the voice recognition function refers to a function of performing voice recognition on external voice data other than the external voice wake-up command; Performing voice recognition outside the vehicle through the two first sound pickup devices outside the vehicle, and detecting the moving direction of the user outside the vehicle; Predicting a target location that the user will reach based on the first voice recognition results of the two first external sound pickup devices and the moving direction, and enabling voice recognition functions of two adjacent second external sound pickup devices corresponding to the target location; The second voice recognition results of the two second external-vehicle sound pickup devices performing external-vehicle voice recognition are obtained.

2. The method according to claim 1, characterized in that The predicting the target location that the user will reach according to the first voice recognition results of the two first external sound pickup devices and the moving direction includes: If the first voice recognition result is empty, determine the next sound zone adjacent to the current sound zone of the user according to the moving direction, and determine the next sound zone as the target position that the user will reach.

3. The method according to claim 1, characterized in that The predicting the target location that the user will reach according to the first voice recognition results of the two first external sound pickup devices and the moving direction includes: If the first speech recognition result is not empty, the target position is determined according to at least one candidate position indicated by the first speech recognition result and the moving direction; the target position belongs to the candidate position.

4. The method according to claim 1, characterized in that: The detecting the moving direction of the user outside the vehicle includes: Determine the moving direction of the user outside the vehicle based on multiple continuous images taken by a camera device on the vehicle; or, The user's moving direction outside the car is determined based on the Bluetooth signal broadcast by the Bluetooth key carried by the user.

5. The method according to claim 1, characterized in that According to the following steps, voice recognition is performed on the external voice data by using two external voice pickup devices, where the two external voice pickup devices are the two first external voice pickup devices or the two second external voice pickup devices: When the voice recognition results provided by the two external sound pickup devices are not empty, comparing whether the text information indicated by the two voice recognition results are consistent; If they are consistent, the consistent text information is used as the target speech recognition result; If there is inconsistency, determine whether the two text messages match the instruction information in a preset text information set, and the preset text information set includes multiple commonly used instruction information in off-vehicle usage scenarios; if one of the two text messages matches the instruction information in the preset text information set, the text information that successfully matches will be determined as the target speech recognition result.

6. The method according to claim 5, characterized in that The speech recognition result also carries the confidence level of the recognized text information; The method further comprises: If it is determined that both of the text information matches the instruction information in the preset text information set, or if both of the text information does not match the instruction information in the preset text information set, the corresponding text information with a higher confidence level is determined as the target speech recognition result.

7. The method according to claim 5, characterized in that The method further comprises: When the speech recognition result provided by one of the two external sound pickup devices is empty, the speech recognition result provided by the other external sound pickup device is used as the target speech recognition result; When the voice recognition results provided by the two external sound pickup devices are both empty, it is determined that the target voice recognition result is empty.

8. The method according to claim 1, characterized in that In response to receiving the vehicle-external voice wake-up instruction, enabling the voice recognition functions of two adjacent first vehicle-external sound pickup devices corresponding to the initiation position of the vehicle-external voice wake-up instruction includes: In response to multiple external sound pickup devices of the target vehicle receiving the external voice wake-up instruction, determining a target sound zone corresponding to the initiation position of the external voice wake-up instruction; the target sound zone is one of multiple external sound zones corresponding to the target vehicle, and each of the multiple external sound zones corresponds to two adjacent external sound pickup devices; The voice recognition functions of two adjacent first external vehicle sound pickup devices corresponding to the target sound zone are enabled.

9. The method according to claim 8, characterized in that The multiple vehicle exterior sound zones include a vehicle left front sound zone, a vehicle right front sound zone, a vehicle front left sound zone, a vehicle front right sound zone, a vehicle rear left sound zone, a vehicle rear right sound zone, a vehicle rear left sound zone, and a vehicle rear right sound zone.

10. The method according to claim 9, characterized in that The target vehicle is provided with a plurality of external sound pickup devices, wherein the plurality of external sound pickup devices include a front sound pickup device, a left sound pickup device, a right sound pickup device and a rear sound pickup device; In the case where the target sound zone is the left front sound zone of the vehicle or the left front sound zone of the vehicle, the two adjacent first external vehicle sound pickup devices corresponding to the target sound zone include the front vehicle sound pickup device and the left vehicle sound pickup device; In the case where the target sound zone is the right front sound zone of the vehicle or the right front sound zone of the vehicle, the two adjacent first external vehicle sound pickup devices corresponding to the target sound zone include the front vehicle sound pickup device and the right vehicle sound pickup device; In the case where the target sound zone is the left rear sound zone of the vehicle or the left rear sound zone of the vehicle, the two adjacent first external vehicle sound pickup devices corresponding to the target sound zone include the left vehicle sound pickup device and the rear vehicle sound pickup device; In the case where the target sound zone is the vehicle right rear sound zone or the vehicle rear right sound zone, the two adjacent first vehicle exterior sound pickup devices corresponding to the target sound zone include the vehicle right sound pickup device and the vehicle rear sound pickup device.

11. A vehicle, characterized in that: A controller is included, the controller comprising: a memory for storing machine-readable instructions; and A processor is used to call and execute the machine-readable instructions stored in the memory to implement the steps of the external vehicle speech recognition method as described in any one of claims 1 to 10.

12. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the method for external vehicle speech recognition as described in any one of claims 1 to 10 are performed.

13. A computer program product, characterized in that The computer program product stores a computer program, and when the computer program is executed by a processor, the steps of the method for external vehicle speech recognition as claimed in any one of claims 1 to 10 are executed.

Images