Audio acquisition device state identification method and device, vehicle and storage medium

Abstract

The invention provides an audio acquisition device state recognition method and device, a vehicle and a storage medium, and the method comprises the steps: receiving a voice instruction from a target detection position outside the vehicle; in response to the voice instruction, acquiring corresponding audio data based on N audio acquisition devices outside the vehicle; determining first audio difference information and a first audio acquisition device based on the audio data acquired by N audio acquisition devices outside the vehicle and the calibrated audio data of each audio acquisition device; determining second audio difference information according to the first audio data acquired by the first audio acquisition device and the second audio data acquired by the M second audio acquisition devices; and determining the working state of the first audio acquisition device according to the second audio difference information.

Description

Technical Field

[0001] The present disclosure relates to the field of information processing technology, and in particular to a method, device, vehicle and storage medium for identifying the state of an audio acquisition device. Background Art

[0002] In vehicles that support outdoor voice recognition, microphones are usually required to be installed around the outside of the vehicle to ensure that voice commands issued by users outside the vehicle can be received at any location around the vehicle.

[0003] In order to ensure good sound reception performance of the external microphone, the sound receiving hole of the external microphone is usually facing outwards. Therefore, the external microphone is easily blocked by foreign objects or fails, resulting in reduced sound reception performance of the external microphone. If the user fails to find the abnormality of the external microphone in time, it is easy to affect the user's car experience. Summary of the invention

[0004] The embodiments of the present disclosure at least provide a method, device, vehicle and storage medium for identifying the state of an audio collection device.

[0005] In a first aspect, an embodiment of the present disclosure provides a method for identifying a state of an audio acquisition device, comprising:

[0006] receiving a voice command from an object detection location outside the vehicle;

[0007] In response to the voice command, collecting corresponding audio data based on N audio collection devices outside the vehicle;

[0008] Based on the audio data collected by the N audio collection devices outside the vehicle and the calibrated audio data of each audio collection device, first audio difference information and a first audio collection device are determined; the first audio collection device is determined based on the first audio difference information and the target detection position; the calibrated audio data corresponds to the target position range where the target detection position is located;

[0009] Determine second audio difference information according to first audio data collected by the first audio collection device and second audio data collected by M second audio collection devices; the M second audio collection devices are determined according to the first audio collection device and the target detection position; the second audio difference information is audio difference information between the first audio collection device and the second audio collection device;

[0010] The working state of the first audio collection device is determined according to the second audio difference information.

[0011] In the above-mentioned audio collection device state recognition method, by comparing the difference between the audio data received by each audio collection device and the corresponding calibrated audio data, the first audio collection device with an abnormal state can be preliminarily determined; for the first audio collection device with an abnormal state preliminarily determined, by further comparing the difference between the first audio data collected by the first audio collection device and the second audio data collected by the second audio collection device, it can be further determined whether the first audio collection device is abnormal. Through the above-mentioned two audio collection device state recognition processes, the accuracy of the audio collection device state recognition result is improved.

[0012] In an optional implementation, the audio data includes: volume information and / or audio content corresponding to the voice command;

[0013] In the case where the audio data includes the volume information, the first audio difference information and the second audio difference information include a volume difference value;

[0014] In the case that the audio data includes the audio content, the first audio difference information and the second audio difference information include audio content difference degrees, and the audio content difference degrees are determined based on an edit distance or a semantic similarity between different audio contents.

[0015] In the above implementation, according to the difference in volume information and / or audio content, the working state of the first audio collection device in terms of volume and / or audio content can be determined more specifically, thereby improving the accuracy of the audio collection device state recognition result.

[0016] In an optional implementation manner, before the corresponding audio data is collected by the N audio collection devices outside the vehicle, the method further includes:

[0017] Based on the target detection position, the N audio collection devices for audio data collection are determined from the L audio collection devices; wherein N is less than L, and the distance between the N audio collection devices and the target detection position is less than a first distance.

[0018] In the above implementation, considering that under normal circumstances, the farther the audio collection device is from the target detection position, the less accurate the audio data received is and the more susceptible it is to the influence of other noises, here, by selecting N audio collection devices whose distance from the target detection position is less than the first distance, the interference of the abnormal state of the audio collection device caused by the distance or environmental factors on the state recognition result of the audio collection device can be eliminated, thereby improving the accuracy of the state recognition result of the audio collection device.

[0019] In an optional implementation manner, before determining the second audio difference information, the method further includes:

[0020] The M second audio collection devices are determined according to the positional relationship between the first audio collection device and each second audio collection device; and the M second audio collection devices satisfy a preset positional relationship with the first audio collection device.

[0021] In the above implementation, by determining M second audio collection devices that satisfy a preset position relationship with the first audio collection device, the first audio data collected by the first audio collection device can be compared with the second audio data collected by the M second audio collection devices at the preset positions, thereby achieving targeted comparison, and eliminating the interference of the abnormal state of the audio collection device caused by the position of the audio collection device on the audio collection device state recognition result, thereby improving the accuracy of the audio collection device state recognition result.

[0022] In an optional implementation manner, determining the first audio difference information and the first audio collection device based on the audio data received by the N audio collection devices outside the vehicle and the calibrated audio data of each audio collection device includes:

[0023] Determine the first audio difference information based on the audio data received by the N audio collection devices outside the vehicle and the calibrated audio data of each audio collection device; the first audio difference information is the audio difference information between the audio data received by the audio collection device and the calibrated audio data of the audio collection device corresponding to the target detection position;

[0024] Based on the first audio difference information and a first difference threshold, the first audio collection device is determined from the N audio collection devices.

[0025] In the above implementation, by comparing the audio data received by each audio acquisition device with the calibrated audio data corresponding to the audio acquisition device, the audio acquisition device whose first audio difference information (such as volume difference) exceeds the first difference threshold can be screened out, so that the first audio acquisition device with an abnormal status can be preliminarily and quickly located.

[0026] In an optional implementation, determining the first audio collection device from the N audio collection devices based on the first audio difference information and a first difference threshold includes:

[0027] Determine a candidate audio collection device based on the first audio difference information respectively corresponding to the N audio collection devices and the first difference threshold; the first audio difference information corresponding to the candidate audio collection device is greater than the first difference threshold;

[0028] If, after the user issues voice commands multiple times, the number of times that the first audio difference information corresponding to the candidate audio collection device is greater than the first difference threshold exceeds a first set number threshold, the candidate audio collection device is determined to be the first audio collection device; and the voice commands issued multiple times are issued at the same target detection position, or are issued at different target detection positions.

[0029] In the above implementation, by determining that the candidate audio collection device is the first audio collection device after the user issues voice commands multiple times, the interference of accidental abnormal state of the audio collection device caused by the user or environmental factors on the audio collection device state recognition result can be eliminated, thereby improving the accuracy of the audio collection device state recognition result.

[0030] In an optional implementation manner, determining the working state of the first audio collection device according to the second audio difference information includes:

[0031] determining third audio difference information according to the second audio difference information and calibrated audio difference information between the first audio collection device and the second audio collection device corresponding to the target detection position;

[0032] Based on the third audio difference information and the second difference threshold, the working state of the first audio collecting device is determined.

[0033] In the above implementation, on the basis of determining the first audio collection device, by further comparing the difference between the audio difference information between the audio collection devices and the calibrated audio difference information, it is possible to further determine whether the first audio collection device is abnormal, thereby improving the confidence level of the abnormal state of the first audio collection device.

[0034] In an optional implementation manner, determining the working state of the first audio acquisition device based on the third audio difference information and the second difference threshold includes:

[0035] determining, according to the distances between each of the plurality of second audio collection devices and the first audio collection device, weights of the third audio difference information respectively corresponding to each of the second audio collection devices;

[0036] Determine a third audio difference comprehensive value according to each of the third audio difference information and the corresponding weight;

[0037] The working state of the first audio collection device is determined according to the third audio difference comprehensive value and the second difference threshold.

[0038] In the above implementation, the greater the distance between the second audio collection device and the first audio collection device, the smaller the weight of the third audio difference information corresponding to the second audio collection device can be, that is, the smaller the impact on the working state recognition result of the first audio collection device may be. The third audio difference comprehensive value determined by each piece of third audio difference information and the corresponding weight can more accurately determine the working state of the first audio collection device.

[0039] In an optional implementation manner, the number of the second audio collection devices is multiple;

[0040] The determining the working state of the first audio acquisition device based on the third audio difference information and the second difference threshold includes:

[0041] For each of the second audio collection devices, determining, based on the third audio difference information and the second difference threshold, whether the third audio difference information corresponding to the second audio collection device is greater than the second difference threshold;

[0042] If the number of second audio collection devices corresponding to the third audio difference information being greater than the second difference threshold is greater than a set number threshold, it is determined that the working state of the first audio collection device is abnormal.

[0043] In the above implementation manner, when there is a difference between the first audio difference information and the calibrated audio difference information between the plurality of second audio collection devices and the first audio collection device, it is determined that the state of the first audio collection device is abnormal, which can improve the confidence of the abnormal state of the first audio collection device, and further improve the accuracy of the audio collection device state recognition result.

[0044] In an optional implementation manner, determining the working state of the first audio acquisition device based on the third audio difference information and the second difference threshold includes:

[0045] If, after the user issues voice commands multiple times, the number of times that the third audio difference information corresponding to the first audio collection device is greater than the second difference threshold exceeds the second set number threshold, it is determined that the working state of the first audio collection device is abnormal; the voice commands issued multiple times are issued at the same target detection position, or are issued at different target detection positions.

[0046] In the above implementation, by determining that the first audio collection device has an abnormal state after the user issues voice commands multiple times, the interference of accidental abnormal state of the audio collection device caused by user or environmental factors on the audio collection device state recognition result can be further eliminated, thereby improving the accuracy of the audio collection device state recognition result.

[0047] In an optional implementation manner, determining the working state of the first audio collection device according to the second audio difference information includes:

[0048] The working state of the first audio collecting device is determined according to the first audio difference information and the second audio difference information.

[0049] In the above implementation, based on the first audio difference information and the second audio difference information, the working state of the first audio acquisition device can be determined from the difference between the audio data received by each audio acquisition device and the corresponding calibration audio data, and the difference between the first audio data collected by the first audio acquisition device and the second audio data collected by the second audio acquisition device. This can improve the accuracy of the audio acquisition device state recognition result.

[0050] In an optional implementation manner, determining the working state of the first audio acquisition device according to the first audio difference information and the second audio difference information includes:

[0051] determining third audio difference information according to the second audio difference information and calibrated audio difference information between the first audio collection device and the second audio collection device corresponding to the target detection position;

[0052] If the third audio difference information is greater than a third difference threshold, determining that the working state of the first audio acquisition device is abnormal;

[0053] If the third audio difference information is smaller than the third difference threshold, but the third audio difference information is larger than the fourth difference threshold, and the first audio difference information is larger than the fifth difference threshold, it is determined that the working state of the first audio collection device is abnormal; and the fifth difference threshold is larger than the first difference threshold used when determining the first audio collection device.

[0054] In the above implementation manner, in the further state recognition process, when the difference between the audio difference information between the audio collection devices and the calibration audio difference information, that is, the third audio difference information is large (larger than the third difference threshold), it is determined that the working state of the first audio collection device is abnormal. Alternatively, in the further state recognition process, although the third audio difference information is small (smaller than the third difference threshold and larger than the fourth difference threshold), in the preliminary state recognition process, when the first audio difference information is large (larger than the fifth difference threshold), it is determined that the working state of the first audio collection device is abnormal. That is, in the two audio collection device state recognition processes, when the state recognition of any audio collection device is abnormal, it can be determined that the working state of the first audio collection device is abnormal, thereby ensuring the state recognition success rate of the first audio collection device.

[0055] In an optional implementation, the voice instruction includes a voice wake-up instruction; and the method further includes:

[0056] If it is determined that there is no audio collection device with an abnormal working state among the multiple audio collection devices, the voice recognition function is started.

[0057] In the above implementation, it is possible to identify the state of the audio acquisition device after receiving the wake-up command and before starting the voice function, that is, at the time of voice wake-up, first eliminate the possibility of abnormality of the audio acquisition device, and ensure that the audio acquisition device can normally receive the voice command after the voice function is started.

[0058] In a second aspect, the present disclosure also provides an audio acquisition device state recognition device, including:

[0059] A receiving module, used for receiving a voice command from a target detection position outside the vehicle;

[0060] A collection module, configured to collect corresponding audio data based on N audio collection devices outside the vehicle in response to the voice command;

[0061] A first determination module is used to determine first audio difference information and a first audio acquisition device based on audio data collected by N audio acquisition devices outside the vehicle and calibrated audio data of each audio acquisition device; the first audio acquisition device is determined based on the first audio difference information and a target detection position; the calibrated audio data corresponds to a target position range where the target detection position is located;

[0062] A second determination module is configured to determine second audio difference information based on first audio data collected by the first audio collection device and second audio data collected by M second audio collection devices; the M second audio collection devices are determined based on the first audio collection device and the target detection position; the second audio difference information is audio difference information between the first audio collection device and the second audio collection device;

[0063] The third determining module is used to determine the working state of the first audio collecting device according to the second audio difference information.

[0064] In a third aspect, an embodiment of the present disclosure further provides a vehicle, comprising the audio collection device state recognition device in the second aspect above.

[0065] In a fourth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned first aspect or any possible implementation of the first aspect are executed.

[0066] For a description of the effects of the above-mentioned audio collection device state recognition device, vehicle, and computer-readable storage medium, please refer to the description of the above-mentioned audio collection device state recognition method, which will not be repeated here.

[0067] 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

[0068] 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.

[0069] Figure 1 A flow chart of a method for identifying the state of an audio acquisition device provided by an embodiment of the present disclosure is shown;

[0070] Figure 2 A schematic diagram showing the distribution of the audio collection device and detection positions provided in an embodiment of the present disclosure is shown;

[0071] Figure 3 A schematic diagram showing the structure of a device for identifying the state of an audio acquisition device provided by an embodiment of the present disclosure is shown;

[0072] Figure 4 A schematic diagram of a computer device provided by an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0073] 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.

[0074] Research has found that in vehicles that support off-board voice recognition, microphones are usually required to be installed around the vehicle to ensure that any position around the vehicle can receive the voice commands issued by the user outside the vehicle. Usually, off-board microphones are mainly deployed in the front grille of the vehicle, the license plate at the rear of the vehicle, and the exterior mirrors on both sides of the vehicle.

[0075] In order to ensure good sound reception performance of the external microphone, the sound receiving hole of the external microphone is usually facing outwards. Therefore, the external microphone is easily blocked by foreign objects or fails, resulting in reduced sound reception performance of the external microphone. For example, when a vehicle is driving on a muddy road on a rainy day, the microphone arranged in front of the vehicle and at a low position is likely to have mud blocking the sound receiving hole, resulting in the sound not being able to directly reach the inside of the microphone, affecting the recognition effect of the external voice.

[0076] After the sound receiving hole of the external microphone is blocked, if the user fails to check the external microphone in time, it will easily lead to a decrease in the recognition effect of the external voice, affecting the user's car experience.

[0077] Based on this, the present disclosure provides a method for identifying the state of an audio collection device. In the above-mentioned audio collection device identification method, by comparing the difference between the audio data received by each audio collection device and the corresponding calibrated audio data, the first audio collection device with an abnormal state can be preliminarily determined; for the first audio collection device with an abnormal state preliminarily determined, by further comparing the difference between the audio difference information between the first audio collection device and the second audio collection device and the calibrated audio difference information, it can be further determined whether the first audio collection device is abnormal. Through the above-mentioned two audio collection device state identification processes, not only the confidence of the audio collection device state identification is improved, but also the accuracy of the audio collection device state identification result is improved.

[0078] The defects existing in the above schemes and the proposed solutions are the results obtained by the inventor after practice and careful research. Therefore, the discovery process of the above problems and the solutions proposed by the present disclosure for the above problems below should be the contributions made by the inventor to the present disclosure during the disclosure process.

[0079] 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.

[0080] To facilitate understanding of this embodiment, a method for identifying the state of an audio acquisition device disclosed in the embodiment of the present disclosure is first introduced in detail. The executor of the method for identifying the state of an audio acquisition device provided in the embodiment of the present disclosure is generally a computer device with certain computing capabilities.

[0081] See also Figure 1 FIG. 1 is a flowchart of a method for identifying the state of an audio acquisition device provided by an embodiment of the present disclosure, wherein the method includes S101 to S105, wherein:

[0082] S101: receiving a voice command from a target detection position outside the vehicle.

[0083] In the embodiment of the present disclosure, a plurality of detection positions are arranged outside the vehicle for detecting whether the working state of the vehicle audio collection device is abnormal. The detection positions outside the vehicle can be arranged according to the position of the audio collection device outside the vehicle, and these detection positions are generally located within a preset range of the vehicle.

[0084] The audio collection device may include a device for collecting audio, such as a microphone. Taking the audio collection device as a microphone as an example, Figure 2 A schematic diagram showing the distribution of microphones and detection positions is shown. Figure 2 It can be seen that microphones 1, 2, 3 and 4 are respectively arranged at the front grille, the left side rearview mirror, the rear license plate and the right side rearview mirror of the vehicle; correspondingly, detection positions 1 to 8 are respectively arranged at the front grille, both sides of the vehicle and the rear license plate of the vehicle. After the user issues a voice command at any of the above detection positions, the vehicle can control the microphones at each detection position to receive audio data.

[0085] The target detection position outside the vehicle may be any detection position among a plurality of detection positions outside the vehicle. In order to realize the recognition of the state of the audio acquisition device, before the user issues a voice command outside the vehicle, the user may be guided to the detection position outside the vehicle to issue a voice command, so that the vehicle can identify the state of the audio acquisition device based on the audio data received by the audio acquisition device and the calibration audio data of each audio acquisition device in a normal state at the detection position. Specifically, in one embodiment, before receiving the voice command from the target detection position outside the vehicle, it is also possible to: play voice guidance information in response to meeting a preset trigger condition.

[0086] Here, the preset trigger condition refers to the condition that triggers the playing of the voice guidance information. The preset trigger condition may include that the distance between the user and the vehicle is less than or equal to the set distance threshold (i.e., quantitatively judging whether the user is approaching the vehicle), the distance between the user and the vehicle is gradually decreasing (i.e., qualitatively judging whether the user is approaching the vehicle), or the detection of voice information outside the vehicle.

[0087] The distance between the user and the vehicle can be determined by the communication signal strength between the car key carried by the user and the vehicle. In one embodiment, the vehicle can store a correspondence between the communication signal strength and the distance between the car key and the vehicle. According to the correspondence and the communication signal strength between the car key and the vehicle, the distance between the car key and the vehicle can be determined. The greater the communication signal strength, the smaller the distance between the car key and the vehicle; otherwise, the greater the distance.

[0088] The above voice guidance information can be used to instruct the user to carry a car key with a positioning function, go to the target detection location and issue a voice command.

[0089] The target detection position here may be a detection position closest to the user's current position among multiple detection positions outside the vehicle. Therefore, the voice guidance information here is used to instruct the user to go to the nearest detection position to initiate a voice command.

[0090] The car key may be any car key with a positioning function, such as a Bluetooth key, an Ultra Wide-Band (UWB) key, etc. The positioning function of the car key is used to determine whether the user has reached the target detection position.

[0091] For example, if the user is currently closest to the detection position in front of the left side of the vehicle according to the positioning information of the car key, the guidance information "Please bring the car key to the left front of the vehicle within 3 meters to wake up the vehicle and issue instructions" can be broadcasted. If the user is currently on the left side of the vehicle according to the positioning information of the car key, the above guidance information can be stopped.

[0092] The above-mentioned voice guidance information can also be used to instruct the user to carry a car key with a positioning function and go to at least one of the multiple detection positions outside the vehicle to issue a voice command. Therefore, the voice guidance information here is used to guide the user to go to any one or more detection positions to initiate a voice command.

[0093] The voice guidance information here may include location information of at least one detection location. For example, the guidance information of "Please bring the car key within 3 meters of the vehicle to wake up the vehicle and give instructions. You can choose the left side or the right side of the vehicle" may be broadcasted.

[0094] S102: In response to the voice command, corresponding audio data is collected based on N audio collection devices outside the vehicle.

[0095] Here, the N audio collecting devices outside the vehicle may include some audio collecting devices outside the vehicle.

[0096] Considering that usually, the farther the audio collection device is from the target detection position, the less accurate the audio data received is and the more susceptible it is to other noises, therefore, in one embodiment, before the corresponding audio data is collected based on the N audio collection devices outside the vehicle, the N audio collection devices for collecting audio data can be determined from the L audio collection devices based on the target detection position. Wherein, N and L are both positive integers, N is less than L, and the distance between the N audio collection devices and the target detection position is less than the first distance.

[0097] The L audio collection devices may be all audio collection devices outside the vehicle. According to the positions of the audio collection devices and the target detection position, N audio collection devices whose distances to the target detection position are less than the first distance may be selected. By selecting N audio collection devices whose distances to the target detection position are less than the first distance, the interference of the abnormal state of the audio collection device caused by the distance or environmental factors on the state recognition result of the audio collection device may be eliminated, thereby improving the accuracy of the state recognition result of the audio collection device.

[0098] The audio data may include volume information and / or audio content corresponding to the voice command. The audio data is used to calibrate the audio data, determine the first audio difference information and the first audio acquisition device. This process will be described in detail in S103.

[0099] S103: Determine first audio difference information and a first audio acquisition device based on audio data collected by N audio acquisition devices outside the vehicle and calibrated audio data of each audio acquisition device; the first audio acquisition device is determined based on the first audio difference information and the target detection position; the calibrated audio data corresponds to a target position range where the target detection position is located.

[0100] Here, the calibrated audio data of each audio acquisition device in a normal state may be pre-calibrated. Specifically, when the audio acquisition device is in a normal state (the normal state here, for example, may be determined after detection by vehicle detection technology, and the determination process of the normal state is not specifically limited here), after the user wakes up the vehicle through a wake-up command, voice commands (which may be the same or different) may be issued at each detection position in turn, and the audio data received by each audio acquisition device is stored as calibrated audio data. The difference information between the audio data of each audio acquisition device and other audio acquisition devices is stored as calibrated audio difference information.

[0101] After receiving the voice command of the target detection position, the calibration audio data corresponding to the target position range where the target detection position is located can be determined.

[0102] Here, the first audio difference information can be determined based on the audio data received by the N audio collection devices outside the vehicle and the calibrated audio data of each audio collection device. The first audio collection device is determined from the N audio collection devices based on the first audio difference information and the first difference threshold.

[0103] The first audio difference information may be audio difference information between audio data received by the audio acquisition device and calibrated audio data corresponding to the target detection position of the audio acquisition device.

[0104] As mentioned above, the audio data may include volume information and / or audio content corresponding to the voice command. In one embodiment, when the audio data includes volume information, the volume information received by the audio acquisition device may be compared with the calibrated volume information to determine the volume difference as the first audio difference information. In the following text, when the audio data includes volume information, the second audio difference information may also include the volume difference.

[0105] Here, assuming that the volume of the voice commands issued by the user is the same, the volume of the audio received by the audio acquisition device in an abnormal state is smaller than the volume of the audio received in a normal state. In order to eliminate the influence of environmental factors, a first difference threshold can be set to indicate the range of error allowed for the volume received by the audio acquisition device. When the first audio difference information corresponding to the audio acquisition device is less than the first difference threshold, the audio acquisition device can be used as the first audio acquisition device.

[0106] By comparing the audio data received by each audio collection device with the calibrated audio data corresponding to the audio collection device, the audio collection devices whose volume difference exceeds the first difference threshold can be screened out, so that the first audio collection device with abnormal status can be preliminarily and quickly located.

[0107] In another embodiment, when the audio data includes audio content, the audio content received by the audio acquisition device can be compared with the calibrated audio content to determine the audio content difference as the first audio difference information. In the following text, when the audio data includes audio content, the second audio difference information can also include the audio content difference. The audio content difference can be determined based on the edit distance or semantic similarity between different audio contents.

[0108] Here, assuming that the voice commands issued by the user are the same, there is a difference between the audio content received by the audio acquisition device in an abnormal state and the audio content received in a normal state. For example, the calibrated audio data in a normal state is "open the music player", and the audio content received in an abnormal state may be "open the sound..." For example, the audio content received by the audio acquisition device can be compared with the calibrated audio content to determine the similarity between the received audio content and the calibrated audio content, and then determine the difference in audio content. The lower the similarity, the greater the difference in audio content. Similarly, a first difference threshold can be set here to indicate the range of errors allowed in the audio content received by the audio acquisition device. When the similarity is less than the first difference threshold, the audio acquisition device can be used as the first audio acquisition device.

[0109] In another embodiment, the above two embodiments may be combined to determine the volume difference and the audio content difference, and use the volume difference and the audio content difference as the first audio difference information. The specific process will not be described in detail.

[0110] In a further embodiment, the step of determining the first audio collection device from the N audio collection devices based on the first audio difference information and the first difference threshold may be performed according to the following steps:

[0111] Based on the first audio difference information corresponding to N audio collection devices and the first difference threshold, a candidate audio collection device is determined; the first audio difference information corresponding to the candidate audio collection device is greater than the first difference threshold; if after the user issues voice commands for multiple times, the number of times the first audio difference information corresponding to the candidate audio collection device is greater than the first difference threshold exceeds a first set number threshold, the candidate audio collection device is determined to be the first audio collection device; the voice commands issued multiple times are issued at the same target detection position, or are issued at different target detection positions.

[0112] Here, it is actually a process of repeatedly performing multiple audio acquisition device status recognition after the user issues multiple voice commands at the same target detection position or different target detection positions, and the specific process will not be repeated.

[0113] Here, by determining that the candidate audio collection device is the first audio collection device after the user issues voice commands multiple times, the interference of accidental abnormal audio collection device status caused by user or environmental factors on the audio collection device status recognition result can be eliminated, thereby improving the accuracy of audio collection device status recognition.

[0114] The abnormal state of the first audio acquisition device determined by step S103 cannot be used as the final state recognition result. This is mainly because, on the one hand, when the user is in different environments, such as a garage environment and a street environment, the audio data received by the same audio acquisition device are also different; on the other hand, the same user sometimes speaks loudly and sometimes speaks softly. In this case, the audio data received by the same audio acquisition device are also different. Therefore, in order to improve the accuracy of the state recognition of the audio acquisition device, the first audio acquisition device can be further recognized. For the specific process, please refer to steps S104 to S105.

[0115] S104: Determine second audio difference information based on first audio data collected by the first audio collection device and second audio data collected by M second audio collection devices; the M second audio collection devices are determined based on the first audio collection device and the target detection position; the second audio difference information is audio difference information between the first audio collection device and the second audio collection device.

[0116] Here, in one embodiment, a second audio collection device other than the first audio collection device can be selected according to the first audio collection device and the target detection position, and the distance between the second audio collection device and the target detection position is less than a second distance. The second distance can be the same as the first distance or different.

[0117] Before determining the second audio difference information, M second audio collection devices may be determined according to the positional relationship between the first audio collection device and each second audio collection device. The M second audio collection devices and the first audio collection device satisfy a preset positional relationship.

[0118] Here, by determining M second audio collection devices that satisfy a preset position relationship with the first audio collection device, the first audio data collected by the first audio collection device can be compared with the second audio data collected by the M second audio collection devices at the preset positions, thereby achieving targeted comparison and eliminating the interference of the abnormal state of the audio collection device caused by the position of the audio collection device on the audio collection device state recognition result, thereby improving the accuracy of the audio collection device state recognition result.

[0119] Here, the first audio data collected by the first audio collection device and the second audio data collected by the second audio collection device can be audio data received after the user issues a voice command at the target detection position. Since the positions of the first audio collection device and the second audio collection device are different, there are differences in the audio data received by the first audio collection device and the second audio collection device.

[0120] By comparing the first audio data with the second audio data, second audio difference information between the first audio data and the second audio data may be determined.

[0121] In a specific implementation, the audio data may include volume information and / or audio content, and therefore, the first volume information may be compared with the second volume information, or the first audio content may be compared with the second audio content, or they may be compared separately.

[0122] S105: Determine a working state of the first audio collection device according to the second audio difference information.

[0123] Here, if the first audio collection device is in an abnormal state, there is a difference between the second audio difference information and the calibrated audio difference information. Therefore, the working state of the first audio collection device can be further determined based on the difference between the second audio difference information and the calibrated audio difference information. That is, after determining the second audio difference information between the first audio data and the second audio data, in one embodiment, the third audio difference information can be determined based on the second audio difference information and the calibrated audio difference information between the first audio collection device and the second audio collection device at the target detection position. Based on the third audio difference information and the second difference threshold, the working state of the first audio collection device is determined.

[0124] Here, when the third audio difference information exceeds the second difference threshold, it means that the difference between the third audio difference information and the calibration audio difference information is relatively large, so it can be determined that the working state of the first audio acquisition device is abnormal.

[0125] Considering that the audio data received by the audio collection devices at different locations are different, the impact on the working state recognition result of the first audio collection device is also different. In one embodiment, the weight of the third audio difference information corresponding to each second audio collection device can also be determined according to the distance between each of the second audio collection devices and the first audio collection device. The third audio difference comprehensive value is determined according to each third audio difference information and the corresponding weight. The working state of the first audio collection device is determined according to the third audio difference comprehensive value and the second difference threshold.

[0126] Here, the greater the distance between the second audio collection device and the first audio collection device, the smaller the weight of the third audio difference information corresponding to the second audio collection device can be, that is, the smaller the impact on the working state recognition result of the first audio collection device may be. The third audio difference comprehensive value determined by each third audio difference information and the corresponding weight can more accurately determine the working state of the first audio collection device.

[0127] In order to further improve the accuracy of audio collection device status recognition, the second audio difference information between the plurality of second audio collection devices and the first audio collection device and the calibration audio difference information can also be used to determine whether the first audio collection device has an abnormal status.

[0128] In one embodiment, the number of the second audio collection device is multiple. Based on the third audio difference information and the second difference threshold, the step of determining the working state of the first audio collection device can be performed according to the following steps:

[0129] For each second audio collection device, based on the third audio difference information and the second difference threshold, it is determined whether the third audio difference information corresponding to the second audio collection device is greater than the second difference threshold.

[0130] If the number of second audio collection devices corresponding to the third audio difference information being greater than the second difference threshold is greater than a set number threshold, it is determined that the working state of the first audio collection device is abnormal.

[0131] In the above implementation, the second difference thresholds corresponding to different second audio collection devices may be different. For each second audio collection device, the third audio difference information corresponding to the second audio collection device may be compared with the second difference threshold corresponding to the second audio collection device to determine whether the third audio difference information is greater than the second difference threshold.

[0132] If the number of second audio collection devices whose corresponding third audio difference information is greater than the second difference threshold is greater than the set number threshold, it means that there is a difference between the third audio difference information and the calibration audio difference information between the multiple second audio collection devices and the first audio collection device, thereby determining that the working state of the first audio collection device is abnormal.

[0133] In a further embodiment, the step of determining the working state of the first audio acquisition device based on the third audio difference information and the second difference threshold may be performed according to the following steps:

[0134] If, after the user issues voice commands multiple times, the number of times that the third audio difference information corresponding to the first audio collection device is greater than the second difference threshold exceeds the second set number threshold, it is determined that the working state of the first audio collection device is abnormal. The multiple voice commands issued are issued at the same target detection position, or at different target detection positions.

[0135] By determining that the first audio collection device has an abnormal state after the user issues voice commands multiple times, it is possible to further eliminate the interference of accidental abnormal state of the audio collection device caused by user or environmental factors on the audio collection device state recognition result, thereby improving the accuracy of audio collection device state recognition.

[0136] In the embodiment of the present disclosure, after determining the first audio difference information, the working state of the first audio collection device can be determined by combining the first audio difference information and the second audio difference information when the second audio difference information is determined. The working state of the first audio collection device is determined by the difference between the two aspects, thereby improving the accuracy of the audio collection device state recognition result.

[0137] In a further embodiment, the third audio difference information may be determined based on the second audio difference information and the calibrated audio difference information corresponding to the target detection position between the first audio collection device and the second audio collection device.

[0138] If the third audio difference information is greater than the third difference threshold, it is determined that the working state of the first audio collecting device is abnormal.

[0139] If the third audio difference information is less than the third difference threshold, but the third audio difference information is greater than the fourth difference threshold, and the first audio difference information is greater than the fifth difference threshold, it is determined that the working state of the first audio collection device is abnormal; the fifth difference threshold is greater than the first difference threshold used when determining the first audio collection device.

[0140] Here, in a further state recognition process, when the difference between the audio difference information between the audio collection devices and the calibrated audio difference information, that is, the third audio difference information is greater than the third difference threshold (in this case, the third audio difference information can be considered to be large), it is determined that the working state of the first audio collection device is abnormal. Alternatively, in a further state recognition process, although the third audio difference information is less than the third difference threshold, the third audio difference information is greater than the fourth difference threshold, and in the preliminary state recognition process, the first audio difference information is greater than the fifth difference threshold (the first audio difference information can be considered to be large), it is determined that the working state of the first audio collection device is abnormal. That is, in the two audio collection device state recognition processes, if the state recognition of any audio collection device is abnormal, it can be determined that the working state of the first audio collection device is abnormal, thereby ensuring the state recognition success rate of the first audio collection device.

[0141] In the disclosed embodiment, the vehicle can support recording the voiceprints of multiple users, and the candidate calibration audio data and candidate calibration audio difference information corresponding to each user identification can be stored in the vehicle. In this case, after receiving a voice command issued by a user at a target detection position outside the vehicle, before determining the first audio acquisition device with an abnormal preliminary state, the user voiceprint recognition can be performed on the voice command to determine the user identification corresponding to the voice command, that is, to determine which user issued the voice command.

[0142] After determining the user identifier corresponding to the voice command, the calibrated audio data and calibrated audio difference information corresponding to the user identifier can be determined from the candidate calibrated audio data and candidate calibrated audio difference information respectively corresponding to multiple user identifiers.

[0143] By performing user voiceprint recognition on voice commands, the calibrated audio data and calibrated audio difference information corresponding to the user who issued the voice command can be used to compare the audio data of the user received by the audio acquisition device, thereby eliminating the interference of the difference in user voiceprints on the state recognition result of the audio acquisition device, and improving the accuracy of the state recognition of the audio acquisition device.

[0144] In an embodiment of the present disclosure, the voice command issued by the user at the target detection position outside the vehicle may include a wake-up command, and the user can wake up the voice recognition function of the vehicle through the wake-up command, after which the voice recognition function can recognize the received task command.

[0145] In the embodiment of the present disclosure, the state recognition process of the audio acquisition device can be completed before the task instruction is recognized.

[0146] If it is determined that there is no audio collection device in an abnormal state among the multiple audio collection devices, the voice recognition function can be started to recognize the received task instruction.

[0147] If it is determined that at least one of the first audio collection devices is in an abnormal state, abnormal prompt information of the audio collection device may be broadcast to the user.

[0148] The abnormal prompt information of the audio collection device may include at least one of the location information of the first audio collection device and abnormal elimination method information.

[0149] Here, the above-mentioned audio acquisition device abnormality prompt information can be broadcasted to the user through a voice broadcast method from text to speech (Text To Speech, TTS). The abnormality of the audio acquisition device may be a blockage of the audio acquisition device or a failure of the audio acquisition device. When broadcasting to the user, it can be broadcasted whether the audio acquisition device is blocked or the audio acquisition device is faulty according to the actual situation.

[0150] For example, when the microphone of the front grille of a vehicle is in abnormal status, when the voice recognition function is activated, the user can be informed through TTS voice broadcast that "the microphone of the current front grille of the vehicle may be blocked. Please check the specific location and cleaning method in the car."

[0151] The above-mentioned abnormal prompt information of the audio collection device can also be displayed on the screen in the car. For example, if the microphone status of the front grille of the vehicle is abnormal, when it is detected that the user is inside the vehicle, the screen in the car can display "The microphone of the current front grille of the vehicle may be blocked, please confirm whether to check and complete the cleaning of the microphone receiving hole", and the location and cleaning method of the microphone can be displayed on the screen in the car.

[0152] In addition, the screen inside the car can also display user operation guidance information such as "Yes, I have cleaned it" and "I haven't checked the cleaning yet".

[0153] If the user selects "Yes, I have cleaned it", if the audio collection device of the front grille of the vehicle is still abnormal, the screen in the vehicle will display a prompt message "Microphone failure, please contact maintenance". If the user selects "I have not checked and cleaned it yet", the user can continue to be reminded in the above manner when the vehicle is powered on next time.

[0154] Through the above process of actively broadcasting the abnormal prompt information of the audio collection device to the user, the user can be reminded in time to eliminate the abnormality of the audio collection device and ensure the recognition performance of the voice outside the vehicle.

[0155] 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.

[0156] Based on the same inventive concept, an audio collection device state recognition device corresponding to the audio collection device state recognition method is also provided in the embodiment of the present disclosure. Since the principle of solving the problem by the device in the embodiment of the present disclosure is similar to the above-mentioned audio collection device state 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.

[0157] Reference Figure 3 FIG. 1 is a schematic diagram of a structure of an audio acquisition device state recognition device provided by an embodiment of the present disclosure, wherein the device comprises:

[0158] A receiving module 301 is used to receive a voice command from a target detection position outside the vehicle;

[0159] A collection module 302, configured to collect corresponding audio data based on N audio collection devices outside the vehicle in response to the voice command;

[0160] A first determination module 303 is configured to determine first audio difference information and a first audio acquisition device based on audio data collected by N audio acquisition devices outside the vehicle and calibrated audio data of each audio acquisition device; the first audio acquisition device is determined based on the first audio difference information and a target detection position; the calibrated audio data corresponds to a target position range where the target detection position is located;

[0161] A second determination module 304 is configured to determine second audio difference information based on the first audio data collected by the first audio collection device and the second audio data collected by M second audio collection devices; the M second audio collection devices are determined based on the first audio collection device and the target detection position; the second audio difference information is audio difference information between the first audio collection device and the second audio collection device;

[0162] The third determining module 304 is configured to determine a working state of the first audio collecting device according to the second audio difference information.

[0163] In an optional implementation, the audio data includes: volume information and / or audio content corresponding to the voice command;

[0164] In the case where the audio data includes the volume information, the first audio difference information and the second audio difference information include a volume difference value;

[0165] In the case that the audio data includes the audio content, the first audio difference information and the second audio difference information include audio content difference degrees, and the audio content difference degrees are determined based on an edit distance or a semantic similarity between different audio contents.

[0166] In an optional implementation manner, before the corresponding audio data is collected by the N audio collection devices outside the vehicle, the method further includes:

[0167] The fourth determination module is used to determine the N audio collection devices for audio data collection from the L audio collection devices based on the target detection position; wherein N is less than L, and the distance between the N audio collection devices and the target detection position is less than the first distance.

[0168] In an optional implementation manner, before determining the second audio difference information, the method further includes:

[0169] The fifth determining module is used to determine the M second audio collecting devices according to the positional relationship between the first audio collecting device and each second audio collecting device; the M second audio collecting devices and the first audio collecting device satisfy a preset positional relationship.

[0170] In an optional implementation manner, the first determining module 303 is specifically configured to:

[0171] Determine the first audio difference information based on the audio data received by the N audio collection devices outside the vehicle and the calibrated audio data of each audio collection device; the first audio difference information is the audio difference information between the audio data received by the audio collection device and the calibrated audio data of the audio collection device corresponding to the target detection position;

[0172] Based on the first audio difference information and a first difference threshold, the first audio collection device is determined from the N audio collection devices.

[0173] In an optional implementation manner, the first determining module 303 is specifically configured to:

[0174] Determine a candidate audio collection device based on the first audio difference information respectively corresponding to the N audio collection devices and the first difference threshold; the first audio difference information corresponding to the candidate audio collection device is greater than the first difference threshold;

[0175] If, after the user issues voice commands multiple times, the number of times that the first audio difference information corresponding to the candidate audio collection device is greater than the first difference threshold exceeds a first set number threshold, the candidate audio collection device is determined to be the first audio collection device; and the voice commands issued multiple times are issued at the same target detection position, or are issued at different target detection positions.

[0176] In an optional implementation manner, the third determining module 305 is specifically configured to:

[0177] determining third audio difference information according to the second audio difference information and calibrated audio difference information between the first audio collection device and the second audio collection device corresponding to the target detection position;

[0178] Based on the third audio difference information and the second difference threshold, the working state of the first audio collecting device is determined.

[0179] In an optional implementation manner, the third determining module 305 is specifically configured to:

[0180] determining, according to the distances between each of the plurality of second audio collection devices and the first audio collection device, weights of the third audio difference information respectively corresponding to each of the second audio collection devices;

[0181] Determine a third audio difference comprehensive value according to each of the third audio difference information and the corresponding weight;

[0182] The working state of the first audio collection device is determined according to the third audio difference comprehensive value and the second difference threshold.

[0183] In an optional implementation manner, the number of the second audio collection devices is multiple;

[0184] The third determining module 305 is specifically used for:

[0185] For each of the second audio collection devices, determining, based on the third audio difference information and the second difference threshold, whether the third audio difference information corresponding to the second audio collection device is greater than the second difference threshold;

[0186] If the number of second audio collection devices corresponding to the third audio difference information being greater than the second difference threshold is greater than a set number threshold, it is determined that the working state of the first audio collection device is abnormal.

[0187] In an optional implementation manner, the third determining module 305 is specifically configured to:

[0188] If, after the user issues voice commands multiple times, the number of times that the third audio difference information corresponding to the first audio collection device is greater than the second difference threshold exceeds the second set number threshold, it is determined that the working state of the first audio collection device is abnormal; the voice commands issued multiple times are issued at the same target detection position, or are issued at different target detection positions.

[0189] In an optional implementation manner, the third determining module 305 is specifically configured to:

[0190] The working state of the first audio collecting device is determined according to the first audio difference information and the second audio difference information.

[0191] In an optional implementation manner, the third determining module 305 is specifically configured to:

[0192] determining third audio difference information according to the second audio difference information and calibrated audio difference information between the first audio collection device and the second audio collection device corresponding to the target detection position;

[0193] If the third audio difference information is greater than a third difference threshold, determining that the working state of the first audio acquisition device is abnormal;

[0194] If the third audio difference information is smaller than the third difference threshold, but the third audio difference information is larger than the fourth difference threshold, and the first audio difference information is larger than the fifth difference threshold, it is determined that the working state of the first audio collection device is abnormal; and the fifth difference threshold is larger than the first difference threshold used when determining the first audio collection device.

[0195] In an optional implementation manner, the voice instruction includes a voice wake-up instruction; and the device further includes:

[0196] The starting module is used to start the speech recognition function if it is determined that there is no audio collection device with abnormal working status among the multiple audio collection devices.

[0197] 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.

[0198] Based on the same technical concept, the embodiment of the present disclosure also provides a computer device. Figure 4 As shown, it is a schematic diagram of the structure of a computer device 400 provided in an embodiment of the present disclosure, including a processor 401, a memory 402, and a bus 403. Among them, the memory 402 is used to store execution instructions, including a memory 4021 and an external memory 4022; the memory 4021 here is also called an internal memory, which is used to temporarily store the operation data in the processor 401, and the data exchanged with the external memory 4022 such as a hard disk. The processor 401 exchanges data with the external memory 4022 through the memory 4021. When the computer device 400 is running, the processor 401 communicates with the memory 402 through the bus 403, so that the processor 401 executes the following instructions:

[0199] receiving a voice command from an object detection location outside the vehicle;

[0200] In response to the voice command, collecting corresponding audio data based on N audio collection devices outside the vehicle;

[0201] Based on the audio data collected by the N audio collection devices outside the vehicle and the calibrated audio data of each audio collection device, first audio difference information and a first audio collection device are determined; the first audio collection device is determined based on the first audio difference information and the target detection position; the calibrated audio data corresponds to the target position range where the target detection position is located;

[0202] Determine second audio difference information according to first audio data collected by the first audio collection device and second audio data collected by M second audio collection devices; the M second audio collection devices are determined according to the first audio collection device and the target detection position; the second audio difference information is audio difference information between the first audio collection device and the second audio collection device;

[0203] The working state of the first audio collection device is determined according to the second audio difference information.

[0204] The disclosed embodiment also provides a vehicle, comprising the above-mentioned audio collection device state recognition device.

[0205] 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 audio acquisition device state identification method described in the above method embodiment are executed. The storage medium can be a volatile or non-volatile computer-readable storage medium.

[0206] The embodiment of the present disclosure also provides a computer program product, which carries a program code. The instructions included in the program code can be used to execute the steps of the audio acquisition device state identification method described in the above method embodiment. For details, please refer to the above method embodiment, which will not be repeated here.

[0207] The computer program product may be implemented in hardware, software or a combination thereof. In one optional embodiment, the computer program product is implemented as a computer storage medium. In another optional embodiment, the computer program product is implemented as a software product, such as a software development kit (SDK).

[0208] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the device described above 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 device and method 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, and the indirect coupling or communication connection of the device or unit can be electrical, mechanical or other forms.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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 shall be based on the protection scope of the claims.

Claims

1. A method for identifying the state of an audio acquisition device, characterized in that: include: receiving a voice command from an object detection location outside the vehicle; In response to the voice command, collecting corresponding audio data based on N audio collection devices outside the vehicle; Determining first audio difference information and a first audio collection device based on audio data collected by N audio collection devices outside the vehicle and calibrated audio data of each audio collection device; The first audio acquisition device is determined based on the first audio difference information and the target detection position; the calibration audio data corresponds to the target position range where the target detection position is located; Determine second audio difference information according to the first audio data collected by the first audio collection device and the second audio data collected by the M second audio collection devices; The M second audio collection devices are determined according to the first audio collection device and the target detection position; the second audio difference information is the audio difference information between the first audio collection device and the second audio collection device; The working state of the first audio collection device is determined according to the second audio difference information.

2. The method according to claim 1, characterized in that The audio data includes: volume information and / or audio content corresponding to the voice command; In the case where the audio data includes the volume information, the first audio difference information and the second audio difference information include a volume difference value; In the case that the audio data includes the audio content, the first audio difference information and the second audio difference information include audio content difference degrees, and the audio content difference degrees are determined based on an edit distance or a semantic similarity between different audio contents.

3. The method according to claim 1, characterized in that Before collecting corresponding audio data based on the N audio collection devices outside the vehicle, the method further includes: Based on the target detection position, the N audio collection devices for audio data collection are determined from the L audio collection devices; wherein N is less than L, and the distance between the N audio collection devices and the target detection position is less than a first distance.

4. The method according to claim 1, characterized in that: Before determining the second audio difference information, the method further includes: The M second audio collection devices are determined according to the positional relationship between the first audio collection device and each second audio collection device; and the M second audio collection devices satisfy a preset positional relationship with the first audio collection device.

5. The method according to claim 1, characterized in that The determining of the first audio difference information and the first audio collection device based on the audio data received by the N audio collection devices outside the vehicle and the calibrated audio data of each audio collection device includes: Determine the first audio difference information based on the audio data received by the N audio collection devices outside the vehicle and the calibrated audio data of each audio collection device; the first audio difference information is the audio difference information between the audio data received by the audio collection device and the calibrated audio data of the audio collection device corresponding to the target detection position; Based on the first audio difference information and a first difference threshold, the first audio collection device is determined from the N audio collection devices.

6. The method according to claim 5, characterized in that The determining the first audio collection device from the N audio collection devices based on the first audio difference information and a first difference threshold comprises: Determine a candidate audio collection device based on the first audio difference information respectively corresponding to the N audio collection devices and the first difference threshold; the first audio difference information corresponding to the candidate audio collection device is greater than the first difference threshold; If, after the user issues voice commands multiple times, the number of times that the first audio difference information corresponding to the candidate audio collection device is greater than the first difference threshold exceeds a first set number threshold, the candidate audio collection device is determined to be the first audio collection device; and the voice commands issued multiple times are issued at the same target detection position, or are issued at different target detection positions.

7. The method according to claim 1, characterized in that The determining the working state of the first audio acquisition device according to the second audio difference information includes: determining third audio difference information according to the second audio difference information and calibrated audio difference information between the first audio collection device and the second audio collection device corresponding to the target detection position; Based on the third audio difference information and the second difference threshold, a working state of the first audio collecting device is determined.

8. The method according to claim 7, characterized in that The determining the working state of the first audio acquisition device based on the third audio difference information and the second difference threshold includes: determining, according to the distances between each of the plurality of second audio collection devices and the first audio collection device, weights of the third audio difference information respectively corresponding to each of the second audio collection devices; Determine a third audio difference comprehensive value according to each of the third audio difference information and the corresponding weight; The working state of the first audio collection device is determined according to the third audio difference comprehensive value and the second difference threshold.

9. The method according to claim 7, characterized in that: The number of the second audio collection devices is multiple; The determining the working state of the first audio acquisition device based on the third audio difference information and the second difference threshold includes: For each of the second audio collection devices, determining, based on the third audio difference information and the second difference threshold, whether the third audio difference information corresponding to the second audio collection device is greater than the second difference threshold; If the number of second audio collection devices corresponding to the third audio difference information being greater than the second difference threshold is greater than a set number threshold, it is determined that the working state of the first audio collection device is abnormal.

10. The method according to any one of claims 7 to 9, characterized in that: The determining the working state of the first audio acquisition device based on the third audio difference information and the second difference threshold includes: If, after the user issues voice commands multiple times, the number of times that the third audio difference information corresponding to the first audio collection device is greater than the second difference threshold exceeds the second set number threshold, it is determined that the working state of the first audio collection device is abnormal; the voice commands issued multiple times are issued at the same target detection position, or are issued at different target detection positions.

11. The method according to claim 1, characterized in that: The determining the working state of the first audio acquisition device according to the second audio difference information includes: The working state of the first audio collecting device is determined according to the first audio difference information and the second audio difference information.

12. The method according to claim 11, characterized in that The determining the working state of the first audio acquisition device according to the first audio difference information and the second audio difference information includes: determining third audio difference information according to the second audio difference information and calibrated audio difference information between the first audio collection device and the second audio collection device corresponding to the target detection position; If the third audio difference information is greater than a third difference threshold, determining that the working state of the first audio acquisition device is abnormal; If the third audio difference information is smaller than the third difference threshold, but the third audio difference information is larger than the fourth difference threshold, and the first audio difference information is larger than the fifth difference threshold, it is determined that the working state of the first audio collection device is abnormal; and the fifth difference threshold is larger than the first difference threshold used when determining the first audio collection device.

13. The method according to claim 1, characterized in that The voice instruction includes a voice wake-up instruction; the method further includes: If it is determined that there is no audio collection device with an abnormal working state among the multiple audio collection devices, the voice recognition function is started.

14. An audio acquisition device state recognition device, characterized in that: include: A receiving module, used for receiving a voice command from a target detection position outside the vehicle; A collection module, configured to collect corresponding audio data based on N audio collection devices outside the vehicle in response to the voice command; A first determination module, configured to determine first audio difference information and a first audio collection device based on audio data collected by N audio collection devices outside the vehicle and calibrated audio data of each audio collection device; The first audio acquisition device is determined based on the first audio difference information and the target detection position; the calibration audio data corresponds to the target position range where the target detection position is located; A second determining module, configured to determine second audio difference information according to the first audio data collected by the first audio collecting device and the second audio data collected by the M second audio collecting devices; The M second audio collection devices are determined according to the first audio collection device and the target detection position; the second audio difference information is the audio difference information between the first audio collection device and the second audio collection device; The third determining module is used to determine the working state of the first audio collecting device according to the second audio difference information.

15. A vehicle, characterized in that: include: An audio acquisition device state recognition device as claimed in any one of claims 1 to 13.

16. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for identifying the state of an audio collection device according to any one of claims 1 to 13 are executed.

Images