Vehicle, vehicle voice recognition method and device and medium

Abstract

The invention discloses a vehicle, a vehicle voice recognition method and device and a medium, and the method comprises the steps: recognizing a target scene where the vehicle is located according to one or more of the internal environment data, external environment data and driving data of the vehicle; according to the target scene, a first instruction type corresponding to the target scene is obtained in a database, and the database comprises multiple scenes of the vehicle and the instruction type corresponding to each scene; adjusting the priority of the first instruction type to be greater than the priorities of other instruction types in the database; and obtaining first voice information of the user, and preferentially calling the first instruction type to recognize the first voice information based on the voice recognition model so as to determine a first instruction corresponding to the first voice information. According to the invention, the accuracy of vehicle speech recognition can be improved.

Description

Technical Field

[0001] The present application belongs to the field of speech recognition technology, and in particular, relates to a vehicle, a vehicle speech recognition method, a device and a medium. Background Art

[0002] With the development of in-vehicle voice recognition technology, there are now voice recognition systems that can automatically recognize user voice commands, identify user intentions and predict vehicle-side control commands to improve user convenience in using the car.

[0003] In the speech recognition system of the related art, the prediction of control instructions may be affected by the results of speech recognition. For example, when the accuracy of speech recognition is low, the system may predict or recommend control instructions that are inconsistent with the user's intention, and the accuracy of speech recognition may deteriorate based on the environmental conditions of the vehicle. Summary of the invention

[0004] The embodiments of the present application provide a vehicle, a vehicle speech recognition method, an apparatus and a medium, thereby being able to improve the accuracy of speech recognition at least to a certain extent.

[0005] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present application.

[0006] The first aspect of the present application provides a vehicle speech recognition method, comprising:

[0007] Identifying a target scenario in which the vehicle is located based on one or more of the vehicle's internal environment data, external environment data, and driving data;

[0008] According to the target scenario, obtaining a first instruction type corresponding to the target scenario in a database, wherein the database includes a plurality of scenarios of the vehicle and an instruction type corresponding to each scenario;

[0009] adjusting the priority of the first instruction type to be greater than the priorities of other instruction types in the database;

[0010] The user's first voice information is obtained, and the first instruction type is preferentially called to recognize the first voice information based on a voice recognition model to determine a first instruction corresponding to the first voice information.

[0011] Optionally, acquiring, in a database according to the target scenario, a first instruction type corresponding to the target scenario includes:

[0012] Acquire a first target identifier, wherein the first target identifier is used to characterize the target scenario;

[0013] Obtain a second target identifier corresponding to the first target identifier in the database, wherein the second target identifier is used to characterize the first instruction type, the database includes multiple first identifiers and a second identifier corresponding to each of the first identifiers, the first identifier is used to characterize the scenario, and the second identifier is used to characterize the instruction type.

[0014] Optionally, adjusting the priority of the first instruction type to be greater than the priorities of other instruction types in the database includes:

[0015] The target value of the first instruction type is adjusted to a first value, and the target value of the other instruction types is adjusted to a second value, wherein the first value is used to represent a first priority, the second value is used to represent a second priority, and the first priority is greater than the second priority.

[0016] Optionally, the acquiring the first voice information of the user and preferentially calling the first instruction type to recognize the first voice information based on a voice recognition model includes:

[0017] Acquire the first voice information, wherein the first voice information includes a first task to be performed and a second task to be performed;

[0018] Based on the speech recognition model, the first instruction type is preferentially called to identify the first task to be executed;

[0019] The other instruction types are called based on the speech recognition model to recognize other second tasks to be performed.

[0020] Optionally, when there are multiple first tasks to be executed, the step of preferentially calling the first instruction type based on the speech recognition model to identify the first execution includes:

[0021] Determine a timestamp of receiving each of the first tasks to be performed;

[0022] The first instruction type is preferentially called based on the speech recognition model, and each of the first tasks to be executed is identified according to the sequence of the timestamps.

[0023] Optionally, the method further comprises:

[0024] Acquire a plurality of second voice information of the user in the target scenario within a period of time;

[0025] Recognize the plurality of second voice information based on the voice recognition model to determine a plurality of second instructions;

[0026] If the plurality of second instructions are of the same instruction type, and the plurality of second instructions do not belong to the first instruction type, the priority of the second instruction type to which the plurality of second instructions belong is increased.

[0027] Optionally, the vehicle includes a voice collection device, and when acquiring the first voice information of the user, the method further includes:

[0028] Obtaining ambient noise intensity and / or vehicle speed;

[0029] If the ambient noise intensity is greater than or equal to the set noise intensity and / or the vehicle speed is greater than or equal to the set vehicle speed, the noise reduction capability of the voice collection device is enhanced.

[0030] A second aspect of an embodiment of the present application provides a vehicle voice recognition device, comprising:

[0031] A first recognition unit, configured to recognize a target scenario in which the vehicle is located based on one or more of internal environment data, external environment data, and driving data of the vehicle;

[0032] an acquisition unit, configured to acquire, according to the target scenario, a first instruction type corresponding to the target scenario in a database, wherein the database includes a plurality of scenarios of the vehicle and an instruction type corresponding to each of the scenarios;

[0033] an adjusting unit, configured to adjust the priority of the first instruction type to be greater than the priorities of other instruction types in the database;

[0034] The second recognition unit is used to obtain the user's first voice information, and preferentially call the first instruction type to recognize the first voice information based on the voice recognition model to determine the first instruction corresponding to the first voice information.

[0035] A third aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores at least one computer program instruction, and the at least one computer program instruction is loaded and executed by a processor to implement the operations performed by any of the methods described in the first aspect.

[0036] A fourth aspect of an embodiment of the present application provides a vehicle, comprising one or more processors and one or more memories, wherein at least one program code is stored in the one or more memories, and the at least one program code is loaded and executed by the one or more processors to implement the operations performed by any of the methods described in the first aspect.

[0037] One or more technical solutions provided by the embodiments of the present invention achieve at least the following technical effects or advantages:

[0038] The vehicle speech recognition method provided in the embodiment of the present application identifies the target scenario of the vehicle according to one or more of the internal environment data, external environment data and driving data of the vehicle; obtains the first instruction type corresponding to the target scenario in the database according to the target scenario, wherein the database includes multiple scenarios of the vehicle and the instruction type corresponding to each scenario; adjusts the priority of the first instruction type to be greater than the priority of other instruction types in the database; obtains the first voice information of the user, and preferentially calls the first instruction type based on the speech recognition model to identify the first voice information, so as to determine the first instruction corresponding to the first voice information. Thus, the embodiment of the present application pre-constructs the correspondence between different scenarios of the vehicle and various instruction types of the vehicle. When it is identified that the vehicle is in a certain target scenario, the priority of the target instruction type corresponding to the target scenario is increased based on the preset correspondence, so that when the user voice is received, the user voice can be recognized using the first instruction type related to the target scenario, thereby improving the recognition accuracy and response speed of the user voice.

[0039] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present application, and together with the specification, are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0041] Figure 1 A flow chart showing a vehicle speech recognition method according to an embodiment of the present application is shown;

[0042] Figure 2 A structural diagram of a vehicle speech recognition device according to an embodiment of the present application is shown;

[0043] Figure 3 A schematic diagram of the structure of a computer system of a vehicle suitable for implementing an embodiment of the present application is shown. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0045] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present application. However, those skilled in the art will appreciate that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, components, devices, steps, etc. can be adopted. In other cases, known methods, devices, realizations or operations are not shown or described in detail to avoid blurring the various aspects of the application.

[0046] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0047] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0048] It should also be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the objects used in this way can be interchanged where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those shown or described.

[0049] The vehicle speech recognition method of an embodiment of the present application is described in detail below with reference to the accompanying drawings.

[0050] See also Figure 1 , shows a flow chart of a vehicle speech recognition method according to an embodiment of the present application.

[0051] like Figure 1 As shown, the first aspect of the present application provides a vehicle speech recognition method, including but not limited to:

[0052] Step S10. Identifying a target scenario of the vehicle based on one or more of the internal environment data, the external environment data, and the driving data of the vehicle;

[0053] Exemplarily, the internal environment data of the vehicle includes but is not limited to: the temperature inside the vehicle, the humidity inside the vehicle, the light intensity inside the vehicle, the noise inside the vehicle, etc. For example, the temperature inside the vehicle can be detected by a vehicle-mounted temperature sensor, the humidity inside the vehicle can be detected by a vehicle-mounted humidity sensor, the light intensity can be detected by a vehicle-mounted light intensity sensor, the noise inside the vehicle can be detected by a vehicle-mounted noise sensor, etc.

[0054] Exemplarily, the external environment data of the vehicle includes but is not limited to weather data (such as sunny days, rainy days, cloudy days, snowy days, temperature, precipitation, wind speed, etc.), road condition data (such as traffic condition data, road type data, etc.), light intensity data outside the vehicle, etc. For example, weather data can be obtained from an external weather server through the vehicle communication terminal, road condition data can be obtained from an external traffic server through the vehicle communication terminal, and light intensity data outside the vehicle can be obtained through a vehicle-mounted light intensity sensor.

[0055] Exemplarily, driving data includes but is not limited to: vehicle speed data, braking data, acceleration data, steering data, etc. For example, vehicle speed data can be detected by wheel-end sensors, braking data can be detected by pressure sensors set on accelerator pedals, steering data can be detected by vehicle-mounted angle sensors, acceleration data can be detected by acceleration sensors, etc.

[0056] On the basis of the above, the target scenario that the vehicle is in can be identified. It is understandable that in a certain target scenario, there may be multiple sub-scenarios under multiple different scenario classifications. For example, in a certain target scenario, the vehicle is in rainy weather, traffic congestion, low light intensity, low temperature in the car, slow speed, etc.

[0057] Step S20. According to the target scenario, obtaining a first instruction type corresponding to the target scenario in a database, wherein the database includes multiple scenarios of the vehicle and an instruction type corresponding to each scenario;

[0058] In the embodiment of the present application, different scenarios of the vehicle can be classified in advance through big data analysis, and different instruction types of the vehicle can be classified, and a correspondence between scenarios and instruction types can be established. Among them, the scenario classification and instruction type classification of the vehicle can have different classification standards, which are not limited here. For ease of understanding, the scenario classification and instruction type classification of the vehicle are exemplified below.

[0059] In some embodiments, the vehicle is classified into the following scenarios:

[0060] 1) Classification by driving scenario: for example, low-speed driving in the city, highway driving, congestion, parking and waiting, etc.

[0061] 2) Classification by weather conditions: such as sunny days, heavy rain, heavy fog, blizzards, extreme temperatures, etc.

[0062] 3) Classification based on the in-car environment: for example, the noise level in the car, high or low temperature, etc.

[0063] Thus, a classification set of multiple scenarios can be constructed, and each classification set includes multiple sub-scenarios.

[0064] In some embodiments, based on the voice content input by the user, the vehicle can be classified into the following instruction types:

[0065] 1) Navigation: For example, “navigate to a certain place”, “next exit”, “select route”, etc.

[0066] 2) Safe driving: for example, “slow down”, “turn on the wipers”, “adjust the seat position”, etc.

[0067] 3) Vehicle control: for example, "turn on the air conditioner", "adjust the window", "adjust the seat", etc.

[0068] 4) Entertainment control: such as "play music", "adjust volume", "switch radio station", etc.

[0069] 5) Information query: for example, "weather query", "traffic information", etc.

[0070] Thus, a classification set of multiple instruction types can be constructed, and each classification set includes multiple sub-scenarios.

[0071] After constructing a classification set of multiple scenarios and a classification set of multiple instruction types, based on big data analysis, the instruction type corresponding to each scenario can be determined, and the corresponding relationship between the scenario and the instruction type can be established. For ease of understanding, the instruction type matching process in some scenarios is described below.

[0072] 1) Driving scene matching.

[0073] For example, when driving at high speed, the command type domains of navigation and safe driving are matched with high-speed driving scenarios to ensure that safety-related operations can be accurately identified and quickly responded to, such as "acceleration command" or "acceleration command".

[0074] For example, when driving at a low speed or on a city road, entertainment control instructions (such as "play music", "switch channels") are matched with the low speed driving or city road driving.

[0075] For example, when parking or waiting, the response requirements for safety instructions are reduced, and entertainment, air conditioning adjustment, etc. are matched with the parking or waiting state.

[0076] 2) Weather conditions match.

[0077] For example, in severe weather conditions (such as heavy rain, fog, and snow), the safety-related instruction type is matched with the severe weather conditions.

[0078] For example, when the weather is sunny or the in-vehicle environment is stable, the entertainment control and information query instruction types are matched with the sunny weather or the in-vehicle environment.

[0079] 3) Matching the interior environment of the vehicle.

[0080] For example, when the noise level in the car is too high, the volume adjustment type of command is matched to the noise level.

[0081] For example, when the temperature inside the vehicle is too high or too low, the instruction type of the air conditioning adjustment class is matched with the scenario where the temperature inside the vehicle is too high or too low.

[0082] 4) User behavior matching.

[0083] For example, when it is detected that the user is concentrating on driving (such as driving at a high speed, operating the steering wheel, etc.), safety-related instructions are matched with the scenario in which the user is concentrating on driving.

[0084] In some embodiments, when matching command types, the scenario data under various categories can be fused and then matched to the corresponding command type. For example, the in-car temperature sensor, humidity sensor, and weather data outside the car can jointly determine the user's air conditioning needs, and the noise sensor and vehicle speed data can help the system determine whether it is necessary to enhance the filtering and processing of voice signals. Data fusion helps improve the accuracy of situational awareness, thereby improving the accuracy of user intent recognition.

[0085] Based on the above, the embodiment of the present application can pre-construct the correspondence between different scenarios and different instruction types according to big data analysis, so that when it is identified that the vehicle is in a certain target scenario, it can quickly locate the instruction type that matches the target scenario based on the preset correspondence, thereby improving work efficiency.

[0086] In step S20, acquiring a first instruction type corresponding to the target scenario in a database according to the target scenario includes:

[0087] Step S21. Obtain a first target identifier, wherein the first target identifier is used to characterize the target scenario;

[0088] It can be understood that after classifying each scenario based on big data analysis, a first identifier can be assigned to each scenario, and the first identifier of each scenario is different. The scenario can be represented by the first identifier, thereby reducing the amount of data processing; similarly, after classifying each instruction type based on big data analysis, a second identifier can be assigned to each instruction type, and the second identifier of each instruction type is different, so the instruction type can be represented by the second identifier, thereby reducing the amount of data processing.

[0089] Step S22. Obtain a second target identifier corresponding to the first target identifier in the database, wherein the second target identifier is used to characterize the first instruction type, the database includes multiple first identifiers, and a second identifier corresponding to each of the first identifiers, the first identifier is used to characterize the scenario, and the second identifier is used to characterize the instruction type.

[0090] Step S30. Adjust the priority of the first instruction type to be greater than the priority of other instruction types in the database;

[0091] It can be understood that when it is recognized that the vehicle is in a certain target scenario, the priority of the first instruction type corresponding to the target scenario is adjusted to be greater than the priority of other instruction types, so that when the user's voice content is subsequently acquired, the first instruction type can be called to recognize the user's voice content first, combining the situational awareness of the vehicle's internal and external environment and driving data, so that the recognition accuracy of the voice content can be higher and the response speed can be faster.

[0092] It should be noted that during the driving process of the vehicle, the target scenario of the vehicle may be in dynamic change. Then, when the target scenario of the vehicle changes, the corresponding first instruction type may also change. Then, when the first instruction type changes, the priority between the various instruction types may also change. For example, when driving at high speed, the priority of instructions related to the entertainment system, such as "accelerate", "slow down", "navigate to the next exit", etc., will be related to driving safety. Therefore, the priority of the first instruction type that matches the target scenario of the vehicle can be dynamically adjusted, so that the subsequent recognition of the user's voice content is combined with the perception of the current scenario of the vehicle, thereby improving the accuracy and response speed of language recognition.

[0093] In some embodiments, adjusting the priority of the first instruction type to be greater than the priorities of other instruction types in the database includes:

[0094] The target value of the first instruction type is adjusted to a first value, and the target value of the other instruction types is adjusted to a second value, wherein the first value is used to represent a first priority, the second value is used to represent a second priority, and the first priority is greater than the second priority.

[0095] It is understandable that after classifying each instruction type based on big data analysis, and matching the first instruction type according to the target scenario, the target value of each instruction type can be dynamically adjusted, wherein the target value is used to characterize the priority size of the instruction type.

[0096] For example, the target value of the first instruction type is adjusted to 0, and the target value of other instruction types is adjusted to 1, wherein the priority of 0 is higher than the priority of 1. Thus, when the user's voice information is acquired, the first instruction type with a higher priority can be preferentially called to recognize the voice information, thereby improving the accuracy and response speed of recognizing the user's voice information.

[0097] Step S40: Obtain the user's first voice information, and preferentially call the first instruction type based on the voice recognition model to recognize the first voice information to determine the first instruction corresponding to the first voice information.

[0098] It is understandable that when acquiring the user's first voice information, multimodal input (such as gestures, touch) and other data can also be combined to improve the context awareness of the language recognition model. For example, when recognizing the voice command "turn on the air conditioner", if it is detected that the user is touching the air conditioner control area or making related gestures, the command can be responded to more quickly and accurately.

[0099] In some embodiments, the acquiring the first voice information of the user and preferentially calling the first instruction type to recognize the first voice information based on the voice recognition model includes:

[0100] Step S41. Acquire the first voice information, wherein the first voice information includes a first task to be performed and a second task to be performed;

[0101] It is understandable that the first voice information output by the user may include multiple concurrent tasks to be executed. For example, the voice information output by the user includes "turn on the wipers, turn up the air conditioner, turn on the interior lights, etc." Then, for the voice recognition model, it is necessary to identify multiple concurrent tasks to be executed and then output the target instructions corresponding to each task to be executed.

[0102] Step S42: Based on the speech recognition model, the first instruction type is preferentially called to identify the first task to be executed;

[0103] When there are multiple concurrent tasks to be executed, the first instruction model is preferentially called based on the speech recognition model to identify the first task to be executed, so that the target instruction most relevant to the target scenario currently in which the vehicle is located can be accurately and quickly output, thereby improving the working efficiency of the speech recognition model. For example, if the current target scenario of the vehicle is high-speed driving in the rain, then "turn on the wipers" in the above "turn on the wipers, increase the air conditioning, turn on the interior lighting, etc." is the first instruction type most relevant to the target scenario, and the task to be executed is preferentially identified and responded to, thereby ensuring safe driving of the vehicle.

[0104] Step S43: calling the other instruction types based on the speech recognition model to identify the other second tasks to be executed.

[0105] Therefore, when multiple tasks are running concurrently, the first instruction type can be called first to identify the first task to be executed based on the preset priority of the first instruction type, thereby ensuring that the speech recognition model can prioritize the output of target instructions corresponding to both the target scenario and the user voice, thereby improving the recognition accuracy and response speed of the speech recognition model.

[0106] In some embodiments, when there are multiple first tasks to be executed, the first instruction type is preferentially called based on the speech recognition model to identify the first execution, including:

[0107] Step S421. Determine the timestamp of receiving each of the first tasks to be executed;

[0108] Step S422: Based on the speech recognition model, the first instruction type is preferentially called, and each of the first tasks to be executed is identified in the order of the timestamps.

[0109] For example: when the target scenario is driving in rainy days with low visibility, the first voice information output by the user includes multiple first tasks to be executed, such as "turn on the wipers, refresh the navigation, turn on the fog lights", etc. It can be understood that the instruction types corresponding to the above-mentioned first tasks to be executed are all instruction types that match the target scenario. Therefore, each task to be executed can be responded to in sequence according to the time when each first task to be executed is received to meet user needs.

[0110] In some embodiments, the method further comprises:

[0111] Step S50. Acquire multiple second voice information of the user in the target scenario within a period of time;

[0112] It is understandable that when a user repeatedly sends a second voice message for a certain target scenario, it indicates that the user has a personalized preference control demand for the target scenario. Therefore, the embodiment of the present application collects multiple second voice messages of the user in the target scenario within a period of time.

[0113] Step S51. Recognize the plurality of second voice information based on the voice recognition model to determine a plurality of second instructions;

[0114] Step S52: If the plurality of second instructions are of the same instruction type, and the plurality of second instructions do not belong to the first instruction type, increase the priority of the second instruction type to which the plurality of second instructions belong.

[0115] It is understandable that if multiple second instructions do not belong to the first instruction type, it means that the user has issued other instructions that are different from the preset priority in the target scenario multiple times. For example: some users like to adjust the music when driving at low speed, while other users may pay more attention to air conditioning adjustment. Through long-term learning, the personalized priority configuration of each user can be gradually optimized. For another example, under urban road conditions, the preset first instruction type that matches the urban road conditions is an entertainment-related instruction type. However, the user has repeatedly issued voices such as "turn off the music" under the urban road conditions, which means that the multiple second instructions recognized do not match the preset instruction type. Then, in order to meet the personalized preference needs of users, the embodiment of the present application adjusts the instruction type that matches the target scenario and increases the priority of the instruction type to adapt to the user's preferences and needs.

[0116] In some embodiments, the vehicle includes a voice collection device, and when acquiring the first voice information of the user, the method further includes:

[0117] Obtaining ambient noise intensity and / or vehicle speed;

[0118] If the ambient noise intensity is greater than or equal to the set noise intensity and / or the vehicle speed is greater than or equal to the set vehicle speed, the noise reduction capability of the voice collection device is enhanced.

[0119] Exemplarily, the voice collection device includes a vehicle-mounted microphone for collecting the user's voice information. When the ambient noise is large and / or the vehicle speed is high, the impact of wind noise and / or ambient noise on voice collection can be reduced by increasing the sensitivity of the microphone and improving the noise reduction capability of the microphone, thereby reducing voice recognition errors caused by interference such as noise and wind noise.

[0120] See also Figure 2 , shows a structural diagram of a vehicle voice recognition device according to an embodiment of the present application.

[0121] like Figure 2 As shown, the second aspect of the embodiment of the present application provides a vehicle speech recognition device 200, including:

[0122] A first identification unit 201, configured to identify a target scenario in which the vehicle is located according to one or more of the internal environment data, the external environment data and the driving data of the vehicle;

[0123] An acquisition unit 202 is used to acquire, according to the target scenario, a first instruction type corresponding to the target scenario in a database, wherein the database includes multiple scenarios of the vehicle and an instruction type corresponding to each scenario;

[0124] An adjusting unit 203, configured to adjust the priority of the first instruction type to be greater than the priorities of other instruction types in the database;

[0125] The second recognition unit 204 is used to obtain the user's first voice information, and preferentially call the first instruction type to recognize the first voice information based on the voice recognition model to determine the first instruction corresponding to the first voice information.

[0126] According to a third aspect of an embodiment of the present application, a computer-readable storage medium is provided, in which at least one computer program instruction is stored. The at least one computer program instruction is loaded and executed by a processor to implement the operations performed by any method described in the first aspect.

[0127] The computer readable storage medium may be a portable compact disk read-only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the computer readable storage medium of the present application is not limited thereto, and in the present application, the readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, apparatus, or device.

[0128] The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more conductors, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0129] Program code for performing the operations of the present application may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0130] See also Figure 3 , which is a schematic diagram of the structure of a computer system of a vehicle suitable for implementing an embodiment of the present application.

[0131] According to a fourth aspect of an embodiment of the present application, a vehicle is provided, comprising one or more processors and one or more memories, wherein at least one program code is stored in the one or more memories, and the at least one program code is loaded and executed by the one or more processors to implement operations performed by any method of the first aspect.

[0132] like Figure 3 As shown, the vehicle 400 is represented in the form of a general computing device. The components of the vehicle 400 may include, but are not limited to: at least one processing unit 410, at least one storage unit 420, and a bus 430 connecting different system components (including the storage unit 420 and the processing unit 410).

[0133] The storage unit stores program codes, which can be executed by the processing unit 410, so that the processing unit 410 executes the steps described in the above “Embodiment Method” section of this specification according to various exemplary implementations of the present application.

[0134] The storage unit 420 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 421 and / or a cache 422 , and may further include a read-only memory unit (ROM) 423 .

[0135] The storage unit 420 may also include a program / utility 424 having a set (at least one) of program modules 425, such program modules 425 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0136] Bus 430 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0137] The vehicle 400 may also communicate with one or more external devices 500 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable a user to interact with the vehicle 400, and / or any device that enables the vehicle 400 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an I / O (input / output) interface 450, which may also be connected to a display unit 440 to display the communication content. Furthermore, the vehicle 400 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 460. As shown, the network adapter 460 communicates with other modules of the vehicle 400 via a bus 430. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the vehicle 400, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0138] The functions described herein may be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions may be stored as one or more instructions or codes on a computer-readable medium or transmitted via a computer-readable medium. Other examples and implementations are within the scope and spirit of the present invention and the appended claims. For example, due to the nature of software, the functions described above may be implemented using software executed by a processor, hardware, firmware, hard wiring, or a combination of any of these. In addition, each functional unit may be integrated into a processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit.

[0139] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of units can be 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 interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0140] The units described as separate components may or may not be physically separated, and the components of the control device may or may not be physical units, that is, they may be located in one place or distributed in multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0141] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or 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, server or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk, etc., which can store program code.

[0142] The above description is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present application shall be included in the scope of the claims of the present application.

Claims

1. A vehicle speech recognition method, characterized in that: include: Identifying a target scenario in which the vehicle is located based on one or more of the vehicle's internal environment data, external environment data, and driving data; According to the target scenario, obtaining a first instruction type corresponding to the target scenario in a database, wherein the database includes a plurality of scenarios of the vehicle and an instruction type corresponding to each scenario; adjusting the priority of the first instruction type to be greater than the priorities of other instruction types in the database; The user's first voice information is obtained, and the first instruction type is preferentially called to recognize the first voice information based on a voice recognition model to determine a first instruction corresponding to the first voice information.

2. The method according to claim 1, characterized in that The acquiring, according to the target scenario, a first instruction type corresponding to the target scenario in a database includes: Acquire a first target identifier, wherein the first target identifier is used to characterize the target scenario; Obtain a second target identifier corresponding to the first target identifier in the database, wherein the second target identifier is used to characterize the first instruction type, the database includes multiple first identifiers and a second identifier corresponding to each of the first identifiers, the first identifier is used to characterize the scenario, and the second identifier is used to characterize the instruction type.

3. The method according to claim 1 or 2, characterized in that: The step of adjusting the priority of the first instruction type to be greater than the priorities of other instruction types in the database includes: The target value of the first instruction type is adjusted to a first value, and the target value of the other instruction types is adjusted to a second value, wherein the first value is used to represent a first priority, the second value is used to represent a second priority, and the first priority is greater than the second priority.

4. The method according to claim 1, characterized in that: The acquiring the first voice information of the user and preferentially calling the first instruction type to recognize the first voice information based on the voice recognition model includes: Acquire the first voice information, wherein the first voice information includes a first task to be performed and a second task to be performed; Based on the speech recognition model, the first instruction type is preferentially called to identify the first task to be executed; The other instruction types are called based on the speech recognition model to recognize other second tasks to be performed.

5. The method according to claim 4, characterized in that When there are multiple first tasks to be executed, the first instruction type is preferentially called based on the speech recognition model to identify the first execution, including: Determine a timestamp of receiving each of the first tasks to be performed; The first instruction type is preferentially called based on the speech recognition model, and each of the first tasks to be executed is identified according to the sequence of the timestamps.

6. The method according to claim 1, characterized in that The method further comprises: Acquire a plurality of second voice information of the user in the target scenario within a period of time; Recognize the plurality of second voice information based on the voice recognition model to determine a plurality of second instructions; If the plurality of second instructions are of the same instruction type, and the plurality of second instructions do not belong to the first instruction type, the priority of the second instruction type to which the plurality of second instructions belong is increased.

7. The method according to claim 1, characterized in that The vehicle includes a voice collection device, and when acquiring the first voice information of the user, the method further includes: Obtaining ambient noise intensity and / or vehicle speed; If the ambient noise intensity is greater than or equal to the set noise intensity and / or the vehicle speed is greater than or equal to the set vehicle speed, the noise reduction capability of the voice collection device is enhanced.

8. A vehicle voice recognition device, characterized in that: include: A first recognition unit, configured to recognize a target scenario in which the vehicle is located based on one or more of internal environment data, external environment data, and driving data of the vehicle; an acquisition unit, configured to acquire, according to the target scenario, a first instruction type corresponding to the target scenario in a database, wherein the database includes a plurality of scenarios of the vehicle and an instruction type corresponding to each of the scenarios; an adjusting unit, configured to adjust the priority of the first instruction type to be greater than the priorities of other instruction types in the database; The second recognition unit is used to obtain the user's first voice information, and preferentially call the first instruction type to recognize the first voice information based on the voice recognition model to determine the first instruction corresponding to the first voice information.

9. A computer-readable storage medium, wherein at least one computer program instruction is stored in the computer-readable storage medium, and the at least one computer program instruction is loaded and executed by a processor to implement the operations performed by any one of the methods according to claims 1-7.

10. A vehicle, characterized in that: The method comprises one or more processors and one or more memories, wherein at least one program code is stored in the one or more memories, and the at least one program code is loaded and executed by the one or more processors to implement the operations performed by the method according to any one of claims 1 to 7.

Images