Voice control method, electronic device, and computer-readable storage medium

Abstract

Embodiments of the present application provide a voice control method, electronic device, and computer-readable storage medium. In some embodiments, the voice control method includes: in response to a vehicle being in continuous speaking mode and receiving multiple voice commands within the same time period, determining a logical relationship between the multiple voice commands, and determining a control command to be ultimately executed based on the logical relationship and the multiple voice commands. The logical relationship includes at least conflict and duplication.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of data processing, and more specifically, to a voice control method, an electronic device, and a computer-readable storage medium. Background Art

[0002] As vehicle technology improves, vehicle control technologies are becoming increasingly sophisticated. For example, some vehicles have added voice control functions to facilitate user control of the vehicle.

[0003] However, the inventors discovered that while voice control simplifies the user's vehicle control process, some issues still exist. For example, after triggering a voice command to turn on a function, the user immediately realizes that they no longer need it and triggers a voice command to turn it off. In this case, the vehicle will first turn the function on and then off, resulting in a poor user experience. Summary of the Invention

[0004] The embodiments of the present application provide a voice control method, an electronic device, and a computer-readable storage medium that can at least partially solve the above-mentioned problems or other problems existing in the prior art.

[0005] On the one hand, an embodiment of the present application provides a voice control method, including: in response to a vehicle being in a continuous speaking mode and obtaining multiple voice instructions within the same time period, determining the logical relationship among the multiple voice instructions, the logical relationship including at least conflict and repetition; and determining the control instruction to be finally executed based on the logical relationship among the multiple voice instructions and the multiple voice instructions.

[0006] On the other hand, an embodiment of the present application provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the voice control method mentioned in the above embodiment.

[0007] Another aspect of the embodiments of the present application provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the voice control method provided in the above embodiments is implemented.

[0008] According to some embodiments of this application, the vehicle is equipped with a continuous speaking mode, allowing users to interact with the vehicle computer without repeatedly saying the wake-up word or repeatedly triggering the voice recording control. This can further simplify user voice operations and reduce driving safety issues caused by users diverting their attention to trigger voice control services while driving. In the vehicle's continuous speaking mode, the vehicle computer performs logical relationship judgment on multiple voice commands triggered by the user in the same time period to determine the final control command to be executed, thereby providing users with better voice control services.

[0009] In some embodiments of the present application, for repeated voice commands triggered by the user in a short period of time, the vehicle computer merges or deletes the repeated voice commands based on the actual operating parameters of the components controlled by the repeated voice commands to obtain control instructions whose control effects are more in line with user habits or current scenarios, thereby optimizing the voice control logic and improving the user experience.

[0010] In some embodiments of the present application, for voice commands that cause processing logic conflicts and are triggered by the user in a short period of time, the vehicle computer responds to voice commands triggered by the user later, optimizes the vehicle computer voice control logic, intercepts erroneous voice commands, gives the user a chance to "regret", and improves the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Other features, objects and advantages of the present application will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings, in which:

[0012] Figure 1 is a schematic block diagram of a vehicle according to some embodiments of the present application;

[0013] Figure 2 is a flowchart of a voice control method according to some embodiments of the present application; and

[0014] Figure 3 is a schematic block diagram of an electronic device according to some embodiments of the present application. DETAILED DESCRIPTION

[0015] For a better understanding of the present application, various aspects of the present application will be described in more detail with reference to the accompanying drawings. It should be understood that these detailed descriptions are merely descriptions of exemplary embodiments of the present application and are not intended to limit the scope of the present application in any way. Throughout the specification, the same reference numerals refer to the same elements. The expression "and / or" includes any and all combinations of one or more of the associated listed items.

[0016] It should be understood that when a phrase such as "at least one of..." appears after a list of listed features, it modifies the entire list of features, rather than just the individual elements in the list. In addition, when describing embodiments of the present application, the use of "may" means "one or more embodiments of the present application."

[0017] Unless otherwise defined, all words used herein (including engineering terms and scientific and technological terms) have the same meaning as commonly understood by those skilled in the art to which this application belongs. It should also be understood that, unless otherwise specified in this application, words defined in commonly used dictionaries should be interpreted as having the same meaning as they do in the context of the relevant technology, and should not be interpreted in an idealized or overly formal sense.

[0018] It should be noted that, unless otherwise specified or inconsistent with the context, the embodiments and features of the embodiments in this application may be combined with each other. Furthermore, unless expressly limited or inconsistent with the context, the specific steps included in the methods described in this application are not necessarily limited to the order in which they are described, but may be performed in any order or in parallel. The present application will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

[0019] Figure 1 is a schematic block diagram of a vehicle 10 according to some embodiments of the present application. Figure 1 As shown, vehicle 10 may include a voice acquisition device 110, a head unit 120, an air conditioner 130, a light emitting device 140, a sound generator 150, and other components 160, such as windows and a sunroof. The voice acquisition device 110 may include a device, such as a microphone, capable of converting sound signals into digital signals. The collected voice data may be recognized by an offline voice engine within the head unit 120 or by a cloud-based system (not shown) with voice recognition capabilities. Based on the recognized voice commands, the head unit 120 may issue control commands to corresponding components (such as the air conditioner 130, the light emitting device 140, and the sound generator 150) to implement voice control of the vehicle 10. For example, the head unit 120 may issue control commands to the air conditioner 130 based on a specified voice command to adjust its operating mode and / or operating parameters. For another example, the head unit 120 may issue control commands to the light emitting device 140 or the sound generator 150 based on a specified voice command to control their operation. The light-emitting device 140 may include at least one of a display screen, interior light, ambient light, and other luminous components, not all of which are listed here. The light-emitting device 140 can be turned on or off under the control of the vehicle computer 120. Some light-emitting devices 140 can also adjust their brightness under the control of the vehicle computer 120.

[0020] It should be understood that, without departing from the teachings of this application, the vehicle computer 120 may also issue control instructions to other components 160 of the vehicle 10 based on specified voice instructions. The way in which the vehicle computer 120 processes voice instructions for controlling other components 160 can refer to the relevant descriptions of the way in which the vehicle computer 120 processes voice instructions for controlling the air conditioner 130, the way in which the light-emitting device 140 processes voice instructions, and the way in which the sounder 150 processes voice instructions, which are not listed one by one in this application.

[0021] Figure 2 2 is a flow chart of a voice control method 200 according to some embodiments of the present application. In some embodiments of the present application, the voice control method 200 of the vehicle 10 may be, for example, Figure 2 The voice control method 200 can be executed by the vehicle computer 120 and includes the following steps.

[0022] S21: In response to the vehicle being in a continuous speaking mode and acquiring multiple voice commands within a same time period, determining a logical relationship among the multiple voice commands, wherein the logical relationship includes at least conflict and repetition.

[0023] S22: Determine a control instruction to be finally executed based on the logical relationship between the multiple voice instructions and the multiple voice instructions.

[0024] According to some embodiments of the present application, vehicle 10 is provided with a continuous speaking mode, allowing users to interact with vehicle computer 120 without repeatedly saying the wake-up word or repeatedly triggering the voice recording control. This further simplifies user voice operations and reduces driving safety issues caused by users diverting their attention to trigger voice control services while driving. In vehicle 10's continuous speaking mode, vehicle computer 120 performs logical relationship analysis on multiple voice commands triggered by the user within the same time period to determine the final control command to be executed, thereby providing users with better voice control services.

[0025] For ease of understanding, the following Figure 2 The various steps of the voice control method 200 are described as examples.

[0026] First, the following exemplifies the collection of voice data and the acquisition of voice instructions.

[0027] In some embodiments of the present application, the vehicle 10 may set a continuous speaking mode for the voice control service. In the continuous speaking mode, if the user triggers the voice control function of the vehicle 10 through a wake-up word or a control (physical control or virtual control) set on the vehicle 10 for triggering voice recording, the vehicle 10 can continuously provide voice control services to the user. For example, after the user turns on the voice control service, the vehicle 10 can keep the voice collection device 110 in the on-state and directly perform voice recognition without determining whether the voice data collected contains the wake-up word. In the above scheme, the user does not need to repeatedly say the wake-up word or repeatedly trigger the voice recording control to interact with the vehicle computer 120, which can further simplify the user's voice operation and reduce driving safety issues caused by the user diverting their attention to trigger the voice control service while driving.

[0028] It should be understood that the vehicle 10 may also be configured with a discontinuous speaking mode for the voice control service. This mode involves collecting voice data after the voice control service is triggered by a wake-up word or other means, and detecting a pause in speech. Instead of directly collecting and recognizing voice data, the vehicle 10 waits until the user triggers the voice control service again by using a wake-up word or other means to perform the collection and recognition operations. In the discontinuous speaking mode, the vehicle 10 may directly determine a voice command as a control command after receiving it, or may determine a control command in the same manner as in the discontinuous speaking mode. This application does not impose any restrictions on this.

[0029] In some embodiments of the present application, when the vehicle 10 is in continuous speaking mode, the vehicle computer 120 or the voice collection device 110 may transmit the currently collected voice data to the cloud and / or an offline voice engine after detecting a gap in the user's speech. The vehicle computer 120 or the voice collection device 110 may determine a speaking gap by, but is not limited to, determining that a speaking gap exists if the voice collection device 110 has not detected a new voice signal after a first preset time has passed since the last voice signal. It should be understood that the first preset time is typically a relatively short period of time, and its specific value can be set as needed, for example, to 1.5 seconds, and this application does not impose any restrictions thereon. The vehicle computer 120 or the voice collection device 110 may also determine a speaking gap by other means, which is not limited thereto by this application.

[0030] As an example, the voice data is transmitted to an offline voice engine. In this example, the offline voice engine recognizes the voice data and transmits the recognition result to the vehicle computer 120. The vehicle computer 120 analyzes the recognition result to obtain a voice command.

[0031] As another example, voice data is transmitted to the cloud. In this example, the cloud recognizes the voice data uploaded by vehicle 10 and transmits the recognition results to vehicle computer 120. Vehicle computer 120 analyzes the recognition results to obtain voice commands. Optionally, after recognizing the received voice data, the cloud can determine the recognition results to be fed back to vehicle 10 based on the recognized voice content. For example, if the recognized voice content indicates a voice command that triggers system control or vehicle control, the cloud can feed back the recognition results including the voice content to vehicle 10. If the recognized voice content indicates a voice command that triggers a data query requiring internet access, the cloud determines whether it has internet query capabilities. If the cloud determines that it has internet query capabilities, it can use the internet query capabilities to query the user's requested data (e.g., recent weather conditions) and generate and feed back a recognition result based on the retrieved data. The recognition result includes a voice command instructing vehicle 10 to feed back the retrieved data. If the cloud determines that it does not have internet query capabilities, the cloud can feed back the recognition results including the recognized voice content to vehicle 10.

[0032] It should be understood that, without departing from the teachings of this application, the cloud may not perform a judgment operation on the recognized voice content after recognizing the received voice data, and directly feedback the recognition results containing the recognized voice content to the vehicle 10. This application does not impose any restrictions on this.

[0033] As another example, voice data is transmitted to an offline voice engine and the cloud. In this example, the offline voice engine and the cloud each recognize the voice data and provide feedback on the recognition results. The cloud's feedback method for the recognition results is described above and will not be further elaborated here. For example, the cloud has a network query function. Because the offline voice engine has low transmission latency, the vehicle computer 120 typically receives the recognition results from the offline voice engine first. The vehicle computer 120 parses the offline voice engine's recognition results. If the parsing result indicates that the user triggered a voice command for system control or vehicle control, the vehicle computer 120 may identify the voice command in the parsing result as the voice command corresponding to the voice data. If the parsing result indicates that the user triggered a voice command for data query requiring internet access or if recognition failed, the vehicle computer 120 may wait for feedback on the recognition results from the cloud. In this solution, compared to simply sending voice data to the cloud or the offline voice engine, the vehicle computer can obtain the voice command corresponding to the voice data more quickly, thereby improving the response speed of the vehicle computer 120.

[0034] It is understandable that in some scenarios, the vehicle computer 120 may receive the recognition results sent by the offline voice engine and the recognition results sent by the cloud at the same time. In this case, the vehicle computer 120 can determine the voice command corresponding to the voice data based on the command type in the recognition result and the preset arbitration mechanism. For example, the preset arbitration mechanism indicates: if the recognition result sent by the offline voice engine and the recognition result sent by the cloud both indicate that the voice command corresponding to the voice data is a voice command of the system control type or the vehicle control type, then the voice command corresponding to the voice data is determined based on the recognition result sent by the offline voice engine; if the recognition result sent by the offline voice engine and the recognition result sent by the cloud both indicate that the voice command corresponding to the voice data is a voice command of the data query type using the Internet, then the voice command corresponding to the voice data is determined based on the recognition result sent by the cloud.

[0035] It should be understood that, under normal circumstances, the recognition results of the offline voice engine and the cloud are the same. Even if there are differences, the instruction type should be able to remain consistent. If there is an inconsistency between the two in some special cases, it can be pre-set to use the cloud recognition result or the offline voice engine recognition result as the basis.

[0036] After completing the exemplary description of the vehicle computer 120 acquiring the voice command corresponding to the voice data, the following exemplary description is given of the manner in which the vehicle computer 120 processes the acquired voice command.

[0037] Because the vehicle 10 is in continuous speech mode, the user's subjective thoughts may change at any time. For example, a user may trigger a voice command to turn on a function and then immediately trigger a voice command to turn off the function. If the vehicle computer 120 sends all these received voice commands to the components it controls, it may place unnecessary data processing burden on the processing module of the component. In addition, the repeated changes in component status may easily cause wear and tear on the component, shortening its service life.

[0038] Based on this, in some embodiments of the present application, after receiving the voice command corresponding to the voice data, the vehicle computer 120 determines whether other voice commands have been received within the time period in which the voice command was received. If it is determined that no other voice commands have been received, the voice command is executed. If other voice commands have been received, the control command to be ultimately executed is determined based on the logical relationship between the voice command and the other voice commands. For example, the vehicle computer 120 may determine the logical relationship between multiple voice commands and determine the control command to be ultimately executed based on the logical relationship and the multiple voice commands. The logical relationship includes at least conflict and duplication.

[0039] For ease of understanding, the following first provides an example of how the vehicle computer 120 determines whether multiple voice commands are obtained within the same time period.

[0040] In some embodiments of the present application, a queue to be executed is provided in the vehicle computer 120, and the voice instructions in the queue to be executed whose time difference between the time triggered and the current time is greater than or equal to the time threshold are executed. After acquiring the voice instruction, the vehicle computer 120 can add the acquired voice instruction to the queue to be executed, and record the time when the voice instruction was triggered in the queue to be executed. The vehicle computer 120 can determine whether there are multiple voice instructions through the queue to be executed. For example, if there are other voice instructions in the queue to be executed in addition to the voice instruction, it means that the vehicle computer 120 has received multiple voice instructions in the same time period, and it is necessary to determine the control instruction based on the logical relationship between the multiple voice instructions.

[0041] In the above scheme, since the acquired voice commands are all stored in the queue to be executed, and the voice commands in the queue to be executed whose time difference between the triggered time and the current time is greater than or equal to the time threshold will be automatically executed, it is convenient for the vehicle computer 120 to determine whether multiple voice commands are received in the same time period. It also allows the vehicle computer 120 to avoid the need to set up a task for each voice command to detect whether it has reached the time for the user to "regret", reducing the algorithm complexity of the vehicle computer 120.

[0042] It should be understood that the time when the voice command is triggered can be the time when the voice data is collected, or it can be the time when the vehicle computer 120 obtains the voice command, and this application does not impose any restrictions on this.

[0043] It should be understood that, without departing from the teachings of this application, in addition to determining whether multiple voice instructions are obtained in the same time period through the queue to be executed, other methods can also be used to determine, for example, based on the time when the voice instruction is triggered and the predefined time window width, whether multiple voice instructions are received in the time period corresponding to the voice instruction. This application does not impose any restrictions on this.

[0044] After completing the exemplary description of the manner in which the vehicle computer 120 determines whether multiple voice commands are acquired within the same time period, the following exemplary description is given of the manner in which the vehicle computer 120 determines the logical relationship between the multiple voice commands.

[0045] In some embodiments of the present application, the vehicle computer 120 may determine the logical relationships between multiple voice commands. For example, if the vehicle computer 120 receives voice commands A, B, and C within the same time period, the vehicle computer 120 may determine the following logical relationships: the logical relationship between voice commands A and B, the logical relationship between voice commands A and C, and the logical relationship between voice commands B and C.

[0046] In other embodiments of the present application, the vehicle computer 120 adds the acquired voice command to a queue to be executed, and each time a voice command is added, determines the logical relationship between the newly added voice command and the previously added voice command in the queue. For example, if the previously added voice commands to the queue include, in order of time, voice commands B and C, and the newly added voice command is voice command A, the vehicle computer 120 then determines the logical relationship between voice commands A and B, and between voice commands A and C. Because the logical relationship between voice commands C and B was already determined when voice command C was added to the queue, and both remain cached in the queue, this indicates that there is no conflicting or duplicate logical relationship between them. Therefore, when voice command A is added, there is no need to determine the logical relationship between voice commands C and B again. As can be seen from the above, compared to determining the logical relationship between multiple voice commands, this solution can effectively determine the logical relationship between multiple voice commands while reducing the data processing workload of the vehicle computer 120 and minimizing the waste of computing resources.

[0047] In some embodiments of the present application, when determining the logical relationship between two voice commands, the vehicle computer 120 first determines whether the components controlled by the two voice commands are the same. If it is determined that the components controlled by the two voice commands are different, the logical relationship between the two voice commands may be determined to be irrelevant. If it is determined that the components controlled by the two voice commands are the same, it may be determined whether the functions of the two voice commands are the same. If they are the same, the two voice commands may be determined to be conflicting or redundant based on their control purposes. If they are different, the logical relationship between the two voice commands may be determined to be irrelevant. The vehicle computer 120 may determine whether the components / functions controlled by the two voice commands are the same by determining whether the instruction codes corresponding to the components / functions in the two voice commands are the same.

[0048] Taking the voice commands obtained by the vehicle computer 120 in the same time period as follows: voice command A instructing to increase the air-conditioning temperature, voice command B instructing to increase the multimedia volume, voice command C instructing to lower the air-conditioning temperature, voice command D instructing to increase the air-conditioning temperature, and voice command E instructing to increase the air-conditioning wind speed, the vehicle computer 120 needs to determine the logical relationship between voice command A and voice command B, voice command C, voice command D, and voice command E respectively.

[0049] In the process of determining the logical relationship between voice command A and voice command B, since the component controlled by voice command A is the air conditioner 130 and the component controlled by voice command B is the speaker 150, the components controlled by the two are different. Therefore, the vehicle computer 120 can determine that the logical relationship between voice command A and voice command B is irrelevant.

[0050] In the process of determining the logical relationship between voice command A and voice command C, since the components controlled by voice command A and voice command C are both the air conditioner 130, and the functions controlled are both the output temperature of the air conditioner 130, but the temperature adjustment directions are different, the vehicle computer 120 can determine that the logical relationship between voice command A and voice command C is a conflict.

[0051] In the process of determining the logical relationship between voice command A and voice command D, since the components controlled by voice command A and voice command D are both the air conditioner 130, the functions controlled are both the output temperature of the air conditioner 130, and the temperature adjustment directions are the same, the vehicle computer 120 can determine that the logical relationship between voice command A and voice command D is repeated.

[0052] It is understandable that in some scenarios, if voice command A and voice command D respectively instruct to increase the air-conditioning temperature to different degrees, although both increase the air-conditioning temperature, due to the different target temperatures they actually control, the vehicle computer 120 may determine that the logical relationship between the two is a conflict.

[0053] In the process of determining the logical relationship between voice command A and voice command E, since the components controlled by voice command A and voice command E are both the air conditioner 130, but the functions controlled are output temperature and wind speed, respectively, the vehicle computer 120 can determine that the logical relationship between voice command A and voice command E is irrelevant.

[0054] It should be understood that, without departing from the teachings of this application, the logical relationship between two voice instructions can also be determined based on other methods, and this application does not limit this.

[0055] After completing the exemplary description of how the vehicle computer 120 determines the logical relationship between voice commands, the following exemplary description is given of how the vehicle computer 120 processes repeated voice commands.

[0056] In some embodiments of the present application, if the vehicle computer 120 determines that there are duplicate voice commands among multiple voice commands, it can directly delete or merge the duplicate voice commands to obtain a control command. Deletion can mean retaining one of the multiple duplicate voice commands as a control command, and merging can mean generating a control command that has the same execution effect as the duplicate voice commands being executed, replacing the multiple duplicate voice commands. In the above solution, deleting or merging duplicate voice commands can reduce the number of responses of the processing module of the component controlled by the voice command, thereby reducing resource consumption.

[0057] In other embodiments of the present application, if the vehicle computer 120 determines that there are repeated voice instructions among multiple voice instructions, it can obtain the actual operating parameters of the component controlled by the repeated voice instructions and the reference operating parameters of the component, and merge or delete the repeated voice instructions based on the numerical relationship between the actual operating parameters and the reference operating parameters to obtain control instructions. The reference operating parameters can be determined based on user behavior data and / or surrounding environmental parameters. In the above solution, the vehicle computer 120 merges or deletes repeated voice instructions to obtain control instructions whose control effects are more in line with user habits or current scenarios, thereby optimizing the voice control logic of the vehicle computer 120 and improving the user experience.

[0058] It should be understood that the reference operating parameters may also be determined in other ways without departing from the teachings of the present application, and the present application does not impose any limitation thereto.

[0059] It should be noted that in the technical solution of the present disclosure, the acquisition, storage and application of user behavior data involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals. It should also be noted that the historical data of output temperature, etc. included in the user behavior data in this embodiment are all obtained for the purpose of determining reference operating parameters and after being authorized by the user (that is, with the consent of the user himself). In addition, the information / data obtained is not intended to characterize a specific type of user, and therefore cannot reflect the personal information of a specific type of user.

[0060] As an example, the vehicle computer 120 may combine or delete repeated voice commands based on the numerical relationship between the actual operating parameter and the reference operating parameter to obtain a control command, including but not limited to: if the vehicle computer 120 determines that the numerical relationship meets a preset combining condition, the repeated voice commands are combined to obtain a control command, and the execution effect of the control command is the same as the execution effect of all repeated voice commands being executed. If the vehicle computer 120 determines that the numerical relationship does not meet the preset combining condition, the repeated voice commands are deleted to obtain a control command, where the control command is one of the repeated voice commands.

[0061] For example, the preset merging condition may indicate that: when the adjustment direction of the operating parameter indicated by the voice instruction is the same as the change direction of the actual operating parameter of the component to the reference operating parameter, if the numerical relationship between the actual operating parameter and the reference operating parameter indicates that the difference between the actual operating parameter and the reference operating parameter is greater than a preset threshold, it is determined that the merging condition is met.

[0062] It should be understood that, without departing from the teachings of this application, if the adjustment direction of the operating parameter indicated by the voice command is opposite to the change direction, the vehicle computer 120 may determine that the merging condition is not currently met. Alternatively, the vehicle computer 120 may further determine based on the numerical relationship between the actual operating parameter and the reference operating parameter. For example, if the difference between the actual operating parameter and the reference operating parameter is less than or equal to a preset threshold, the vehicle computer 120 may determine that the merging condition is met. The preset threshold may be determined based on the type of component, the function of the component controlled by the voice command, development experience, etc., and is not limited here.

[0063] It should be understood that the merging conditions can be set as needed without departing from the teachings of this application, and this application does not impose any restrictions on this.

[0064] For ease of understanding, the process of merging or deleting repeated voice commands is exemplarily described below with reference to some specific components in the vehicle 10 .

[0065] Example 1

[0066] In some embodiments of the present application, the component controlled by the voice command is the speaker 150 of the vehicle 10, and the repeated voice command functions to adjust the volume of the speaker 150. In this scenario, the actual operating parameter of the component includes the actual volume of the speaker 150, the user behavior data of the component includes historical volume data of the speaker 150, and the reference operating data includes a reference volume determined based on the historical volume data. For example, the vehicle computer 120 may determine a value, such as a mode or mean, of the volume of the speaker 150 based on the historical volume data. This value may reflect the volume that the user is accustomed to using, and the vehicle computer 120 may determine this value as the reference volume.

[0067] For example, if the vehicle computer 120 receives N voice commands for increasing the volume in the same time period (N is an integer greater than 1 in this article), and the volume adjustment value currently set on the vehicle computer 120 is a decibel, the vehicle computer 120 processes the repeated voice commands as follows:

[0068] If the current actual volume is lower than the reference volume, the vehicle computer 120 determines that the adjustment direction is the same as the change direction, and continues to determine whether the difference between the actual volume and the reference volume is greater than a first threshold. If so, the N voice commands are merged to obtain a control command instructing to increase the volume by N*a decibels. If not, the N voice commands are deleted to remove N-1 voice commands and leave one voice command as the control command instructing to increase the volume by a decibel.

[0069] If the current actual volume is greater than or equal to the reference volume, the vehicle computer 120 may determine that the adjustment direction is opposite to the change direction, and delete the N voice commands to remove N-1 voice commands and leave one voice command as a control command, which instructs to increase the volume by a decibel.

[0070] For example, if the vehicle computer 120 receives N voice commands to lower the volume in the same time period, and the current volume adjustment setting of the vehicle computer 120 is a decibel, the vehicle computer 120 processes the repeated voice commands as follows:

[0071] If the current actual volume is less than or equal to the reference volume, the vehicle computer 120 determines that the adjustment direction is opposite to the change direction, and deletes N voice commands to remove N-1 voice commands and leaves one voice command as the control command. The final control command indicates to increase the volume by a decibel.

[0072] If the current actual volume is greater than the reference volume, the vehicle computer 120 determines that the adjustment direction and the change direction are the same, and continues to determine whether the difference between the actual volume and the reference volume is greater than the first threshold. If it is determined to be so, the N voice instructions are merged to obtain a control instruction instructing to increase the volume by N*a decibels. If it is determined not to be, the N voice instructions are deleted to remove N-1 voice instructions and the remaining voice instruction is used as the control instruction, which instructs to increase the volume by a decibel.

[0073] It should be understood that the first threshold may be a preset value, or may be determined according to the value of N*a. For example, the first threshold may be equal to or slightly less than N*a.

[0074] It should be understood that voice commands are queued for execution. Typically, there are two repeated voice commands, i.e., N=2. If the two voice commands respectively instruct to increase the volume by a1 decibels and a2 decibels (a1≠a2), then the control command obtained after the merged processing instructs to increase the volume by (a1+a2) decibels, and the first threshold value may be equal to or slightly less than a1+a2. In other words, the control effect of the merged control command is determined based on the control effect achieved by the repeated voice commands, and the first threshold value may also be determined based on the control effect achieved by the repeated voice commands.

[0075] From the above content, it can be seen that when the adjustment direction and the change direction are the same and the actual volume and the reference volume are far apart, the car computer 120 will merge the voice commands to make the adjusted volume closer to the reference volume, more in line with the user's usage habits, reduce the probability of the user triggering repeated voice commands again, improve the user experience, and reduce the data processing volume of the car computer 120 to a certain extent.

[0076] Example 2

[0077] In some embodiments of the present application, the component controlled by the voice command is the air conditioner 130 of the vehicle 10, and the repeated voice command functions to adjust the output temperature of the air conditioner 130. In this scenario, the actual operating parameter of the component includes the actual output temperature of the air conditioner 130, the user behavior data includes historical data on the output temperature of the air conditioner 130, and the reference operating parameter includes a reference output temperature determined based on the historical output temperature data.

[0078] For example, the historical output temperature data includes the output temperatures of the air conditioner 130 at different weather temperatures. If the same weather temperature corresponds to multiple output temperatures, the mode or average of the multiple output temperatures can be used as the output temperature corresponding to that weather temperature. The vehicle computer 120 can determine the reference output temperature based on the historical output temperature data by obtaining the current weather temperature and determining the output temperature corresponding to that weather temperature as the reference output temperature.

[0079] It should be understood that the reference output temperature of the air conditioner may be set in other ways without departing from the teachings of this application, and this application does not limit this.

[0080] For example, if the vehicle computer 120 receives N voice commands to increase the air conditioning temperature during the same time period, and the temperature adjustment amount currently set on the vehicle computer 120 is b°, the vehicle computer 120 processes the repeated voice commands as follows:

[0081] If the current actual output temperature of the air conditioner 130 is lower than the reference output temperature, the vehicle computer 120 determines that the adjustment direction and the change direction are the same, and continues to determine whether the difference between the actual output temperature and the reference output temperature is greater than a second threshold. If so, the N voice commands are merged to obtain a control command instructing to increase the output temperature by N*b°. If not, the N voice commands are deleted to remove N-1 voice commands and leave one remaining voice command as the control command instructing to increase the output temperature by b°.

[0082] If the current actual output temperature of the air conditioner 130 is greater than the reference output temperature, it is determined that the adjustment direction and the change direction are opposite, and the N voice instructions are deleted to remove N-1 voice instructions and the remaining voice instruction is used as a control instruction, which instructs to increase the output temperature by b°.

[0083] For example, if the vehicle computer 120 receives N voice commands to lower the air conditioner temperature during the same time period, and the temperature adjustment amount currently set on the vehicle computer 120 is b°, the vehicle computer 120 processes the repeated voice commands as follows:

[0084] If the current actual output temperature of the air conditioner 130 is less than or equal to the reference output temperature, it is determined that the adjustment direction and the change direction are opposite, and the N voice instructions are deleted to remove N-1 voice instructions and the remaining voice instruction is used as the control instruction, which instructs to reduce the output temperature by b°;

[0085] If the current actual output temperature of the air conditioner 130 is greater than the reference output temperature, the vehicle computer 120 determines that the adjustment direction and the change direction are the same, and continues to determine whether the difference between the actual output temperature and the reference output temperature is greater than a second threshold. If it is determined to be so, the N voice instructions are merged to obtain a control instruction instructing to lower the output temperature by N*b°. If it is determined not to be, the N voice instructions are deleted to remove N-1 voice instructions and the remaining voice instruction is used as the control instruction, which instructs to lower the output temperature by b°.

[0086] It should be understood that the second threshold may be a preset value, or may be determined according to the value of N*b. For example, the second threshold may be equal to or slightly less than N*b.

[0087] It should be understood that voice commands are queued for execution. Typically, there are two repeated voice commands, i.e., N=2. If the two voice commands respectively instruct to increase the volume by b1 degrees and b2 degrees (b1≠b2), then the control command obtained after the merged processing instructs to increase the volume by (b1+b2) degrees, and the second threshold value may be equal to or slightly less than b1+b2. In other words, the control effect of the merged control command is determined based on the control effect achieved by the repeated voice commands, and the second threshold value may also be determined based on the control effect achieved by the repeated voice commands.

[0088] From the above content, it can be seen that when the current adjustment direction and the change direction are the same and the actual output temperature and the reference output temperature are far apart, the vehicle computer 120 will merge the voice commands to make the adjusted output temperature closer to the reference output temperature, which is more in line with the user's usage habits, reduces the probability of the user triggering repeated voice commands again, improves the user experience, and reduces the data processing volume of the vehicle computer 120 to a certain extent.

[0089] It should be understood that the voice instructions corresponding to the air conditioner 130 can also include voice instructions for instructing wind speed adjustment, etc. The processing logic of the vehicle computer 120 for such repeated voice instructions can refer to the processing logic of repeated voice instructions for output temperature adjustment, which will not be repeated here.

[0090] Example 3

[0091] In some embodiments of the present application, the component controlled by the voice command is the light emitting device 140 of the vehicle 10, and the repeated voice command functions to adjust the brightness of the light emitting device 140. In this scenario, the actual operating parameter of the component includes the current brightness of the light emitting device 140, and the reference operating parameter includes a reference brightness of the light emitting device 140. The reference brightness can be determined based on historical brightness data of the light emitting device 140 and / or environmental parameters of the vehicle 10. The environmental parameters of the vehicle 10 include the ambient brightness detected by the vehicle 10 or the weather information of the day queried by the vehicle 10.

[0092] As an example, the vehicle computer 120 may store screen brightness corresponding to different ambient brightnesses. In the process of determining the reference brightness, the vehicle computer 120 may use the screen brightness corresponding to the detected ambient brightness as the reference brightness.

[0093] It should be understood that the screen brightness corresponding to different ambient brightness can be set by the manufacturer or user, or it can be determined by the vehicle computer 120 based on historical data of the brightness of the light-emitting device under the ambient brightness. This application does not impose any restrictions on this.

[0094] As another example, the vehicle computer 120 may store screen brightness corresponding to different weather conditions. When determining the reference brightness, the vehicle computer 120 may use the screen brightness corresponding to the current weather conditions as the reference brightness.

[0095] It should be understood that the screen brightness corresponding to different weather conditions can be set by the manufacturer or the user, or can be determined by the vehicle computer 120 based on historical data of the brightness of the light-emitting device under the weather conditions. This application does not impose any restrictions on this.

[0096] It should be understood that, without departing from the teachings of this application, the vehicle computer 120 may also determine the reference brightness in other ways, and this application does not limit this.

[0097] Assume that the vehicle computer 120 receives N voice commands for turning on the light emitting device 140 in the same time period, and the temperature adjustment value currently set by the vehicle computer 120 is t cd / m 2 For example, the vehicle computer 120 processes repeated voice commands as follows:

[0098] If the current brightness of the light emitting device 140 is lower than the reference brightness, the vehicle computer 120 determines that the adjustment direction is the same as the change direction, and continues to determine whether the difference between the current brightness and the reference brightness is greater than a third threshold. If so, the N voice commands are combined to obtain an instruction to increase the brightness by N*t cd / m 2 If it is determined that it is not, the N voice instructions are deleted to remove N-1 voice instructions and the remaining voice instruction is used as the control instruction, which instructs to increase the brightness by t cd / m 2 ;

[0099] If the current brightness of the light emitting device 140 is greater than or equal to the reference brightness, it is determined that the adjustment direction is opposite to the change direction, and the N voice instructions are deleted to remove N-1 voice instructions and the remaining voice instruction is used as the control instruction, which instructs to increase the brightness by t cd / m 2 .

[0100] Assume that the vehicle computer 120 receives N voice commands instructing to reduce the temperature of the light emitting device 140 in the same time period, and the temperature adjustment value currently set by the vehicle computer 120 is t cd / m 2 For example, the vehicle computer 120 processes repeated voice commands as follows:

[0101] If the current brightness of the light emitting device 140 is less than or equal to the reference brightness, it is determined that the adjustment direction is opposite to the change direction, and the N voice instructions are deleted to remove N-1 voice instructions and the remaining voice instruction is used as the control instruction, which instructs to reduce the brightness by t cd / m 2 ;

[0102] If the current brightness of the light emitting device 140 is greater than the reference brightness, the vehicle computer 120 determines that the adjustment direction is the same as the change direction, and continues to determine whether the difference between the actual output temperature and the reference output temperature is greater than a third threshold. If it is determined to be, the N voice commands are combined and processed to obtain an instruction to reduce the brightness by N*t cd / m 2 If it is determined that it is not, the N voice instructions are deleted to remove N-1 voice instructions and the remaining voice instruction is used as the control instruction, which instructs to reduce the brightness by t cd / m 2 .

[0103] It should be understood that the third threshold may be a preset value, or may be determined according to the value of N*t. For example, the third threshold may be equal to or slightly less than N*t.

[0104] It should be understood that the voice commands are queued for execution. Normally, there are two repeated voice commands, that is, N=2. If the two voice commands respectively indicate to increase the volume by t1 cd / m 2 and t2 cd / m 2 (t1≠t2), then the control instruction obtained after the combined processing indicates to increase the volume by (t1+t2) cd / m 2 , and the third threshold value can be equal to or slightly less than t1 + t2. In other words, the control effect of the combined control instruction is determined based on the control effect achieved by each repeated voice instruction, and the third threshold value can also be determined based on the control effect achieved by each repeated voice instruction.

[0105] From the above content, it can be seen that when the current brightness and the reference brightness are far apart, and the current adjustment direction and the change direction are the same, the car computer 120 will merge the voice commands to make the adjusted brightness closer to the reference brightness, more in line with the user's usage habits, reduce the probability of the user triggering repeated voice commands again, improve the user experience, and reduce the data processing volume of the car computer 120 to a certain extent.

[0106] It should be understood that, without departing from the teachings of the present application, the voice instructions for controlling other components of the vehicle 10 may also refer to the exemplary descriptions of the above embodiments, and the present application does not limit this.

[0107] After completing the exemplary description of the manner in which the vehicle computer 120 processes repeated voice commands, the following exemplary description of the manner in which the vehicle computer 120 processes conflicting voice commands is given.

[0108] In some embodiments of the present application, after determining that conflicting voice commands exist among multiple voice commands, the vehicle computer 120 may determine the conflicting voice command that was triggered later as the control command. For example, if voice commands A and C conflict, and voice command C is added to the queue to be executed first, while voice command A is about to be added to the queue to be executed, voice command A will be determined as the control command.

[0109] Optionally, the determined control instruction can be directly sent to the processing module of the controlled component, or it can be added to the queue to be executed and its triggering time can be updated. This application does not impose any restrictions on this.

[0110] In the above solution, the vehicle computer 120 determines the late-triggered voice command as a control command, optimizes the voice control logic of the vehicle computer 120, intercepts erroneous voice commands, gives the user a chance to "regret", and improves the user experience.

[0111] According to some embodiments of the present application, vehicle 10 is provided with a continuous speaking mode, allowing users to interact with vehicle computer 120 without repeatedly saying the wake-up word or repeatedly triggering the voice recording control. This further simplifies user voice operations and reduces driving safety issues caused by users diverting their attention to trigger voice control services while driving. In vehicle 10's continuous speaking mode, vehicle computer 120 performs logical relationship analysis on multiple voice commands triggered by the user within the same time period to determine the final control command to be executed, thereby providing users with better voice control services.

[0112] The steps of the various methods above are divided only for the purpose of clear description. During implementation, they can be combined into one step or some steps can be split and decomposed into multiple steps. As long as they include the same logical relationship, they are all within the scope of protection of this patent. Adding insignificant modifications or introducing insignificant designs to the algorithm or process without changing the core design of the algorithm and process are all within the scope of protection of this patent.

[0113] An embodiment of the present application also provides an electronic device, which may include: at least one processor and a memory, the memory being communicatively connected to the at least one processor and storing instructions that can be executed by the at least one processor, and the instructions being executed by the at least one processor so that the at least one processor can execute the voice control method 200 mentioned in the above embodiment.

[0114] In some embodiments of the present application, the electronic device may be the vehicle computer 120 in the vehicle 10 , or may be other terminals that can control components in the vehicle 10 , and the present application does not impose any restrictions on this.

[0115] One embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the voice control method 200 mentioned in the above embodiment is implemented.

[0116] Figure 3 is a schematic block diagram of an electronic device 30 according to some embodiments of the present application. Figure 3 As shown, the electronic device 30 includes a processor 301, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 302 or a computer program loaded from a memory 308 into a random access memory (RAM) 303. Various programs and data required for the operation of the electronic device 30 can also be stored in the RAM 303. The processor 301, ROM 302, and RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0117] Multiple components in electronic device 30 are connected to I / O interface 305, including: an input unit 306, such as buttons and a touch screen; an output unit 307, connected to, for example, various types of displays and speakers, to output various forms of signals; a memory 308, including any medium for storing computer-executable programs; and a communication unit 309, such as a network card, a modem, a wireless communication transceiver, etc. Communication unit 309 allows electronic device 30 to exchange information / data with other devices via, for example, a local area network or other wireless communication network.

[0118] The processor 301 can be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The processor 301 performs the various methods and processes described above, such as the voice control method mentioned in the above embodiment. For example, in some embodiments, the voice control method mentioned in the above embodiment can be implemented as a computer software program, which is tangibly contained in a computer-readable storage medium, such as memory 308. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 30 via ROM 302 and / or communication unit 309. When the computer program is loaded into RAM 303 and executed by the processor 301, one or more steps of the voice control method mentioned in the above embodiment described above can be performed. Alternatively, in other embodiments, the processor 301 can be configured to perform the voice control method mentioned in the above embodiment by any other appropriate means (e.g., by means of firmware).

[0119] Various aspects of the present application are described herein with reference to flowcharts and / or sequence diagrams of methods, devices (systems), and computer program products according to exemplary embodiments of the present application. It should be understood that each step of the flowcharts and / or sequence diagrams, and combinations of the steps in the flowcharts and / or sequence diagrams, can be implemented by computer-readable program instructions.

[0120] These computer-readable program instructions can be provided to a processor in an electronic device, a general-purpose computer, a special-purpose computer, or a processing unit of other programmable data processing devices, thereby producing a machine such that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device is generated that implements the functions / steps specified in one or more steps in the flowchart and / or timing diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, where these instructions cause the computer, programmable data processing device, and / or other device to operate in a specific manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing various aspects of the functions / steps specified in one or more steps in the flowchart and / or timing diagram.

[0121] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / steps specified in one or more steps in the flowchart and / or timing diagram.

[0122] The flowcharts and timing diagrams in the accompanying drawings show the possible architectures, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each step in the flowchart or timing diagram can represent a portion of a module, program segment or instruction, and the portion of the module, program segment or instruction contains one or more executable instructions for implementing the specified logical function. In some alternative embodiments, the functions marked in the steps can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each step in the timing diagram and / or flowchart, and the combination of steps in the timing diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or can be implemented using a combination of dedicated hardware and computer instructions.

[0123] The above description is merely an embodiment of the present application and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of protection involved in this application is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the technical concept. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in this application.

Claims

1. A voice control method, characterized in that: include: In response to the vehicle being in a continuous speaking mode and acquiring multiple voice commands within a same time period, determining a logical relationship among the multiple voice commands, the logical relationship including at least conflict and repetition; as well as Determining a control instruction to be finally executed based on a logical relationship between the multiple voice instructions and the multiple voice instructions; The determining of the control instruction to be finally executed based on the logical relationship of the multiple voice instructions and the multiple voice instructions includes: In response to an indication by the logical relationship of the plurality of voice instructions that a repeated voice instruction exists among the plurality of voice instructions, obtaining actual operating parameters of a component controlled by the repeated voice instruction and reference operating parameters of the controlled component; and According to the numerical relationship between the actual operating parameter and the reference operating parameter, the repeated voice instructions are merged or deleted to obtain the control instruction.

2. The method according to claim 1, wherein The merging or deleting the repeated voice instructions according to the numerical relationship between the actual operating parameter and the reference operating parameter to obtain the control instruction includes: In response to the numerical relationship meeting a preset merging condition, merging the repeated voice instructions to obtain the control instruction, wherein the execution effect of the control instruction is the same as the execution effect of all the repeated voice instructions being executed; and In response to the numerical relationship not meeting a preset merging condition, the repeated voice instructions are deleted to obtain the control instruction, where the control instruction is one of the repeated voice instructions.

3. The method according to claim 1, wherein The reference operating parameters of the component are determined according to user behavior data of the component.

4. The method according to claim 3, wherein: The component controlled by the repeated voice command includes a sounder of the vehicle, the function of the repeated voice command is to adjust the volume of the sounder, the actual operating parameter includes the actual volume of the sounder, and the user behavior data includes historical data of the volume of the sounder; or The component controlled by the repeated voice command includes the air conditioner of the vehicle, the function of the repeated voice command is to adjust the output temperature of the air conditioner, the actual operating parameters include the actual output temperature of the air conditioner, and the user behavior data includes historical data of the output temperature of the air conditioner.

5. The method according to claim 1, wherein The reference operating parameters of the component are determined according to environmental parameters surrounding the component.

6. The method according to claim 5, wherein: The components controlled by the repeated voice commands include the light-emitting devices of the vehicle, the function of the repeated voice commands is to adjust the brightness of the light-emitting devices, the actual operating parameters include the current brightness of the light-emitting devices, and the environmental parameters of the vehicle include the ambient brightness detected by the vehicle or the weather information of the day queried by the vehicle.

7. The method according to claim 1, wherein The determining of the control instruction to be finally executed based on the logical relationship of the multiple voice instructions and the multiple voice instructions includes: In response to the logical relationship between the multiple voice instructions indicating that there are conflicting voice instructions among the multiple voice instructions, a voice instruction that is triggered later among the conflicting voice instructions is determined as the control instruction.

8. The method according to any one of claims 1 to 7, wherein The method further comprises: Get voice data; Recognizing the voice data to obtain a voice instruction corresponding to the voice data; Adding the voice command corresponding to the voice data to a queue to be executed, and recording the time when the voice command corresponding to the voice data is triggered in the queue to be executed, wherein the voice command in the queue to be executed whose time difference between the triggered time and the current time is greater than or equal to a time threshold is executed; and It is determined whether there are multiple voice commands through the queue to be executed.

9. The method according to claim 8, wherein Determining the logical relationship between the plurality of voice instructions includes: Determine a logical relationship between the newly added voice command and the previously added voice command in the queue to be executed.

10. An electronic device, characterized in that: include: at least one processor; as well as, A memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor so as to enable the at least one processor to execute the voice control method according to any one of claims 1 to 9.

11. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the voice control method according to any one of claims 1 to 9 is implemented.

Images