Instruction processing method and device, equipment, storage medium and vehicle

Abstract

The embodiment of the application provides a kind of instruction processing method, device, equipment, storage medium and vehicle, instruction processing method includes: obtaining text instruction to be handled;Extract instruction element information corresponding to preset instruction element item in text instruction;Each instruction element information extracted is respectively filled into the target slot of preset instruction element structure, and instruction element representation structure is obtained;Based on the position of first instruction element item in instruction element representation structure, split instruction element representation structure, obtain multiple preset instruction element items belonging to same intent;Same label is added to the preset instruction element item belonging to same intent, and multiple-intent text instruction with first target representation structure is obtained.According to the embodiment of the application, the vehicle machine system can accurately identify all user intents contained in multi-intent voice instruction.

Description

Technical Field

[0001] This application belongs to the field of speech processing technology, and in particular relates to an instruction processing method, apparatus, device, storage medium and vehicle. Background Technology

[0002] During human-machine dialogue, the vehicle system needs to convert the user's voice commands into text commands in advance based on Automatic Speech Recognition (ASR) technology, and then recognize the user's intent contained in the text commands based on Natural Language Understanding (NLU) technology, so as to execute the corresponding operation according to the recognized user intent.

[0003] When a user's voice command contains multiple user intentions, existing technologies typically break down the resulting text command based on special words such as punctuation marks and verb conjunctions, enabling the vehicle's infotainment system to recognize all the user intentions contained within the text command. However, this approach cannot guarantee that a single text command containing multiple intentions will be accurately broken down into multiple text commands each containing a single intention, nor can it guarantee that each of the broken-down commands fully expresses a single intention. Therefore, this approach poses a challenge to the vehicle's infotainment system's intention recognition, resulting in lower accuracy and potentially preventing the system from accurately understanding all the user intentions contained in the voice command. Summary of the Invention

[0004] This application provides an instruction processing method, apparatus, device, storage medium, and vehicle that enables the vehicle system to accurately identify all user intents contained in multi-intent voice commands.

[0005] In a first aspect, embodiments of this application provide an instruction processing method, which includes: acquiring a text instruction to be processed, wherein the text instruction is converted from a multi-intent voice instruction issued by a user; extracting instruction element information corresponding to preset instruction element items from the text instruction; filling each extracted instruction element information into a target slot of a preset instruction element structure to obtain an instruction element representation structure, wherein the target slot is the position corresponding to the preset instruction element item corresponding to the instruction element information; splitting the instruction element representation structure based on the position of the first instruction element item in the instruction element representation structure to obtain multiple preset instruction element items belonging to the same intent, wherein the preset instruction element items include the first instruction element item; adding the same annotation to the preset instruction element items belonging to the same intent to obtain a multi-intent text instruction with a first target representation structure.

[0006] According to the first aspect of this application, each extracted instruction element information is filled into a target slot of a preset instruction element structure to obtain an instruction element representation structure, including: filling each extracted instruction element information into a target slot of a preset instruction element structure according to the order in which the instruction element information appears in the text instruction to obtain an instruction element representation structure.

[0007] According to any of the foregoing embodiments of the first aspect of this application, after obtaining a multi-intent text instruction with a first target representation structure, the instruction processing method further includes: when there are at least two first instruction element items with the same instruction element information in the multi-intent text instruction, merging the slots corresponding to the at least two first instruction element items to obtain a multi-intent text instruction with a second target representation structure.

[0008] According to any of the foregoing embodiments of the first aspect of this application, before adding the same annotation to preset instruction element items belonging to the same intent, the instruction processing method further includes: when there are at least two first instruction element items with the same instruction element information in the multi-intent text instruction, merging the slots corresponding to at least two first instruction element items to obtain a merged instruction element representation structure; adding the same annotation to preset instruction element items belonging to the same intent includes: adding the same annotation to preset instruction element items belonging to the same intent in the merged instruction element representation structure.

[0009] According to any of the foregoing embodiments of the first aspect of this application, each extracted instruction element information is respectively filled into the target slot of the preset instruction element structure to obtain an instruction element representation structure, including: filling each extracted instruction element information into the target slot of the preset instruction element structure; and deleting the unfilled target slots in the target slots of the preset instruction element structure to obtain an instruction element representation structure.

[0010] According to any of the foregoing embodiments of the first aspect of this application, the first instruction element item includes an instruction operation action. Based on the position of the first instruction element item in the instruction element representation structure, the instruction element representation structure is split to obtain multiple preset instruction element items belonging to the same intention, including: based on the position of the instruction operation action in the instruction element representation structure, the instruction element representation structure is split to obtain multiple preset instruction element items belonging to the same intention.

[0011] Secondly, embodiments of this application provide an instruction processing device, comprising: an acquisition module for acquiring a text instruction to be processed, wherein the text instruction is converted from a multi-intent voice instruction issued by a user; an extraction module for extracting instruction element information corresponding to preset instruction element items from the text instruction; a filling module for filling each extracted instruction element information into a target slot of a preset instruction element structure to obtain an instruction element representation structure, wherein the target slot is the position corresponding to the preset instruction element item corresponding to the instruction element information; a splitting module for splitting the instruction element representation structure based on the position of the first instruction element item in the instruction element representation structure to obtain multiple preset instruction element items belonging to the same intent, wherein the preset instruction element items include the first instruction element item; and an annotation module for adding the same annotation to the preset instruction element items belonging to the same intent to obtain a multi-intent text instruction with a first target representation structure.

[0012] Thirdly, embodiments of this application provide an electronic device, which includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the steps of the instruction processing method provided in the first aspect.

[0013] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the instruction processing method provided in the first aspect.

[0014] Fifthly, embodiments of this application provide a vehicle, which includes at least one of the following: an instruction processing device as provided in the second aspect; an electronic device as provided in the third aspect; and a computer-readable storage medium as provided in the fourth aspect.

[0015] This application provides an instruction processing method, apparatus, device, storage medium, and vehicle. After obtaining a text instruction converted from a multi-intent voice instruction issued by a user, instruction element information corresponding to preset instruction element items is extracted from the text instruction to selectively obtain key information related to the user's intent. Each extracted instruction element information is then filled into a slot corresponding to a preset instruction element item, resulting in an instruction element representation structure that fully represents the user's intent. Based on the position of the first instruction element item in the instruction element representation structure, the structure is split to accurately distinguish preset instruction element items corresponding to different user intents. Finally, the same annotation is added to preset instruction element items belonging to the same intent in the instruction element representation structure, resulting in a multi-intent text instruction with a first target representation structure. Thus, through the extraction, filling, splitting, and annotation of instruction element information, the vehicle system can identify all user intents from multi-intent voice instructions and accurately distinguish multiple identified user intents into multiple individual intents that fully express the user's intent, improving the accuracy of user intent recognition in multi-intent voice instructions. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart illustrating an instruction processing method provided in an embodiment of this application;

[0018] Figure 2 This is a schematic diagram of the structure of an instruction processing device provided in an embodiment of this application;

[0019] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0020] To better understand the above-mentioned objectives, features, and advantages of this application, the solution of this application will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0021] Many specific details are set forth in the following description in order to provide a full understanding of this application, but this application may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some embodiments of this application, and not all embodiments.

[0022] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the term "comprising" or any other variations thereof is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0023] Before describing the technical solutions provided in the embodiments of this application, in order to facilitate understanding of the embodiments of this application, this application first specifically explains the problems existing in the prior art:

[0024] As mentioned above, the inventors of this application have discovered that existing technologies, when a user's voice command contains multiple user intentions, typically split the text command converted from the voice command based on special words such as punctuation marks and verb conjunctions, so that the vehicle system can recognize all the user intentions contained in the text command. However, this processing method cannot guarantee that a single text command containing multiple intentions will be accurately split into multiple text commands containing single intentions, nor can it guarantee that each split command can completely express an intention. Therefore, this processing method will cause certain difficulties for the vehicle system's intention recognition, resulting in a lower accuracy rate of intention recognition and the inability to accurately understand all the user intentions contained in the voice command.

[0025] To address the problems of the prior art, embodiments of this application provide an instruction processing method, apparatus, device, storage medium, and vehicle.

[0026] The instruction processing method provided in the embodiments of this application will be described below.

[0027] Figure 1 This is a flowchart illustrating an instruction processing method provided in an embodiment of this application. Figure 1 As shown, the method may include the following steps S101 to S105:

[0028] S101. Obtain the text command to be processed. The text command is converted from the multi-intent voice command issued by the user.

[0029] During the human-machine dialogue, the vehicle system first obtains the multi-intent voice commands issued by the user, such as "open the car window and air conditioner", "open the car window and turn off the air conditioner", "play the video and adjust the air conditioner temperature to 23 degrees", etc., and then converts the multi-intent voice commands into corresponding text commands based on voice recognition technology.

[0030] S102. Extract instruction element information from the text instructions that corresponds to the preset instruction element items.

[0031] In this embodiment, the preset instruction element items include at least instruction operation actions and instruction operation objects, and may also include at least one of the attributes corresponding to the instruction operation object and the application scenario to which the instruction operation object belongs. Those skilled in the art can also set the preset instruction element items according to actual needs. The instruction element information corresponding to the instruction operation action may include, but is not limited to, opening, closing, selecting, playing, navigating, adjusting, deleting, and setting; the instruction element information corresponding to the instruction operation object may include, but is not limited to, windows, sunroof, sunshade, air conditioner, refrigerator, location, video, audio, and application software; the instruction element information corresponding to the attributes of the instruction operation object may include, but is not limited to, temperature, gear, episode, video resolution, and audio playback mode; the instruction element information corresponding to the application scenario to which the instruction operation object belongs may include, but is not limited to, driver's seat, passenger seat, central control screen, and passenger side screen. The vehicle system extracts the instruction element information corresponding to the preset instruction element items from the text instruction based on the preset instruction element items.

[0032] For example, when a user issues a voice command "Play for me", the vehicle system can extract the command element information corresponding to the command operation action as "Play" from the converted text command; when a user issues a voice command "Open the car window for me", the vehicle system can extract the command element information corresponding to the command operation action as "Open" from the converted text command, and the command element information corresponding to the command operation object as "Car window"; when a user issues a voice command "Set the air conditioning temperature to 23 degrees", the vehicle system can extract the command element information corresponding to the command operation action as "Adjust", the command element information corresponding to the command operation object as "Air conditioning", and the command element information corresponding to the attribute of the command operation object as "Temperature 23 degrees"; when a user issues a voice command "Set the passenger side air conditioning temperature to 23 degrees", the vehicle system can extract the command element information corresponding to the command operation action as "Adjust", the command element information corresponding to the command operation object as "Air conditioning", the command element information corresponding to the attribute of the command operation object as "Temperature 23 degrees", and the command element information corresponding to the application scenario to which the command operation object belongs as "Passenger side".

[0033] S103. Fill each extracted instruction element information into the target slot of the preset instruction element structure to obtain the instruction element representation structure. The target slot is the position corresponding to the preset instruction element item corresponding to the instruction element information.

[0034] The preset instruction element structure can be "Instruction operation action {} Instruction operation object {} Attributes corresponding to the instruction operation object {} Application scenario to which the instruction operation object belongs {} Instruction operation action {} Instruction operation object {} Attributes corresponding to the instruction operation object {} Application scenario to which the instruction operation object belongs {}", where the "{}" after each preset instruction element item is the target slot corresponding to that preset instruction element item. A preset instruction element structure can contain multiple "Instruction operation action {}", "Instruction operation object {}", "Attributes corresponding to the instruction operation object {}", and "Application scenario to which the instruction operation object belongs {}". This application embodiment does not limit the specific form of the instruction element structure. The vehicle system fills each extracted instruction element information into the target slot corresponding to the preset instruction element item according to its corresponding preset instruction element item, thus obtaining the filled instruction element representation structure.

[0035] S104. Based on the position of the first instruction element item in the instruction element representation structure, split the instruction element representation structure to obtain multiple preset instruction element items belonging to the same intent. The preset instruction element items include the first instruction element item.

[0036] The position of the first instruction element item in the instruction element representation structure is used as a marker of the appearance of an intent. The instruction element representation structure is split by referring to the relative positions of each preset instruction element item and the first instruction element item, resulting in multiple preset instruction element items belonging to the same intent.

[0037] S105. Add the same annotation to the preset instruction element items belonging to the same intent to obtain a multi-intent text instruction with a first target representation structure.

[0038] Instruction element representation structures that belong to the same intent are labeled in one form, and instruction element representation structures that belong to different intents are labeled in different forms, resulting in a labeled instruction element representation structure, which is a multi-intent text instruction with a first target representation structure.

[0039] For example, instruction element items belonging to the same intent in the instruction element representation structure can be labeled with the same sequence number, and instruction element items belonging to different intents can be distinguished with different sequence numbers. For example, a multi-intent text instruction with a first target representation structure can be "Instruction operation action 1 {} Instruction operation object 1 {} Attribute 1 corresponding to the instruction operation object {} Application scenario 1 to which the instruction operation object belongs {} Instruction operation action 2 {} Instruction operation object 2 {} Attribute 2 corresponding to the instruction operation object {} Application scenario 2 to which the instruction operation object belongs {}". This application embodiment does not limit the labeling form of the instruction element representation structure.

[0040] This application provides an instruction processing method. After obtaining a text instruction converted from a multi-intent voice instruction issued by a user, the method extracts instruction element information corresponding to preset instruction element items from the text instruction, thereby selectively acquiring key information related to the user's intent. Each extracted instruction element information is then filled into a slot of a preset instruction element item corresponding to that instruction element information, resulting in an instruction element representation structure that fully represents the user's intent. Based on the position of the first instruction element item in the instruction element representation structure, the structure is split to accurately distinguish the preset instruction element items corresponding to different user intents. Finally, the same annotation is added to preset instruction element items belonging to the same intent in the instruction element representation structure, resulting in a multi-intent text instruction with a first target representation structure. Thus, through the extraction of instruction element information, the filling of instruction element information, the splitting of the instruction element representation structure, and the annotation of preset instruction element items, the vehicle system can identify all user intents from multi-intent voice instructions issued by the user, and can accurately distinguish the identified multiple user intents into multiple single intents that can fully express the user's intent, improving the accuracy of the vehicle system in recognizing user intents from multi-intent voice instructions.

[0041] In some embodiments, each extracted instruction element information is filled into a target slot of a preset instruction element structure to obtain an instruction element representation structure, including: filling each extracted instruction element information into a target slot of a preset instruction element structure according to the order in which the instruction element information appears in the text instruction to obtain an instruction element representation structure.

[0042] For example, each instruction element information is filled into the target slot according to the order in which it appears in the text instruction. In this way, the order in which the instruction element information appears in the resulting instruction element representation structure can perfectly match the order in which the user expresses their intention, thus ensuring the accuracy of the instruction element representation structure.

[0043] In some embodiments, each extracted instruction element information is filled into a target slot of a preset instruction element structure to obtain an instruction element representation structure, including: filling each extracted instruction element information into a target slot of a preset instruction element structure; and deleting unfilled target slots in the preset instruction element structure to obtain an instruction element representation structure.

[0044] For example, after filling the target slots with each instruction element information in the order they appear in the text instruction, the extracted instruction element information may not completely include all the instruction element information corresponding to all preset instruction element items. For example, it may not completely include instruction operation action information, instruction operation object information, attribute information corresponding to the instruction operation object, and application scenario information to which the instruction operation object belongs. Therefore, some target slots may not be filled. In this case, simply deleting the unfilled target slots will yield the instruction element representation structure.

[0045] For example, when the multi-intent text command is "Open the car window and air conditioning", or "Open the car window and turn on the air conditioning", or "Open the car window and the air conditioning is on", the extracted command element information appears in the order of "Open the car window" first, followed by "Turn on the air conditioning". Following this order, the extracted command element information "Open", "Car window", "Open", and "Air conditioning" are filled into the target slots of the preset command element structure, resulting in a command element representation structure of "Command operation action {Open} Command operation object {Car window} Attributes corresponding to the command operation object {} Application scenario to which the command operation object belongs {} Command operation action {Open} Command operation object {Air conditioning} Attributes corresponding to the command operation object {} Application scenario to which the command operation object belongs {}". Since the extracted command information does not include the attribute information corresponding to the command operation object and the application scenario information to which the command operation object belongs, the target slots corresponding to these two preset command element items are not filled and need to be deleted, ultimately resulting in a command element representation structure of "Command operation action {Open} Command operation object {Car window} Command operation action {Open} Command operation object {Air conditioning}".

[0046] When the multi-intent text command is "Close the driver's side window and set the air conditioning temperature to 23 degrees" or "Close the driver's side window and set the air conditioning temperature to 23 degrees", the extracted command element information appears in the following order: "Close the driver's side window" first, then "Adjust the air conditioning temperature to 23 degrees". Following this order, the extracted command element information "Close", "Driver's side", "Window", "Adjust", "Air conditioning", and "Temperature 23 degrees" are filled into the target slots of the preset command element structure, resulting in a command element representation structure of "Command operation action {Close} Command operation object {Window} Attributes corresponding to the command operation object {} Application scenario of the command operation object {Driver's side} Command operation action {Adjust} Command operation object {Air conditioning} Attributes corresponding to the command operation object {Temperature 23 degrees} Application scenario of the command operation object {}". Unfilled target slots are then deleted, resulting in the final command element representation structure of "Command operation action {Close} Command operation object {Window} Application scenario of the command operation object {Driver's side} Command operation action {Adjust} Command operation object {Air conditioning} Attributes corresponding to the command operation object {Temperature 23 degrees}".

[0047] In some embodiments, after obtaining a multi-intent text instruction with a first target representation structure, the instruction processing method further includes: if there are at least two first instruction element items with the same instruction element information in the multi-intent text instruction, merging the slots corresponding to the at least two first instruction element items to obtain a multi-intent text instruction with a second target representation structure.

[0048] For example, after obtaining a multi-intent text instruction with a first target representation structure, if at least two first instruction element items belonging to different intents in the multi-intent text instruction have the same instruction element information, then the slots corresponding to these first instruction element items with the same instruction element information are merged to obtain a multi-intent text instruction with a second target representation structure. By merging the slots of preset instruction element items with the same instruction element information, the redundancy of the multi-intent text instruction expression can be reduced to a certain extent while ensuring the complete expression of all user intents.

[0049] For example, when the multi-intent text instruction is "Open the car window and air conditioner", or "Open the car window and turn on the air conditioner", or "Open the car window and the air conditioner is on", or "Open the car window and the air conditioner is on", the instruction element representation structure is obtained as "Instruction operation action {open} Instruction operation object {car window} Instruction operation action {open} Instruction operation object {air conditioner}". Adding the same annotation to the instruction element items belonging to the same intent in this instruction element representation structure results in a multi-intent text instruction with a first target representation structure as "Instruction operation action 1 {open} Instruction operation object 1 {car window} Instruction operation action 2 {open} Instruction operation object 2 {air conditioner}". Since the instruction element information corresponding to the instruction operation actions "open the car window" and "turn on the air conditioner" is both "open", it is necessary to merge the slots corresponding to the instruction operation actions in the multi-intent text instruction. The merged instruction element item may not have annotations, thus obtaining a multi-intent text instruction with a second target representation structure as "Instruction operation action {open} Instruction operation object 1 {car window} Instruction operation object 2 {air conditioner}".

[0050] When the multi-intent text instruction is "Open the driver's side window, open the passenger side window", or "Open both the driver's side window and the passenger side window", or "Open both the driver's side and the passenger side window", the resulting instruction element representation structure is "Instruction action {open} Instruction object {window} Application scenario of the instruction object {driver's side} Instruction action {open} Instruction object {window} Application scenario of the instruction object {passenger's side}". Adding the same annotation to instruction element items belonging to the same intent within this instruction element representation structure yields a multi-intent text instruction with a first target representation structure: "Instruction action 1 {open} Instruction object 1 {window} Application scenario 1 {driver's side} Instruction action 2 {open} Instruction object 2 {window} Application scenario 2 {passenger's side}". Since the instruction element information corresponding to the "open driver's side window" and "open passenger side window" commands is "open", and the instruction element information corresponding to the command operation object is "window", it is necessary to merge the slots corresponding to the command operation actions and command operation objects in the multi-intent text command. The merged instruction element items do not need to be labeled. This results in a multi-intent text command with a second target representation structure, which is "Command operation action {open} Command operation object {window} Application scenario 1 of command operation object {driver's side} Application scenario 2 of command operation object {passenger's side}".

[0051] In some embodiments, before adding the same annotation to preset instruction element items belonging to the same intent, the instruction processing method further includes: when there are at least two first instruction element items with the same instruction element information in the multi-intent text instruction, merging the slots corresponding to at least two first instruction element items to obtain a merged instruction element representation structure; adding the same annotation to preset instruction element items belonging to the same intent includes: adding the same annotation to preset instruction element items belonging to the same intent in the merged instruction element representation structure.

[0052] For example, before adding the same annotation to preset instruction element items belonging to the same intent, if at least two first instruction element items belonging to different intents in a multi-intent text instruction have the same instruction element information, then the slots corresponding to these first instruction element items with the same instruction element information are merged to obtain a merged instruction element representation structure. Then, the same annotation is added to the preset instruction element items belonging to the same intent in the merged instruction element representation structure.

[0053] For example, when the multi-intent text command is "Open the driver's side window and the passenger side air conditioner", or "Open the driver's side window and the passenger side air conditioner", or "Open the driver's side window and turn on the passenger side air conditioner", the command element representation structure is obtained as "Command operation action {open} Command operation object {window} Application scenario of the command operation object {driver's side} Command operation action {open} Command operation object {air conditioner} Application scenario of the command operation object {passenger's side}". Since the command element information corresponding to the command operation actions of "open the driver's side window" and "turn on the passenger side air conditioner" is "open", it is necessary to merge the slots corresponding to the command operation actions in the multi-intent text command. The merged command element representation structure is "Command operation action {open} Command operation object {window} Application scenario of the command operation object {driver's side} Command operation object {air conditioner} Application scenario of the command operation object {passenger's side}". Then, add the same annotation to the preset instruction element items belonging to the same intent in the merged instruction element representation structure to obtain a multi-intent text instruction with a first target representation structure, such as "Instruction operation action {open} Instruction operation object 1 {car window} Application scenario 1 of instruction operation object {driver} Instruction operation object 2 {air conditioning} Application scenario 2 of instruction operation object {passenger}".

[0054] In some embodiments, the first instruction element item includes an instruction operation action. Based on the position of the first instruction element item in the instruction element representation structure, the instruction element representation structure is split to obtain multiple preset instruction element items belonging to the same intention. This includes: based on the position of the instruction operation action in the instruction element representation structure, the instruction element representation structure is split to obtain multiple preset instruction element items belonging to the same intention.

[0055] For example, when the multi-intent text instruction is "Close the driver's side window, turn on the passenger side air conditioner, and play the fifth episode video" or "Close the driver's side window, then turn on the passenger side air conditioner, and then play the fifth episode video", the instruction element representation structure is obtained as follows: "Instruction operation action {close} Instruction operation object {window} Application scenario of instruction operation object {driver's side} Instruction operation action {open} Instruction operation object {air conditioner} Application scenario of instruction operation object {passenger's side} Instruction operation action {play} Instruction operation object {video} Attribute of instruction operation object {episode 5}". In this embodiment, the preset instruction element item includes a first instruction element item. If the first instruction element item includes an instruction operation action, the position of the instruction operation action in the instruction element representation structure is used as a marker of the appearance of an intent. The preset instruction element item appearing after the position of one instruction operation action and before the position of the next instruction operation action is regarded as a preset instruction element item belonging to the same intent as the previous instruction operation action. That is, "Instruction operation action {close} Instruction operation object {car window} Application scenario to which the instruction operation object belongs {driver's seat}" is a preset instruction element item belonging to the same intent; "Instruction operation action {open} Instruction operation object {air conditioner} Application scenario to which the instruction operation object belongs {passenger's seat}" is a preset instruction element item belonging to the same intent; "Instruction operation action {play} Instruction operation object {video} Attribute to which the instruction operation object belongs {episode 5}" is a preset instruction element item belonging to the same intent. Thus, by splitting the instruction element representation structure, multiple preset instruction element items belonging to the same intent are obtained.

[0056] Based on the instruction processing method provided in the above embodiments, this application also provides specific implementations of the instruction processing apparatus. Please refer to the following embodiments.

[0057] like Figure 2 As shown, the instruction processing apparatus 200 provided in this application embodiment includes the following modules:

[0058] The acquisition module 201 is used to acquire the text instructions to be processed, which are converted from the multi-intent voice instructions issued by the user.

[0059] Extraction module 202 is used to extract instruction element information from text instructions that corresponds to preset instruction element items;

[0060] The filling module 203 is used to fill each extracted instruction element information into the target slot of the preset instruction element structure to obtain the instruction element representation structure. The target slot is the position corresponding to the preset instruction element item corresponding to the instruction element information.

[0061] The splitting module 204 is used to split the instruction element representation structure based on the position of the first instruction element item in the instruction element representation structure to obtain multiple preset instruction element items belonging to the same intent. The preset instruction element items include the first instruction element item.

[0062] The annotation module 205 is used to add the same annotation to preset instruction element items belonging to the same intent, so as to obtain multi-intent text instructions with a first target representation structure.

[0063] This application provides an instruction processing device. After acquiring a text instruction converted from a multi-intent voice instruction issued by a user, it extracts instruction element information corresponding to preset instruction element items from the text instruction, thereby selectively acquiring key information related to the user's intent. Each extracted instruction element information is then filled into a slot corresponding to a preset instruction element item, resulting in an instruction element representation structure that fully represents the user's intent. Based on the position of the first instruction element item in the instruction element representation structure, the structure is split to accurately distinguish preset instruction element items corresponding to different user intents. Finally, the same annotation is added to preset instruction element items belonging to the same intent in the instruction element representation structure, resulting in a multi-intent text instruction with a first target representation structure. Thus, through the extraction, filling, splitting, and annotation of instruction element information, the vehicle system can identify all user intents from multi-intent voice instructions and accurately distinguish multiple identified user intents into multiple individual intents that fully express the user's intent, improving the accuracy of user intent recognition in multi-intent voice instructions.

[0064] In some embodiments, the filling module 203 is specifically used to fill each extracted instruction element information into the target slot of the preset instruction element structure according to the order in which the instruction element information appears in the text instruction, so as to obtain the instruction element representation structure.

[0065] In some embodiments, the instruction processing apparatus 200 may further include: a first merging module, configured to, after obtaining a multi-intent text instruction having a first target representation structure, merge the slots corresponding to at least two first instruction element items with the same instruction element information in the multi-intent text instruction to obtain a multi-intent text instruction having a second target representation structure.

[0066] In some embodiments, the instruction processing device 200 may further include: a second merging module, configured to merge the slots corresponding to at least two first instruction element items with the same instruction element information in a multi-intent text instruction before adding the same annotation to preset instruction element items belonging to the same intent, to obtain a merged instruction element representation structure; adding the same annotation to preset instruction element items belonging to the same intent includes: adding the same annotation to preset instruction element items belonging to the same intent in the merged instruction element representation structure.

[0067] In some embodiments, the filling module 203 is specifically used to fill each extracted instruction element information into the target slot of the preset instruction element structure; if there are unfilled target slots in the target slots of the preset instruction element structure, the unfilled target slots are deleted to obtain the instruction element representation structure.

[0068] In some embodiments, the first instruction element item includes an instruction operation action. The splitting module 204 is specifically used to split the instruction element representation structure based on the position where the instruction operation action appears in the instruction element representation structure to obtain multiple preset instruction element items belonging to the same intent.

[0069] Figure 2 Each module in the illustrated device has the ability to implement Figure 1 The functions of each step in the process and their corresponding technical effects are described briefly and will not be elaborated here.

[0070] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0071] The electronic device may include a processor 301 and a memory 302 storing computer program instructions.

[0072] Specifically, the processor 301 may include a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0073] Memory 302 may include mass storage for data or instructions. For example, and not limitingly, memory 302 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. In one example, memory 302 may include removable or non-removable (or fixed) media, or memory 302 may be non-volatile solid-state memory. Memory 302 may be internal or external to the integrated gateway disaster recovery device.

[0074] In one example, memory 302 may be read-only memory (ROM). In one example, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM), or flash memory, or a combination of two or more of these.

[0075] Memory 302 may include read-only memory (ROM), random access memory (RAM), disk storage media device, optical storage media device, flash memory device, electrical, optical, or other physical / tangible memory storage device. Therefore, typically, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to one aspect of this application.

[0076] The processor 301 reads and executes computer program instructions stored in the memory 302 to achieve... Figure 1 The method / steps S101 to S105 in the illustrated embodiment achieve the following: Figure 1 The technical effects achieved by executing the methods / steps shown in the examples are not elaborated here for the sake of brevity.

[0077] In one example, the electronic device may also include a communication interface 303 and a bus 310. For example, Figure 3 As shown, the processor 301, memory 302, and communication interface 303 are connected through bus 310 and complete communication with each other.

[0078] The communication interface 303 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0079] Bus 310 includes hardware, software, or both, that couples components of an electronic device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 310 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, this application contemplates any suitable bus or interconnect.

[0080] Furthermore, in conjunction with the instruction processing methods in the above embodiments, this application embodiment can provide a computer-readable storage medium for implementation. This computer-readable storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the instruction processing methods in the above embodiments. Examples of computer-readable storage media include non-transitory computer-readable storage media, such as electronic circuits, semiconductor memory devices, ROM, random access memory, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, and hard disks.

[0081] In addition, embodiments of this application also provide a vehicle, which includes at least one of the following: an instruction processing device as provided in any of the second aspects; an electronic device as provided in any of the third aspects; and a computer-readable storage medium as provided in any of the fourth aspects.

[0082] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0083] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0084] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0085] The aspects of this application have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by dedicated hardware performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0086] The above description is merely a specific implementation of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. An instruction processing method, characterized by, The method comprises: acquiring a text instruction to be processed, the text instruction being converted from a multi-intent voice instruction issued by a user; extracting instruction element information corresponding to a preset instruction element item in the text instruction; filling each of the extracted instruction element information into a target slot of a preset instruction element structure respectively to obtain an instruction element representation structure, the target slot being a position corresponding to the preset instruction element item corresponding to the instruction element information; the preset instruction element structure comprising a plurality of repeated instruction element item slot sequences, each sequence comprising an instruction operation action slot, an instruction operation object slot, an instruction operation object attribute slot, and an instruction operation object application scenario slot; based on a position where a first instruction element item appears in the instruction element representation structure, splitting the instruction element representation structure to obtain a plurality of preset instruction element items belonging to a same intent, the preset instruction element item comprising the first instruction element item; adding the same label to the preset instruction element items belonging to the same intent to obtain a multi-intent text instruction having a first target representation structure, the first target representation structure distinguishing instruction element items of different intents through the label.

2. The method of claim 1, wherein, The method further comprises: in a case where there are at least two first instruction element items with the same instruction element information in the multi-intent text instruction, merging slots corresponding to the at least two first instruction element items to obtain a multi-intent text instruction having a second target representation structure.

3. The method according to claim 1 or 2, characterized in that, The method further comprises: in a case where there are at least two first instruction element items with the same instruction element information in the multi-intent text instruction, merging slots corresponding to the at least two first instruction element items to obtain a merged instruction element representation structure; 4. The method according to claim 1 or 2, characterized in that, The method further comprises: adding the same label to the preset instruction element items belonging to the same intent in the merged instruction element representation structure. The method further comprises: in a case where there are un-filled target slots in the target slots of the preset instruction element structure, deleting the un-filled target slots to obtain the instruction element representation structure.

5. The method of claim 1, wherein, The method further comprises: in a case where there are un-filled target slots in the target slots of the preset instruction element structure, deleting the un-filled target slots to obtain the instruction element representation structure. ​ 6. The method of claim 1, wherein, The first instruction element item includes an instruction operation action, and the instruction element representation structure is split based on a position of the first instruction element item in the instruction element representation structure to obtain a plurality of preset instruction element items belonging to a same intent, including: The instruction element representation structure is split based on a position of the instruction operation action in the instruction element representation structure to obtain a plurality of preset instruction element items belonging to a same intent.

7. An instruction processing apparatus, characterized by, The apparatus includes: An acquisition module configured to acquire a text instruction to be processed, the text instruction being converted from a multi-intent voice instruction issued by a user; An extraction module configured to extract instruction element information corresponding to a preset instruction element item in the text instruction; A filling module configured to fill each of the extracted instruction element information into a target slot of a preset instruction element structure respectively to obtain an instruction element representation structure, the target slot being a position corresponding to the preset instruction element item corresponding to the instruction element information; the preset instruction element structure including a plurality of repeated instruction element item slot sequences, each sequence including an instruction operation action slot, an instruction operation object slot, an instruction operation object attribute slot, and an instruction operation object application scenario slot; A splitting module configured to split the instruction element representation structure based on a position of a first instruction element item in the instruction element representation structure to obtain a plurality of preset instruction element items belonging to a same intent, the preset instruction element item including the first instruction element item; A labeling module configured to add a same label to the preset instruction element items belonging to the same intent to obtain a multi-intent text instruction having a first target representation structure, the first target representation structure distinguishing instruction element items of different intents through the label.

8. An electronic device, comprising: The electronic device includes a processor, a memory, and a computer program stored on the memory and executable on the processor, the computer program being executed by the processor to implement the steps of the instruction processing method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and the computer program is executed by the processor to implement the steps of the instruction processing method according to any one of claims 1 to 6.

10. A vehicle characterized by comprising: The vehicle includes at least one of: The instruction processing apparatus according to claim 7; The electronic device according to claim 8; The computer-readable storage medium according to claim 9.

Images