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

Abstract

The invention provides an instruction processing method and device, electronic equipment, a vehicle and a storage medium, and relates to the technical field of computers, in particular to the technical fields of voice recognition, natural language processing, intelligent voice, human-computer interaction, automatic driving and the like. The specific implementation scheme is as follows: acquiring a multi-intention voice instruction; obtaining a plurality of initial single-intention instructions based on the multi-intention voice instruction; according to a detection rule, detecting and / or adjusting the plurality of initial single-intention instructions to obtain a plurality of target single-intention instructions; each target single intent instruction of the plurality of target single intent instructions is executed.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to technical fields such as speech recognition, natural language processing, intelligent speech, human-computer interaction, and autonomous driving, and specifically to an instruction processing method, device, electronic device, vehicle, and storage medium. Background Art

[0002] With the widespread use of intelligent voice assistants, users are increasingly accustomed to interacting with electronic devices through voice input. However, users often give a combined intent command containing multiple intent commands in a single voice input, for example, "turn on the air conditioner and increase the temperature." However, in the prior art, when electronic devices execute combined intent commands, execution errors and error messages frequently occur, thereby reducing user experience. Summary of the invention

[0003] The present disclosure provides an instruction processing method, device, electronic device, vehicle and storage medium.

[0004] According to a first aspect of the present disclosure, there is provided an instruction processing method, comprising:

[0005] Get multi-intent voice commands;

[0006] Based on the multi-intent voice command, multiple initial single-intent commands are obtained;

[0007] According to the detection rules, multiple initial single-intention instructions are detected and / or adjusted to obtain multiple target single-intention instructions;

[0008] Execute each of the multiple target single-intent instructions.

[0009] According to a second aspect of the present disclosure, there is provided an instruction processing device, comprising:

[0010] A first instruction acquisition unit, used to acquire multi-intention voice instructions;

[0011] A second instruction acquisition unit, configured to obtain a plurality of initial single-intent instructions based on the multi-intent voice instruction;

[0012] An instruction processing unit, configured to detect and / or adjust a plurality of initial single-intention instructions according to a detection rule to obtain a plurality of target single-intention instructions;

[0013] An instruction execution unit is used to execute each target single-intent instruction among multiple target single-intent instructions.

[0014] According to a third aspect of the present disclosure, there is provided an electronic device, including:

[0015] at least one processor;

[0016] a memory communicatively coupled to the at least one processor;

[0017] The memory stores instructions that can be executed 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 method provided in the first aspect of the present disclosure.

[0018] According to a fourth aspect of the present disclosure, a vehicle is provided, comprising the electronic device provided by the third aspect of the present disclosure.

[0019] According to a fifth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to execute the method provided according to the first aspect of the present disclosure.

[0020] According to a sixth aspect of the present disclosure, a computer program product is provided, comprising a computer program, which implements the method provided according to the first aspect of the present disclosure when executed by a processor.

[0021] The use of the present disclosure can avoid the high frequency of execution errors and error reports when electronic devices execute multi-intent voice commands, thereby enhancing the user experience.

[0022] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0024] Figure 1 A flowchart of an instruction processing method provided by an embodiment of the present disclosure;

[0025] Figure 2 An auxiliary illustration of the completeness flow of an instruction processing method provided by an embodiment of the present disclosure;

[0026] Figure 3 A schematic diagram of a scenario of an instruction processing method provided by an embodiment of the present disclosure;

[0027] Figure 4 A schematic structural block diagram of an instruction processing device provided in an embodiment of the present disclosure;

[0028] Figure 5 A schematic structural block diagram of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0029] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope of the present disclosure. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0030] As described in the background technology, with the widespread use of intelligent voice assistants, users are increasingly accustomed to interacting with electronic devices (e.g., car computers, smart home devices, intelligent voice devices, or other similar computing devices) through voice input. However, users often give a combined intent command containing multiple intent commands in a single voice input, for example, "turn on the air conditioner and increase the temperature." However, in the prior art, when electronic devices execute combined intent commands, execution errors and error reports frequently occur, thereby reducing the user experience.

[0031] Specifically, the inventors have found that in the prior art, when electronic devices execute combined intent instructions, execution errors and error reports frequently occur because the combined intent instructions are original instructions input by users, lacking professionalism and rigor. Therefore, combined intent instructions often have execution problems. The execution problem may include at least one of priority error problems, resource conflict problems, logic conflict problems, and execution barrier problems.

[0032] For example, for the combined intention instruction "start the engine and close the door", it includes two intention instructions, "start the engine" and "close the door", and the intention instruction "start the engine" is in the front, and the intention instruction "close the door" is in the back. Therefore, when executing the combined intention instruction, the intention instruction "start the engine" will be executed first, and then the intention instruction "close the door". However, considering safety issues, the intention instruction "close the door" should be executed first, and then the intention instruction "start the engine". Based on this, it can be understood that the combined intention instruction "start the engine and close the door" has a priority error problem. Therefore, when the electronic device executes the combined intention instruction, an execution error will occur and an error will be reported.

[0033] For example, for the combined intent instruction "play music and call Zhang San", it includes two intent instructions "play music" and "call Zhang San", and these two intent instructions involve the same resources (specifically audio resources). Based on this, it can be understood that there is a resource conflict problem in the combined intent instruction. Therefore, when the electronic device executes the combined intent instruction, an execution error will occur and an error will be reported.

[0034] For example, the combined intention command "turn off the air conditioner, turn on the air conditioner" includes two intention commands, "turn off the air conditioner" and "turn on the air conditioner", and the intention command "turn off the air conditioner" is located in front, and the intention command "turn on the air conditioner" is located in the back. Therefore, when executing the combined intention command, the intention command "turn off the air conditioner" will be executed first, and then the intention command "turn on the air conditioner" will be executed. However, there is a logical conflict between the two intention commands, that is, there is a logical conflict problem in the combined intention command "turn off the air conditioner, turn on the air conditioner". Therefore, when the electronic device executes the combined intention command, an execution error will occur and an error will be reported.

[0035] For example, the combined intention instruction "turn on the air conditioner, increase the air volume" includes two intention instructions "turn on the air conditioner" and "increase the air volume". Among them, the intention instruction "increase the air volume" lacks an operated object and cannot be executed smoothly. That is, the combined intention instruction "turn on the air conditioner, increase the air volume" has an execution obstacle problem. Therefore, when the electronic device executes the combined intention instruction, an execution error will occur and an error will be reported.

[0036] In view of the above problems, the embodiments of the present disclosure provide a command processing method, which can be applied to electronic devices. The electronic device can be a terminal device. Here, the terminal device can be a car computer, a smart home device, a smart voice device or other similar computing devices. Figure 1 The flowchart diagram shown in the figure illustrates an instruction processing method provided by an embodiment of the present disclosure. It should be noted that although the logical order is shown in the flowchart diagram, in some cases, the steps shown or described in the flowchart can also be executed in other orders.

[0037] Step S101, obtaining multi-intent voice instructions.

[0038] Among them, the multi-intention voice command is a combined intention command, which may include multiple intention commands given by the user in a single voice input, and each of the multiple intention commands may be in voice form. For example, there is a multi-intention voice command "start the engine and close the door", which includes the intention command in voice form of "start the engine" and the intention command in voice form of "and close the door". For another example, there is a multi-intention voice command "play music and call Zhang San", which includes the intention command in voice form of "play music" and the intention command in voice form of "call Zhang San".

[0039] Step S102, obtaining multiple initial single-intent instructions based on the multi-intent voice instructions.

[0040] In one example, after obtaining a multi-intent voice command, the multi-intent voice command can be processed by automatic speech recognition (ASR) technology and natural language understanding (NLU) technology to obtain multiple initial single-intent commands, and each of the multiple initial single-intent commands is in text form. For example, there is a multi-intent voice command "start the engine and close the door". Through ASR technology and NLU technology, it can be processed to obtain the initial single-intent command in text form of "start the engine" and the initial single-intent command in text form of "close the door". For another example, there is a multi-intent voice command "play music and call Zhang San". Through ASR technology and NLU technology, it can be processed to obtain the initial single-intent command in text form of "play music" and the initial single-intent command in text form of "call Zhang San".

[0041] Step S103, detecting and / or adjusting the multiple initial single-intent instructions according to the detection rules to obtain multiple target single-intent instructions.

[0042] The detection rule is preset and is used to indicate how to detect multiple initial single-intent instructions, so that when there are no execution problems with the multiple initial single-intent instructions, the multiple initial single-intent instructions are used as multiple target single-intent instructions; or when there are execution problems with the multiple initial single-intent instructions, the multiple initial single-intent instructions are adjusted to obtain multiple target single-intent instructions. Here, the execution problem may include at least one of a priority error problem, a resource conflict problem, a logic conflict problem, and an execution barrier problem.

[0043] Further, in the embodiments of the present disclosure, the priority error problem may be that the initial execution order of multiple initial single-intent instructions is inconsistent with the priority order determined based on the priority detection rules; the resource conflict problem may be that there are multiple first target instructions involving the same resources in the multiple initial single-intent instructions; the logical conflict problem may be that there are multiple second target instructions with logical conflicts in the multiple initial single-intent instructions; the execution obstacle problem may be that there are third target instructions that have a dependency on a specified self-starting item, fourth target instructions that lack integrity, or fifth target instructions that have a dependency on a specified user confirmation item in the multiple initial single-intent instructions.

[0044] In the embodiment of the present disclosure, when there are execution problems with multiple initial single-intent instructions, the multiple initial single-intent instructions can be adjusted to solve the execution problems of the multiple initial single-intent instructions and obtain multiple target single-intent instructions.

[0045] Step S104, executing each target single-intent instruction among multiple target single-intent instructions.

[0046] After obtaining multiple target single-intent instructions, each of the multiple target single-intent instructions can be used as a to-be-executed instruction through the instruction distribution module, and the to-be-executed instruction is distributed to the corresponding vertical business module, so that the to-be-executed instruction is executed through the vertical business module. Among them, the vertical business module can be a window control module, an in-vehicle hardware control module, a media resource control module, and a voice call control module.

[0047] By adopting the instruction processing method provided by the embodiment of the present disclosure, after obtaining a multi-intent voice instruction and obtaining a plurality of initial single-intent instructions based on the multi-intent voice instruction, the plurality of initial single-intent instructions can be detected and / or adjusted according to the detection rules to obtain a plurality of target single-intent instructions to ensure that there are no execution problems with the plurality of target single-intent instructions, and then each of the plurality of target single-intent instructions is executed. In this way, when the electronic device executes a multi-intent voice instruction, it can instead execute each of the plurality of target single-intent instructions, and there are no execution problems with the plurality of target single-intent instructions. Therefore, it can avoid the situation where the electronic device frequently encounters execution errors and reports errors when executing a multi-intent voice instruction, thereby enhancing the user experience.

[0048] In some optional implementations, step S102, that is, “obtaining multiple initial single-intent instructions based on the multi-intent voice instruction” may include:

[0049] Convert multi-intent voice commands into multi-intent text commands;

[0050] The multi-intent text instructions are parsed to obtain multiple initial single-intent instructions.

[0051] In one example, the multi-intent voice instructions can be converted into multi-intent text instructions through ASR technology, and the multi-intent text instructions can be parsed through NLU technology to obtain multiple initial single-intent instructions.

[0052] It should be noted that in the above example, before parsing the multi-intent text instructions to obtain multiple initial single-intent instructions, the multi-intent text instructions can also be preprocessed to delete redundant words in the multi-intent text instructions, such as conjunctions, modal particles, etc.

[0053] Exemplarily, there is a multi-intent text instruction "Open navigation, turn down the volume, and call Zhang San ha", after preprocessing the multi-intent text instruction to delete redundant words (that is, "and" and "ha") in the multi-intent text instruction, the preprocessed multi-intent text instruction "Open navigation, turn down the volume, and call Zhang San" can be obtained. Based on this, it can be understood that in the above example, "parse the multi-intent text instruction to obtain multiple initial single-intent instructions" can include: parse the preprocessed multi-intent text instruction to obtain multiple initial single-intent instructions.

[0054] It should also be noted that in the above implementation, each of the multiple initial single-intent instructions may have a specific data structure. For example, each of the multiple initial single-intent instructions includes a single user intent, vertical category information to which the single user intent belongs, and control parameters of the single user intent.

[0055] Among them, the vertical information to which a single user intention belongs can be one of the vertical information such as window control, in-vehicle hardware control, media resource control, voice call control, etc.

[0056] Here, the single user intention under the window control can include page control, switch control of various applications, etc.; the single user intention under the in-vehicle hardware control can include air conditioning control, lighting control, window control, etc.; the single user intention under the media resource control can include video playback control, playback control of audio resources (for example, music players, radios, etc.), etc.; the single user intention under the voice phone control can include making a phone call or hanging up, etc.

[0057] Based on the above, in one example, “parsing the multi-intent text instructions to obtain multiple initial single-intent instructions” may include:

[0058] Decompose the multi-intent text instructions to obtain multiple single-intent text instructions;

[0059] Each single-intent text instruction among the multiple single-intent text instructions is used as a target text instruction, and the target text instruction is parsed to obtain a single user intent, vertical category information to which the single user intent belongs, and control parameters of the single user intent;

[0060] Based on the single user intent, the vertical category information to which the single user intent belongs, and the control parameters of the single user intent, an initial single intent instruction corresponding to the target text instruction is obtained.

[0061] It is understandable that in the above examples, the single user intent, the vertical information to which the single user intent belongs, and the control parameters of the single user intent can have specific content or be empty. When any of the single user intent, the vertical information to which the single user intent belongs, and the control parameters of the single user intent is empty, it indicates that the initial single intent instruction lacks integrity.

[0062] For example, there is a target text instruction "open navigation", and parsing it can get:

[0063] (1) Single user intent, and the single user intent has specific content: GOTO_PAGE (i.e., page control);

[0064] (2) Vertical category information to which a single user intent belongs, and the vertical category information to which a single user intent belongs has specific content: windowControl (i.e., window control);

[0065] (3) Control parameters of a single user intention, including a first control parameter, wherein the first control parameter has specific content: "name": "action", "value": "OPEN", "normalizedValue": "OPEN", and a second control parameter, wherein the second control parameter has specific content: "name": "name", "value": "NAVI_SETTING (i.e., navigation page)", "normalizedValue": "NAVI_SETTING".

[0066] Thereafter, based on the above single user intention, the vertical category information to which the single user intention belongs, and the control parameters of the single user intention, an initial single intention instruction corresponding to the target text instruction and having a specific data structure can be obtained.

[0067] Through the above implementation, in the embodiment of the present disclosure, the multi-intent voice instruction can be converted into a multi-intent text instruction, and the multi-intent text instruction can be parsed to obtain multiple initial single-intent instructions. Moreover, each of the multiple initial single-intent instructions has a specific data structure. In this way, the difficulty of subsequent processing of each of the multiple initial single-intent instructions can be reduced, thereby improving the execution efficiency of the instruction processing method. At the same time, when executing step S103, the accuracy of the detection results and / or adjustment results for the multiple initial single-intent instructions can be ensured, thereby further avoiding the high frequency of execution errors and error reports when the electronic device executes multi-intent voice instructions, so as to enhance the user experience.

[0068] In addition, when parsing the multi-intent text instructions to obtain multiple initial single-intent instructions, the multi-intent text instructions are disassembled to obtain multiple single-intent text instructions, and each single-intent text instruction in the multiple single-intent text instructions is used as a target text instruction, and the target text instruction is parsed to obtain a single user intention, the vertical category information to which the single user intention belongs, and the control parameters of the single user intention, and then based on the single user intention, the vertical category information to which the single user intention belongs, and the control parameters of the single user intention, the initial single-intent instruction corresponding to the target text instruction is obtained. Obviously, the initial single-intent instruction has a specific data structure that is finely divided. In this way, when executing step S103, the accuracy of the detection results and / or adjustment results for multiple initial single-intent instructions can be further ensured, thereby further avoiding the high frequency of execution errors and error reports when the electronic device executes multi-intent voice instructions, so as to enhance the user experience.

[0069] In addition, in an embodiment of the present disclosure, the detection rules may include at least one of priority detection rules, resource conflict detection rules, logical conflict detection rules, context relationship detection rules and user confirmation item detection rules to achieve relatively comprehensive detection of multiple initial single-intent instructions.

[0070] Among them, the priority detection rule is used to detect whether there are priority error problems in multiple initial single-intention instructions, that is, to detect whether the initial execution order of multiple initial single-intention instructions is consistent with the priority order determined based on the priority detection rule; the resource conflict detection rule is used to detect whether there are resource conflict problems in multiple initial single-intention instructions, that is, to detect whether there are multiple first target instructions involving the same resources in multiple initial single-intention instructions; the logic conflict detection rule is used to detect whether there are logic conflict problems in multiple initial single-intention instructions, that is, to detect whether there are multiple second target instructions with logic conflicts in multiple initial single-intention instructions; the context relationship detection rule is used to detect whether there are execution barrier problems in multiple initial single-intention instructions, specifically, to detect whether there are third target instructions that have a dependency relationship with a specified self-starting item in multiple initial single-intention instructions, and to detect whether there are fourth target instructions that lack integrity in multiple initial single-intention instructions; the user confirmation item detection rule is used to detect whether there are execution barrier problems in multiple initial single-intention instructions, specifically, to detect whether there are fifth target instructions that have a dependency relationship with a specified user confirmation item in multiple initial single-intention instructions.

[0071] Further, in some optional implementations, step S103, that is, "detecting and / or adjusting the multiple initial single-intention instructions according to the detection rule to obtain multiple target single-intention instructions" may include:

[0072] Using a current detection rule among multiple detection rules to detect multiple input instructions to obtain detection results; wherein the multiple input instructions are obtained based on multiple initial single-intention instructions;

[0073] Based on the detection results, multiple output instructions are obtained;

[0074] Based on multiple output instructions, multiple target single-intent instructions are obtained.

[0075] The multiple detection rules may include any two or more of a priority detection rule, a resource conflict detection rule, a logic conflict detection rule, a context relationship detection rule, and a user confirmation item detection rule.

[0076] In one example, “detecting multiple input instructions using a current detection rule among multiple detection rules to obtain a detection result” may include:

[0077] Get multiple detection rules;

[0078] According to the detection order, the current detection rule is determined from multiple detection rules in turn;

[0079] The current detection rules are used to detect multiple input instructions to obtain detection results.

[0080] The detection order may be determined randomly or preset.

[0081] In a specific example, multiple detection rules include priority detection rules, resource conflict detection rules, logical conflict detection rules, context relationship detection rules and user confirmation item detection rules, and the detection order corresponding to the multiple detection rules can be: priority detection rule → resource conflict detection rule → logical conflict detection rule → context relationship detection rule → user confirmation item detection rule.

[0082] In addition, it can be understood that in the embodiments of the present disclosure, when the current detection rule is the first detection rule among multiple detection rules, the multiple input instructions corresponding to the current detection rule are multiple initial single-intent instructions; when the current detection rule is not the first detection rule among multiple detection rules, the multiple input instructions corresponding to the current detection rule are multiple output instructions corresponding to the previous detection rule of the current detection rule, that is, when the current detection rule is not the first detection rule among multiple detection rules, the output of the previous detection rule of the current detection rule will be used as the input of the current detection rule.

[0083] In yet another example, “obtaining multiple output instructions based on the detection result” may include:

[0084] When the detection result indicates that there are execution problems with multiple input instructions, the multiple input instructions are adjusted according to an adjustment strategy corresponding to the current detection rule to obtain multiple output instructions.

[0085] The adjustment strategy includes at least one of the following:

[0086] Sequentially adjust multiple input instructions;

[0087] Perform resource adjustments for multiple input instructions;

[0088] Partially delete multiple input instructions;

[0089] Performing command expansion on multiple input commands;

[0090] Perform command replacement on multiple input commands.

[0091] In a specific example, the adjustment strategy corresponding to the priority detection rule may be: adjusting the sequence of multiple input instructions; the adjustment strategy corresponding to the resource conflict detection rule may be: adjusting the resources of multiple input instructions (for example, adjusting the resource allocation amount); the adjustment strategy corresponding to the logic conflict detection rule may be: partially deleting multiple input instructions; the adjustment strategy corresponding to the context relationship detection rule may be: expanding the instructions of multiple input instructions and / or replacing the instructions of multiple input instructions; the adjustment strategy corresponding to the user confirmation item detection rule may be: expanding the instructions of multiple input instructions.

[0092] When the current detection rule is not the last detection rule among multiple detection rules, the multiple output instructions are taken as new multiple input instructions and provided to the subsequent detection rule of the current detection rule, so that the new multiple input instructions can be detected and / or adjusted using the subsequent detection rule of the current detection rule; when the current detection rule is the last detection rule among multiple detection rules, the multiple output instructions are taken as multiple target single-intent instructions.

[0093] Through the above implementation, in the embodiment of the present disclosure, the current detection rule among multiple detection rules can be used to detect multiple input instructions obtained based on multiple initial single-intent instructions to obtain detection results, and based on the detection results, multiple output instructions are obtained, and then based on the multiple output instructions, multiple target single-intent instructions are obtained. In this way, multiple detection rules can be used to perform relatively comprehensive detection on multiple initial single-intent instructions to ensure the accuracy of the detection results and adjustment results for multiple initial single-intent instructions, thereby further avoiding the high frequency of execution errors and error reports when electronic devices execute multi-intent voice instructions, so as to enhance the user experience.

[0094] In addition, in the embodiment of the present disclosure, the current detection rule is determined from multiple detection rules in sequence according to the detection order, and multiple input instructions are detected using the current detection rule to obtain the detection result. In other words, when multiple initial single-intent instructions are detected and / or adjusted using multiple detection rules, they are executed serially, so that multiple detection results are interactive to further ensure the accuracy of the detection results and / or adjustment results for multiple initial single-intent instructions, thereby further avoiding the high frequency of execution errors and error reports when the electronic device executes multi-intent voice instructions, so as to enhance the user experience.

[0095] Furthermore, in the disclosed embodiment, the current detection rule has a corresponding adjustment strategy. When multiple output instructions are obtained based on the detection result, the multiple input instructions are adjusted according to the adjustment strategy corresponding to the current detection rule to obtain multiple output instructions. In this way, the detection efficiency can be improved, the user waiting time can be reduced, and the user experience can be further enhanced.

[0096] In some optional implementations, the multiple detection rules may include a priority detection rule, and the current detection rule is a priority detection rule. Based on this, "using the current detection rule among the multiple detection rules to detect multiple input instructions and obtain a detection result" may include:

[0097] Obtaining a predetermined priority order determined based on a priority detection rule;

[0098] When the initial execution order of the plurality of input instructions is inconsistent with the predetermined priority order, a detection result for characterizing that the plurality of input instructions have execution problems is obtained.

[0099] Among them, in the predetermined priority order determined based on the priority detection rule, usually the single-intention instructions related to security are set to the first high priority, the single-intention instructions customized by the user as high priority are set to the second medium priority, and other single-intention instructions are set to the third low priority. Here, the single-intention instructions related to security include phone (including voice calls and video calls) instructions and navigation instructions, and the priority of the phone instructions can be higher than the priority of the navigation instructions.

[0100] Exemplarily, there are multiple input instructions, and the initial execution order of the multiple input instructions is: "Play music" → "Call Zhang San" → "Turn off the air conditioner" → "Adjust the air conditioner temperature to 22 degrees" → "Turn on the ambient light" → "Adjust to blue" → "Open navigation". Among them, "Call Zhang San" and "Open navigation" are single-intention instructions related to security. In the predetermined priority order determined based on the priority detection rule, they are the first high priority. Obviously, the initial execution order of multiple input instructions is inconsistent with the priority order determined based on the priority detection rule. Therefore, a detection result can be obtained for characterizing that multiple input instructions have execution problems. Here, the execution problem of multiple input instructions is specifically a priority error problem.

[0101] Further, in some optional implementations, when a detection result is obtained for characterizing that multiple input instructions have execution problems, and the execution problems of the multiple input instructions are specifically priority error problems, “adjusting the multiple input instructions according to the adjustment strategy corresponding to the current detection rule to obtain multiple output instructions” may include:

[0102] According to the adjustment strategy corresponding to the priority detection rule, based on the predetermined priority order, multiple input instructions are sequentially adjusted to obtain multiple output instructions.

[0103] Continuing with the above example, according to the adjustment strategy corresponding to the priority detection rule, based on the predetermined priority order, multiple input instructions are sequentially adjusted, and the resulting multiple output instructions can be: "Call Zhang San" → "Open navigation" → "Play music" → "Turn off the air conditioner" → "Adjust the air conditioner temperature to 22 degrees" → "Turn on the ambient light" → "Adjust to blue".

[0104] Through the above implementation, in the embodiment of the present disclosure, a predetermined priority order determined based on the priority detection rule can be obtained, and when the initial execution order of multiple input instructions is inconsistent with the predetermined priority order, a detection result for characterizing that multiple input instructions have execution problems can be obtained, so that multiple input instructions can be sequentially adjusted based on the predetermined priority order according to the adjustment strategy corresponding to the priority detection rule to obtain multiple output instructions. In this way, it can be ensured that the execution order of multiple output instructions is consistent with the predetermined priority order determined based on the priority detection rule, thereby ensuring the security and reliability of the instruction processing method provided by the embodiment of the present disclosure.

[0105] In some optional implementations, the multiple detection rules may include a resource conflict detection rule, and the current detection rule is a resource conflict detection rule. Based on this, "using the current detection rule among the multiple detection rules to detect multiple input instructions and obtain a detection result" may include:

[0106] determining a resource involved by each of the plurality of input instructions;

[0107] When the resource conflict detection rule is used to determine that there are multiple first target instructions involving the same resource among the multiple input instructions, a detection result for characterizing that the multiple input instructions have execution problems is obtained.

[0108] The resource involved in each of the multiple input instructions may be an audio resource, a video resource, etc. Based on this, the multiple input instructions involving the same resource may be that the multiple input instructions all involve audio resources, for example, input instructions related to video playback control, input instructions related to playback control of audio resources, and input instructions related to voice phone control all involve audio resources; the multiple input instructions involving the same resource may also be that the multiple input instructions all involve video resources, for example, input instructions related to video playback control and input instructions related to video phone control all involve video resources.

[0109] For example, there are multiple input instructions: "Call Zhang San" → "Open navigation" → "Play music" → "Turn off air conditioning" → "Adjust air conditioning temperature to 22 degrees" → "Turn on ambient light" → "Adjust to blue". Among them, "Call Zhang San" and "Play music" are multiple first target instructions involving the same resource (specifically audio resource), so a detection result for characterizing that multiple input instructions have execution problems can be obtained. Here, the execution problem of multiple input instructions is specifically a resource conflict problem.

[0110] Further, in some optional implementations, when a detection result is obtained for characterizing that multiple input instructions have execution problems, and the execution problem of each input instruction is specifically a resource conflict problem, it can be determined that the multiple detection rules also include a priority detection rule, and “adjusting the multiple input instructions according to the adjustment strategy corresponding to the current detection rule to obtain multiple output instructions” may include:

[0111] Obtaining a predetermined priority order determined based on a priority detection rule;

[0112] According to an adjustment strategy corresponding to the resource conflict detection rule, based on a predetermined priority order, resources are adjusted for a plurality of first target instructions among a plurality of input instructions to obtain a plurality of output instructions.

[0113] Among them, the adjustment strategy corresponding to the resource conflict detection rule is intended to allocate a large amount or all of the same resource to input instructions with high priority in the predetermined priority order determined based on the priority detection rule (for example, input instructions related to voice phone control, and input instructions related to video phone control). Specifically, a first supplementary intention instruction can be generated to indicate that the same resource is allocated in large amount or all to input instructions with high priority in the predetermined priority order determined based on the priority detection rule; or, the same resource is allocated in small amount or not to input instructions with low priority in the predetermined priority order determined based on the priority detection rule (for example, input instructions related to video playback control, and input instructions related to playback control of audio resources). Specifically, a second supplementary intention instruction can be generated to indicate that the same resource is allocated in small amount or not to input instructions with low priority in the predetermined priority order determined based on the priority detection rule.

[0114] Continuing with the above example, after obtaining the predetermined priority order determined based on the priority detection rule, according to the adjustment strategy corresponding to the resource conflict detection rule, based on the predetermined priority order, resources are adjusted for multiple first target instructions in the multiple input instructions, and the multiple output instructions obtained can be: "Call Zhang San" → "Open navigation" → "Play music" → "Lower the music volume" → "Turn off the air conditioner" → "Adjust the air conditioning temperature to 22 degrees" → "Turn on the atmosphere light" → "Adjust to blue"; or it can be: "Call Zhang San" → "Open navigation" → "Play music" → "Pause music" → "Turn off the air conditioner" → "Adjust the air conditioning temperature to 22 degrees" → "Turn on the atmosphere light" → "Adjust to blue".

[0115] Among them, "lower the music volume" belongs to the second supplementary intention instruction, which is used to indicate that a small amount of audio resources should be allocated to the input instruction of "play music"; "pause music" belongs to the second supplementary intention instruction, which is used to indicate that audio resources should not be allocated to the input instruction of "play music".

[0116] Through the above implementation, in the embodiment of the present disclosure, the resources involved in each input instruction among multiple input instructions can be determined, and when the resource conflict detection rule is used to determine that there are multiple first target instructions involving the same resources among the multiple input instructions, a detection result for characterizing that there are execution problems in the multiple input instructions is obtained, so as to obtain a predetermined priority order determined based on the priority detection rule, and according to the adjustment strategy corresponding to the resource conflict detection rule, based on the predetermined priority order, multiple first target instructions among the multiple input instructions are resource adjusted to obtain multiple output instructions. In this way, a reasonable resource allocation for multiple first target instructions can be achieved through a simple resource adjustment strategy to meet the actual needs of users, thereby further enhancing the user experience.

[0117] In some optional implementations, the multiple detection rules may include a logic conflict detection rule, and the current detection rule is a logic conflict detection rule. Based on this, "using the current detection rule among the multiple detection rules to detect multiple input instructions and obtain a detection result" may include:

[0118] determining key logic information of each input instruction among a plurality of input instructions;

[0119] When the logic conflict detection rule is used to determine that there are multiple second target instructions with key logic information conflicts among multiple input instructions, a detection result for characterizing that there are execution problems in the multiple input instructions is obtained.

[0120] Among them, the key logic information of each input instruction in the multiple input instructions may be a control parameter of a single user intention included in the input instruction.

[0121] In one example, for two input instructions, for example, input instruction A and input instruction B, input instruction A and input instruction B may be determined as two second target instructions having key logic information conflicts when the following logic conditions are met:

[0122] (1) The single user intention included in input instruction A is the same as the single user intention included in input instruction B;

[0123] (2) The vertical category information to which the single user intent included in input instruction A belongs is the same as the vertical category information to which the single user intent included in input instruction B belongs;

[0124] (3) The control parameters of the single user intention included in the input instruction A and the control parameters of the single user intention included in the input instruction B are different.

[0125] Exemplarily, there are multiple input instructions: "Call Zhang San" → "Open navigation" → "Play music" → "Lower music volume" → "Turn off air conditioning" → "Adjust air conditioning temperature to 22 degrees" → "Turn on ambient light" → "Adjust to blue". Among them, the single user intention included in the input instruction of "Turn off air conditioning" is "air conditioning control", and the vertical category information to which the single user intention included in the input instruction of "Turn off air conditioning" (that is, "air conditioning control") belongs is in-vehicle hardware control, and the control parameter of the single user intention included in the input instruction of "Turn off air conditioning" (that is, "air conditioning control") is "off"; the single user intention included in the input instruction of "Adjust air conditioning temperature to 22 degrees" is "air conditioning control", and the vertical category information to which the single user intention included in the input instruction of "Adjust air conditioning temperature to 22 degrees" (that is, "air conditioning control") belongs is in-vehicle hardware control, and the control parameter of the single user intention included in the input instruction of "Adjust air conditioning temperature to 22 degrees" (that is, "air conditioning control") is "temperature adjusted to 22 degrees".

[0126] That is to say, the single user intention included in the input instruction "turn off the air conditioner" is the same as the single user intention included in the input instruction "adjust the air conditioner temperature to 22 degrees", and the vertical information to which the single user intention included in the input instruction "turn off the air conditioner" belongs is the same as the vertical information to which the single user intention included in the input instruction "adjust the air conditioner temperature to 22 degrees" belongs. However, the control parameters of the single user intention included in the input instruction "turn off the air conditioner" and the control parameters of the single user intention included in the input instruction "adjust the air conditioner temperature to 22 degrees" are different. Therefore, the input instruction "turn off the air conditioner" and the input instruction "adjust the air conditioner temperature to 22 degrees" can be determined as two second target instructions with a key logical information conflict, and a detection result for characterizing that multiple input instructions have execution problems is obtained. Here, the execution problems of multiple input instructions are specifically logical conflict problems, and there is a high probability that they are logical conflict problems caused by user verbal errors.

[0127] Further, in some optional implementations, when a detection result is obtained for characterizing that multiple input instructions have execution problems, and the execution problems of the multiple input instructions are specifically logic conflict problems, “adjusting the multiple input instructions according to the adjustment strategy corresponding to the current detection rule to obtain multiple output instructions” may include:

[0128] According to the adjustment strategy corresponding to the logic conflict detection rule, non-last instructions among the plurality of second target instructions are determined as instructions to be deleted, so as to delete the instructions to be deleted from the plurality of input instructions to obtain a plurality of output instructions.

[0129] Continuing with the above example, according to the adjustment strategy corresponding to the logical conflict detection rule, the non-last instruction among the multiple second target instructions (that is, the input instruction of "turn off the air conditioner") is determined as the instruction to be deleted, so as to delete the instruction to be deleted from the multiple input instructions, and the multiple output instructions obtained can be: "Call Zhang San" → "Open navigation" → "Play music" → "Lower the music volume" → "Adjust the air conditioning temperature to 22 degrees" → "Turn on the ambient light" → "Adjust to blue".

[0130] Through the above implementation, in the disclosed embodiment, the key logic information of each input instruction in multiple input instructions can be determined, and when the logic conflict detection rule is used to determine that there are multiple second target instructions with key logic information conflicts in the multiple input instructions, a detection result for characterizing that the multiple input instructions have execution problems is obtained, so that according to the adjustment strategy corresponding to the logic conflict detection rule, the non-last instructions in the multiple second target instructions are determined as instructions to be deleted, so as to delete the instructions to be deleted from the multiple input instructions and obtain multiple output instructions. In this way, it is possible to avoid the electronic device from executing input instructions generated due to user slips of the tongue, so that the execution results obtained by executing multi-intention voice instructions can be more adapted to the user's true meaning, thereby further enhancing the user experience.

[0131] In an optional implementation, the multiple detection rules include a contextual relationship detection rule, and the current detection rule is a contextual relationship detection rule. Based on this, "using the current detection rule in the multiple detection rules to detect multiple input instructions and obtain a detection result" may include:

[0132] Determine the specified auto-start item;

[0133] When the context relationship detection rule is used to determine that there is a third target instruction in the multiple input instructions that has a dependency relationship with the specified self-starting item, a detection result for characterizing that the multiple input instructions have execution problems is obtained.

[0134] Among them, the designated self-startup items can be items that the electronic device can automatically control to start, which can specifically be items with no security threats or low security threats, such as air conditioning startup items, lighting startup items, video playback startup items, music players, radios, etc.

[0135] In addition, in the embodiment of the present disclosure, for a certain input instruction among the multiple input instructions, the dependency relationship between the input instruction and the designated self-starting item can be understood as follows: the input instruction can be executed only when the designated self-starting item is started.

[0136] Exemplarily, there are multiple input instructions: "Call Zhang San" → "Open navigation" → "Play music" → "Lower music volume" → "Adjust air conditioning temperature to 22 degrees" → "Turn on ambient light" → "Adjust to blue". Among them, "Adjust air conditioning temperature to 22 degrees" is a third target instruction that has a dependency relationship with the specified self-starting item (specifically, the air conditioning startup item). Therefore, a detection result can be obtained for characterizing that there are execution problems with multiple input instructions. Here, the execution problems with multiple input instructions are specifically execution barrier problems (here, it can be understood that the air conditioning temperature cannot be adjusted to 22 degrees without turning on the air conditioner).

[0137] Further, in some optional implementations, when a detection result is obtained for characterizing that multiple input instructions have execution problems, and the execution problems of the multiple input instructions are specifically execution obstacle problems caused by the presence of a third target instruction in the multiple input instructions that has a dependency relationship with the specified self-starting item, “adjusting the multiple input instructions according to the adjustment strategy corresponding to the current detection rule to obtain multiple output instructions” may include:

[0138] Generate a self-start instruction corresponding to the specified self-start item;

[0139] According to the adjustment strategy corresponding to the context relationship detection rule, based on the self-starting instruction, multiple input instructions are expanded to obtain multiple output instructions.

[0140] Among them, the self-start instruction corresponding to the specified self-start item is used to start the automatic startup item.

[0141] Continuing with the above example, "adjust the air conditioning temperature to 22 degrees" is a third target instruction that has a dependency relationship with a specified self-starting item (specifically, the air conditioning startup item). Therefore, a self-starting instruction corresponding to the air conditioning startup item can be generated, for example, "turn on the air conditioner." Thereafter, based on the self-starting instruction, multiple input instructions are expanded, and multiple output instructions obtained may be: "Call Zhang San" → "Open navigation" → "Play music" → "Turn down the music volume" → "Turn on the air conditioner" → "Adjust the air conditioning temperature to 22 degrees" → "Turn on the atmosphere light" → "Adjust to blue."

[0142] Through the above implementation, in the embodiment of the present disclosure, a designated self-starting item can be determined, and when the context relationship detection rule is used to determine that there is a third target instruction with a dependency relationship with the designated self-starting item in multiple input instructions, a detection result for characterizing that multiple input instructions have execution problems is obtained, so as to generate a self-starting instruction corresponding to the designated self-starting item, and expand multiple input instructions based on the self-starting instruction according to the adjustment strategy corresponding to the context relationship detection rule to obtain multiple output instructions. In this way, even if there is a third target instruction with an execution obstacle problem in multiple input instructions (that is, an input instruction with a dependency relationship with the designated self-starting item), the third target instruction can be smoothly adjusted to resolve the execution obstacle problem, thereby ensuring the smooth execution of multi-intention voice instructions, so as to further improve the reliability of the instruction processing method provided in the embodiment of the present disclosure.

[0143] In an optional implementation, the multiple detection rules include a contextual relationship detection rule, and the current detection rule is a contextual relationship detection rule. Based on this, "using the current detection rule among the multiple detection rules to detect multiple input instructions and obtain a detection result" may include:

[0144] When the context relationship detection rule is used to determine that a fourth target instruction lacking integrity exists among the multiple input instructions, a detection result for characterizing that the multiple input instructions have execution problems is obtained.

[0145] Among them, for a certain input instruction among multiple input instructions, its lack of completeness may be that any one of its single user intention, the vertical category information to which the single user intention belongs, and the control parameters of the single user intention is empty.

[0146] Exemplarily, there are multiple input instructions: "Call Zhang San" → "Open navigation" → "Play music" → "Lower music volume" → "Turn on air conditioning" → "Adjust air conditioning temperature to 22 degrees" → "Turn on ambient light" → "Adjust to blue". Among them, the input "Adjust to blue" lacks a single user intent and the vertical category information to which the single user intent belongs. Therefore, the input "Adjust to blue" can be determined as a fourth target instruction that lacks completeness, and then a detection result can be obtained for characterizing that multiple input instructions have execution problems. Here, the execution problems of multiple input instructions are specifically execution barrier problems (here, it can be understood that the input instruction "Adjust to blue" lacks an operated object and therefore cannot be executed smoothly).

[0147] Further, in some optional implementations, when a detection result characterizing that a plurality of input instructions have execution problems is obtained, and the execution problems of the plurality of input instructions are specifically execution obstacle problems caused by the presence of a fourth target instruction lacking integrity in the plurality of input instructions, “adjusting the plurality of input instructions according to an adjustment strategy corresponding to the current detection rule to obtain a plurality of output instructions” may include:

[0148] Supplement the fourth target instruction to obtain a complete intention instruction;

[0149] According to the adjustment strategy corresponding to the context relationship detection rule, the fourth target instruction in the multiple input instructions is replaced with the complete intention instruction to obtain multiple output instructions.

[0150] In one example, the fourth target instruction may be supplemented by linking the context information of the fourth target instruction to obtain a complete intended instruction.

[0151] Continuing with the above example, the fourth target instruction (that is, the input instruction "adjust to blue") can be supplemented by contacting the context information of the fourth target instruction to obtain a complete intent instruction, for example, "adjust the atmosphere light to blue". Thereafter, according to the adjustment strategy corresponding to the contextual relationship detection rule, the fourth target instruction in multiple input instructions is replaced with the complete intent instruction, and the multiple output instructions obtained can be: "Call Zhang San" → "Open navigation" → "Play music" → "Turn down the music volume" → "Turn on the air conditioner" → "Adjust the air conditioner temperature to 22 degrees" → "Turn on the atmosphere light" → "Adjust the atmosphere light to blue".

[0152] Through the above implementation, in the embodiment of the present disclosure, when the context relationship detection rule is used to determine that there is a fourth target instruction lacking integrity among multiple input instructions, a detection result for characterizing that multiple input instructions have execution problems can be obtained, so as to supplement the fourth target instruction and obtain a complete intention instruction, and according to the adjustment strategy corresponding to the context relationship detection rule, the complete intention instruction is used to replace the fourth target instruction in the multiple input instructions to obtain multiple output instructions. In this way, even if there is a fourth target instruction with execution obstacle problems (that is, an input instruction lacking integrity) among the multiple input instructions, the fourth target instruction can be smoothly adjusted to resolve the execution obstacle problems, thereby ensuring the smooth execution of multi-intention voice instructions, so as to further improve the reliability of the instruction processing method provided in the embodiment of the present disclosure.

[0153] In an optional implementation, the multiple detection rules include a user confirmation item detection rule, and the current detection rule is a user confirmation item detection rule. Based on this, "using the current detection rule among the multiple detection rules to detect multiple input instructions and obtain a detection result" may include:

[0154] When the user confirmation item detection rule is used to determine that there is a fifth target instruction having a dependency relationship with the specified user confirmation item among the multiple input instructions, a detection result for characterizing that there are execution problems in the multiple input instructions is obtained.

[0155] The designated user confirmation item may be an item that the electronic device cannot automatically control to start, and may specifically be an item that poses a security threat or a high security threat, such as a vehicle engine.

[0156] In addition, in the embodiment of the present disclosure, for a certain input instruction among the multiple input instructions, the dependency relationship between the input instruction and the designated user confirmation item can be understood as follows: the input instruction can be executed only when the designated user confirmation item is activated.

[0157] Exemplarily, there are multiple input instructions: "Call Zhang San" → "Open navigation" → "Play music" → "Lower music volume" → "Turn on air conditioning" → "Adjust air conditioning temperature to 22 degrees" → "Turn on ambient light" → "Adjust ambient light to blue". Among them, "Turn on air conditioning" is the fifth target instruction that has a dependency relationship with the specified user confirmation item (specifically the vehicle engine). Therefore, a detection result can be obtained for characterizing that there are execution problems with multiple input instructions. Here, the execution problems with multiple input instructions are specifically execution barrier problems (here, it can be understood that the air conditioner cannot be turned on without starting the vehicle engine).

[0158] Further, in some optional implementations, when a detection result characterizing that multiple input instructions have execution problems is obtained, and the execution problems of the multiple input instructions are specifically execution obstacles caused by the presence of a fifth target instruction in the multiple input instructions that has a dependency relationship with the specified user confirmation item, “adjusting the multiple input instructions according to the adjustment strategy corresponding to the current detection rule to obtain multiple output instructions” may include:

[0159] Generate a prompt information broadcast instruction corresponding to the specified user confirmation item;

[0160] According to the adjustment strategy corresponding to the user confirmation item detection rule, based on the prompt information broadcast instruction, multiple input instructions are expanded to obtain multiple output instructions.

[0161] The prompt information broadcast instruction corresponding to the designated user confirmation item is used to prompt the user to manually start the designated user confirmation item.

[0162] Continuing with the above example, "turn on the air conditioner" is the fifth target instruction that has a dependency relationship with the specified user confirmation item (specifically the vehicle engine). Therefore, a prompt information broadcast instruction corresponding to the vehicle engine can be generated, for example, "Please confirm whether the vehicle engine is started. If the vehicle engine is not started, please start the vehicle engine manually." Thereafter, based on the prompt information broadcast instruction, multiple input instructions are expanded, and the resulting multiple output instructions may be: "Prompt information broadcast instruction" → "Call Zhang San" → "Open navigation" → "Play music" → "Lower the music volume" → "Turn on the air conditioner" → "Adjust the air conditioning temperature to 22 degrees" → "Turn on the ambient light" → "Adjust the ambient light to blue."

[0163] Through the above implementation, in the embodiment of the present disclosure, when the user confirmation item detection rule is used to determine that there is a fifth target instruction with a dependency relationship with the specified user confirmation item in multiple input instructions, a detection result for characterizing that multiple input instructions have execution problems can be obtained, so as to generate a prompt information broadcast instruction corresponding to the specified user confirmation item, and expand multiple input instructions based on the prompt information broadcast instruction according to the adjustment strategy corresponding to the user confirmation item detection rule to obtain multiple output instructions. In this way, even if there is a fifth target instruction with an execution obstacle problem (that is, an input instruction with a dependency relationship with the specified user confirmation item) in multiple input instructions, the fifth target instruction can be smoothly adjusted to resolve the execution obstacle problem, thereby ensuring the smooth execution of multi-intention voice instructions, so as to further improve the reliability of the instruction processing method provided in the embodiment of the present disclosure.

[0164] In an optional implementation, after step S101, step S102, step S103 and step S104, the instruction processing method may further include:

[0165] After each of the multiple target single-intention instructions is successfully executed, generating overall feedback information related to the multiple target single-intention instructions;

[0166] Report overall feedback information.

[0167] As mentioned above, in the embodiment of the present disclosure, after obtaining multiple target single-intent instructions, each of the multiple target single-intent instructions can be used as a to-be-executed instruction through the instruction distribution module, and the to-be-executed instruction is distributed to the corresponding vertical business module, so as to execute the to-be-executed instruction through the vertical business module. Among them, the vertical business module can be a window control module, an in-vehicle hardware control module, a media resource control module, and a voice phone control module.

[0168] In the above implementation, after the instruction distribution module is used to treat each of the multiple target single-intent instructions as an instruction to be executed, and the instruction to be executed is distributed to the corresponding vertical business module so that the instruction to be executed is executed by the vertical business module, the instruction distribution business module can be used to collect the single-intent execution results fed back by each vertical business module, and simplify these single-intent execution results to generate overall feedback information related to the multiple target single-intent instructions, and broadcast the overall feedback information.

[0169] Exemplarily, there are multiple target single-intent instructions: "Turn on navigation" → "Turn on air conditioning" → "Turn on ambient lighting", and the usual feedback information may be "OK, the navigation has been turned on for you, the air conditioning has been turned on for you, and the ambient lighting has been turned on for you", which is a bit cumbersome. Through the above implementation, overall feedback information related to multiple target single-intent instructions can be generated, for example, "navigation, air conditioning, and ambient lighting are all turned on", and the overall feedback information is broadcast. In this way, the user can be notified through the overall feedback information related to multiple target single-intent instructions and obtained after simplification, so as to further enhance the user experience.

[0170] In addition, it should be noted that in the embodiments of the present disclosure, for a single-intent voice command, after the single-intent voice command is successfully executed, single-intent feedback information can be randomly selected from multiple candidate feedback information, and the single-intent feedback information can be broadcast. Exemplarily, there is a single-intent voice command "turn on the air conditioner". After the single-intent voice command is successfully executed, single-intent feedback information can be randomly selected from multiple candidate feedback information, and the single-intent feedback information can be broadcast. Among them, multiple candidate feedback information may include: OK, the air conditioner has been turned on for you; No problem, the air conditioner has been turned on for you; OK, the air conditioner has been turned on for you.

[0171] The following will be combined Figure 2 , the integrity process of an instruction method provided by an embodiment of the present disclosure is described.

[0172] (1) Obtain multi-intent voice commands.

[0173] Among them, the multi-intention voice command is a combined intention command, which may include multiple intention commands given by the user in a single voice input, and each of the multiple intention commands may be in voice form. For example, there is a multi-intention voice command "start the engine and close the door", which includes the intention command in voice form of "start the engine" and the intention command in voice form of "and close the door". For another example, there is a multi-intention voice command "play music and call Zhang San", which includes the intention command in voice form of "play music" and the intention command in voice form of "call Zhang San". .

[0174] (2) Based on the multi-intent voice commands, multiple initial single-intent commands are obtained.

[0175] For example, a voice software development kit (SDK) may be used to perform voice processing on a multi-intent voice command to obtain a plurality of initial single-intent commands.

[0176] In one example, “obtaining multiple initial single-intent instructions based on the multi-intent voice instructions” may include:

[0177] Voice command conversion: convert multi-intent voice commands into multi-intent text commands;

[0178] Multi-intent text instruction disassembly: disassemble the multi-intent text instruction to obtain multiple single-intent text instructions;

[0179] Generation of initial single-intent instruction: Take each single-intent text instruction among multiple single-intent text instructions as the target text instruction, parse the target text instruction, obtain the single user intent, the vertical category information to which the single user intent belongs, and the control parameters of the single user intent, and based on the single user intent, the vertical category information to which the single user intent belongs, and the control parameters of the single user intent, obtain the initial single-intent instruction corresponding to the target text instruction.

[0180] (3) Using the instruction detection and adjustment module, according to the detection rules, multiple initial single-intention instructions are detected and / or adjusted to obtain multiple target single-intention instructions.

[0181] The detection rule is preset and is used to indicate how to detect multiple initial single-intent instructions, so that when there are no execution problems with the multiple initial single-intent instructions, the multiple initial single-intent instructions are used as multiple target single-intent instructions; or when there are execution problems with the multiple initial single-intent instructions, the multiple initial single-intent instructions are adjusted to obtain multiple target single-intent instructions. Here, the execution problem may include at least one of a priority error problem, a resource conflict problem, a logic conflict problem, and an execution barrier problem.

[0182] In addition, in the embodiment of the present disclosure, the detection rule may include at least one of a priority detection rule, a resource conflict detection rule, a logic conflict detection rule, a context relationship detection rule, and a user confirmation item detection rule.

[0183] In one example, “according to the detection rule, detecting and / or adjusting the multiple initial single-intention instructions to obtain the multiple target single-intention instructions” may include:

[0184] Using a current detection rule among multiple detection rules to detect multiple input instructions to obtain detection results; wherein the multiple input instructions are obtained based on multiple initial single-intention instructions;

[0185] Based on the detection results, multiple output instructions are obtained;

[0186] Based on multiple output instructions, multiple target single-intent instructions are obtained.

[0187] The multiple detection rules may include any two or more of a priority detection rule, a resource conflict detection rule, a logic conflict detection rule, a context relationship detection rule, and a user confirmation item detection rule.

[0188] In a specific example, “using a current detection rule among multiple detection rules to detect multiple input instructions to obtain a detection result” may include:

[0189] Get multiple detection rules;

[0190] According to the detection order, the current detection rule is determined from multiple detection rules in turn;

[0191] The current detection rules are used to detect multiple input instructions to obtain detection results.

[0192] The detection order may be determined randomly or preset.

[0193] In a more specific example, the multiple detection rules include priority detection rules, resource conflict detection rules, logical conflict detection rules, context relationship detection rules and user confirmation item detection rules, and the detection order corresponding to the multiple detection rules can be: priority detection rule → resource conflict detection rule → logical conflict detection rule → context relationship detection rule → user confirmation item detection rule.

[0194] In addition, it can be understood that in the embodiments of the present disclosure, when the current detection rule is the first detection rule among multiple detection rules, the multiple input instructions corresponding to the current detection rule are multiple initial single-intent instructions; when the current detection rule is not the first detection rule among multiple detection rules, the multiple input instructions corresponding to the current detection rule are multiple output instructions corresponding to the previous detection rule of the current detection rule, that is, when the current detection rule is not the first detection rule among multiple detection rules, the output of the previous detection rule of the current detection rule will be used as the input of the current detection rule.

[0195] In another specific example, “obtaining multiple output instructions based on the detection result” may include:

[0196] When the detection result indicates that there are execution problems with multiple input instructions, the multiple input instructions are adjusted according to an adjustment strategy corresponding to the current detection rule to obtain multiple output instructions.

[0197] The adjustment strategy includes at least one of the following:

[0198] Sequentially adjust multiple input instructions;

[0199] Perform resource adjustments for multiple input instructions;

[0200] Partially delete multiple input instructions;

[0201] Performing command expansion on multiple input commands;

[0202] Perform command replacement on multiple input commands.

[0203] In a more specific example, the adjustment strategy corresponding to the priority detection rule may be: sequentially adjusting multiple input instructions; the adjustment strategy corresponding to the resource conflict detection rule may be: resource adjustment for multiple input instructions (for example, adjusting the resource allocation amount); the adjustment strategy corresponding to the logic conflict detection rule may be: partially deleting multiple input instructions; the adjustment strategy corresponding to the context relationship detection rule may be: expanding instructions for multiple input instructions and / or replacing instructions for multiple input instructions; the adjustment strategy corresponding to the user confirmation item detection rule may be: expanding instructions for multiple input instructions.

[0204] When the current detection rule is not the last detection rule among multiple detection rules, the multiple output instructions are taken as new multiple input instructions and provided to the subsequent detection rule of the current detection rule, so that the new multiple input instructions can be detected and / or adjusted using the subsequent detection rule of the current detection rule; when the current detection rule is the last detection rule among multiple detection rules, the multiple output instructions are taken as multiple target single-intent instructions.

[0205] In the following, multiple detection rules including priority detection rules, resource conflict detection rules, logical conflict detection rules, contextual relationship detection rules and user confirmation item detection rules, and the detection order corresponding to the multiple detection rules is: priority detection rule → resource conflict detection rule → logical conflict detection rule → contextual relationship detection rule → user confirmation item detection rule, are taken as an example to explain the specific process of "detecting and / or adjusting multiple initial single-intent instructions according to the detection rules to obtain multiple target single-intent instructions":

[0206] The first detection process can be based on the priority detection rules to implement the detection and adjustment of priority errors, which can specifically include:

[0207] Obtaining a predetermined priority order determined based on a priority detection rule;

[0208] In the case where the initial execution order of the multiple initial single-intention instructions is inconsistent with the predetermined priority order, a detection result for characterizing that the multiple initial single-intention instructions have execution problems is obtained, and the multiple initial single-intention instructions are sequentially adjusted based on the predetermined priority order according to an adjustment strategy corresponding to the priority detection rule to obtain multiple first output instructions;

[0209] Alternatively, when the initial execution order of multiple initial single-intent instructions is consistent with the predetermined priority order, a detection result is obtained to characterize that there are no execution problems with the multiple initial single-intent instructions, and the multiple initial single-intent instructions are used as multiple first output instructions.

[0210] The second detection process can be based on resource conflict detection rules to implement detection and adjustment of resource conflict issues, which may include:

[0211] Determine a resource involved by each of the plurality of input instructions (ie, a plurality of first output instructions);

[0212] In the case where it is determined by using the resource conflict detection rule that there are multiple first target instructions involving the same resource in the multiple input instructions, a detection result for characterizing that the multiple input instructions have execution problems is obtained, and a predetermined priority order determined based on the priority detection rule is obtained, and then according to an adjustment strategy corresponding to the resource conflict detection rule, resources are adjusted for the multiple first target instructions in the multiple input instructions based on the predetermined priority order to obtain multiple second output instructions;

[0213] Alternatively, when using resource conflict detection rules to determine that there are no multiple first target instructions involving the same resource among multiple input instructions, a detection result is obtained to characterize that there are no execution problems with the multiple input instructions, and the multiple input instructions are used as multiple second output instructions.

[0214] The third detection process can be based on the logic conflict detection rules to achieve the detection and adjustment of logic conflict problems, which can specifically include:

[0215] Determining key logic information of each input instruction in a plurality of input instructions (ie, a plurality of second output instructions);

[0216] In the case where a plurality of second target instructions having key logic information conflicts are determined by using a logic conflict detection rule, a detection result for characterizing that the plurality of input instructions have execution problems is obtained, and a non-last instruction in the plurality of second target instructions is determined as an instruction to be deleted according to an adjustment strategy corresponding to the logic conflict detection rule, so as to delete the instruction to be deleted from the plurality of input instructions, and obtain a plurality of third output instructions;

[0217] Alternatively, by utilizing logic conflict detection rules to determine that there are no second target instructions with key logic information conflicts among multiple input instructions, a detection result is obtained to characterize that there are no execution problems with the multiple input instructions, and the multiple input instructions are used as multiple third output instructions.

[0218] The fourth detection process can be based on the contextual relationship detection rules to achieve the detection and adjustment of execution barriers, which can specifically include the 4.1 detection process:

[0219] Determine the specified auto-start item;

[0220] When the context relationship detection rule is used to determine that there is a third target instruction having a dependency relationship with the specified self-starting item among the multiple input instructions (that is, the multiple third output instructions), a detection result for characterizing that the multiple input instructions have an execution problem is obtained, and a self-starting instruction corresponding to the specified self-starting item is generated, and then according to the adjustment strategy corresponding to the context relationship detection rule, the multiple input instructions are expanded based on the self-starting instruction to obtain multiple fourth output instructions;

[0221] Alternatively, when utilizing contextual relationship detection rules to determine that there is no third target instruction among multiple input instructions that has a dependency relationship with a specified self-starting item, a detection result is obtained that characterizes that there are no execution problems with the multiple input instructions, and the multiple input instructions are used as multiple fourth output instructions.

[0222] It can also include the 4.2nd test process:

[0223] When the context relationship detection rule is used to determine that a fourth target instruction lacking integrity exists in the plurality of input instructions (that is, the plurality of third output instructions), a detection result for characterizing that the plurality of input instructions have execution problems is obtained, and the fourth target instruction is supplemented to obtain a complete intention instruction, and then the fourth target instruction in the plurality of input instructions is replaced with the complete intention instruction according to an adjustment strategy corresponding to the context relationship detection rule to obtain a plurality of fourth output instructions;

[0224] Alternatively, when the context relationship detection rule is used to determine that there is no fourth target instruction lacking integrity among the multiple input instructions, a detection result is obtained to characterize that there are no execution problems with the multiple input instructions, and the multiple input instructions are used as multiple fourth output instructions.

[0225] It should be noted that the above-mentioned 4.1 detection process and 4.2 detection process can exist separately or simultaneously (for example, serial execution). That is, when the 4.1 detection process and the 4.2 detection process exist simultaneously, multiple third output instructions can be used as input of the 4.1 detection process, and the output of the 4.1 detection process can be used as input of the 4.2 detection process, and the output of the 4.2 detection process can be used as multiple fourth output instructions; multiple third output instructions can also be used as input of the 4.2 detection process, and the output of the 4.2 detection process can be used as input of the 4.1 detection process, and the output of the 4.1 detection process can be used as multiple fourth output instructions. The embodiments of the present disclosure do not limit this.

[0226] The fifth detection process can be based on the user confirmation item detection rules to achieve the detection and adjustment of execution barriers, which can specifically include:

[0227] When the user confirmation item detection rule is used to determine that there is a fifth target instruction having a dependency relationship with the specified user confirmation item in the multiple input instructions (that is, the multiple fourth outputs), a detection result for characterizing that the multiple input instructions have execution problems is obtained, and a prompt information broadcast instruction corresponding to the specified user confirmation item is generated, and then according to an adjustment strategy corresponding to the user confirmation item detection rule, the multiple input instructions are expanded based on the prompt information broadcast instruction to obtain multiple target single-intent instructions;

[0228] Alternatively, when utilizing the user confirmation item detection rule to determine that there is no fifth target instruction among multiple input instructions that has a dependency relationship with the specified user confirmation item, a detection result is obtained that characterizes that there are no execution problems with the multiple input instructions, and the multiple input instructions are treated as multiple target single-intent instructions.

[0229] (4) Execute each target single-intent instruction among multiple target single-intent instructions.

[0230] After obtaining multiple target single-intent instructions, each of the multiple target single-intent instructions can be used as a to-be-executed instruction through the instruction distribution module, and the to-be-executed instruction is distributed to the corresponding vertical business module, so that the to-be-executed instruction is executed through the vertical business module. Among them, the vertical business module can be a window control module, an in-vehicle hardware control module, a media resource control module, and a voice call control module.

[0231] After that, the instruction distribution business module can be used to collect the single-intent execution results fed back by each vertical business module, and simplify these single-intent execution results to generate overall feedback information related to multiple target single-intent instructions, and broadcast the overall feedback information.

[0232] See also Figure 3 , which is a scenario diagram of an instruction processing method provided in an embodiment of the present disclosure.

[0233] As mentioned above, the instruction processing method provided by the embodiment of the present disclosure is applied to an electronic device. The electronic device may be a terminal device. Here, the terminal device may be an onboard computer (such as Figure 3 As shown, the on-board computer can be installed in a vehicle), smart home equipment, smart voice equipment or other similar computing devices.

[0234] Electronic devices are used for:

[0235] Get multi-intent voice commands;

[0236] Based on the multi-intent voice command, multiple initial single-intent commands are obtained;

[0237] According to the detection rules, multiple initial single-intention instructions are detected and / or adjusted to obtain multiple target single-intention instructions;

[0238] Execute each of the multiple target single-intent instructions.

[0239] It should be noted that in the embodiments of the present disclosure, Figure 3 The scene diagram shown is only illustrative and not restrictive. Those skilled in the art can Figure 3 Various obvious changes and / or substitutions are made to the examples, and the obtained technical solutions still fall within the scope of the disclosure of the embodiments of the present disclosure.

[0240] In order to better implement the instruction processing method, the embodiment of the present disclosure also provides an instruction processing device, which can be integrated in an electronic device. The electronic device can be a terminal device. Here, the terminal device can be a car computer, a smart home device, an intelligent voice device or other similar computing devices. Figure 4 The schematic structural block diagram shown is used to illustrate an instruction processing device 400 provided in the disclosed embodiment.

[0241] The instruction processing device 400 comprises:

[0242] A first instruction acquisition unit 401 is used to acquire a multi-intention voice instruction;

[0243] A second instruction acquisition unit 402, configured to obtain a plurality of initial single-intent instructions based on the multi-intent voice instruction;

[0244] The instruction processing unit 403 is used to detect and / or adjust the multiple initial single-intention instructions according to the detection rules to obtain multiple target single-intention instructions;

[0245] The instruction execution unit 404 is used to execute each target single-intent instruction among multiple target single-intent instructions.

[0246] In some optional implementations, the detection rule includes at least one of a priority detection rule, a resource conflict detection rule, a logic conflict detection rule, a context relationship detection rule, and a user confirmation item detection rule.

[0247] In some optional implementations, the instruction processing unit 403 is used to:

[0248] Using a current detection rule among multiple detection rules to detect multiple input instructions to obtain detection results; wherein the multiple input instructions are obtained based on multiple initial single-intention instructions;

[0249] Based on the detection results, multiple output instructions are obtained;

[0250] Based on multiple output instructions, multiple target single-intent instructions are obtained.

[0251] In some optional implementations, the instruction processing unit 403 is used to:

[0252] When the detection result indicates that there are execution problems with multiple input instructions, the multiple input instructions are adjusted according to an adjustment strategy corresponding to the current detection rule to obtain multiple output instructions.

[0253] In some optional implementations, the adjustment strategy includes at least one of the following:

[0254] Sequentially adjust multiple input instructions;

[0255] Perform resource adjustments for multiple input instructions;

[0256] Partially delete multiple input instructions;

[0257] Performing command expansion on multiple input commands;

[0258] Perform command replacement on multiple input commands.

[0259] In some optional implementations, the instruction processing unit 403 is used to:

[0260] Get multiple detection rules;

[0261] According to the detection order, the current detection rule is determined from multiple detection rules in turn;

[0262] The current detection rules are used to detect multiple input instructions to obtain detection results.

[0263] In some optional embodiments,

[0264] In the case where the current detection rule is the first detection rule among multiple detection rules, the multiple input instructions corresponding to the current detection rule are multiple initial single-intent instructions;

[0265] In the case that the current detection rule is not the first detection rule among the multiple detection rules, the multiple input instructions corresponding to the current detection rule are multiple output instructions corresponding to the detection rule before the current detection rule.

[0266] In some optional implementations, the multiple detection rules include a priority detection rule, and the current detection rule is a priority detection rule; the instruction processing unit 403 is used to:

[0267] Obtaining a predetermined priority order determined based on a priority detection rule;

[0268] When the initial execution order of the plurality of input instructions is inconsistent with the predetermined priority order, a detection result for characterizing that the plurality of input instructions have execution problems is obtained.

[0269] In some optional implementations, the instruction processing unit 403 is used to:

[0270] According to the adjustment strategy corresponding to the priority detection rule, based on the predetermined priority order, multiple input instructions are sequentially adjusted to obtain multiple output instructions.

[0271] In some optional implementations, the multiple detection rules include a resource conflict detection rule, and the current detection rule is a resource conflict detection rule; the instruction processing unit 403 is used to:

[0272] determining a resource involved by each of the plurality of input instructions;

[0273] When the resource conflict detection rule is used to determine that there are multiple first target instructions involving the same resource among the multiple input instructions, a detection result for characterizing that the multiple input instructions have execution problems is obtained.

[0274] In some optional implementations, the multiple detection rules further include a priority detection rule; the instruction processing unit 403 is used to:

[0275] Obtaining a predetermined priority order determined based on a priority detection rule;

[0276] According to an adjustment strategy corresponding to the resource conflict detection rule, based on a predetermined priority order, resources are adjusted for a plurality of first target instructions among a plurality of input instructions to obtain a plurality of output instructions.

[0277] In some optional implementations, the multiple detection rules include a logic conflict detection rule, and the current detection rule is a logic conflict detection rule; the instruction processing unit 403 is used to:

[0278] determining key logic information of each input instruction among a plurality of input instructions;

[0279] When the logic conflict detection rule is used to determine that there are multiple second target instructions with key logic information conflicts among multiple input instructions, a detection result for characterizing that there are execution problems in the multiple input instructions is obtained.

[0280] In some optional implementations, the instruction processing unit 403 is used to:

[0281] According to the adjustment strategy corresponding to the logic conflict detection rule, non-last instructions among the plurality of second target instructions are determined as instructions to be deleted, so as to delete the instructions to be deleted from the plurality of input instructions to obtain a plurality of output instructions.

[0282] In some optional implementations, the multiple detection rules include a contextual relationship detection rule, and the current detection rule is a contextual relationship detection rule; the instruction processing unit 403 is used to:

[0283] Determine the specified auto-start item;

[0284] When the context relationship detection rule is used to determine that there is a third target instruction in the multiple input instructions that has a dependency relationship with the specified self-starting item, a detection result for characterizing that the multiple input instructions have execution problems is obtained.

[0285] In some optional implementations, the instruction processing unit 403 is used to:

[0286] Generate a self-start instruction corresponding to the specified self-start item;

[0287] According to the adjustment strategy corresponding to the context relationship detection rule, based on the self-starting instruction, multiple input instructions are expanded to obtain multiple output instructions.

[0288] In some optional implementations, the multiple detection rules include a contextual relationship detection rule, and the current detection rule is a contextual relationship detection rule; the instruction processing unit 403 is used to:

[0289] When the context relationship detection rule is used to determine that a fourth target instruction lacking integrity exists among the multiple input instructions, a detection result for characterizing that the multiple input instructions have execution problems is obtained.

[0290] In some optional implementations, the instruction processing unit 403 is used to:

[0291] Supplement the fourth target instruction to obtain a complete intention instruction;

[0292] According to the adjustment strategy corresponding to the context relationship detection rule, the fourth target instruction in the multiple input instructions is replaced with the complete intention instruction to obtain multiple output instructions.

[0293] In some optional implementations, the multiple detection rules include a user confirmation item detection rule, and the current detection rule is a user confirmation item detection rule; the instruction processing unit 403 is used to:

[0294] When the user confirmation item detection rule is used to determine that there is a fifth target instruction having a dependency relationship with the specified user confirmation item among the multiple input instructions, a detection result for characterizing that there are execution problems in the multiple input instructions is obtained.

[0295] In some optional implementations, the instruction processing unit 403 is used to:

[0296] Generate a prompt information broadcast instruction corresponding to the specified user confirmation item;

[0297] According to the adjustment strategy corresponding to the user confirmation item detection rule, based on the prompt information broadcast instruction, multiple input instructions are expanded to obtain multiple output instructions.

[0298] In some optional implementations, the instruction processing unit 403 is used to:

[0299] Convert multi-intent voice commands into multi-intent text commands;

[0300] The multi-intent text instruction is parsed to obtain a plurality of initial single-intent instructions; wherein each of the plurality of initial single-intent instructions has a specific data structure.

[0301] In some optional implementations, the instruction processing unit 403 is used to:

[0302] Decompose the multi-intent text instructions to obtain multiple single-intent text instructions;

[0303] Each single-intent text instruction among the multiple single-intent text instructions is used as a target text instruction, and the target text instruction is parsed to obtain a single user intent, vertical category information to which the single user intent belongs, and control parameters of the single user intent;

[0304] Based on the single user intent, the vertical category information to which the single user intent belongs, and the control parameters of the single user intent, an initial single intent instruction corresponding to the target text instruction is obtained.

[0305] In some optional implementations, the instruction processing device 400 further includes an information broadcasting unit, which is used to:

[0306] After each of the multiple target single-intention instructions is successfully executed, generating overall feedback information related to the multiple target single-intention instructions;

[0307] Report overall feedback information.

[0308] In the embodiment of the present disclosure, the specific functions and examples of each unit in the instruction processing device 400 can be found in the relevant description of the corresponding steps in the aforementioned instruction processing method embodiment, and will not be repeated here.

[0309] In the technical solution disclosed herein, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0310] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a vehicle, a readable storage medium, and a computer program product.

[0311] Figure 5 A schematic block diagram of an example electronic device 500 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as vehicle-mounted computing devices, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0312] like Figure 5As shown, the electronic device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 to a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic device 500 can also be stored. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0313] A number of components in the electronic device 500 are connected to the I / O interface 505, including: an input unit 506, such as a keyboard, a mouse, etc.; an output unit 507, such as various types of renderers, speakers, etc.; a storage unit 508, such as a disk, an optical disk, etc.; and a communication unit 509, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 509 allows the electronic device 500 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0314] The computing unit 501 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSP), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 501 performs the various methods and processes described above, such as instruction processing methods. For example, in some embodiments, the instruction processing method may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps in the instruction processing method described above may be executed. Alternatively, in other embodiments, the computing unit 501 may be configured as an instruction processing method in any other appropriate manner (eg, by means of firmware).

[0315] Various embodiments of the systems and techniques described above herein may be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0316] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0317] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a RAM, a ROM, an erasable programmable read-only memory (EPROM) or a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0318] To provide interaction with a user, the systems and techniques described herein may be implemented on a computer having: a rendering device (e.g., a cathode ray tube (CRT) renderer or a liquid crystal display (LCD)) for rendering information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices are also used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0319] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: Local Area Network (LAN), Wide Area Network (WAN), and the Internet.

[0320] The computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server can be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0321] The disclosed embodiment also provides a vehicle, including an electronic device.

[0322] The embodiment of the present disclosure also provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute the instruction processing method.

[0323] The embodiment of the present disclosure also provides a computer program product, including a computer program, which implements the instruction processing method when executed by a processor.

[0324] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in the present disclosure can be executed in parallel, sequentially or in a different order, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, and this document is not limited here. In addition, in the present disclosure, relational terms such as "first", "second", "third", etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. In addition, "multiple" in the present disclosure can be understood as at least two.

[0325] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the principles of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A command processing method, comprising: Get multi-intent voice commands; Based on the multi-intent voice command, obtaining multiple initial single-intent commands; According to the detection rules, the multiple initial single-intention instructions are detected and / or adjusted to obtain multiple target single-intention instructions; Each of the plurality of target single-intent instructions is executed.

2. The method according to claim 1, wherein: The detection rules include at least one of priority detection rules, resource conflict detection rules, logic conflict detection rules, context relationship detection rules, and user confirmation item detection rules.

3. The method according to claim 1, wherein: The detecting and / or adjusting the multiple initial single-intention instructions according to the detection rule to obtain multiple target single-intention instructions includes: Detecting multiple input instructions using a current detection rule among multiple detection rules to obtain detection results; wherein the multiple input instructions are obtained based on multiple initial single-intention instructions; Based on the detection results, a plurality of output instructions are obtained; Based on the multiple output instructions, multiple target single-intention instructions are obtained.

4. The method according to claim 3, wherein: Based on the detection result, a plurality of output instructions are obtained, including: When the detection result indicates that the multiple input instructions have execution problems, the multiple input instructions are adjusted according to an adjustment strategy corresponding to the current detection rule to obtain multiple output instructions.

5. The method according to claim 4, wherein: The adjustment strategy includes at least one of the following: adjusting the order of the multiple input instructions; performing resource adjustment on the plurality of input instructions; Partially deleting the multiple input instructions; Performing instruction expansion on the multiple input instructions; Instruction replacement is performed on the multiple input instructions.

6. The method according to claim 3, wherein: The method of detecting multiple input instructions using a current detection rule among multiple detection rules to obtain detection results includes: Get multiple detection rules; Determine the current detection rule from the multiple detection rules in sequence according to the detection order; The current detection rule is used to detect multiple input instructions to obtain detection results.

7. The method according to claim 6, wherein: In a case where the current detection rule is the first detection rule among the multiple detection rules, the multiple input instructions corresponding to the current detection rule are the multiple initial single-intention instructions; In the case that the current detection rule is not the first detection rule among the multiple detection rules, the multiple input instructions corresponding to the current detection rule are multiple output instructions corresponding to a detection rule preceding the current detection rule.

8. The method according to claim 4, wherein: The multiple detection rules include a priority detection rule, and the current detection rule is the priority detection rule; the current detection rule among the multiple detection rules is used to detect multiple input instructions to obtain a detection result, including: Obtaining a predetermined priority order determined based on the priority detection rule; In the case where the initial execution order of the multiple input instructions is inconsistent with the predetermined priority order, a detection result for characterizing that the multiple input instructions have execution problems is obtained.

9. The method according to claim 8, wherein: The adjusting the multiple input instructions according to the adjustment strategy corresponding to the current detection rule to obtain multiple output instructions includes: According to the adjustment strategy corresponding to the priority detection rule, based on the predetermined priority order, the multiple input instructions are sequentially adjusted to obtain multiple output instructions.

10. The method according to claim 4, wherein: The multiple detection rules include a resource conflict detection rule, and the current detection rule is the resource conflict detection rule; the current detection rule among the multiple detection rules is used to detect multiple input instructions to obtain a detection result, including: Determining a resource involved by each of the plurality of input instructions; When the resource conflict detection rule is used to determine that there are multiple first target instructions involving the same resource among the multiple input instructions, a detection result for characterizing that there are execution problems with the multiple input instructions is obtained.

11. The method according to claim 10, wherein: The multiple detection rules also include a priority detection rule; the multiple input instructions are adjusted according to the adjustment strategy corresponding to the current detection rule to obtain multiple output instructions, including: Obtaining a predetermined priority order determined based on the priority detection rule; According to the adjustment strategy corresponding to the resource conflict detection rule, based on the predetermined priority order, resources are adjusted for the multiple first target instructions in the multiple input instructions to obtain multiple output instructions.

12. The method according to claim 4, wherein: The multiple detection rules include a logic conflict detection rule, and the current detection rule is the logic conflict detection rule; the current detection rule among the multiple detection rules is used to detect multiple input instructions to obtain a detection result, including: Determining key logic information of each input instruction in the plurality of input instructions; When the logic conflict detection rule is used to determine that there are multiple second target instructions with key logic information conflicts among the multiple input instructions, a detection result for characterizing that there are execution problems in the multiple input instructions is obtained.

13. The method according to claim 12, wherein: The adjusting the multiple input instructions according to the adjustment strategy corresponding to the current detection rule to obtain multiple output instructions includes: According to the adjustment strategy corresponding to the logic conflict detection rule, the non-last instructions in the plurality of second target instructions are determined as instructions to be deleted, so as to delete the instructions to be deleted from the plurality of input instructions to obtain a plurality of output instructions.

14. The method according to claim 4, wherein: The multiple detection rules include a contextual relationship detection rule, and the current detection rule is the contextual relationship detection rule; the current detection rule among the multiple detection rules is used to detect multiple input instructions to obtain a detection result, including: Determine the specified auto-start item; When the context relationship detection rule is used to determine that there is a third target instruction in the multiple input instructions that has a dependency relationship with the designated self-starting item, a detection result for characterizing that there is an execution problem with the multiple input instructions is obtained.

15. The method according to claim 14, wherein: The adjusting the multiple input instructions according to the adjustment strategy corresponding to the current detection rule to obtain multiple output instructions includes: Generate a self-start instruction corresponding to the specified self-start item; According to the adjustment strategy corresponding to the context relationship detection rule, based on the self-starting instruction, the multiple input instructions are expanded to obtain multiple output instructions.

16. The method according to claim 4, wherein: The multiple detection rules include a contextual relationship detection rule, and the current detection rule is the contextual relationship detection rule; The detecting multiple input instructions using the current detection rule among the multiple detection rules to obtain the detection result includes: When the context relationship detection rule is used to determine that a fourth target instruction lacking integrity exists in the multiple input instructions, a detection result for characterizing that the multiple input instructions have execution problems is obtained.

17. The method according to claim 16, wherein: The adjusting the multiple input instructions according to the adjustment strategy corresponding to the current detection rule to obtain multiple output instructions includes: Supplementing the fourth target instruction to obtain a complete intention instruction; According to the adjustment strategy corresponding to the context relationship detection rule, the fourth target instruction in the multiple input instructions is replaced with the complete intention instruction to obtain multiple output instructions.

18. The method according to claim 4, wherein: The multiple detection rules include a user confirmation item detection rule, and the current detection rule is the user confirmation item detection rule; the current detection rule among the multiple detection rules is used to detect multiple input instructions to obtain a detection result, including: When the user confirmation item detection rule is used to determine that there is a fifth target instruction in the multiple input instructions that has a dependency relationship with the specified user confirmation item, a detection result for characterizing that there is an execution problem in the multiple input instructions is obtained.

19. The method according to claim 18, wherein: The adjusting the multiple input instructions according to the adjustment strategy corresponding to the current detection rule to obtain multiple output instructions includes: Generate a prompt information broadcast instruction corresponding to the specified user confirmation item; According to the adjustment strategy corresponding to the user confirmation item detection rule, based on the prompt information broadcast instruction, the multiple input instructions are expanded to obtain multiple output instructions.

20. The method according to any one of claims 1 to 19, wherein: The obtaining of a plurality of initial single-intent instructions based on the multi-intent voice instructions includes: Converting the multi-intent voice command into a multi-intent text command; The multi-intent text instruction is parsed to obtain a plurality of initial single-intent instructions; wherein each of the plurality of initial single-intent instructions has a specific data structure.

21. The method according to claim 20, wherein: The parsing of the multi-intent text instruction to obtain the multiple initial single-intent instructions includes: Decomposing the multi-intent text instruction to obtain a plurality of single-intent text instructions; Taking each single-intent text instruction among the multiple single-intent text instructions as a target text instruction, parsing the target text instruction to obtain a single user intent, vertical category information to which the single user intent belongs, and control parameters of the single user intent; Based on the single user intention, the vertical category information to which the single user intention belongs, and the control parameters of the single user intention, an initial single intention instruction corresponding to the target text instruction is obtained.

22. The method of claim 1, further comprising: After each of the plurality of target single-intention instructions is successfully executed, generating overall feedback information related to the plurality of target single-intention instructions; The overall feedback information is broadcasted.

23. An instruction processing device, comprising: A first instruction acquisition unit, used to acquire a multi-intention voice instruction; A second instruction acquisition unit, configured to obtain a plurality of initial single-intent instructions based on the multi-intent voice instruction; An instruction processing unit, configured to detect and / or adjust the plurality of initial single-intention instructions according to a detection rule to obtain a plurality of target single-intention instructions; An instruction execution unit is used to execute each target single-intent instruction among the multiple target single-intent instructions.

24. The device according to claim 23, wherein: The detection rules include at least one of priority detection rules, resource conflict detection rules, logic conflict detection rules, context relationship detection rules, and user confirmation item detection rules.

25. The device according to claim 23, wherein: The instruction processing unit is used for: Detecting multiple input instructions using a current detection rule among multiple detection rules to obtain detection results; wherein the multiple input instructions are obtained based on multiple initial single-intention instructions; Based on the detection results, a plurality of output instructions are obtained; Based on the multiple output instructions, multiple target single-intention instructions are obtained.

26. The device according to claim 25, wherein The instruction processing unit is used for: When the detection result indicates that the multiple input instructions have execution problems, the multiple input instructions are adjusted according to an adjustment strategy corresponding to the current detection rule to obtain multiple output instructions.

27. The device according to claim 26, wherein: The adjustment strategy includes at least one of the following: adjusting the order of the multiple input instructions; performing resource adjustment on the plurality of input instructions; Partially deleting the multiple input instructions; Performing instruction expansion on the multiple input instructions; Instruction replacement is performed on the multiple input instructions.

28. The device according to claim 25, wherein: The instruction processing unit is used for: Get multiple detection rules; Determine the current detection rule from the multiple detection rules in sequence according to the detection order; The current detection rule is used to detect multiple input instructions to obtain detection results.

29. The device according to claim 28, wherein In a case where the current detection rule is the first detection rule among the multiple detection rules, the multiple input instructions corresponding to the current detection rule are the multiple initial single-intention instructions; In the case that the current detection rule is not the first detection rule among the multiple detection rules, the multiple input instructions corresponding to the current detection rule are multiple output instructions corresponding to a detection rule preceding the current detection rule.

30. The device according to claim 26, wherein: The multiple detection rules include a priority detection rule, and the current detection rule is the priority detection rule; and the instruction processing unit is used for: Obtaining a predetermined priority order determined based on the priority detection rule; In the case where the initial execution order of the multiple input instructions is inconsistent with the predetermined priority order, a detection result for characterizing that the multiple input instructions have execution problems is obtained.

31. The device according to claim 30, wherein The instruction processing unit is used for: According to the adjustment strategy corresponding to the priority detection rule, based on the predetermined priority order, the multiple input instructions are sequentially adjusted to obtain multiple output instructions.

32. The apparatus of claim 26, wherein: The multiple detection rules include a resource conflict detection rule, and the current detection rule is the resource conflict detection rule; the instruction processing unit is used for: Determining a resource involved by each of the plurality of input instructions; When the resource conflict detection rule is used to determine that there are multiple first target instructions involving the same resource among the multiple input instructions, a detection result for characterizing that there are execution problems with the multiple input instructions is obtained.

33. The device according to claim 32, wherein: The multiple detection rules also include a priority detection rule; the instruction processing unit is used for: Obtaining a predetermined priority order determined based on the priority detection rule; According to the adjustment strategy corresponding to the resource conflict detection rule, based on the predetermined priority order, resources are adjusted for the multiple first target instructions in the multiple input instructions to obtain multiple output instructions.

34. The apparatus of claim 26, wherein: The multiple detection rules include a logic conflict detection rule, and the current detection rule is the logic conflict detection rule; the instruction processing unit is used for: Determining key logic information of each input instruction in the plurality of input instructions; When the logic conflict detection rule is used to determine that there are multiple second target instructions with key logic information conflicts among the multiple input instructions, a detection result for characterizing that there are execution problems in the multiple input instructions is obtained.

35. The device according to claim 34, wherein The instruction processing unit is used for: According to the adjustment strategy corresponding to the logic conflict detection rule, the non-last instructions in the plurality of second target instructions are determined as instructions to be deleted, so as to delete the instructions to be deleted from the plurality of input instructions to obtain a plurality of output instructions.

36. The apparatus of claim 26, wherein: The multiple detection rules include a contextual relationship detection rule, and the current detection rule is the contextual relationship detection rule; and the instruction processing unit is used for: Determine the specified auto-start item; When the context relationship detection rule is used to determine that there is a third target instruction in the multiple input instructions that has a dependency relationship with the designated self-starting item, a detection result for characterizing that there is an execution problem with the multiple input instructions is obtained.

37. The device according to claim 36, wherein The instruction processing unit is used for: Generate a self-start instruction corresponding to the specified self-start item; According to the adjustment strategy corresponding to the context relationship detection rule, based on the self-starting instruction, the multiple input instructions are expanded to obtain multiple output instructions.

38. The apparatus of claim 26, wherein: The multiple detection rules include a contextual relationship detection rule, and the current detection rule is the contextual relationship detection rule; and the instruction processing unit is used for: When the context relationship detection rule is used to determine that a fourth target instruction lacking integrity exists in the multiple input instructions, a detection result for characterizing that the multiple input instructions have execution problems is obtained.

39. The device according to claim 38, wherein The instruction processing unit is used for: Supplementing the fourth target instruction to obtain a complete intention instruction; According to the adjustment strategy corresponding to the context relationship detection rule, the fourth target instruction in the multiple input instructions is replaced with the complete intention instruction to obtain multiple output instructions.

40. The apparatus of claim 26, wherein: The multiple detection rules include a user confirmation item detection rule, and the current detection rule is the user confirmation item detection rule; and the instruction processing unit is used for: When the user confirmation item detection rule is used to determine that there is a fifth target instruction in the multiple input instructions that has a dependency relationship with the specified user confirmation item, a detection result for characterizing that there is an execution problem in the multiple input instructions is obtained.

41. The device according to claim 40, wherein The instruction processing unit is used for: Generate a prompt information broadcast instruction corresponding to the specified user confirmation item; According to the adjustment strategy corresponding to the user confirmation item detection rule, based on the prompt information broadcast instruction, the multiple input instructions are expanded to obtain multiple output instructions.

42. The device according to any one of claims 23 to 41, wherein: The instruction processing unit is used for: Converting the multi-intent voice command into a multi-intent text command; The multi-intent text instruction is parsed to obtain a plurality of initial single-intent instructions; wherein each of the plurality of initial single-intent instructions has a specific data structure.

43. The device according to claim 42, wherein: The instruction processing unit is used for: Decomposing the multi-intent text instruction to obtain a plurality of single-intent text instructions; Taking each single-intent text instruction among the multiple single-intent text instructions as a target text instruction, parsing the target text instruction to obtain a single user intent, vertical category information to which the single user intent belongs, and control parameters of the single user intent; Based on the single user intention, the vertical category information to which the single user intention belongs, and the control parameters of the single user intention, an initial single intention instruction corresponding to the target text instruction is obtained.

44. The device according to claim 23, further comprising an information broadcast unit, configured to: After each of the plurality of target single-intention instructions is successfully executed, generating overall feedback information related to the plurality of target single-intention instructions; The overall feedback information is broadcasted.

45. An electronic device comprising: at least one processor; a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed 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 perform the method according to any one of claims 1 to 22.

46. ​​A vehicle comprising the electronic device of claim 45.

47. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 22.

48. A computer program product, comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 22.

Images