Voice task scheduling method and device, terminal air conditioner, system and storage medium

Abstract

The invention relates to the technical field of data processing, and discloses a voice task scheduling method and device, a terminal air conditioner, a system and a storage medium, the method is applied to the terminal air conditioner, and the method comprises the steps of obtaining a non-awakening task and a network type of a network where the terminal air conditioner is located; analyzing the non-wake-up task to obtain a task instruction corresponding to the non-wake-up task; and according to the task instruction and the network type, locally processing the non-wake-up task or unloading to the collaborative equipment end to process the non-wake-up task. The method can improve the user experience under voice interaction.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, for example, to a method and device for scheduling voice tasks, a terminal air conditioner, a system, and a storage medium. Background Art

[0002] With the deep integration of 5G (fifth-generation mobile communication technology) networks and edge computing, smart home systems are rapidly developing towards distributed collaborative processing. In the field of smart air conditioner voice interaction, traditional centralized cloud-based processing models are no longer able to cope with the challenges posed by the growing user base and massive concurrent voice tasks. Especially under fluctuating network conditions, sole reliance on cloud-based processing can lead to response delays, command loss, and other issues, severely impacting the user experience.

[0003] In order to solve the problems of response delay and command loss caused by relying solely on the cloud, the related technology (publication number CN118555282A) discloses an edge computing method for a whole-house smart central control tablet computer, which is applied to the central control tablet computer in the edge computing system. The method includes: establishing a local area network and connecting multiple edge devices through local area network communication; collecting user operation instructions and status information of home appliances, and generating multiple computing tasks based on the operation instructions and status information; based on the computing power and network bandwidth parameters of the edge devices, distributing multiple computing tasks with different priorities to multiple edge devices through a scheduling optimization algorithm; receiving the calculation results returned by the edge devices after calculating the calculation tasks; summarizing the calculation results to obtain result instructions; controlling the corresponding home appliances to execute the result instructions, and displaying the execution results.

[0004] During the implementation of the embodiments of the present disclosure, it was found that at least the following problems exist in the related art:

[0005] The scheduling optimization algorithms used in related technologies employ a one-way task distribution method, which is difficult to meet the diverse needs of voice interaction. Furthermore, these technologies distribute tasks based on edge device computing power and network bandwidth parameters, lacking a flexible scheduling mechanism. This can easily lead to high response delays and low task execution success rates during network fluctuations. These limitations severely impact the user experience during voice interaction.

[0006] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of this application, and therefore may include information that does not constitute prior art known to ordinary technicians in this field. Summary of the Invention

[0007] In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not an extensive review, nor is it intended to identify key / critical elements or delineate the scope of protection of these embodiments, but rather serves as a prelude to the detailed description that follows.

[0008] Embodiments of the present disclosure provide a method, device, terminal air conditioner, system, and storage medium for scheduling voice tasks to improve user experience under voice interaction.

[0009] In some embodiments, the method is applied to a terminal air conditioner, and the method includes: obtaining a non-wake-up task and the network type of the terminal air conditioner; parsing the non-wake-up task to obtain the task instruction corresponding to the non-wake-up task; and processing the non-wake-up task locally or offloading it to a collaborative device to process the non-wake-up task according to the task instruction and the network type.

[0010] In some embodiments, the collaborative device side includes an edge device side and a cloud side, and processes non-wake-up tasks locally or offloads them to the collaborative device side according to the task instructions and the network type, including: obtaining the instruction type of the task instruction; when the network type is a strong WiFi network, offloading the non-wake-up task to the cloud side; when the network type is a weak WiFi network, obtaining the network level of the network, and processing the non-wake-up task locally or offloading it to the edge device side according to the network level and instruction type; when the network type is a cellular network, processing the non-wake-up task locally or offloading it to the cloud side according to the instruction type.

[0011] In some embodiments, non-wake-up tasks are processed locally or offloaded to the edge device for processing according to the network level and instruction type, including: when the instruction type indicates a task execution instruction and the network level is a stable weak network, the non-wake-up task is processed locally and synchronized to the edge device for confirmation; when the instruction type indicates a cloud request and the network level is a stable weak network, the non-wake-up task is offloaded to the edge device to parse the non-wake-up task through the edge device and then send the parsed result to the cloud; when the instruction type indicates a task execution instruction and the network level is a fluctuating weak network, the non-wake-up task is processed locally and confirmed through the cellular network; when the instruction type indicates a cloud request and the network level is a fluctuating weak network, the voice features of the non-wake-up task are extracted locally and uploaded asynchronously to the cloud so that the control instruction can be constructed based on the voice features through the cloud and sent to the terminal air conditioner locally.

[0012] In some embodiments, non-wake-up tasks are processed locally or offloaded to the edge device for processing based on the network level and instruction type, and also include: when the instruction type indicates a task execution instruction and the network type is a critical packet loss network, the non-wake-up task is processed locally; when the instruction type indicates a cloud request and the network type is a critical packet loss network, the updated non-wake-up task is re-received locally.

[0013] In some embodiments, obtaining the network level of a network includes: obtaining a network bandwidth evaluation result; determining that the network level is a stable weak network when the network bandwidth evaluation result indicates that the network bandwidth evaluation score matches a first score threshold; determining that the network level is a fluctuating weak network when the network bandwidth evaluation result indicates that the network bandwidth evaluation score matches a second score threshold; and determining that the network level is a critical packet loss network when the network bandwidth evaluation result indicates that the network bandwidth evaluation score matches a third score threshold; wherein the first score threshold is greater than the second score threshold, and the second score threshold is greater than the third score threshold.

[0014] In some embodiments, it also includes: before obtaining the non-wake-up task and the network type of the network where the terminal air conditioner is located, audio classification is performed on the received voice task to obtain a voice classification task; wherein the voice classification task includes a non-wake-up task and a wake-up task; and a local response wake-up task.

[0015] In some embodiments, the apparatus includes a processor and a memory storing program instructions, and the processor is configured to execute the aforementioned method for scheduling voice tasks when running the program instructions.

[0016] In some embodiments, the terminal air conditioner includes: an air conditioner body; and a scheduling device for voice tasks as described above, installed in the air conditioner body.

[0017] In some embodiments, the system includes: a collaborative device end, including an edge device end and a cloud end; such as the aforementioned terminal air conditioner, the terminal air conditioner is communicatively connected with the collaborative device end.

[0018] In some embodiments, the storage medium stores program instructions, which, when executed, enable a computer to execute the aforementioned method for scheduling voice tasks.

[0019] The voice task scheduling method, device, terminal air conditioner, system, and storage medium provided by the embodiments of the present disclosure can achieve the following technical effects:

[0020] This disclosed embodiment integrates task instructions and network type factors to process non-wake-up tasks locally or distributed to collaborative devices. It uses a flexible scheduling mechanism to allocate non-wake-up tasks, ensuring that different types of non-wake-up tasks can be reliably executed. Furthermore, this disclosed embodiment incorporates network type into task scheduling considerations, which can improve response speed and stability in fluctuating network environments, thereby reducing response latency and task execution success rates in fluctuating network environments, and improving the user experience under voice interaction.

[0021] The above general description and the following description are exemplary and explanatory only and are not intended to limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] One or more embodiments are exemplarily described by corresponding drawings. These exemplary descriptions and drawings do not limit the embodiments. Elements with the same reference numerals in the drawings are shown as similar elements. The drawings do not constitute a scale limitation. In addition,

[0023] Figure 1 This is an architectural diagram of a voice task scheduling system provided by an embodiment of the present disclosure;

[0024] Figure 2 is a schematic diagram of a first voice task scheduling method provided by an embodiment of the present disclosure;

[0025] Figure 3 is a schematic diagram of a second voice task scheduling method provided by an embodiment of the present disclosure;

[0026] Figure 4 is a schematic diagram of a third voice task scheduling method provided by an embodiment of the present disclosure;

[0027] Figure 5 is an application diagram of an embodiment of the present disclosure;

[0028] Figure 6 is a schematic diagram of a voice task scheduling device provided by an embodiment of the present disclosure;

[0029] Figure 7 It is a schematic diagram of a terminal air conditioner provided by an embodiment of the present disclosure.

[0030] Reference numerals:

[0031] 100: terminal air conditioner; 200: edge device; 300: cloud;

[0032] 70: voice task scheduling device; 700: processor;

[0033] 701: memory; 702: communication interface; 703: bus. DETAILED DESCRIPTION

[0034] In order to be able to understand the features and technical content of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure is described in detail below in conjunction with the accompanying drawings. The accompanying drawings are for reference only and are not used to limit the embodiments of the present disclosure. In the following technical description, for the sake of convenience of explanation, a full understanding of the disclosed embodiments is provided through multiple details. However, one or more embodiments can still be implemented without these details. In other cases, to simplify the drawings, well-known structures and devices can be simplified for display.

[0035] In the description of the embodiments of the present disclosure and the accompanying drawings, the terms "first," "second," and the like are used to distinguish similar items and are not necessarily used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate to describe the embodiments of the present disclosure herein. In addition, the terms "including," "having," and any variations thereof are intended to cover non-exclusive inclusions.

[0036] Unless otherwise stated, the term "plurality" means two or more.

[0037] In the embodiment of the present disclosure, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B means: A or B.

[0038] The term "and / or" describes an association between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or A and B.

[0039] The term "correspondence" may refer to an association relationship or a binding relationship. The correspondence between A and B means that there is an association relationship or a binding relationship between A and B.

[0040] Figure 1 FIG. 1 is a schematic diagram of a scheduling system for voice tasks according to an embodiment of the present disclosure. Figure 1 As shown, the scheduling system includes a terminal air conditioner 100, an edge device 200, and a cloud 300. The terminal air conditioner 100 is communicatively connected to the edge device 200 and the cloud 300, and the edge device 200 is communicatively connected to the cloud 300.

[0041] The terminal air conditioner 100 represents an intelligent voice air conditioner with a voice interaction function.

[0042] The cloud 300 may be a single server, a server cluster consisting of several servers, or a cloud computing service center, which is not limited in the embodiments of the present disclosure.

[0043] It should be understood that Figure 1The number of terminal air conditioners and edge device ends in the figure is only for reference. According to actual needs, there can be any number of terminal air conditioners and edge device ends. For example, one terminal air conditioner can correspond to multiple edge device ends.

[0044] It should be noted that the voice task scheduling method provided in the embodiment of the present disclosure is generally jointly executed by the mobile terminal air conditioner, the edge device and the cloud.

[0045] Based on the system architecture of the above-mentioned voice task scheduling system, combined with Figure 2 As shown, the embodiment of the present disclosure provides a method for scheduling voice tasks, including:

[0046] S01, the terminal air conditioner obtains a non-wake-up task and the network type of the network where the terminal air conditioner is located.

[0047] S02, the terminal air conditioner analyzes the non-wake-up task and obtains the task instruction corresponding to the non-wake-up task.

[0048] S03, the terminal air conditioner processes the non-wake-up task locally or offloads the non-wake-up task to the collaborative device end according to the task instruction and network type.

[0049] Using the voice task scheduling method provided by the embodiment of the present disclosure, after obtaining the non-wake-up task and the network type of the terminal air conditioner, the embodiment of the present disclosure parses the non-wake-up task to obtain its corresponding task instruction. The embodiment of the present disclosure then chooses to process the non-wake-up task locally or offload it to the collaborative device end for processing based on the task instruction and the network type. The embodiment of the present disclosure comprehensively considers the two factors of task instruction and network type to process the non-wake-up task locally or to the collaborative device end, and uses a flexible scheduling mechanism to allocate non-wake-up tasks to ensure that different types of non-wake-up tasks can be reliably executed. In addition, the embodiment of the present disclosure also incorporates the network type into the considerations of task scheduling, which can improve the response speed and stability in a fluctuating network environment, thereby improving the response delay and task execution success rate in a fluctuating network environment.

[0050] Optionally, combined Figure 3 As shown, the terminal air conditioner processes non-wake-up tasks locally or offloads them to the collaborative device side based on the task instructions and network type, including:

[0051] S11, the terminal air conditioner obtains the instruction type of the task instruction.

[0052] S12: When the network type is a strong WiFi (Wireless Fidelity) network, the terminal air conditioner offloads non-wake-up tasks to the cloud.

[0053] In this step, after the terminal air conditioner offloads the non-wake-up task to the cloud, it also includes: the cloud obtains the task processing result and forwards it to the terminal air conditioner through the edge device.

[0054] S13, when the network type is a weak WiFi network, the terminal air conditioner obtains the network level of the network, and processes the non-wake-up task locally or offloads the non-wake-up task to the edge device end according to the network level and instruction type.

[0055] S14, when the network type is a cellular network, the terminal air conditioner processes the non-wake-up task locally or offloads the non-wake-up task to the cloud according to the instruction type.

[0056] In this way, after the embodiment of the present disclosure obtains the task instruction corresponding to the non-wake-up task, it first determines the instruction type of the task instruction, and then judges the network type. By classifying the task instructions, redundant calculations can be reduced. If the network type is a strong WiFi network, there is no need to distinguish the task instructions, and the non-wake-up tasks are directly offloaded to the cloud to ensure the effective throughput and diversity of the non-wake-up tasks. If the network type is a weak WiFi network, the local or edge device end is selected to process the non-wake-up task based on the comprehensive network level and instruction type. If the network type is a cellular network, the local or edge device end is selected to process the non-wake-up task according to the instruction type. The embodiment of the present disclosure can obtain the network status of the network where the terminal air conditioner is located based on the network type, and establish a flexible hierarchical scheduling mechanism in combination with the instruction type to ensure that non-wake-up tasks of different instruction types are executed reliably and efficiently, further improving the response delay and task execution success rate in a fluctuating network environment.

[0057] Optionally, the terminal air conditioner processes the non-wake-up task locally or offloads the processing of the non-wake-up task to the cloud according to the instruction type, including: when the instruction type indicates a task execution instruction, the terminal air conditioner processes the non-wake-up task locally; when the instruction type indicates a cloud request, the terminal air conditioner locally extracts the audio features of the non-wake-up task and uploads them asynchronously to the cloud via a cellular network to restore the original audio based on the audio features through the cloud.

[0058] The cloud-based restoration of the original audio based on audio features includes: restoring the original audio based on audio features to obtain the original audio; and, if the original audio is semantically incomplete, performing semantic completion processing on the original audio to obtain the target original audio. The semantic completion processing can adopt any of the following methods: context-aware completion method, knowledge graph-assisted completion method, or semantic role labeling method.

[0059] In this way, the disclosed embodiments can distribute tasks multi-directionally based on the command type, achieving flexible hierarchical scheduling. When the command type is a cloud request, the audio features of non-wake-up tasks are extracted and asynchronously uploaded to the cloud via the cellular network to restore the original audio through the cloud, ensuring the integrity of the voice command under high latency.

[0060] It should be noted that when the instruction type indicates a task execution instruction, the terminal air conditioner processes the non-wake-up task locally while also pushing messages through the application configured by the terminal air conditioner to notify the user of the execution status of the non-wake-up task.

[0061] Optionally, the terminal air conditioner processes non-wake-up tasks locally or offloads them to the edge device based on the network level and instruction type, including:

[0062] When the instruction type indicates a task execution instruction and the network level is a stable weak network, the terminal air conditioner processes the non-wake-up task locally and synchronizes it to the edge device for confirmation.

[0063] When the instruction type indicates a cloud request and the network level is a stable weak network, the terminal air conditioner is offloaded to the edge device to parse the non-wake-up task through the edge device and then send the parsing result to the cloud.

[0064] When the instruction type indicates a task execution instruction and the network level is a fluctuating weak network, the terminal air conditioner processes the non-wake-up task locally and confirms it through the cellular network.

[0065] If the command type indicates a cloud request and the network level is fluctuating and weak, the terminal air conditioner extracts the voice features of the non-wake-up task locally and uploads them asynchronously to the cloud. The cloud then constructs a control command based on the voice features and sends it to the terminal air conditioner locally. The voice features can be low-dimensional feature vectors to reduce the terminal air conditioner's memory usage and network bandwidth usage.

[0066] In this way, when the instruction type represents a task instruction and the network level is a stable weak network, the terminal air conditioner processes the non-wake-up task locally and synchronizes it to the edge device for confirmation. When the instruction type represents a cloud request and the network level is a stable weak network, the terminal air conditioner is unloaded to the edge device to parse the non-wake-up task through the edge device and send the parsing result to the cloud. When the instruction type represents a cloud task instruction and the network level is a fluctuating network, the terminal air conditioner processes the non-wake-up task locally and confirms it through the cellular network to ensure high throughput and low latency of the non-wake-up task. When the instruction type represents a halo request and the network level is fluctuating, the terminal air conditioner extracts the voice features of the non-wake-up task and asynchronously uploads it to the cloud to construct a control instruction based on the voice features through the cloud and feedback it to the terminal air conditioner locally. The embodiment of the present disclosure can obtain the network status of the network in which the terminal air conditioner is located based on the network type, and establish a flexible hierarchical scheduling mechanism in combination with the instruction type to ensure that non-wake-up tasks of different instruction types can be executed reliably and efficiently, further improving the response delay and task execution success rate in a fluctuating network environment.

[0067] Optionally, the edge device parses the non-wake-up task and sends the parsing result to the cloud, including: the edge device divides and compresses the non-wake-up task in sequence to obtain block audio; the edge device performs intent parsing on the block audio, obtains the parsing result and forwards it to the cloud; the cloud processes the parsing result.

[0068] In the disclosed embodiments described above, a task execution instruction indicates that the terminal air conditioner is instructed to execute a preset function. A cloud request indicates a request for a task such as information query or audio playback. As an example, a task execution instruction may be to turn on the air conditioner, activate heating mode, or switch from cooling mode to dehumidification mode. Cloud requests may also be to query the weather, play a song, or query the ambient humidity.

[0069] Optionally, the terminal air conditioner processes non-wake-up tasks locally or offloads them to the edge device based on the network level and instruction type, further comprising:

[0070] When the instruction type indicates a task execution instruction and the network type is a critical packet loss network, the terminal air conditioner locally processes non-wake-up tasks.

[0071] When the instruction type indicates a cloud request and the network type is a critical packet loss network, the terminal air conditioner locally re-receives the updated non-wake-up task.

[0072] In this way, when the network type is a critical packet loss network, the network environment is poor. If the instruction type is a task execution instruction, the terminal air conditioner chooses to process the non-wake-up task locally. If the instruction type is a cloud request, the terminal air conditioner re-receives the updated non-wake-up task locally. The disclosed embodiment can still perform task processing under extremely weak network conditions such as critical packet loss, ensuring the throughput of non-wake-up tasks.

[0073] Optionally, the terminal air conditioner obtains the network level of the network, including:

[0074] Obtain a network bandwidth assessment result, wherein the network bandwidth assessment result includes a network bandwidth assessment score.

[0075] When the network bandwidth evaluation result indicates that the network bandwidth evaluation score matches the first score threshold, the terminal air conditioner determines that the network level is a stable weak network.

[0076] When the network bandwidth evaluation result indicates that the network bandwidth evaluation score matches the second score threshold, the terminal air conditioner determines that the network level is a fluctuating weak network.

[0077] When the network bandwidth evaluation result indicates that the network bandwidth evaluation score matches the third score threshold, the terminal air conditioner determines that the network level is a critical packet loss network.

[0078] The first score threshold is greater than the second score threshold, and the second score threshold is greater than the third score threshold.

[0079] In this way, the embodiment of the present disclosure determines the network level according to the matching conditions between the obtained network bandwidth evaluation score and different score thresholds, thereby ensuring the reliability of the network level determination.

[0080] As an example, the first score threshold is [60, 79], the second score threshold is [40, 60), and the third score threshold is (0, 40).

[0081] Optionally, the terminal air conditioner obtains a network bandwidth assessment result, including: obtaining the basic bandwidth and stability parameters, delay parameters, and packet loss rate of the network; and weighting the basic bandwidth, stability parameters, delay parameters, and packet loss rate to obtain a network bandwidth assessment score. Bandwidth includes basic bandwidth or actual available bandwidth; stability parameters include bandwidth fluctuation or network congestion; delay parameters include average delay; and packet loss rate includes packet loss rate under normal traffic or packet loss rate under high load.

[0082] Combine Figure 4 As shown, the embodiment of the present disclosure also provides a method for scheduling voice tasks, including:

[0083] S21: The terminal air conditioner performs audio classification on the received voice task to obtain a voice classification task, wherein the voice classification task includes a non-wake-up task and a wake-up task.

[0084] S22, the terminal air conditioner locally responds to the wake-up task.

[0085] S23, the terminal air conditioner obtains a non-wake-up task and the network type of the network where the terminal air conditioner is located.

[0086] S24, the terminal air conditioner analyzes the non-wake-up task and obtains a task instruction corresponding to the non-wake-up task.

[0087] S25, the terminal air conditioner processes the non-wake-up task locally or offloads the non-wake-up task to the collaborative device end according to the task instruction and network type.

[0088] The voice task scheduling method provided by the embodiment of the present disclosure is adopted. After receiving the voice task, the embodiment of the present disclosure first performs audio classification on it to obtain a voice frequency division task including a non-wake-up task and a wake-up task, and then obtains the network type of the network where the terminal air conditioner is located and parses the non-wake-up task to obtain its corresponding task instruction. For the wake-up task, the terminal air conditioner responds directly locally. For the non-wake-up task, the embodiment of the present disclosure chooses to process the non-wake-up task locally or offload it to the collaborative device end for processing based on the task instruction and the network type. The embodiment of the present disclosure comprehensively considers the two factors of task instruction and network type to process the non-wake-up task locally or to the collaborative device end, and adopts a flexible scheduling mechanism to allocate non-wake-up tasks to ensure that different types of non-wake-up tasks can be reliably executed. In addition, the embodiment of the present disclosure also incorporates the network type into the consideration of task scheduling, which can improve the response speed and stability in a network fluctuation environment, thereby improving the response delay and task execution success rate in a fluctuating network environment.

[0089] In practical applications, such as Figure 5 As shown, the method for scheduling voice tasks specifically performs the following steps:

[0090] S31: The terminal air conditioner performs audio classification on the received voice task to obtain a voice classification task, wherein the voice classification task includes a non-wake-up task and a wake-up task.

[0091] S32, the terminal air conditioner determines whether the voice classification task is a non-wake-up task, if so, executes S33, otherwise executes S44.

[0092] S33, the terminal air conditioner obtains a non-wake-up task and the network type of the network where the terminal air conditioner is located.

[0093] S34, the terminal air conditioner parses the non-wake-up task, obtains the task instruction corresponding to the non-wake-up task, and obtains the instruction type of the task instruction.

[0094] S35, when the network type is a strong WiFi network, the terminal air conditioner offloads the non-wake-up task to the cloud.

[0095] S36, when the network type is a cellular network, the terminal air conditioner processes the non-wake-up task locally or offloads the non-wake-up task to the cloud according to the instruction type.

[0096] S37: If the network type is a weak WiFi network, execute S38 to S41.

[0097] S38, when the instruction type indicates a task execution instruction and the network level is a stable weak network, the terminal air conditioner locally processes the non-wake-up task and synchronizes it to the edge device for confirmation.

[0098] S39, when the instruction type indicates a cloud request and the network level is a stable weak network, the terminal air conditioner is unloaded to the edge device to parse the non-wake-up task through the edge device and then send the parsing result to the cloud.

[0099] S40, when the instruction type indicates a task execution instruction and the network level is a fluctuating weak network, the terminal air conditioner locally processes the non-wake-up task and confirms it through the cellular network.

[0100] S41, when the instruction type indicates a cloud request and the network level is a fluctuating weak network, the terminal air conditioner locally extracts the voice features of the non-wake-up task and asynchronously uploads them to the cloud so that the cloud constructs a control instruction based on the voice features and sends it to the terminal air conditioner locally.

[0101] S42: When the instruction type indicates a task execution instruction and the network type is a critical packet loss network, the terminal air conditioner locally processes the non-wake-up task.

[0102] S43, when the instruction type indicates a cloud request and the network type is a critical packet loss network, the terminal air conditioner locally re-receives the updated non-wake-up task.

[0103] S44, the terminal air conditioner locally responds to the wake-up task.

[0104] Combine Figure 6 As shown, an embodiment of the present disclosure provides a voice task scheduling device 70, including a processor 700 and a memory 701. Optionally, the device 70 may also include a communication interface 702 and a bus 703. The processor 700, the communication interface 702, and the memory 701 may communicate with each other via the bus 703. The communication interface 702 may be used for information transmission. The processor 700 may call the logic instructions in the memory 701 to execute the voice task scheduling method of the above embodiment.

[0105] In addition, the logic instructions in the memory 701 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product.

[0106] Memory 701, as a computer-readable storage medium, can be used to store software programs and computer-executable programs, such as program instructions / modules corresponding to the methods in the embodiments of the present disclosure. Processor 700 executes the program instructions / modules stored in memory 701 to execute functional applications and data processing, thereby implementing the voice task scheduling method in the above-mentioned embodiments.

[0107] The memory 701 may include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function; the data storage area may store data generated based on the use of the terminal device. Furthermore, the memory 701 may include high-speed random access memory and non-volatile memory.

[0108] Combine Figure 7 As shown, the embodiment of the present disclosure provides a terminal air conditioner 100, including: an air conditioner body, and the above-mentioned voice task scheduling device 70. The voice task scheduling device 70 is installed on the air conditioner body. The installation relationship described here is not limited to placement inside the air conditioner body, but also includes installation connections with other components of the terminal air conditioner 100, including but not limited to physical connections, electrical connections or signal transmission connections. It can be understood by those skilled in the art that the voice task scheduling device 70 can be adapted to a feasible air conditioner body, thereby realizing other feasible embodiments.

[0109] The disclosed embodiments further provide a voice task scheduling system, including a collaborative device and a terminal air conditioner. The collaborative device includes an edge device and a cloud. The terminal air conditioner is communicatively connected to the collaborative device.

[0110] An embodiment of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured to execute the above-mentioned method for scheduling voice tasks.

[0111] The technical solutions of the embodiments of the present disclosure may be embodied in the form of a software product, which is stored in a storage medium and includes one or more instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiments of the present disclosure. The aforementioned storage medium may be a non-transitory storage medium, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, among other media capable of storing program code.

[0112] The above description and accompanying drawings sufficiently illustrate the embodiments of the present disclosure to enable those skilled in the art to practice them. Other embodiments may include structural, logical, electrical, process, and other changes. The embodiments represent only possible variations. Unless expressly required, individual components and functions are optional, and the order of operations may vary. Portions and features of some embodiments may be included in or substituted for portions and features of other embodiments. Furthermore, the terms used in this application are intended only to describe the embodiments and are not intended to limit the claims. In addition, when used in this application, the terms "comprise" and its variations "comprises" and / or "comprising" refer to the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. Without further limitation, an element defined by the phrase "comprises a..." does not preclude the presence of additional identical elements in the process, method, or apparatus that includes the element. Each embodiment herein may focus on its differences from other embodiments, and similar portions between the various embodiments may be referenced across them. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method part disclosed in the embodiments, then the relevant parts can be found in the description of the method part.

[0113] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software may depend on the specific application and design constraints of the technical solution. The technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the embodiments of the present disclosure. The technicians will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0114] In the embodiments disclosed herein, the disclosed methods and products (including but not limited to devices, equipment, etc.) can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units can be merely a logical functional division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, and can be electrical, mechanical or other forms. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected to implement this embodiment according to actual needs. In addition, the functional units in the embodiments of the present disclosure may be integrated into a processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0115] The flowcharts and block diagrams in the accompanying drawings show the possible implementation architectures, functions and operations of the systems, methods and computer program products according to the embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment or part of the code, and the module, program segment or part of the code contains one or more executable instructions for implementing the specified logical functions. In some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, or they can sometimes be executed in the opposite order, which can depend on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in an order different from that disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, or they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified function or action, or may be implemented by a combination of dedicated hardware and computer instructions.

Claims

1. A method for scheduling voice tasks, characterized in that: Applied to terminal air conditioners, the methods include: Get the network type of the network where the non-wake-up task and the terminal air conditioner are located; Analyze the non-wake-up task and obtain the task instruction corresponding to the non-wake-up task; Depending on the task instructions and network type, non-wake-up tasks are processed locally or offloaded to the collaborative device for processing.

2. The method according to claim 1, characterized in that Collaborative devices include edge devices and the cloud. Depending on the task instructions and network type, non-wake-up tasks are processed locally or offloaded to collaborative devices for processing, including: Get the instruction type of the task instruction; When the network type is a strong wireless fidelity WiFi network, non-wake-up tasks are offloaded to the cloud; If the network type is a weak WiFi network, obtain the network level of the network and process the non-wake-up task locally or offload it to the edge device based on the network level and instruction type; When the network type is a cellular network, non-wake-up tasks are processed locally or offloaded to the cloud according to the instruction type.

3. The method according to claim 2, characterized in that Depending on the network level and command type, non-wake-up tasks are processed locally or offloaded to edge devices, including: When the instruction type indicates a task execution instruction and the network level is stable weak network, the non-wake-up task is processed locally and synchronized to the edge device for confirmation; When the instruction type indicates a cloud request and the network level is a stable weak network, the task is offloaded to the edge device to parse the non-wake-up task and then send the parsing result to the cloud. When the instruction type indicates a task execution instruction and the network level is a fluctuating weak network, non-wake-up tasks are processed locally and confirmed through the cellular network; When the command type indicates a cloud request and the network level is a fluctuating weak network, the voice features of the non-wake-up task are extracted locally and uploaded asynchronously to the cloud so that the cloud can construct a control command based on the voice features and send it to the terminal air conditioner locally.

4. The method according to claim 3, characterized in that Depending on the network level and instruction type, non-wake-up tasks are processed locally or offloaded to the edge device for processing, including: When the instruction type indicates a task execution instruction and the network type is a critical packet loss network, the non-wake-up task is processed locally; In the case where the instruction type indicates a cloud request and the network type is a critical packet loss network, the local re-receives the updated non-wake-up task.

5. The method according to claim 4, characterized in that Get the network level of the network, including: Obtain network bandwidth assessment results; When the network bandwidth evaluation result indicates that the network bandwidth evaluation score matches the first score threshold, determining the network level as a stable weak network; When the network bandwidth evaluation result indicates that the network bandwidth evaluation score matches the second score threshold, determining the network level as a fluctuating weak network; If the network bandwidth evaluation result indicates that the network bandwidth evaluation score matches the third score threshold, determining the network level as a critical packet loss network; The first score threshold is greater than the second score threshold, and the second score threshold is greater than the third score threshold.

6. The method according to any one of claims 1 to 5, characterized in that Also includes: Before obtaining the non-wake-up task and the network type of the terminal air conditioner, the received voice task is audio classified to obtain a voice classification task; wherein the voice classification task includes a non-wake-up task and a wake-up task; Local response wake-up task.

7. A voice task scheduling device, comprising a processor and a memory storing program instructions, characterized in that: The processor is configured to execute the method for scheduling voice tasks according to any one of claims 1 to 6 when running the program instructions.

8. A terminal air conditioner, characterized in that: include: Air conditioner body; The voice task scheduling device according to claim 7 is installed on the air conditioner body.

9. A voice task scheduling system, characterized in that: include: Collaborative device side, including edge device side and cloud side; The terminal air conditioner as described in claim 8 is communicatively connected to the collaborative device end.

10. A storage medium storing program instructions, characterized in that: When the program instructions are executed, the computer is configured to execute the method for scheduling voice tasks according to any one of claims 1 to 6.

Images