Voice control method, first server, second server and voice control system

Abstract

The embodiment of the invention relates to the technical field of communication interaction, in particular to a voice control method, a first server, a second server and a voice control system.The method is applied to the first server in a third-party service platform and comprises the steps that voice control data collected by voice equipment in the third-party service platform are received; analyzing the voice control data, and determining a target service platform to which a target device to be controlled by the voice control data belongs; and forwarding the voice control data to a second server in the target service platform, thereby enabling the second server to control the target equipment based on an equipment instruction obtained by performing natural language processing on the voice control data. According to the method and the device, the voice control data is converted into the device instruction which can be understood by the device by utilizing the natural language processing technology of the second server, so that a protocol conversion mode in traditional control is omitted, and complicated protocol conversion logic does not need to be independently realized for each third-party service platform.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of communication interaction technology, and in particular to a voice control method, a first server, a second server, and a voice control system. Background Art

[0002] With the rapid development of Internet of Things technology, various smart home devices are increasingly accepted by everyone. At the same time, many companies have also developed voice-based smart home platforms. Users can control the smart home devices of the entire family through the company's speakers and other voice collection devices, bringing convenience to users' lives.

[0003] However, for each smart home device manufacturing company, their smart home control system needs to be connected to as many third-party service platforms as possible. However, for each third-party service platform connected, a protocol conversion service needs to be developed for the third-party service platform to convert the smart home control instructions of the third-party service platform into the company's smart home instructions, so that when the instructions are sent to the company's smart home devices, the devices will correctly identify and execute them.

[0004] However, there are many third-party service platforms, and the instructions of each platform are different. Smart device manufacturers need to develop a set of protocol conversion services for each third-party service platform they connect to, which makes the development of protocol conversion docking cumbersome and affects the low efficiency of device access. Summary of the invention

[0005] The purpose of the present invention is to at least provide a voice control method, a first server, a second server and a voice control system, which can at least solve the problem that current smart device manufacturers need to develop a set of protocol conversion services for each third-party service platform they connect to, resulting in cumbersome docking development work for protocol conversion, and at least can achieve the effect of reducing the workload of protocol development.

[0006] To solve the above technical problems, at least one embodiment of the present application provides a voice control method, which is applied to a first server in a third-party service platform, including:

[0007] Receiving voice control data collected by the voice device in the third-party service platform;

[0008] Parsing the voice control data to determine a target service platform to which a target device to be controlled by the voice control data belongs;

[0009] The voice control data is forwarded to a second server in the target service platform, so that the second server controls the target device based on the device instructions obtained after natural language processing of the voice control data.

[0010] At least one embodiment of the present application further provides a voice control method, which is applied to a second server of a target service platform, comprising:

[0011] Receiving voice control data sent by a first server in a third-party service platform, wherein the voice control data is collected by a voice device in the third-party service platform and uploaded to the first server;

[0012] Performing natural language processing on the voice control data to obtain a target device to be voice-controlled and a device instruction to control the target device;

[0013] The device instruction is sent to the target device to control the target device.

[0014] At least one embodiment of the present application further provides a first server, which is located on a third-party service platform and includes:

[0015] A voice receiving module, used to receive voice control data collected by the voice device in the third-party service platform;

[0016] A voice analysis module, used to analyze the voice control data and determine the target service platform to which the target device to be controlled by the voice control data belongs;

[0017] A data forwarding module is used to forward the voice control data to a second server in the target service platform, so that the second server controls the target device based on the device instructions obtained after natural language processing of the voice control data.

[0018] At least one embodiment of the present application further provides a second server, where the second server is located on the target service platform and includes:

[0019] A control data receiving module, used to receive voice control data sent by a first server in a third-party service platform, wherein the voice control data is collected by a voice device in the third-party service platform and uploaded to the first server;

[0020] A natural language processing module, used to perform natural language processing on the voice control data to obtain a target device to be voice-controlled and a device instruction to control the target device;

[0021] The device instruction sending module is used to send the device instruction to the target device to control the target device.

[0022] At least one embodiment of the present application further provides a voice control system, including: a first server and a second server,

[0023] The first server is located in the third-party service platform and is used to receive voice control data collected by a voice device in the third-party service platform; parse the voice control data to determine the target service platform to which the target device to be controlled by the voice control data belongs; and forward the voice control data to the second server in the target service platform;

[0024] The second server is located on the target service platform and is used to receive the voice control data sent by the first server, perform natural language processing on the voice control data, obtain the target device to be voice controlled, and the device instructions to control the target device; and send the device instructions to the target device to control the target device.

[0025] At least one embodiment of the present application also provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned voice control method.

[0026] At least one embodiment of the present application further provides a computer-readable storage medium storing a computer program, wherein the computer program implements the above-mentioned voice control method when executed by a processor.

[0027] The embodiments of the present application provide a voice control method, a first server, a second server, and a voice control system, wherein the voice control method receives voice control data in the first server of the third-party service platform when performing voice control across service platforms, parses these data to determine the target service platform to which the target device belongs, sends the voice control data to the second server of the target service platform for parsing, and finally generates device instructions by the second server to control the target device. In this process, the natural language processing platform that the second server already has is used to convert the voice control data into device instructions that the device can "understand", thereby eliminating the protocol conversion method in traditional control and eliminating the need to implement complex protocol conversion logic for each third-party service platform.

[0028] In addition, with the development of the Internet of Things and smart homes, new third-party service platforms continue to emerge. The method of this embodiment makes adding third-party service platforms more flexible and simple by centrally processing voice control data and forwarding it to the corresponding target service platform. Only by updating the parsing logic and forwarding rules on the first server can support new third-party service platforms or devices without modifying the code of each existing service platform.

[0029] In some optional embodiments, forwarding the voice control data to a second server in the target service platform includes:

[0030] The voice control data is forwarded to the second server in the target service platform in text form or voice form.

[0031] In this embodiment, voice data usually contains a lot of redundant information and noise, but after being converted into voice text, these redundant information can be removed and only key control instructions are transmitted, thereby reducing communication overhead and improving the efficiency and reliability of data transmission. A more flexible forwarding method is provided.

[0032] In some optional embodiments, forwarding the voice control data in text form to a second server in the target service platform includes:

[0033] The voice control data is converted into text data in a target language, and the text data in the target language is forwarded to a second server in the target service platform.

[0034] In this embodiment, after the voice control data is converted into text data in the target language, it is forwarded to the second server in the target service platform, which can make the processing process of the second server simpler and more efficient.

[0035] In some optional embodiments, performing natural language processing on the voice control data includes:

[0036] The voice control data is converted into a second voice text in a second target language, and the second voice text is subjected to natural language processing.

[0037] In this embodiment, the second target language is the language that the natural language processing system processes by default. By first converting the voice control data into the voice text of the specific second target language, it can be ensured that the natural language processing system can process the language more accurately and efficiently. This helps the system to more accurately understand the user's intentions and needs, thereby improving the accuracy and efficiency of voice control.

[0038] In some optional embodiments, converting the voice control data into a second voice text in a second target language includes:

[0039] The application programming interface of the target translation software is called, and the voice control data is converted into a second voice text in a second target language through the target translation software.

[0040] In this embodiment, the target translation software is usually trained with a large amount of data and optimized with algorithms, and can provide high-quality translation services. By calling the application programming interface of these software, the accuracy and timeliness of the translation can be ensured. Developers do not need to develop translation functions from scratch, but can directly call the target translation software, thereby reducing development time and development costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] One or more embodiments are exemplarily described by the pictures in the corresponding drawings, and these exemplary descriptions do not constitute limitations on the embodiments.

[0042] Figure 1 This is the process of the voice control method provided by an embodiment of the present application Figure 1 ;

[0043] Figure 2 It is a schematic diagram of the process / scenario of implementing the voice control solution in the prior art;

[0044] Figure 3 This is the process of the voice control method provided by an embodiment of the present application Figure 2 ;

[0045] Figure 4 is a schematic diagram of a first server provided by another embodiment of the present application;

[0046] Figure 5 is a schematic diagram of a second server provided by another embodiment of the present application;

[0047] Figure 6 It is a schematic diagram of a voice control system provided by another embodiment of the present application. DETAILED DESCRIPTION

[0048] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the embodiments of the present application will be described in detail below in conjunction with the accompanying drawings. However, it will be appreciated by those skilled in the art that in the present application, many technical details are proposed in order to enable the reader to better understand the present application. However, even without these technical details and various changes and modifications based on the following embodiments, the technical scheme claimed in the present application can also be implemented. The division of the following embodiments is for the convenience of description, and the specific implementation of the present application should not be construed as any limitation, and the various embodiments can be combined and referenced with each other under the premise of no contradiction.

[0049] In order to facilitate understanding of the embodiments of the present application, relevant contents about protocol conversion in the prior art are first introduced here.

[0050] Usually, each platform-based company will develop its own smart home control platform. The platform generally uses smart speakers as the smart home control entrance. Users only need to use voice to control the smart devices in their homes, but these devices are limited to the devices of the companies connected to these platforms. The platform will convert the voice received by the speaker into a unified device control command, referred to as "platform command", and then transmit the platform command to each connected smart home manufacturer. Each manufacturer that accesses a third-party service platform needs to use the protocol conversion service developed separately for the platform company to convert the third-party service platform command into a "device command" that can be recognized by its own company's smart devices, and then send it to the device for execution.

[0051] like Figure 2 As shown in the figure, it is a control logic diagram of the smart home control system that currently relies on the protocol conversion platform. The voice control process is usually as follows: first, the voice device of the third-party service platform (such as Google speakers, Amazon speakers, Tmall Genie, Baidu speakers, etc.) collects the user's voice commands, and then the voice device converts the voice commands into control commands of the third-party service platform. Then, the protocol conversion service developed for the third-party service platform is used to convert the control commands of the third-party service platform into corresponding control commands and send them to the target device.

[0052] However, there are many companies that provide third-party service platforms, and the platform instructions of each company are different. Therefore, smart device manufacturers need to develop a set of protocol conversion services for each platform they connect to. Secondly, there are many categories and models of smart home devices produced by manufacturers, hundreds or even thousands, and the "device instructions" of each small model of device are partially different. If a manufacturer wants to develop a set of protocol conversion services that support all models of its own devices after connecting to a platform, it will undoubtedly cause a huge workload and is basically impossible to achieve. Therefore, manufacturers usually only connect some models of devices to third-party service platforms. The result is that although manufacturer A has connected to platform B, users cannot control manufacturer A's device C through the smart speaker of platform B because device C is not connected to the platform.

[0053] In order to solve the technical problem that each current smart device manufacturer needs to develop a set of protocol conversion services for each access to a third-party service platform, resulting in cumbersome docking and development work for protocol conversion, the present invention proposes a voice control method. The implementation details of the voice control method of this embodiment are specifically described below. The following content is only the implementation details provided for easy understanding and is not necessary for the implementation of this solution.

[0054] Embodiment 1:

[0055] The voice control method of this embodiment can be applied to electronic devices with communication, computing and data storage capabilities. The specific process can be as follows: Figure 1 As shown:

[0056] A voice control method, applied to a first server in a third-party service platform, comprising:

[0057] Step 110, receiving voice control data collected by the voice device in the third-party service platform;

[0058] There are various third-party service platforms that provide a unified management and control interface for smart devices. In this embodiment, the third-party service platform can be the Xiaomi Mijia platform, the Baidu Smart Life platform, or the Tencent Lianlian platform. Voice devices in the third-party service platform include smart speakers, smart TVs, voice assistants in mobile phone applications, etc. Voice control data usually includes the user's control requirements for specific devices, such as adjusting the brightness of lights, playing music, turning on air conditioning, etc. Voice data can be transmitted to the server in the form of an audio file or a real-time audio stream, and may be accompanied by some metadata, such as acquisition time, device ID, etc., for subsequent processing and tracking. During the data transmission process, encryption measures can be taken to ensure the security of voice data to prevent information leakage or malicious use.

[0059] Step 120, parsing the voice control data to determine the target service platform to which the target device to be controlled by the voice control data belongs;

[0060] In this embodiment, the first server converts the received voice data into text information using speech recognition technology, such as ASR automatic speech recognition technology. This step is the first step to understand the user's intention. Subsequently, the text information is parsed by natural language processing (NLP) technology to identify the user's control intention, such as "turn on the lights in the living room", and possible entities involved, such as "the lights in the living room". Based on the intention recognition and entity recognition results, the first server determines the target service platform to which the target device belongs through predefined rules or query databases, that is, the first server has the ability to recognize different target service platforms and their device identifiers.

[0061] For example, a user issues a voice command "turn on the air conditioner in the living room". The voice device in the third-party service platform collects the voice command or voice control information and sends it to the first server. The first server analyzes and determines that the target device to be controlled by the voice command is the air conditioner in the living room. Then, by querying the database, it determines that the air conditioner in the living room is a product produced by manufacturer A.

[0062] Step 130: forwarding the voice control data to a second server in the target service platform, so that the second server controls the target device based on the device instructions obtained after natural language processing of the voice control data.

[0063] In this embodiment, the target service platform is the service platform of manufacturer A, and a natural language processing platform (NLP platform) is stored on the second server. The main task of the NLP platform is to convert voice control data into instructions that the device can understand. This conversion process relies more on the mapping relationship between natural language processing technology and device instructions, rather than on a specific communication protocol. Therefore, as long as the NLP platform can correctly parse the voice control data and generate corresponding device instructions, no additional protocol conversion steps are required.

[0064] Once the target service platform is determined, the first server packages the user's voice control data and necessary context information (such as user ID, device ID) and forwards it to the second server in the target service platform through message queues, etc. On the second server of the target service platform, the received voice control data will be further processed by natural language processing, such as grammar checking, context understanding optimization, etc., to ensure the accuracy and executability of device instructions.

[0065] Finally, the second server sends a control signal directly to the target device through its internal communication protocol and interface according to the processed device instruction to realize the user's control needs.

[0066] In some optional embodiments, in order to improve user experience, the target service platform may also return operation results or status updates to the first server, which then communicates this information to the user in the form of voice feedback, screen prompts, etc., forming a complete closed-loop control process.

[0067] In summary, the voice control method provided in this embodiment receives voice control data in the first server of the third-party service platform, analyzes the data to determine the target service platform to which the target device belongs, sends the voice control data to the second server of the target service platform for analysis and processing, and finally generates device instructions by the second server to control the target device. In this process, the natural language processing platform already possessed by the second server is used to convert the voice control data into device instructions that the device can "understand", thereby eliminating the protocol conversion method in traditional control and eliminating the need to implement complex protocol conversion logic for each third-party service platform separately.

[0068] In addition, with the development of the Internet of Things and smart homes, new third-party service platforms continue to emerge. The method of this embodiment makes adding third-party service platforms more flexible and simple by centrally processing voice control data and forwarding it to the corresponding target service platform. Only by updating the parsing logic and forwarding rules on the first server can support new third-party service platforms or devices without modifying the code of each existing service platform.

[0069] On the other hand, in actual applications, the natural language processing platforms of manufacturers are usually in a state of continuous updating and optimization. Manufacturers only need to continuously improve their own NLP platforms to allow various third-party service platforms to control almost all of their smart devices, thereby gradually reducing the development costs required for manufacturers to subsequently connect to new third-party service platforms.

[0070] In one embodiment, forwarding the voice control data to the second server in the target service platform includes: forwarding the voice control data to the second server in the target service platform in text form or voice form.

[0071] In this embodiment, the voice control data may be forwarded in a variety of forms, which are set according to actual required scenarios to improve the flexibility and compatibility of data transmission.

[0072] In one embodiment, after the voice control data is converted into text form, some interference information or noise carried in the voice can be filtered out, so that the information retained in the text form is the core information, which is helpful for the second server to identify and process. In addition, forwarding in text form can simplify the data transmission process, reduce the complexity and delay of data transmission, and avoid recognition errors or distortions caused by factors such as signal interference and noise during the transmission of voice data.

[0073] For example, in some application scenarios, such as smart home, industrial automation, etc., voice control data in text form may be more applicable. These scenarios usually require higher data accuracy and stability, and data in text form can better meet these requirements.

[0074] In one embodiment, the first server directly forwards the voice control data to the second server in the form of voice. Direct transmission of voice data may be more intuitive in some cases, but it also requires the target service platform to have corresponding voice recognition and processing capabilities. With the continuous development of voice recognition technology, more and more platforms and devices begin to support voice input and control, so direct transmission of voice data has also become a reliable option.

[0075] For example, in some specific application scenarios, such as in-car entertainment systems, smartphone assistants, etc., it may be more convenient and intuitive to directly transmit voice data and allow users to interact through voice. These scenarios usually pay more attention to user experience and convenience, so direct transmission of voice data may be more appropriate.

[0076] In summary, the third-party service platform forwards the voice control data in text or voice form to the target service platform to which the controlled device is connected. This can improve the flexibility and compatibility of data transmission, enhance the accuracy of data processing and analysis, improve user experience and convenience, and support a variety of application scenarios and needs, which will help promote the further development and popularization of cross-platform device control.

[0077] In one embodiment, forwarding the voice control data in text form to a second server in the target service platform includes: converting the voice control data into text data in a target language, and forwarding the text data in the target language to the second server in the target service platform.

[0078] In this embodiment, the target language is the language processed by the second server by default. The voice control issued by the user can be issued in any language, which is not necessarily a language that the second server can recognize. Therefore, when the first server forwards the voice control data in text form, it converts the original voice into text data in the target language and then sends it to the second server, which can reduce the recognition difficulty of the second server and make the processing more efficient.

[0079] Embodiment 2

[0080] like Figure 3 As shown, in this embodiment, a voice control method is provided, which is applied to a second server of a target service platform, including:

[0081] Step 310, receiving voice control data sent by a first server in a third-party service platform, wherein the voice control data is collected by a voice device in the third-party service platform and uploaded to the first server;

[0082] In this embodiment, the second service platform receives the voice control data sent by the first server in real time through a stable network connection (such as TCP / IP protocol). To ensure the integrity and accuracy of the data, a data verification mechanism (such as CRC verification) and a retransmission mechanism can be used. The received voice control data can be voice data that has been preliminarily processed (such as audio formats such as WAV, PCM, etc.), or text converted by voice recognition technology.

[0083] In some optional embodiments, the voice control data is obtained in batches from the first server at specific time intervals or when specific conditions are met. This method is suitable for scenarios where real-time requirements are not high, such as the scheduled task setting of smart homes. Batch data can be stored and transmitted in the form of files (such as .txt, .json) or database records.

[0084] In some optional embodiments, to ensure the security of data transmission, the first server uses encryption technology (such as HTTPS, TLS) to encrypt and transmit the voice control data. Correspondingly, at the receiving end, that is, the second server, the encrypted data is decrypted using a corresponding decryption algorithm to restore the original voice control data.

[0085] Step 320, performing natural language processing on the voice control data to obtain a target device to be voice-controlled and a device instruction to control the target device;

[0086] In this embodiment, a set of rule bases are predefined to parse keywords and phrases in the voice control data to determine the target device and device command. For example, if the voice control data contains "turn on the light in the living room", the target device is parsed as "the light in the living room" and the device command is "turn on" according to the rule base.

[0087] After receiving the voice control data, the second server will pre-process the voice control data, including data cleaning, removal of irrelevant characters, word segmentation and other steps to ensure the accuracy and efficiency of subsequent processing. Next, the natural language processing platform performs intent recognition based on predetermined rules and extracts key information from the voice control data to determine the user's true intention. After identifying the intent, the natural language processing platform will perform entity extraction. An entity refers to a specific object or concept mentioned in the voice control data, such as device name, location, time, etc. In the instruction "turn on the lights in the living room", the platform will extract "the lights in the living room" as an entity, that is, the specific device that needs to be controlled.

[0088] The natural language processing platform then performs grammatical and semantic analysis on the voice control data. Syntactic analysis focuses on the structure and grammatical rules of the sentence to ensure the accuracy and compliance of the data. Semantic analysis provides a deeper understanding of the meaning and context of the sentence, so as to more accurately grasp the user's intentions and needs. After completing the grammatical and semantic analysis, the natural language processing platform generates corresponding device instructions based on the user's intentions and entity information. Device instructions are usually encoded in a format that the device can understand, such as a specific command code or protocol. For example, for smart home devices, the instruction may be a specific HTTP request or MQTT message.

[0089] In some optional embodiments, natural language processing (NLP) and machine learning (ML) techniques are used to train a control parsing model to parse voice control data. The control parsing model can be built based on deep learning (such as LSTM, BERT) or traditional machine learning algorithms (such as SVM, Naive Bayes). The training process can be to train the model using a large amount of annotated voice control data so that it can accurately identify and parse the target device and device instructions.

[0090] In some optional embodiments, the user's historical voice control data and current context information (such as time, location, user behavior, etc.) are combined to perform more accurate analysis. For example, if the user has previously set "automatically turn off the bedroom lights at 7 pm", when the voice control data of "turn off the lights" is received at 7 pm, the target device can be automatically analyzed as "bedroom lights". In this embodiment, by combining the user's historical voice control data and current context information (such as time, location, user behavior, etc.), a more accurate and humanized analysis is performed.

[0091] Step 330: Send the device instruction to the target device to control the target device.

[0092] In this embodiment, if the target device supports direct network connection (such as Wi-Fi, Bluetooth), the device command is directly sent to the target device through the corresponding communication protocol (such as HTTP, MQTT). If the target device needs to be controlled through an intermediate platform, the device command is first sent to the intermediate platform, and the intermediate platform then forwards the command to the target device.

[0093] In some optional embodiments, in order to ensure the correct execution of the instruction, the natural language processing platform will also receive feedback information from the target device and verify it. If the instruction is successfully executed, the natural language processing platform will record the relevant information; if the execution fails, error handling can be performed or the instruction can be resent.

[0094] In summary, the voice control method of this embodiment utilizes the target service platform or the manufacturer's own natural language processing platform to convert the user's voice control instructions into device instructions that the manufacturer's own target device can "understand", thereby omitting the work of the third-party service platform and the target service platform (manufacturer) to develop protocol conversion services one by one. Manufacturers only need to continuously improve their own NLP platforms to allow each platform to control almost all of their devices, so that the development costs required for the manufacturer to subsequently access new third-party service platforms are gradually reduced. At the same time, as the NLP platform continues to learn and evolve with more and more uses, and the number of smart devices controlled by the third-party service platform of this manufacturer is increasing, the accuracy of voice control is gradually improved.

[0095] In some optional embodiments, the voice control data is in text form or voice form, and the natural language processing of the voice control data includes: converting the voice control data in text form or voice form into text data of a target language, and performing natural language processing on the text data of the target language.

[0096] In this embodiment, the target language is the language that the natural language processing system processes by default. By first converting the voice control data into text data of the target language, it can be ensured that the natural language processing system can process the language more accurately and efficiently. This helps the system to more accurately understand the user's intentions and needs, thereby improving the accuracy and efficiency of voice control.

[0097] For example, a user issues a control command in English to control an electric fan produced in China. The preferred recognition language of the natural language processing platform of the Chinese manufacturer is Chinese. Therefore, the English voice control data needs to be converted into Chinese (the target language) and then input into the natural language recognition platform for recognition.

[0098] In some embodiments, the voice control data is in voice form, and the second server needs to convert the voice control data in voice form into text data in the target language and then input it into the natural language processing platform. In other embodiments, the voice control data is in text form, that is, it has been converted in advance by the first server. The language of the voice control data in text form can be the same as the target language or different from the target language. Finally, when input into the natural language processing platform, the voice control data needs to be converted into text data in the target language.

[0099] In some optional embodiments, the first server converts the speech control data in the form of speech into text data in the target language, and then sends the text data in the target language to the second server. After receiving the text data in the target language, the second server directly inputs it into the natural language processing platform.

[0100] In some optional embodiments, the converting of the voice control data in text or voice form into text data in the target language includes: using the target translation software to convert the voice control data into text data in the target language by calling an application programming interface of the target translation software. The process of calling the application programming interface of the target translation software can be executed by the first server or by the second server, depending on actual needs, and is not limited here.

[0101] In this embodiment, the target translation software is usually trained with a large amount of data and optimized with algorithms, and can provide high-quality translation services. By calling the application programming interface of these software, the accuracy and timeliness of the translation can be ensured. Developers do not need to develop translation functions from scratch, but can directly call the target translation software, thereby reducing development time and development costs.

[0102] For example, you can call the Google Translate API to convert voice control data into text data in the target language. The complete voice control method is as follows:

[0103] Taking Google Speaker and Gree Air Conditioner as examples, Google Speaker receives the user's voice (voice control data), and uploads it to Google Cloud (first server) after recognition. Google Cloud then sends the "voice text" (converting the voice control data into text form) to Gree Cloud (second server). The "voice text" at this time is in English. After Gree Cloud receives the "voice text" in English, it calls the API interface of Google Translate to convert the English "voice text" into Chinese, and then sends the voice control data in Chinese to the natural language processing platform. The natural language processing platform generates device instructions based on the voice control data in Chinese, and sends the device instructions to Gree Air Conditioner, and finally completes the device control.

[0104] Embodiment three:

[0105] Another embodiment of the present application relates to a first server, which is located on a third-party service platform. The implementation details of the first server of this embodiment are described in detail below. The following content is only for the convenience of understanding the implementation details, and is not necessary for the implementation of this solution. The schematic diagram of the first server of this embodiment can be as follows: Figure 4 As shown, it includes a voice receiving module 410, a voice parsing module 420 and a data forwarding module 430.

[0106] The voice receiving module 410 is used to receive the voice control data collected by the voice device in the third-party service platform;

[0107] The voice analysis module 420 is used to analyze the voice control data and determine the target service platform to which the target device to be controlled by the voice control data belongs;

[0108] The data forwarding module 430 is used to forward the voice control data to the second server in the target service platform, so that the second server controls the target device based on the device instructions obtained after natural language processing of the voice control data.

[0109] It is worth mentioning that all modules involved in this embodiment are logic modules. In practical applications, a logic unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. In addition, in order to highlight the innovative part of this application, this embodiment does not introduce units that are not closely related to solving the technical problems proposed by this application, but this does not mean that there are no other units in this embodiment.

[0110] Embodiment 4:

[0111] Another embodiment of the present application relates to a second server, which is located on the target service platform. The implementation details of the second server of this embodiment are described in detail below. The following content is only for the convenience of understanding the implementation details, and is not necessary for the implementation of this solution. The schematic diagram of the first server of this embodiment can be as follows Figure 5 As shown, it includes a control data receiving module 510, a natural language processing module 520 and a device instruction issuing module 530.

[0112] A control data receiving module 510 is used to receive voice control data sent by a first server in a third-party service platform, wherein the voice control data is collected by a voice device in the third-party service platform and uploaded to the first server;

[0113] A natural language processing module 520, configured to perform natural language processing on the voice control data to obtain a target device to be voice-controlled and a device instruction to control the target device;

[0114] The device instruction sending module 530 is used to send the device instruction to the target device to control the target device.

[0115] It is worth mentioning that all modules involved in this embodiment are logic modules. In practical applications, a logic unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. In addition, in order to highlight the innovative part of this application, this embodiment does not introduce units that are not closely related to solving the technical problems proposed by this application, but this does not mean that there are no other units in this embodiment.

[0116] Embodiment five:

[0117] like Figure 6 As shown, another embodiment of the present application relates to a voice control system, including: a first server 610 and a second server 620,

[0118] The first server 610 is located in the third-party service platform and is used to receive voice control data collected by a voice device in the third-party service platform; parse the voice control data to determine the target service platform to which the target device to be controlled by the voice control data belongs; and forward the voice control data to the second server in the target service platform;

[0119] The second server 620 is located on the target service platform and is used to receive the voice control data sent by the first server, perform natural language processing on the voice control data, obtain the target device to be voice controlled, and the device command to control the target device; send the device command to the target device to control the target device.

[0120] The first server includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the voice control method in the above-mentioned embodiment one.

[0121] The second server includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the voice control method in the above-mentioned embodiment 2.

[0122] Among them, the memory and the processor are connected in a bus manner, and the bus may include any number of interconnected buses and bridges, and the bus connects various circuits of one or more processors and memories together. The bus can also connect various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface between the bus and the transceiver. The transceiver can be one element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices on a transmission medium. The data processed by the processor is transmitted on a wireless medium via an antenna, and further, the antenna also receives data and transmits the data to the processor.

[0123] The processor is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. Memory can be used to store data used by the processor when performing operations.

[0124] Embodiment six:

[0125] Another embodiment of the present application relates to a computer-readable storage medium storing a computer program, which implements the above method embodiment when executed by a processor.

[0126] That is, those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium, including a number of instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as: ROM), random access memory (Random Access Memory, referred to as: RAM), disk or optical disk and other media that can store program codes.

[0127] Those skilled in the art will appreciate that the above embodiments are specific embodiments for implementing the present application, and in actual applications, various changes may be made thereto in form and detail without departing from the spirit and scope of the present application.

Claims

1. A voice control method, characterized in that: The first server applied to the third-party service platform includes: Receiving voice control data collected by the voice device in the third-party service platform; Parsing the voice control data to determine a target service platform to which a target device to be controlled by the voice control data belongs; The voice control data is forwarded to a second server in the target service platform, so that the second server controls the target device based on the device instructions obtained after natural language processing of the voice control data.

2. The voice control method according to claim 1, characterized in that: The forwarding of the voice control data to the second server in the target service platform includes: The voice control data is forwarded to the second server in the target service platform in text form or voice form.

3. The voice control method according to claim 2, characterized in that: Forwarding the voice control data in text form to a second server in the target service platform includes: The voice control data is converted into text data in a target language, and the text data in the target language is forwarded to a second server in the target service platform.

4. A voice control method, characterized in that: The second server applied to the target service platform includes: Receiving voice control data sent by a first server in a third-party service platform, wherein the voice control data is collected by a voice device in the third-party service platform and uploaded to the first server; Performing natural language processing on the voice control data to obtain a target device to be voice-controlled and a device instruction to control the target device; The device instruction is sent to the target device to control the target device.

5. The voice control method according to claim 4, characterized in that: The voice control data is in text form or voice form, and the performing natural language processing on the voice control data includes: The voice control data in text form or voice form is converted into text data in a target language, and natural language processing is performed on the text data in the target language.

6. The voice control method according to claim 5, characterized in that: The step of converting the voice control data in text or voice form into text data in a target language includes: The target translation software is used to convert the voice control data into text data in the target language by calling the application programming interface of the target translation software.

7. A first server, characterized in that: The first server is located on a third-party service platform and includes: A voice receiving module, used to receive voice control data collected by the voice device in the third-party service platform; A voice analysis module, used to analyze the voice control data and determine the target service platform to which the target device to be controlled by the voice control data belongs; A data forwarding module is used to forward the voice control data to a second server in the target service platform, so that the second server controls the target device based on the device instructions obtained after natural language processing of the voice control data.

8. A second server, characterized in that: The second server is located on the target service platform and includes: A control data receiving module, used to receive voice control data sent by a first server in a third-party service platform, wherein the voice control data is collected by a voice device in the third-party service platform and uploaded to the first server; A natural language processing module, used to perform natural language processing on the voice control data to obtain a target device to be voice-controlled and a device instruction to control the target device; The device instruction sending module is used to send the device instruction to the target device to control the target device.

9. A voice control system, characterized in that: include: a first server and a second server, The first server is located on the third-party service platform and is used to receive voice control data collected by the voice device in the third-party service platform; Parsing the voice control data to determine a target service platform to which a target device to be controlled by the voice control data belongs; forwarding the voice control data to the second server in the target service platform; The second server is located on the target service platform and is used to receive the voice control data sent by the first server, perform natural language processing on the voice control data, obtain the target device to be voice controlled, and the device instructions to control the target device; and send the device instructions to the target device to control the target device.

10. An electronic device, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the voice control method as described in any one of claims 1-6.

11. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the voice control method according to any one of claims 1 to 6 is implemented.

Images