Speech processing method and system based on multiple devices

Abstract

The present invention relates to the field of speech processing technology, and discloses a speech processing method and system based on multiple devices, the method comprising: obtaining speech command information, and extracting corresponding pulse code modulation data from the speech command information; obtaining device identifications of multiple pre-associated smart devices, and obtaining the operating status information of each smart device according to the device identifications; performing speech recognition processing on the pulse modulation data through a cloud server according to the operating status information to obtain a speech recognition result; and selecting a target smart device from multiple smart devices to respond to the speech recognition result according to the speech recognition result. By performing speech recognition processing on the speech command information according to the operating status information of multiple smart devices in combination with a cloud server, and then selecting the corresponding target smart device to respond according to the speech recognition result, the smart device and the cloud can work together, and the response speed of online speech processing and the user's speech interaction experience can be improved.

Description

Technical Field

[0001] The present invention relates to the field of speech processing technology, and in particular to a speech processing method and system based on multiple devices. Background Art

[0002] The intelligence of Internet of Things (IoT) devices requires the support of many technologies, among which online voice processing technology, as an interface for human-computer dialogue, plays a pivotal role. However, the existing technologies mostly recognize voice command information locally through intelligent devices, then generate corresponding control instructions based on the recognized text, and then perform corresponding operations based on the control instructions to respond to the voice command information. Due to the limited local storage space, the locally stored voice recognition database cannot recognize various types of voice command information like cloud analysis, resulting in poor accuracy and response speed of voice interaction, slowing down the voice processing speed and affecting the user's voice interaction experience. Therefore, how to improve the response speed of online voice processing to improve the user's voice interaction experience has become a problem that needs to be solved urgently.

[0003] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of the present invention is to provide a multi-device based voice processing method and system, aiming to solve the technical problem of how to improve the response speed of online voice processing to improve the user's voice interaction experience.

[0005] To achieve the above object, the present invention provides a multi-device based voice processing method, the method comprising the following steps:

[0006] Acquire voice command information, and extract corresponding pulse code modulation data from the voice command information;

[0007] Obtaining device identifications of a plurality of pre-associated smart devices, and obtaining operating status information of each smart device according to the device identifications;

[0008] According to the operation status information, the pulse modulation data is processed by a cloud server for speech recognition to obtain a speech recognition result;

[0009] A target smart device is selected from the multiple smart devices according to the voice recognition result to respond to the voice recognition result.

[0010] Preferably, the step of performing speech recognition processing on the pulse modulation data through a cloud server according to the operating status information to obtain a speech recognition result specifically includes:

[0011] Determining whether the operating status information meets the working status condition;

[0012] When the running status information does not meet the working status condition, the pulse modulation data is uploaded to the cloud server, so that the cloud server performs speech recognition processing on the pulse modulation data to obtain a speech recognition result.

[0013] Preferably, the operation status information includes processor occupancy rate and / or processor idle rate;

[0014] Accordingly, the step of determining whether the operating status information meets the working status condition specifically includes:

[0015] Extracting the processor occupancy rate from the operation status information;

[0016] Detecting whether the processor occupancy rate is greater than a preset occupancy rate, and judging whether the operation status information meets the working status condition according to the detection result;

[0017] and / or;

[0018] Extracting the processor idle rate from the operating status information;

[0019] Detect whether the processor idle rate is less than a preset idle rate, and determine whether the operating state information meets the working state condition according to the detection result.

[0020] Preferably, when the running status information does not meet the working status condition, uploading the pulse modulation data to a cloud server so that the cloud server performs speech recognition processing on the pulse modulation data to obtain a speech recognition result specifically includes:

[0021] When the operating status information does not meet the working status conditions, the pulse modulation data is uploaded to the cloud server so that the cloud server obtains the corresponding cloud space feature value, and when it is detected that the cloud space feature value meets the preset storage conditions, the pulse modulation data is processed for speech recognition to obtain a speech recognition result.

[0022] Preferably, the step of selecting a target smart device from the plurality of smart devices to respond to the speech recognition result according to the speech recognition result specifically includes:

[0023] Selecting a corresponding target smart device from the multiple smart devices according to the speech recognition result;

[0024] The speech recognition result is stored in the memory of the target smart device, so that the target smart device responds to the speech recognition result.

[0025] In addition, to achieve the above-mentioned purpose, the present invention also proposes a multi-device based speech processing system, characterized in that the system comprises:

[0026] A data acquisition module, used to acquire voice command information and extract corresponding pulse code modulation data from the voice command information;

[0027] A status acquisition module, used to acquire device identifications of a plurality of pre-associated smart devices, and acquire operating status information of each smart device according to the device identifications;

[0028] A speech recognition module, used to perform speech recognition processing on the pulse modulation data through a cloud server according to the operation status information to obtain a speech recognition result;

[0029] The voice response module is used to select a target smart device from the multiple smart devices according to the voice recognition result to respond to the voice recognition result.

[0030] Preferably, the speech recognition module is further used to determine whether the operation status information meets the working status condition;

[0031] The speech recognition module is also used to upload the pulse modulation data to the cloud server when the operating status information does not meet the working status condition, so that the cloud server performs speech recognition processing on the pulse modulation data to obtain a speech recognition result.

[0032] Preferably, the operation status information includes processor occupancy rate and / or processor idle rate;

[0033] The speech recognition module is further used to extract the processor occupancy rate from the operation status information;

[0034] The speech recognition module is further used to detect whether the processor occupancy rate is greater than a preset occupancy rate, and determine whether the operating state information meets the working state condition according to the detection result;

[0035] The speech recognition module is further used to extract the processor idle rate from the running status information;

[0036] The speech recognition module is further used to detect whether the processor idle rate is less than a preset idle rate, and determine whether the operating status information meets the working status condition based on the detection result.

[0037] Preferably, the speech recognition module is also used to upload the pulse modulation data to the cloud server when the operating status information does not meet the working status conditions, so that the cloud server obtains the corresponding cloud space feature value, and when it is detected that the cloud space feature value meets the preset storage conditions, perform speech recognition processing on the pulse modulation data to obtain a speech recognition result.

[0038] Preferably, the voice response module is further used to select a corresponding target smart device from the multiple smart devices according to the voice recognition result;

[0039] The voice response module is also used to store the voice recognition result in the memory of the target smart device, so that the target smart device responds to the voice recognition result.

[0040] In the present invention, voice command information is obtained, and corresponding pulse code modulation data is extracted from the voice command information, device identifiers of multiple pre-associated smart devices are obtained, and the running status information of each smart device is obtained according to the device identifier, and the pulse modulation data is subjected to voice recognition processing through a cloud server according to the running status information to obtain a voice recognition result, and a target smart device is selected from the multiple smart devices according to the voice recognition result to respond to the voice recognition result. Different from the prior art, in which the voice command information is locally recognized by the smart device, and then the corresponding control instruction is generated based on the recognized text, and then the corresponding operation is performed based on the control instruction to respond to the voice command information, which leads to poor accuracy and response speed of voice interaction, slows down the voice processing speed, and also affects the user's voice interaction experience, the present invention obtains the pulse code modulation data corresponding to the voice command information and the running status information of multiple pre-associated smart devices, and then performs voice recognition processing on the pulse modulation data through a cloud server according to the running status information to obtain a voice recognition result, and then selects the corresponding target smart device from the multiple smart devices according to the voice recognition result to respond to the voice recognition result, so as to realize the collaborative work of the smart device and the cloud, improve the response speed of online voice processing, and further improve the user's voice interaction experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a flowchart of a first embodiment of a multi-device based voice processing method of the present invention;

[0042] Figure 2 It is a schematic diagram of the structure of an intelligent device in a hardware operating environment involved in an embodiment of the present invention;

[0043] Figure 3 It is a flowchart of a second embodiment of the multi-device voice processing method of the present invention;

[0044] Figure 4 It is a structural block diagram of the first embodiment of the multi-device based speech processing system of the present invention.

[0045] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0046] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0047] The embodiment of the present invention provides a multi-device based voice processing method, referring to Figure 1 , Figure 1 It is a flowchart of the first embodiment of the multi-device based voice processing method of the present invention.

[0048] In this embodiment, the multi-device based voice processing method includes the following steps:

[0049] Step S10: Acquire voice command information, and extract corresponding pulse code modulation data from the voice command information;

[0050] It is easy to understand that the execution subject of this embodiment is the intelligent control terminal, which can be understood as an interactive medium between a user and multiple intelligent devices. Figure 2 , Figure 2 FIG. 1 is a schematic diagram of the structure of an intelligent device in a hardware operating environment according to an embodiment of the present invention. Figure 2 As shown, the smart device may include: a processor 1001, such as a central processing unit (CPU), a microcontroller unit (MCU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen, an input unit such as a keyboard, and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (WIreless-FIdelity, WI-FI) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) memory, or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0051] Those skilled in the art will understand that Figure 2 The structure shown in the figure does not constitute a limitation on the smart device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0052] like Figure 2 As shown, the memory 1005 as a storage medium may include an operating system, a data storage module, a network communication module, a user interface module, and a multi-device based voice processing program.

[0053] exist Figure 2 In the smart device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the smart device of the present invention can be set in the smart device or in the smart control terminal. When the processor 1001 and the memory 1005 are set in the smart device, the smart control terminal calls the multi-device based voice processing program stored in the memory 1005 through the processor 1001 in the smart device, and executes the multi-device based voice processing method provided by the embodiment of the present invention; when the processor 1001 and the memory 1005 are set in the smart control terminal, the smart control terminal directly calls the multi-device based voice processing program stored in the memory 1005 through the processor 1001, and executes the multi-device based voice processing method provided by the embodiment of the present invention.

[0054] It should be noted that when the intelligent control terminal obtains voice command information, it can extract corresponding pulse code modulation (Pulse Code Modulation, PCM) data from the voice command information. The voice command information can be voice command information issued by the user, or it can be voice command information generated by an input unit (such as a keyboard). In a specific implementation, the voice command information can be first converted into a time-continuous, continuous-value analog signal, and then the analog signal can be converted into a time-discrete, discrete-value digital signal, and then transmitted in the channel. It can be understood that the analog signal corresponding to the voice command information is first sampled, and then the sample value amplitude corresponding to the analog signal is quantized and encoded to obtain pulse code modulation data, and then the pulse code modulation data is saved in the memory 00, and the memory 00 is used to store the pulse code modulation data.

[0055] Step S20: obtaining device identifications of a plurality of pre-associated smart devices, and obtaining operating status information of each smart device according to the device identifications;

[0056] It is easy to understand that when the intelligent control terminal obtains the pulse code modulation data corresponding to the voice command information, it can also obtain the device identification of multiple pre-associated running intelligent devices, and then control the intelligent device to start the status detection function to obtain its own operating status information. The device identification can be used to indicate the type of device, such as a television, a humidifier, an air conditioner, etc. The operating status information can be used to indicate the status of the processor (such as a micro control unit) of the intelligent device, including but not limited to the processor occupancy rate and the processor idle rate.

[0057] In a specific implementation, when controlling the smart device to start the status detection function, the corresponding interface identifier can be set to 1, and the identification result can be saved in the memory 01. The smart control end then accesses the memory 01 to obtain the identification result of 1, and obtains the device identifiers of multiple smart devices, which are saved in the memory 11, the memory 22, the memory 33..., respectively, and sets the corresponding interface identifier to 1, and then saves the identification result in the memory 02. The smart control end accesses the memory 02 to obtain the identification result of 1, and accesses the memory storing the device identifier, obtains the device identifier in the memory storing the device identifier, and queries the corresponding smart device's operating status information according to the device identifier.

[0058] Step S30: performing speech recognition processing on the pulse modulation data through the cloud server according to the operation status information to obtain a speech recognition result;

[0059] It is easy to understand that after obtaining the operating status information of the smart device, in order to improve the user's voice interaction experience, the pulse modulation data can be uploaded to the cloud server, and the cloud server can be controlled to perform voice recognition processing on the pulse modulation data according to the operating status information to obtain the voice recognition result. The voice recognition result includes but is not limited to voiceprint features, speech speed, frequency, duration, emotion and other sound-related feature information, as well as text information obtained through semantic recognition in voice recognition processing. Text information can be understood as feature information related to text, including but not limited to text length, specific characters, difficulty of semantic analysis, etc.

[0060] In a specific implementation, in order to improve the response speed of online voice processing, only semantic recognition in voice recognition processing may be performed on pulse modulation data to obtain a voice recognition result containing only text information, and then a target smart device is selected from multiple smart devices based on the text information, and the text information is stored in the memory of the target smart device, so that the target smart device responds to the voice recognition result.

[0061] Step S40: selecting a target smart device from the plurality of smart devices according to the voice recognition result to respond to the voice recognition result.

[0062] It should be noted that after obtaining the voice recognition result, the device identifier (such as the device name) can be extracted from the text information in the voice recognition result, and then the corresponding target smart device can be selected from multiple smart devices based on the device identifier, and the voice recognition result can be stored in the memory of the target smart device so that the target smart device can respond to the voice recognition result.

[0063] In the specific implementation, in order to improve the user's voice interaction experience, feature information such as voiceprint features can also be extracted from the voice recognition results to determine the initiator of the voice command information, and then the corresponding device preference settings are obtained according to the identity of the initiator, and then the response results are further optimized according to the device preference settings. The device preferences are set to the initiator's usual settings for each smart device obtained from the preset command database according to the identity of the initiator. For example, if the target smart device is determined to be an air conditioner according to the voice recognition results, and the initiator's usual setting for the air conditioner is 26°C, then when the voice command information received from the initiator is "turn on the air conditioner", the air conditioner will be started according to the identity of the initiator and the opening temperature of the air conditioner will be set to 26°C.

[0064] It should be understood that the above is only an example and does not constitute any limitation on the technical solution of the present invention. In specific applications, technicians in this field can make settings as needed, and the present invention does not limit this.

[0065] In this embodiment, voice command information is obtained, and corresponding pulse code modulation data is extracted from the voice command information, device identifiers of multiple pre-associated smart devices are obtained, and the running state information of each smart device is obtained according to the device identifier, and voice recognition processing is performed on the pulse modulation data through a cloud server according to the running state information to obtain a voice recognition result, and a target smart device is selected from the multiple smart devices according to the voice recognition result to respond to the voice recognition result. Different from the prior art, in which the voice command information is locally recognized by the smart device, and then the corresponding control instruction is generated based on the recognized text, and then the corresponding operation is performed based on the control instruction to respond to the voice command information, which leads to poor accuracy and response speed of voice interaction, slows down the voice processing speed, and also affects the user's voice interaction experience, this embodiment obtains the pulse code modulation data corresponding to the voice command information and the running state information of multiple pre-associated smart devices, and then voice recognition processing is performed on the pulse modulation data through a cloud server according to the running state information to obtain a voice recognition result, and then the corresponding target smart device is selected from the multiple smart devices according to the voice recognition result to respond to the voice recognition result, so as to realize the collaborative work of the smart device and the cloud, improve the response speed of online voice processing, and further improve the user's voice interaction experience.

[0066] refer to Figure 3 , Figure 3 It is a flowchart of the second embodiment of the multi-device based voice processing method of the present invention.

[0067] Based on the above first embodiment, in this embodiment, step S30 includes:

[0068] Step S301: determining whether the operation status information meets the working status condition;

[0069] It should be noted that the operating status information can be used to indicate the status of the processor (such as a microcontroller unit) of the smart device, including but not limited to the processor occupancy rate and the processor idle rate. In a specific implementation, the processor occupancy rate can be extracted from the operating status information, and then the operating status information is judged to meet the working status conditions based on whether the processor occupancy rate is greater than the preset occupancy rate. The preset occupancy rate can be set according to actual needs, such as 80%, which is not limited in this embodiment. And / or; extract the processor idle rate from the operating status information, and judge whether the operating status information meets the working status conditions based on whether the processor idle rate is less than the preset idle rate. The preset idle rate can be set according to actual needs, such as 10%, which is not limited in this embodiment.

[0070] In a specific implementation, when querying the operation status information of a smart device (such as a TV), if the processor occupancy rate of the TV is greater than 80%, and / or the processor idle rate is less than 10% (i.e., the processor corresponding to the TV is in a busy state), the corresponding interface identifier is set to 1, and the identification result is saved in the memory 02; otherwise, the corresponding interface identifier is set to 2, and the identification result is saved in the memory 03. The smart control terminal accesses the memory 03, obtains the identification result 2, and then accesses the memory 00 to obtain the PCM data, controls the TV to upload the PCM data to the cloud server, sets the corresponding interface identifier 1, and saves the identification result in the memory 04.

[0071] In another implementation, when querying the operation status information of a smart device (such as a humidifier), if the processor occupancy rate of the humidifier is greater than 80%, and / or the processor idle rate is less than 10% (i.e., the processor corresponding to the humidifier is in a busy state), the corresponding interface identifier is set to 1, and the identification result is saved in the memory 05, otherwise, the corresponding interface identifier is set to 2, and the identification result is saved in the memory 05. The smart control terminal accesses the memory 05, obtains the identification result 2, and then accesses the memory 00 to obtain the PCM data, controls the humidifier to upload the PCM data to the cloud server, sets the corresponding interface identifier 1, and saves the identification result in the memory 06.

[0072] In another implementation, when querying the operation status information of a smart device (such as an air conditioner), if the processor occupancy rate of the air conditioner is greater than 80%, and / or the processor idle rate is less than 10% (i.e., the processor corresponding to the air conditioner is in a busy state), the corresponding interface identifier is set to 1, and the identification result is saved in the memory 07; otherwise, the corresponding interface identifier is set to 2, and the identification result is saved in the memory 07. The smart control terminal accesses the memory 07, obtains the identification result 2, and then accesses the memory 00 to obtain the PCM data, controls the air conditioner to upload the PCM data to the cloud server, sets the corresponding interface identifier 1, and saves the identification result in the memory 08.

[0073] Repeat the above operation to traverse other smart devices, obtain the running status information of each smart device, and use it to determine whether the running status information of each smart device meets the working status condition.

[0074] Step S302: when the running status information does not meet the working status condition, uploading the pulse modulation data to the cloud server, so that the cloud server performs speech recognition processing on the pulse modulation data to obtain a speech recognition result.

[0075] It is easy to understand that when the running state information does not meet the working state condition (such as the processor occupancy rate is less than or equal to 80%, and the processor idle rate is greater than or equal to 10%, that is, the processor is not in a busy state), the pulse modulation data can be uploaded to the cloud server so that the cloud server can obtain the corresponding cloud space feature value, and when it is detected that the cloud space feature value meets the preset storage condition, the pulse modulation data is processed for voice recognition to obtain a voice recognition result, and the corresponding target smart device is selected from the multiple smart devices according to the voice recognition result to respond to the voice recognition result. The cloud space feature value can be understood as a feature value indicating the usage of the storage space corresponding to each smart device in the cloud server, including but not limited to the cloud space occupancy rate and the cloud space idle rate. Accordingly, the preset storage condition can be set to determine whether the cloud space idle rate is greater than the preset cloud idle rate, and the preset cloud idle rate can be set according to actual needs, such as 60%, which is not limited in this embodiment; or, determine whether the cloud space occupancy rate is less than the preset cloud occupancy rate, and the preset cloud occupancy rate can be set according to actual needs, such as 40%, which is not limited in this embodiment.

[0076] In a specific implementation, when processing the operating status information of a smart device (such as a television), the smart control terminal accesses the memory 04, obtains an identification result of 1, controls the cloud server to obtain the PCM data corresponding to the television, so that the cloud server obtains the cloud space characteristic value corresponding to the television, such as the cloud space idle rate. If the cloud space idle rate corresponding to the television is greater than 60%, the cloud server is controlled to perform semantic recognition on the PCM data corresponding to the television, and save the obtained text information to the memory 44, so that the television executes the corresponding operation to respond to the text information; if the cloud space idle rate corresponding to the television is less than 40%, the corresponding interface identifier is set to 1, and the identification result is saved in the memory 08.

[0077] In another implementation, when processing the operating status information of a smart device (such as a humidifier), the smart control end accesses the memory 06, obtains an identification result of 1, controls the cloud server to obtain the PCM data corresponding to the humidifier, so that the cloud server obtains the cloud space characteristic value corresponding to the humidifier, such as the cloud space idle rate. If the cloud space idle rate corresponding to the humidifier is greater than 60%, control the cloud server to perform semantic recognition on the PCM data corresponding to the humidifier, and save the obtained text information to the memory 55, so that the humidifier performs the corresponding operation to respond to the text information; if the cloud space idle rate corresponding to the humidifier is less than 40%, set the corresponding interface identifier to 1, and save the identification result to the memory 09.

[0078] In another implementation, when processing the operating status information of a smart device (such as an air conditioner), the smart control terminal accesses the memory 08, obtains an identification result of 1, controls the cloud server to obtain the PCM data corresponding to the air conditioner, so that the cloud server obtains the cloud space characteristic value corresponding to the air conditioner, such as the cloud space idle rate. If the cloud space idle rate corresponding to the air conditioner is greater than 60%, control the cloud server to perform semantic recognition on the PCM data corresponding to the air conditioner, and save the obtained text information to the memory 66, so that the humidifier performs the corresponding operation to respond to the text information; if the cloud space idle rate corresponding to the humidifier is less than 40%, set the corresponding interface identifier to 1, and save the identification result to the memory 10.

[0079] Based on the above implementation, the intelligent control terminal accesses the memory 44, the memory 55 or the memory 66 to obtain the voice recognition result. Furthermore, the above operation can be repeated to traverse other intelligent devices to obtain the voice recognition results of each intelligent device.

[0080] It should be understood that the above is only an example and does not constitute any limitation on the technical solution of the present invention. In specific applications, technicians in this field can make settings as needed, and the present invention does not limit this.

[0081] In this embodiment, it is determined whether the running status information meets the working status conditions. When the running status information does not meet the working status conditions, the pulse modulation data is uploaded to the cloud server so that the cloud server performs speech recognition processing on the pulse modulation data to obtain a speech recognition result. Different from the prior art that only performs speech recognition processing through a locally stored speech recognition database, this embodiment controls the cloud server to perform speech recognition processing on the pulse modulation data of each smart device according to the running status information of each smart device, such as the processor occupancy rate and the processor idle rate, so as to improve the speech recognition efficiency and the accuracy of speech recognition, and further, improve the response speed of online speech processing and the user's speech interaction experience.

[0082] Reference Figure 4 , Figure 4 It is a structural block diagram of the first embodiment of the multi-device based speech processing system of the present invention.

[0083] like Figure 4 As shown, the multi-device based speech processing system proposed in the embodiment of the present invention includes:

[0084] The data acquisition module 10 is used to acquire voice command information and extract corresponding pulse code modulation data from the voice command information;

[0085] The status acquisition module 20 is used to acquire the device identifications of the plurality of pre-associated smart devices, and acquire the operation status information of each smart device according to the device identifications;

[0086] A speech recognition module 30, configured to perform speech recognition processing on the pulse modulation data through a cloud server according to the operation status information to obtain a speech recognition result;

[0087] The voice response module 40 is used to select a target smart device from the multiple smart devices according to the voice recognition result to respond to the voice recognition result.

[0088] In this embodiment, voice command information is obtained, and corresponding pulse code modulation data is extracted from the voice command information, device identifiers of multiple pre-associated smart devices are obtained, and the running state information of each smart device is obtained according to the device identifier, and voice recognition processing is performed on the pulse modulation data through a cloud server according to the running state information to obtain a voice recognition result, and a target smart device is selected from the multiple smart devices according to the voice recognition result to respond to the voice recognition result. Different from the prior art, in which the voice command information is locally recognized by the smart device, and then the corresponding control instruction is generated based on the recognized text, and then the corresponding operation is performed based on the control instruction to respond to the voice command information, which leads to poor accuracy and response speed of voice interaction, slows down the voice processing speed, and also affects the user's voice interaction experience, this embodiment obtains the pulse code modulation data corresponding to the voice command information and the running state information of multiple pre-associated smart devices, and then voice recognition processing is performed on the pulse modulation data through a cloud server according to the running state information to obtain a voice recognition result, and then the corresponding target smart device is selected from the multiple smart devices according to the voice recognition result to respond to the voice recognition result, so as to realize the collaborative work of the smart device and the cloud, improve the response speed of online voice processing, and further improve the user's voice interaction experience.

[0089] Based on the above-mentioned first embodiment of the speech processing system based on multiple devices of the present invention, a second embodiment of the speech processing system based on multiple devices of the present invention is proposed.

[0090] In this embodiment, the speech recognition module 30 is also used to determine whether the operation status information meets the working status condition;

[0091] The speech recognition module 30 is further configured to upload the pulse modulation data to a cloud server when the operating status information does not meet the working status condition, so that the cloud server performs speech recognition processing on the pulse modulation data to obtain a speech recognition result.

[0092] The operation status information includes processor occupancy rate and / or processor idle rate;

[0093] The speech recognition module 30 is further used to extract the processor occupancy rate from the operation status information;

[0094] The speech recognition module 30 is further used to detect whether the processor occupancy rate is greater than a preset occupancy rate, and determine whether the operating state information meets the working state condition according to the detection result;

[0095] The speech recognition module 30 is further used to extract the processor idle rate from the operation status information;

[0096] The speech recognition module 30 is further used to detect whether the processor idle rate is less than a preset idle rate, and determine whether the operating state information meets the working state condition according to the detection result.

[0097] The speech recognition module 30 is also used to upload the pulse modulation data to the cloud server when the operating status information does not meet the working status conditions, so that the cloud server obtains the corresponding cloud space feature value, and when it is detected that the cloud space feature value meets the preset storage conditions, perform speech recognition processing on the pulse modulation data to obtain a speech recognition result.

[0098] The voice response module 40 is further configured to select a corresponding target smart device from the multiple smart devices according to the voice recognition result;

[0099] The voice response module 40 is further used to store the voice recognition result in the memory of the target smart device, so that the target smart device responds to the voice recognition result.

[0100] Other embodiments or specific implementations of the multi-device speech processing system of the present invention may refer to the above-mentioned method embodiments and will not be described in detail here.

[0101] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0102] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0103] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory / random access memory, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0104] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A multi-device based voice processing method, characterized in that: The method comprises the following steps: Acquire voice command information, and extract corresponding pulse modulation data from the voice command information; Obtaining device identifications of a plurality of pre-associated smart devices, and obtaining operating status information of each smart device according to the device identifications; According to the operation status information, the pulse modulation data is processed by a cloud server for speech recognition to obtain a speech recognition result; Selecting a target smart device from the plurality of smart devices according to the speech recognition result to respond to the speech recognition result; The step of performing speech recognition processing on the pulse modulation data through the cloud server according to the operating status information to obtain a speech recognition result specifically includes: Determining whether each of the operation status information meets the working state condition, the operation status information including the processor occupancy rate and / or the processor idle rate; When each of the operating status information does not meet the working status condition, the pulse modulation data is uploaded to the cloud server, so that the cloud server performs speech recognition processing on the pulse modulation data to obtain a speech recognition result.

2. The method according to claim 1, characterized in that The step of judging whether each of the operation status information meets the working status condition specifically includes: Extracting the processor occupancy rate from each of the operation status information; Detecting whether the processor occupancy rate is greater than a preset occupancy rate, and judging whether the operation status information meets the working status condition according to the detection result; and / or; Extracting the processor idle rate from each of the operation status information; Detect whether the processor idle rate is less than a preset idle rate, and determine whether the operating state information meets the working state condition according to the detection result.

3. The method according to claim 1, characterized in that When each of the operating status information does not meet the working status condition, the pulse modulation data is uploaded to the cloud server so that the cloud server performs speech recognition processing on the pulse modulation data to obtain the speech recognition result, specifically including: When each of the operating status information does not meet the working status condition, the pulse modulation data is uploaded to the cloud server so that the cloud server obtains the corresponding cloud space feature value, and when it is detected that the cloud space feature value meets the preset storage condition, the pulse modulation data is processed by voice recognition to obtain a voice recognition result; The cloud space characteristic value is a characteristic value representing the usage of the storage space corresponding to each smart device in the cloud server, including but not limited to the cloud space occupancy rate and the cloud space idle rate.

4. The method according to claim 1, characterized in that The step of selecting a target smart device from the multiple smart devices to respond to the speech recognition result according to the speech recognition result specifically includes: Selecting a corresponding target smart device from the multiple smart devices according to the speech recognition result; The speech recognition result is stored in the memory of the target smart device, so that the target smart device responds to the speech recognition result.

5. A multi-device based speech processing system, characterized in that: The system comprises: A data acquisition module, used to acquire voice command information and extract corresponding pulse modulation data from the voice command information; A status acquisition module, used to acquire device identifications of a plurality of pre-associated smart devices, and acquire operating status information of each smart device according to the device identifications; A speech recognition module, used to perform speech recognition processing on the pulse modulation data through a cloud server according to the operation status information to obtain a speech recognition result; A voice response module, configured to select a target smart device from the plurality of smart devices according to the voice recognition result to respond to the voice recognition result; The speech recognition module is further used for: Determining whether each of the operation status information meets the working state condition, the operation status information including the processor occupancy rate and / or the processor idle rate; When each of the operating status information does not meet the working status condition, the pulse modulation data is uploaded to the cloud server, so that the cloud server performs speech recognition processing on the pulse modulation data to obtain a speech recognition result.

6. The system according to claim 5, characterized in that The speech recognition module is further used to extract the processor occupancy rate from each of the operation status information; The speech recognition module is further used to detect whether the processor occupancy rate is greater than a preset occupancy rate, and determine whether the operating state information meets the working state condition according to the detection result; The speech recognition module is further used to extract the processor idle rate from each of the operation status information; The speech recognition module is further used to detect whether the processor idle rate is less than a preset idle rate, and determine whether the operating status information meets the working status condition based on the detection result.

7. The system according to claim 5, characterized in that The speech recognition module is further configured to upload the pulse modulation data to the cloud server when each of the operating status information does not meet the working status condition, so that the cloud server obtains the corresponding cloud space feature value, and when it is detected that the cloud space feature value meets the preset storage condition, perform speech recognition processing on the pulse modulation data to obtain a speech recognition result; The cloud space characteristic value is a characteristic value representing the usage of the storage space corresponding to each smart device in the cloud server, including but not limited to the cloud space occupancy rate and the cloud space idle rate.

8. The system according to claim 5, characterized in that The voice response module is further used to select a corresponding target smart device from the multiple smart devices according to the voice recognition result; The voice response module is also used to store the voice recognition result in the memory of the target smart device, so that the target smart device responds to the voice recognition result.

Images