Instruction receiving method, system, electronic device, cloud server and storage medium

Abstract

The embodiment of the present application relates to the field of artificial intelligence technology, and discloses a method, system, electronic device, cloud server and storage medium for receiving instructions, the method comprising: picking up the voice information of the user; performing voice recognition on the voice information to generate a first voice recognition result; obtaining a second voice recognition result generated by a second device; wherein the second device is a device with a sound pickup function and a voice recognition function, and the second voice recognition result is generated by the second device performing voice recognition on the voice information of the user picked up by the second device; based on the first voice recognition result, the second voice recognition result and the preset voice recognition credibility of each device, an instruction is generated for execution by the first device. The instruction receiving method provided in the embodiment of the present application can break through the limitation of the sound pickup range, accurately, completely and quickly receive the voice instructions issued by the user, thereby improving the user experience.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of artificial intelligence technology, and in particular to a command receiving method, system, electronic device, cloud server and storage medium. Background Art

[0002] With the rapid development of artificial intelligence technology, more and more smart devices are entering people's lives, such as smart home robots of various types and functions. Smart home robots are special robots that provide services to users. They are mainly engaged in household services, maintenance, repair, transportation, guardianship and children's education. Smart home robots have flexible multi-joint arms and rely on various sensors to not only understand users' voice commands, but also recognize three-dimensional objects. These smart home robots perform different tasks in different locations in the user's home and can receive voice commands from users in real time.

[0003] However, the inventors of the present application have discovered that the robot's sound pickup range is limited, and when the user and the robot are in different rooms, it is difficult for the robot to accurately obtain the voice commands issued by the user. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a command receiving method, system, electronic device, cloud server and storage medium, which can break through the limitations of the pickup range and accurately, completely and quickly receive the voice commands issued by the user, thereby improving the user experience.

[0005] To solve the above technical problems, an embodiment of the present application provides a method for receiving instructions, comprising the following steps: picking up the user's voice information; performing voice recognition on the voice information to generate a first voice recognition result; obtaining a second voice recognition result generated by a second device; wherein the second device is a device with a sound pickup function and a voice recognition function, and the second voice recognition result is generated by the second device performing voice recognition on the user's voice information picked up by the second device; and generating instructions based on the first voice recognition result, the second voice recognition result and the preset voice recognition credibility of each device for execution by the first device.

[0006] An embodiment of the present application also provides an instruction receiving system, including: a first device and a second device, the second device being a device having a sound pickup function and a voice recognition function; the first device is used to obtain the user's voice information, perform voice recognition on the voice information, and generate a first voice recognition result; the second device is used to pick up the user's voice information, perform voice recognition on the voice information, and generate a second voice recognition result; the first device is also used to obtain the second voice recognition result, generate instructions according to the first voice recognition result, the second voice recognition result and the preset voice recognition credibility of each device, and execute the instructions.

[0007] An 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 instruction receiving method.

[0008] An embodiment of the present application also provides a cloud server, 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 instruction receiving method.

[0009] An embodiment of the present application further provides a computer-readable storage medium storing a computer program, wherein the computer program implements the above-mentioned instruction receiving method when executed by a processor.

[0010] The command receiving method, system, electronic device, cloud server and storage medium provided by the embodiments of the present application, the first device picks up the user's voice information, performs voice recognition on the acquired voice information, generates a first voice recognition result, and then obtains the second voice recognition result generated by the second device, the second device is a device with a sound pickup function and a voice recognition function, the second device performs voice recognition on the voice information picked up by the second device itself to generate a second voice recognition result, the first device then generates a command based on the first voice recognition result, the second voice recognition result and the preset voice recognition credibility of each device, for the first device itself to execute the generated command, considering that the device has a limited sound pickup range, when the user When the second device and the first device are in a different room, it is difficult for the first device to accurately obtain the voice command issued by the user. However, in the embodiment of the present application, when receiving the command, the first device not only relies on the recognition result obtained by the first device itself picking up the user's voice information for voice recognition, but can also obtain the recognition result obtained by the second device picking up the user's voice information, that is, multiple devices in the home are combined to jointly obtain the voice command issued by the user, which can break through the limitation of the pickup range. When generating the command, the voice recognition credibility of each device is also combined to ensure that the generated command is credible and in line with the user's intention, thereby accurately, completely and quickly receiving the voice command issued by the user, thereby improving the user experience.

[0011] In addition, the generating of instructions according to the first speech recognition result, the second speech recognition result and the preset speech recognition credibility of the device includes: performing word segmentation on the first speech recognition result to obtain a plurality of first word segmentation segments; performing word segmentation on a plurality of second speech recognition results to obtain a plurality of second word segmentation segments; determining the speech recognition credibility of a plurality of first word segmentation segments and the speech recognition credibility of a plurality of second word segmentation segments according to the preset speech recognition credibility of each device; generating instructions according to the speech recognition credibility of a plurality of first word segmentation segments, a plurality of first word segmentation segments, a plurality of second word segmentation segments and a plurality of second word segmentation segments. In the process of generating instructions, the first device may perform word segmentation processing on the first speech recognition result and the second speech recognition result respectively to obtain a plurality of first word segmentation segments and a plurality of second word segmentation segments, and then determine the speech recognition credibility of each word segmentation segment in combination with the preset speech recognition credibility of the device, so as to generate instructions according to each word segmentation segment and the speech recognition credibility of each word segmentation segment, so as to further improve the accuracy of the acquired instructions, thereby further improving the user experience.

[0012] In addition, before generating the instruction according to the first voice recognition result, the second voice recognition result and the preset voice recognition credibility of each device, the method includes: obtaining the position of the user, the position of the first device and the positions of several second devices; determining the relative position between the first device and the user according to the position of the user and the position of the first device; determining the relative position between several second devices and the user according to the position of the user and the positions of several second devices; generating the instruction according to the first voice recognition result, the second voice recognition result and the preset voice recognition credibility of each device includes: generating the instruction according to the first voice recognition result, the second voice recognition result, the relative position between the first device and the user, the relative position between several second devices and the user and the preset voice recognition credibility of each device. Considering that in real life, the second devices are also distributed in various positions in the home and the sound pickup range of the second devices is also limited, the first device of this embodiment also comprehensively considers the relative position between the first device and the user, and the relative position between each second device and the user when receiving the instruction, so as to achieve that when the first device is very close to the user, there is no need to refer to the voice recognition result of the second device, and when a second device is very close to the user, the voice recognition result of the second device is mainly referred to.

[0013] In addition, the voice recognition credibility of each preset device includes the voice recognition credibility of the first device and the voice recognition credibility of the second device. The voice recognition credibility of the second device is obtained by the first device through the following steps: conducting several conversations with the second device through voice to obtain the voice recognition results of the several conversations by the second device; comparing the voice recognition results of the several conversations by the second device with the text content of the several conversations to determine the voice recognition credibility of the second device. The voice recognition credibility of the second device is obtained in advance by the first device through several conversations. The obtained voice recognition credibility of the second device is scientific, authentic and reliable, thereby further improving the accuracy of the acquired instructions.

[0014] In addition, the first device comprehensively considers the voice recognition accuracy of each device for dialects, the voice recognition credibility of each device for different languages, the voice recognition credibility of each device for different volume levels, the voice recognition credibility of each device in different noise levels, and the voice recognition credibility of each device for users with different identity information when generating instructions, which can further improve the accuracy of the acquired instructions.

[0015] In addition, before generating instructions according to the first voice recognition result, the second voice recognition result and the preset voice recognition credibility of each device, it includes: obtaining the voice information of the user picked up by the third device; wherein the third device is a device with a sound pickup function but not a voice recognition function; performing voice recognition on the voice information of the user picked up by the third device to generate a third voice recognition result; generating instructions according to the first voice recognition result, the second voice recognition result and the preset voice recognition credibility of each device includes: generating instructions according to the first voice recognition result, the second voice recognition result, the third voice recognition result and the preset voice recognition credibility of each device, the third device is a device with a sound pickup function but not a voice recognition function, in this embodiment, the first device can also refer to the voice information of the user picked up by the third device to further improve the sound pickup range, so that the first device can obtain more accurate and complete voice instructions.

[0016] In addition, after the instruction is generated, the method also includes: directly making a voice reply to the instruction; or, making a voice reply to the instruction through the second device. The first device can choose its own voice to reply to the user's instruction, or it can reply to the user's instruction through any second device, which can better meet the user's actual needs and further enhance the user's experience.

[0017] In addition, obtaining the second voice recognition result generated by the second device includes: obtaining filtering information; wherein the filtering information includes any combination of the following: the identity information of the user, the location information of the user and the location information of each second device; determining the target second device based on the filtering information and a preset correspondence; wherein the correspondence is the correspondence between the filtering information and the target second device; obtaining the second voice recognition result generated by the target second device, determining the target second device among the second devices based on one or more of the identity information of the user, the location information of the user and the location information of each second device, and only obtaining the second voice recognition result generated by the target second device, that is, only taking the target second device into consideration when receiving instructions, which can effectively improve the efficiency of instruction reception. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] 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.

[0019] Figure 1 This is a flow chart of a command receiving method according to an embodiment of the present application. Figure 1 ;

[0020] Figure 2is a schematic diagram of distribution of users, first devices and second devices in a home provided in one embodiment of the present application;

[0021] Figure 3 According to an embodiment of the present application, a flowchart of generating instructions according to a first voice recognition result, a second voice recognition result and a preset voice recognition credibility of a device;

[0022] Figure 4 This is a flow chart of a command receiving method according to another embodiment of the present application. Figure 2 ;

[0023] Figure 5 is a flow chart of obtaining the voice recognition credibility of a second device according to an embodiment of the present application;

[0024] Figure 6 This is a flow chart of a command receiving method according to another embodiment of the present application. Figure 3 ;

[0025] Figure 7 is a flowchart of obtaining a second speech recognition result generated by a second device according to an embodiment of the present application;

[0026] Figure 8 is a schematic diagram of an instruction receiving system according to another embodiment of the present application;

[0027] Fig. 9 is a schematic structural diagram of an electronic device according to another embodiment of the present application;

[0028] Fig.10 It is a structural diagram of a cloud server according to another embodiment of the present application. DETAILED DESCRIPTION

[0029] 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.

[0030] An embodiment of the present application relates to an instruction receiving method, which is applied to a first device. The implementation details of the instruction receiving method of this embodiment are specifically described below. The following content is only the implementation details provided for the convenience of understanding and is not necessary for implementing this solution.

[0031] The specific process of the instruction receiving method of this embodiment can be as follows Figure 1 As shown, including:

[0032] Step 101, picking up the user's voice information.

[0033] Step 102: Perform speech recognition on the speech information to generate a first speech recognition result.

[0034] Specifically, the first device is a device that can receive voice commands issued by users, understand voice commands issued by users, and execute voice commands issued by users, such as smart home robots, smart speakers, smart refrigerators, smart washing machines, and smart air conditioners.

[0035] In a specific implementation, the first device has a sound pickup function and a voice recognition function. The first device can be a real-time monitoring environment for voice information. When a preset wake-up word is recognized, the user's voice information can be picked up, and voice recognition is performed on the picked-up user's voice information to generate a first voice recognition result, wherein the preset wake-up word is used to wake up the first device, that is, to instruct the first device to pick up sound. The preset keywords can be set by technicians in this field according to actual needs, and the embodiments of the present application do not specifically limit this.

[0036] In one example, the first device is a smart home robot, and the preset wake-up word is "Xiao A Xiao A". When the first device recognizes "Xiao A Xiao A" in the voice information in the environment, it immediately starts to pick up the user's voice information, and performs voice recognition on the picked up voice information to obtain a first voice recognition result.

[0037] Step 103: Obtain a second speech recognition result generated by the second device.

[0038] Specifically, after the first device picks up the user's voice information, performs voice recognition on the picked up user's voice information, and generates a first voice recognition result, it can obtain a second voice recognition result generated by the second device, wherein the second device is a device with both sound pickup and voice recognition functions, and the second voice recognition result is generated by the second device performing voice recognition on the user's voice information picked up by the second device.

[0039] In a specific implementation, the second device may also monitor the voice information in the environment in real time, pick up the user's voice information, and perform voice recognition on the picked up user's voice information to generate a second voice recognition result.

[0040] In one example, the second device is a device with sound pickup function and voice recognition function, such as a smart speaker, a home background music system or a smart TV.

[0041] In one example, the first device and the second device can be converted into each other. For example, there are multiple smart home robots in the user's home, including robot A and robot B. The preset wake-up word of robot A is "Little A Little A", and the preset wake-up word of robot B is "Little B Little B". Robot A and robot B can both monitor the voice information in the environment in real time. If robot A recognizes the preset wake-up word "Little A Little A", robot A is the first device and robot B can be the second device; if robot B recognizes the preset wake-up word "Little B Little B", robot B is the first device and robot A can be the second device.

[0042] In one example, the first device and the second device can be wirelessly connected through any one or any combination of the following methods: Wifi connection, IEEE.802.bgn connection, 2.4GHz connection, smart gateway connection, Bluetooth Mesh gateway connection, Zigbee protocol gateway connection, multi-mode network connection, smart socket connection, smart wireless switch connection, etc.

[0043] In one example, there are multiple second devices, and the distribution diagram of users, first devices, and second devices in a home can be as follows: Figure 2 As shown, wireless connections are established between the first device and the second device A, the second device B, the second device C, and the second device D.

[0044] Step 104, generating an instruction for execution by the first device according to the first voice recognition result, the second voice recognition result and the preset voice recognition credibility of each device.

[0045] In a specific implementation, after obtaining the first voice recognition result and the second voice recognition result, the first device can generate instructions for execution by the first device based on the first voice recognition result, the second voice recognition result and the preset voice recognition credibility of each device, wherein the preset voice recognition credibility of each device can be set by a technician in this field according to actual needs.

[0046] In an example, there are several second devices and several second recognition results. The preset voice recognition credibility of each device can characterize the voice recognition capability and voice recognition quality of each device. The voice recognition capability and voice recognition quality of a device are usually proportional to the performance of the device. The higher the performance of the device, the higher the voice recognition capability and voice recognition quality of the device, and the higher the voice recognition credibility of the device, then the more reliable the voice recognition result of the device. The server can select the most reliable voice recognition result from the first voice recognition result and several second voice recognition results, and use the voice recognition result as an instruction for the first device to execute.

[0047] In one example, the preset voice recognition credibility of each device may be the voice recognition credibility set by the user, including the voice recognition credibility of each device actively input by the user in the background, and also including the voice recognition credibility of the device set by the user inadvertently, for example: the user says to a second device: "Where is the nearby flower shop?", and the second device replies: "Sorry, I didn't hear it clearly", and the user then says to the second device: "Why are you so bad", indicating that the user does not trust the second device, and the first device automatically sets the voice recognition credibility of the second device to a low value.

[0048] In this embodiment, compared with the technical solution of only picking up the voice command issued by the user according to the first device and executing the picked up voice command, the first device picks up the user's voice information, performs voice recognition on the acquired voice information, generates a first voice recognition result, and then obtains the second voice recognition result generated by the second device. The second device is a device with a sound pickup function and a voice recognition function. The second device performs voice recognition on the voice information picked up by the second device itself to generate a second voice recognition result. The first device then generates an instruction based on the first voice recognition result, the second voice recognition result and the preset voice recognition credibility of each device, for the first device to execute the generated instruction itself. Considering that the sound pickup range of the device is When the user and the first device are in different rooms, it is difficult for the first device to accurately obtain the voice command issued by the user. In the embodiments of the present application, when receiving the command, the first device not only relies on the first device itself to pick up the user's voice information for voice recognition to obtain the recognition result, but can also obtain the recognition result obtained by the second device picking up the user's voice information, that is, multiple devices in the home are combined to jointly obtain the voice command issued by the user, which can break through the limitation of the pickup range. When generating the command, the voice recognition credibility of each device is also combined to ensure that the generated command is credible and in line with the user's intention, thereby accurately, completely and quickly receiving the voice command issued by the user, thereby improving the user's experience.

[0049] In one embodiment, there are multiple second devices and multiple second voice recognition results.

[0050] In one embodiment, there are multiple second devices and multiple second voice recognition results. The first device generates an instruction based on the first voice recognition result, the second voice recognition result and the voice recognition credibility of the preset device, which can be performed as follows: Figure 3 The steps shown are implemented, specifically including:

[0051] Step 201 : segment the first speech recognition result to obtain a plurality of first segmented word segments.

[0052] Step 202: Segment the plurality of second speech recognition results to obtain a plurality of second segmented word segments.

[0053] In a specific implementation, after the first device generates a first voice recognition result and obtains several second voice recognition results, it can segment the first voice recognition result according to a preset word segmentation dictionary to obtain several first word segmentation fragments, and segment the several second voice recognition results to obtain several second word segmentation fragments, wherein the preset word segmentation dictionary can be set by a technician in this field according to actual needs, and the embodiments of the present application do not specifically limit this.

[0054] In an example, the first voice recognition result is "agree to bank flyers". The first device segments the first voice recognition result according to a preset word segmentation dictionary to obtain three first word segmentation fragments of "agree", "bank", and "flyers". The second voice recognition result J is "print bank flyers", the second voice recognition result K is "print bank flyers", the second voice recognition result L is "print English-Chinese sheets", the second voice recognition result M is "print implied sheets", and the second voice recognition result N is "print bank flyers". The first device segments the second voice recognition result J, the second voice recognition result K, the second voice recognition result L, the second voice recognition result M, and the second voice recognition result N according to a preset word segmentation dictionary to obtain five second word segmentation fragments of "print", "bank", "English-Chinese", "implicit", "flyers" and "sheets".

[0055] Step 203: Determine the speech recognition credibility of a plurality of first word segmentation segments and the speech recognition credibility of a plurality of second word segmentation segments according to the preset speech recognition credibility of each device.

[0056] In a specific implementation, after obtaining several first word segmentation segments and several second word segmentation segments, the first device can determine the speech recognition credibility of several first word segmentation segments and the speech recognition credibility of several second word segmentation segments according to the preset speech recognition credibility of each device.

[0057] In an example, the speech recognition credibility of the first device is 0.9, the speech recognition credibility of the second device J is 0.6, the speech recognition credibility of the second device K is 0.6, the speech recognition credibility of the second device L is 0.3, the speech recognition credibility of the second device M is 0.8, and the speech recognition credibility of the second device N is 0.4. The server determines the speech recognition credibility of each word segmentation segment according to the speech recognition credibility of each device as follows: The speech recognition credibility of "答应" (promise) is: 0.9; The speech recognition credibility of "打印" (print) is: 0.6 + 0.6 + 0.3 + 0.8 + 0.4 = 3.1; The speech recognition credibility of "银行" (bank) is: 0.9 + 0.6 + 0.6 + 0.4 = 2.5; The speech recognition credibility of "英汉" (English-Chinese) is: 0.3; The speech recognition credibility of "隐含" (implied) is: 0.8; The speech recognition credibility of "传单" (leaflet) is: 0.9 + 0.6 + 0.6 + 0.4 = 2.5; The speech recognition credibility of "床单" (sheet) is: 0.3 + 0.8 = 1.1.

[0058] Step 204: Generate an instruction according to a plurality of first word segmentation segments, the speech recognition credibility of the plurality of first word segmentation segments, a plurality of second word segmentation segments, and the speech recognition credibility of the plurality of second word segmentation segments.

[0059] In a specific implementation, after the first device determines the speech recognition credibility of a plurality of first word segmentation segments and the speech recognition credibility of a plurality of second word segmentation segments, it may generate an instruction according to the plurality of first word segmentation segments, the speech recognition credibility of the plurality of first word segmentation segments, the plurality of second word segmentation segments, and the speech recognition credibility of the plurality of second word segmentation segments.

[0060] In an example, the first device determines that the speech recognition credibility of "答应" (promise) is 0.9, the speech recognition credibility of "打印" (print) is 3.1, the speech recognition credibility of "银行" (bank) is 2.5, the speech recognition credibility of "英汉" (English-Chinese) is 0.3, the speech recognition credibility of "隐含" (implied) is 0.8, the speech recognition credibility of "传单" (leaflet) is 2.5, and the speech recognition credibility of "床单" (sheet) is 1.1. The first device may form a sentence according to the word segmentation segment with the highest speech recognition credibility, that is, form the sentence "打印银行传单" (print bank leaflet) according to "打印" (print), "银行" (bank), and "传单" (leaflet). This sentence is a credible sentence, and the first device takes "打印银行传单" (print bank leaflet) as an instruction.

[0061] In this embodiment, the generating of instructions according to the first speech recognition result, the second speech recognition result and the preset speech recognition credibility of the device includes: performing word segmentation on the first speech recognition result to obtain a plurality of first word segmentation segments; performing word segmentation on a plurality of second speech recognition results to obtain a plurality of second word segmentation segments; determining the speech recognition credibility of a plurality of first word segmentation segments and the speech recognition credibility of a plurality of second word segmentation segments according to the preset speech recognition credibility of each device; generating instructions according to the speech recognition credibility of a plurality of first word segmentation segments, a plurality of first word segmentation segments, a plurality of second word segmentation segments and a plurality of second word segmentation segments. In the process of generating instructions, the first device may perform word segmentation processing on the first speech recognition result and the second speech recognition result respectively to obtain a plurality of first word segmentation segments and a plurality of second word segmentation segments, and then determine the speech recognition credibility of each word segmentation segment in combination with the preset speech recognition credibility of the device, so as to generate instructions according to each word segmentation segment and the speech recognition credibility of each word segmentation segment, so as to further improve the accuracy of the acquired instructions, thereby further improving the user experience.

[0062] Another embodiment of the present application relates to a method for receiving instructions. In this embodiment, there are multiple second devices and multiple second voice recognition results. The implementation details of the method for receiving instructions in 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 implementing this solution. The specific process of the method for receiving instructions in this embodiment can be as follows: Figure 4 As shown, including:

[0063] Step 301, picking up the user's voice information.

[0064] Step 302: Perform speech recognition on the speech information to generate a first speech recognition result.

[0065] Step 303: Obtain a second speech recognition result generated by the second device.

[0066] Among them, steps 301 to 303 are substantially the same as steps 101 to 103 and are not described again here.

[0067] Step 304: Acquire the user's location, the first device's location, and the locations of several second devices.

[0068] Step 305: Determine the relative position between the first device and the user according to the position of the user and the position of the first device.

[0069] Step 306: Determine relative positions between the plurality of second devices and the user according to the position of the user and the positions of the plurality of second devices.

[0070] In a specific implementation, the first device can obtain the user's position, the position of the first device and the positions of several second devices. After obtaining the user's position, the position of the first device and the positions of several second devices, the first device can determine the relative position between the first device and the user based on the user's position and the position of the first device, and determine the relative position between the several second devices and the user based on the user's position and the positions of the several second devices.

[0071] In an example, the first device can determine the user's location, the location of the first device and the locations of several second devices through its own camera, Bluetooth positioning light and other devices. The first device can also determine the user's location, the location of the first device and the locations of several second devices through the Global Positioning System (GPS), 3D semantic map and other functions.

[0072] In one example, the relative position between the device and the user may include, but is not limited to: the distance between the device and the user, the number of walls between the device and the user, the number of rooms between the device and the user, the number of floors between the device and the user, etc.

[0073] Step 307, generating an instruction according to the first voice recognition result, the second voice recognition result, the relative position between the first device and the user, the relative position between the plurality of second devices and the user, and the preset voice recognition credibility of each device.

[0074] In a specific implementation, after the first device determines the relative position between the first device and the user, and the relative position between several second devices and the user, it can generate instructions based on the first voice recognition result, the second voice recognition result, the relative position between the first device and the user, the relative positions between several second devices and the user, and the preset voice recognition credibility of each device.

[0075] In one example, the first device assigns weights to a first voice recognition result and several second voice recognition results based on the distance between each device and the user. The first device considers that the voice recognition results of the device closer to the user are more credible, and the voice recognition results of the device farther from the user are less credible.

[0076] In one example, the first device assigns weights to a first voice recognition result and several second voice recognition results according to the number of walls between each device and the user. The first device considers that the voice recognition results of the device with fewer walls between it and the user are more credible, and the voice recognition results of the device with more walls between it and the user are less credible.

[0077] In this embodiment, before generating an instruction according to the first voice recognition result, the second voice recognition result and the preset voice recognition credibility of each device, the method includes: obtaining the position of the user, the position of the first device and the positions of several second devices; determining the relative position between the first device and the user according to the position of the user and the position of the first device; determining the relative position between several second devices and the user according to the position of the user and the positions of several second devices; generating an instruction according to the first voice recognition result, the second voice recognition result and the preset voice recognition credibility of each device includes: generating an instruction according to the first voice recognition result, the second voice recognition result, the relative position between the first device and the user, the relative position between several second devices and the user and the preset voice recognition credibility of each device. Considering that in real life, the second devices are also distributed in various positions in the home and the sound pickup range of the second devices is also limited, the first device of this embodiment also comprehensively considers the relative position between the first device and the user, and the relative position between each second device and the user when receiving the instruction, so as to achieve that when the first device is very close to the user, there is no need to refer to the voice recognition result of the second device, and when a second device is very close to the user, the voice recognition result of the second device is mainly referred to.

[0078] In one embodiment, the preset voice recognition credibility of each device includes the voice recognition credibility of the first device and the voice recognition credibility of the second device, and the voice recognition credibility of the second device is determined by the first device through Figure 5 The steps of obtaining specifically include:

[0079] Step 401, conduct several conversations with a second device through voice, and obtain voice recognition results of the second device for the several conversations.

[0080] Step 402, compare the speech recognition results of the second device for several conversations with the text content of the several conversations to determine the credibility of the speech recognition of the second device.

[0081] Specifically, the first device can have several conversations with the second device through voice, obtain the voice recognition results of the second device for the several conversations, and compare the voice recognition results of the second device for the several conversations with the text content of the several conversations, so as to determine the credibility of the voice recognition of the second device.

[0082] In a specific implementation, the first device and the second device can be converted into each other, and any device in the home that can serve as the first device can have several conversations with other devices through voice to obtain the voice recognition credibility of other devices.

[0083] In one example, the first device is a robot. When a second device is added to the home, the robot can turn on the camera to determine the location of the newly added second device, move to the vicinity of the newly added second device, and have several conversations with the newly added second device to determine the voice recognition credibility of the newly added second device.

[0084] In one example, the first device may obtain the voice recognition credibility of the first device from the second device.

[0085] In this embodiment, the voice recognition credibility of each preset device includes the voice recognition credibility of the first device and the voice recognition credibility of the second device. The voice recognition credibility of the second device is obtained by the first device through the following steps: conducting several conversations with the second device through voice to obtain the voice recognition results of the several conversations by the second device; comparing the voice recognition results of the several conversations by the second device with the text content of the several conversations to determine the voice recognition credibility of the second device. The voice recognition credibility of the second device is obtained in advance by the first device through several conversations. The obtained voice recognition credibility of the second device is scientific, authentic and reliable, thereby further improving the accuracy of the acquired instructions.

[0086] In one embodiment, the voice recognition credibility of each device includes any combination of the following: the voice recognition credibility of each device for dialects, the voice recognition credibility of each device for different languages, the voice recognition credibility of each device for different volume levels, the voice recognition credibility of each device in different noise levels, and the voice recognition credibility of each device for users with different identity information. Considering that different users have different living habits, such as some users often use dialects, some users often use English, some users have relatively low voices, and some users have children at home, etc., and the actual environments in which the second devices are located are different, such as some second devices are located at windows close to the road, and some second devices are located in a quiet study, etc., the first device comprehensively considers the voice recognition credibility of these aspects when generating instructions, which can further improve the accuracy of the acquired instructions.

[0087] Another embodiment of the present application relates to a method for receiving an instruction. The implementation details of the instruction receiving method of this embodiment are specifically described below. The following content is only for the convenience of understanding the implementation details provided, and is not necessary for implementing this solution. The specific process of the instruction receiving method of this embodiment can be as follows: Figure 6 As shown, including:

[0088] Step 501, picking up the user's voice information.

[0089] Step 502: Perform speech recognition on the speech information to generate a first speech recognition result.

[0090] Step 503: Obtain a second speech recognition result generated by the second device.

[0091] Among them, steps 501 to 503 are substantially the same as steps 101 to 103 and are not described again here.

[0092] Step 504: Acquire the user's voice information picked up by the third device.

[0093] Step 505: Perform voice recognition on the user's voice information picked up by the third device to generate a third voice recognition result.

[0094] In a specific implementation, after generating the first voice recognition result and obtaining the second voice recognition result, the first device can also obtain the voice information of the user picked up by the third device, and perform voice recognition on the voice information of the user picked up by the third device to generate a third voice recognition result, wherein the third device is a device with a sound pickup function but not a voice recognition function. The first device can include the third device with a sound pickup function but not a voice recognition function into the reference range, which is equivalent to further expanding the sound pickup range of the first device.

[0095] In an example, the first device may also execute step 504 and step 505 first, and then execute step 503; or may execute step 502, step 503 and step 504 simultaneously.

[0096] Step 506: Generate an instruction based on the first voice recognition result, the second voice recognition result, the third voice recognition result, and the preset voice recognition credibility of each device.

[0097] In a specific implementation, after the first device generates the first voice recognition result, the third voice recognition result, and obtains the second voice recognition result, it can generate instructions based on the first voice recognition result, the second voice recognition result, the third voice recognition result and the preset voice recognition credibility of each device, so that the first device can obtain more accurate and complete voice instructions.

[0098] In this embodiment, before generating instructions according to the first voice recognition result, the second voice recognition result and the preset voice recognition credibility of each device, the method includes: obtaining the voice information of the user picked up by the third device; wherein the third device is a device with a sound pickup function but not a voice recognition function; performing voice recognition on the voice information of the user picked up by the third device to generate a third voice recognition result; generating instructions according to the first voice recognition result, the second voice recognition result and the preset voice recognition credibility of each device includes: generating instructions according to the first voice recognition result, the second voice recognition result, the third voice recognition result and the preset voice recognition credibility of each device, the third device is a device with a sound pickup function but not a voice recognition function, and in this embodiment, the first device can also refer to the voice information of the user picked up by the third device to further improve the sound pickup range, so that the first device can obtain more accurate and complete voice instructions.

[0099] In one embodiment, after generating an instruction, the first device can directly respond to the instruction by voice through the first device itself, or respond to the instruction by voice through the second device, thereby better meeting the actual needs of the user and further improving the user experience.

[0100] In one example, the first device may determine whether to make a voice reply to the instruction through the first device itself or choose to make a voice reply to the instruction through the second device closest to the user based on the relative positions between the first device and the user, and the relative positions between several second devices and the user.

[0101] In one example, the first device may respond to the command by voice through the first device itself, and may also respond to the command by voice through all the second devices.

[0102] In one embodiment, the first device obtains the second speech recognition result generated by the second device, which can be performed as follows: Figure 7 The steps shown are implemented, specifically including:

[0103] Step 601, obtaining filtering information, where the filtering information includes any combination of the following: user identity information, user location information, and location information of each second device.

[0104] Step 602: Determine the target second device according to the screening information and the preset corresponding relationship.

[0105] In a specific implementation, when generating a first voice recognition result, the first device can first obtain filtering information, where the filtering information includes one or more of the user's identity information, the user's location information, and the location information of each second device. After obtaining the filtering information, the first device can determine the target second device based on the filtering information and a preset correspondence. The preset correspondence includes the correspondence between the user's identity information and the target second device, the correspondence between the user's location information and the target second device, and the correspondence between the location information of each second device and the target second device, to determine the target second device, that is, the second device that the first device needs to consider.

[0106] In an example, the first device determines that the user's location information is a kitchen. The first device can determine that each second device in the kitchen is a target device based on the location information of the kitchen.

[0107] In one example, the first device determines that the identity information of the user is a child, and the first device may use the second device corresponding to the child among the second devices as the target second device.

[0108] Step 603: Obtain a second speech recognition result generated by the target second device.

[0109] In a specific implementation, the first device only obtains the second voice recognition result generated by the target second device, which can effectively improve the efficiency of command reception.

[0110] In this embodiment, the obtaining of the second voice recognition result generated by the second device includes: obtaining filtering information; wherein the filtering information includes any combination of the following: the identity information of the user, the location information of the user and the location information of each second device; determining the target second device according to the filtering information and a preset correspondence; wherein the correspondence is the correspondence between the filtering information and the target second device; obtaining the second voice recognition result generated by the target second device, determining the target second device among the second devices according to one or more of the identity information of the user, the location information of the user and the location information of each second device, and only obtaining the second voice recognition result generated by the target second device, that is, only taking the target second device into consideration when receiving the command, which can effectively improve the efficiency of command reception.

[0111] The step division of the above methods is only for the purpose of clear description. When implemented, they can be combined into one step or some steps can be split and decomposed into multiple steps. As long as they include the same logical relationship, they are all within the scope of protection of this patent; adding insignificant modifications to the algorithm or process or introducing insignificant designs without changing the core design of the algorithm and process are all within the scope of protection of this patent.

[0112] Another embodiment of the present application relates to an instruction receiving system. The details of the instruction receiving system of this embodiment are described in detail below. The following content is only for the convenience of understanding the implementation details provided, and is not necessary for implementing this example. Figure 8 701 is a schematic diagram of the instruction receiving system described in this embodiment, including: a first device 701 and a second device 702, wherein the second device 702 is a device with sound pickup function and voice recognition function.

[0113] The first device 701 is used to obtain voice information of the user, perform voice recognition on the voice information, and generate a first voice recognition result.

[0114] The second device 702 is used to pick up the user's voice information, perform voice recognition on the voice information, and generate a second voice recognition result.

[0115] The first device 701 is further used to obtain a second voice recognition result, generate an instruction according to the first voice recognition result, the second voice recognition result and the preset voice recognition credibility of each device, and execute the generated instruction.

[0116] It is not difficult to find that this embodiment is a system embodiment corresponding to the above method embodiment, and this embodiment can be implemented in conjunction with the above method embodiment. The relevant technical details and technical effects mentioned in the above embodiment are still valid in this embodiment, and in order to reduce repetition, they are not repeated here. Accordingly, the relevant technical details mentioned in this embodiment can also be applied in the above embodiment.

[0117] 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.

[0118] Another embodiment of the present application relates to an electronic device, such as Fig. 9 As shown, it includes: at least one processor 801; and a memory 802 that is communicatively connected to the at least one processor 801; wherein the memory 802 stores instructions that can be executed by the at least one processor 801, and the instructions are executed by the at least one processor 801 so that the at least one processor 801 can execute the instruction receiving method in the above-mentioned embodiments.

[0119] 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.

[0120] 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.

[0121] Another embodiment of the present application relates to a cloud server, such as Fig.10 As shown, it includes: at least one processor 901; and a memory 902 that is communicatively connected to the at least one processor 901; wherein the memory 902 stores instructions that can be executed by the at least one processor 901, and the instructions are executed by the at least one processor 901 so that the at least one processor 901 can execute the instruction receiving method in the above-mentioned embodiments.

[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] 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.

[0125] 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.

[0126] 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 command receiving method, applied to a first device, characterized in that: include: Pick up the user's voice information; Performing voice recognition on the voice information to generate a first voice recognition result; Obtaining a second voice recognition result generated by a second device; wherein the second device is a device having a sound pickup function and a voice recognition function, and the second voice recognition result is generated by the second device performing voice recognition on the voice information of the user picked up by the second device; Generate an instruction for execution by the first device according to the first speech recognition result, the second speech recognition result and the preset speech recognition credibility of each device; Among them, there are several second devices and several second speech recognition results; the generating of instructions according to the first speech recognition result, the second speech recognition result and the speech recognition credibility of the preset device includes: performing word segmentation on the first speech recognition result to obtain several first word segmentation fragments; performing word segmentation on several second speech recognition results to obtain several second word segmentation fragments; determining the speech recognition credibility of several first word segmentation fragments and the speech recognition credibility of several second word segmentation fragments according to the preset speech recognition credibility of each device; generating instructions according to several first word segmentation fragments, the speech recognition credibility of several first word segmentation fragments, several second word segmentation fragments and the speech recognition credibility of several second word segmentation fragments.

2. The instruction receiving method according to claim 1, characterized in that: Before generating an instruction according to the first speech recognition result, the second speech recognition result and the preset speech recognition credibility of each device, the method includes: Acquire the location of the user, the location of the first device, and the locations of a plurality of the second devices; Determining a relative position between the first device and the user according to the position of the user and the position of the first device; Determining relative positions between the plurality of second devices and the user according to the position of the user and the positions of the plurality of second devices; The generating an instruction according to the first speech recognition result, the second speech recognition result and the preset speech recognition credibility of each device includes: An instruction is generated according to the first voice recognition result, the second voice recognition result, the relative position between the first device and the user, the relative positions between a plurality of the second devices and the user, and the preset voice recognition credibility of each device.

3. The instruction receiving method according to claim 1, characterized in that: The preset voice recognition credibility of each device includes the voice recognition credibility of the first device and the voice recognition credibility of the second device, and the voice recognition credibility of the second device is obtained by the first device through the following steps: Conducting multiple conversations with the second device through voice, and obtaining voice recognition results of the multiple conversations by the second device; The speech recognition results of the second device for the plurality of conversations are compared with the text contents of the plurality of conversations to determine the credibility of the speech recognition of the second device.

4. The instruction receiving method according to claim 1 or 3, characterized in that: The voice recognition credibility of each device includes any combination of the following: the voice recognition credibility of each device for dialects, the voice recognition credibility of each device for different languages, the voice recognition credibility of each device for different volume levels, the voice recognition credibility of each device in different noise level environments, and the voice recognition credibility of each device for users with different identity information.

5. The instruction receiving method according to claim 1, characterized in that: Before generating an instruction according to the first speech recognition result, the second speech recognition result and the preset speech recognition credibility of each device, the method includes: Acquire the user's voice information picked up by a third device; wherein the third device is a device with a sound pickup function but without a voice recognition function; Performing voice recognition on the user's voice information picked up by the third device to generate a third voice recognition result; The generating an instruction according to the first speech recognition result, the second speech recognition result and the preset speech recognition credibility of each device includes: An instruction is generated according to the first voice recognition result, the second voice recognition result, the third voice recognition result and the preset voice recognition credibility of each device.

6. The instruction receiving method according to claim 1, characterized in that: After the generating instruction, the method further comprises: Directly respond to the command by voice; Alternatively, a voice reply is made to the instruction through the second device.

7. The instruction receiving method according to claim 1, characterized in that: The obtaining of the second speech recognition result generated by the second device includes: Acquire screening information; wherein the screening information includes any combination of the following: identity information of the user, location information of the user and location information of each second device; Determine the target second device according to the filtering information and a preset corresponding relationship; wherein the corresponding relationship is a corresponding relationship between the filtering information and the target second device; A second speech recognition result generated by the target second device is obtained.

8. A command receiving system, characterized in that: The device comprises a first device and a second device, wherein the second device is a device having a sound pickup function and a voice recognition function; The first device is used to obtain voice information of the user, perform voice recognition on the voice information, and generate a first voice recognition result; The second device is used to pick up the user's voice information, perform voice recognition on the voice information, and generate a second voice recognition result; wherein the second device is a plurality of devices, and the second voice recognition results are a plurality of results; The first device is also used to obtain the second speech recognition result, generate instructions according to the first speech recognition result, the second speech recognition result and the preset speech recognition credibility of each device, and execute the instructions; the generating instructions according to the first speech recognition result, the second speech recognition result and the preset speech recognition credibility of each device includes: performing word segmentation on the first speech recognition result to obtain a plurality of first word segmentation fragments; performing word segmentation on a plurality of second speech recognition results to obtain a plurality of second word segmentation fragments; determining the speech recognition credibility of a plurality of first word segmentation fragments and the speech recognition credibility of a plurality of second word segmentation fragments according to the preset speech recognition credibility of each device; generating instructions according to a plurality of first word segmentation fragments, a plurality of speech recognition credibility of the first word segmentation fragments, a plurality of second word segmentation fragments and a plurality of speech recognition credibility of the second word segmentation fragments.

9. 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 instruction receiving method according to any one of claims 1 to 7.

10. A cloud server, 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 instruction receiving method according to any one of claims 1 to 7.

11. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the instruction receiving method according to any one of claims 1 to 7 is implemented.

Images