Voice interaction method and device for smart device, and storage medium

Abstract

The present invention discloses a voice interaction method and device of a smart device, and a storage medium. Relating to the field of smart home technology, the voice interaction method of the smart device comprises: when a target voice is acquired, semantic recognition is performed on the target voice to obtain target semantics, wherein the target voice is an interactive voice emitted by a target object in a target environment; correction information associated with the target voice is acquired, wherein the correction information includes object information generated by the target object in the target environment and / or environmental information of the target environment; the target semantics is corrected using the correction information to obtain target interactive semantics; target interactive data matching the target interactive semantics is determined, and the target voice is replied using the target interactive data. The present invention solves the technical problem of low interactive satisfaction caused by failure to correctly understand interactive voice.

Description

Technical Field

[0001] The present invention relates to the field of smart homes, and in particular to a voice interaction method and device for smart devices, and a storage medium. Background Art

[0002] Currently, the use of smart homes in households is becoming more and more popular, and many smart devices have voice interaction functions.

[0003] When users interact with smart devices through voice, the language is relatively complex. If semantic analysis is performed only based on voice commands, the accurate semantics of the interactive voice cannot be correctly analyzed, and the correct reply voice cannot be determined, resulting in low interaction satisfaction.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present invention provide a voice interaction method and apparatus for an intelligent device, and a storage medium, so as to at least solve the technical problem of low interaction satisfaction caused by failure to correctly understand the interactive voice.

[0006] According to one aspect of an embodiment of the present invention, a voice interaction method for an intelligent device is provided, comprising: when a target voice is acquired, performing semantic recognition on the target voice to obtain target semantics, wherein the target voice is an interactive voice emitted by a target object in a target environment; acquiring correction information associated with the target voice, wherein the correction information includes object information generated by the target object in the target environment and / or environmental information of the target environment; correcting the target semantics using the correction information to obtain target interaction semantics; determining target interaction data matching the target interaction semantics, and using the target interaction data to reply to the target voice.

[0007] According to another aspect of an embodiment of the present invention, a voice interaction device of an intelligent device is also provided, including: a recognition unit, for performing semantic recognition on the target voice to obtain target semantics when a target voice is acquired, wherein the target voice is an interactive voice emitted by a target object in a target environment; an acquisition unit, for acquiring correction information associated with the target voice, wherein the correction information includes object information generated by the target object in the target environment and / or environmental information of the target environment; a correction unit, for correcting the target semantics using the correction information to obtain target interaction semantics; an interaction unit, for determining target interaction data matching the target interaction semantics, and replying to the target voice using the target interaction data.

[0008] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the voice interaction method of the above-mentioned smart device when running.

[0009] According to another aspect of an embodiment of the present invention, there is further provided an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the voice interaction method of the smart device through the computer program.

[0010] In an embodiment of the present invention, after acquiring a target speech emitted by a target object in a target environment, semantic recognition is performed on the target speech to obtain target semantics, and correction information associated with the target speech is obtained, wherein the correction information includes object information generated by the target object in the target environment and / or environmental information of the target environment, the target semantics is corrected using the correction information to obtain target interaction semantics, target interaction data matching the target interaction semantics is determined, and the target speech is replied using the target interaction data. After semantic recognition is performed on the target speech emitted by the target object, the target semantics is corrected based on the correction information associated with the target speech to obtain target interaction semantics, and target interaction data for replying to the target speech is determined based on the target interaction semantics, thereby achieving the purpose of correcting the semantics of the interactive speech to obtain more accurate target interaction semantics, thereby replying to the target speech based on the target interaction data determined by the target interaction semantics, thereby achieving the technical effect of obtaining more accurate interaction semantics through semantic correction based on the environmental information and object information associated with the interactive speech, thereby solving the technical problem of low interaction satisfaction caused by the inability to correctly understand the interactive speech. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0012] Figure 1 is a schematic diagram of an application environment of an optional voice interaction method for an intelligent device according to an embodiment of the present invention;

[0013] Figure 2 is a flow chart of an optional voice interaction method of an intelligent device according to an embodiment of the present invention;

[0014] Figure 3 is a flow chart of an optional voice interaction method of an intelligent device according to an embodiment of the present invention;

[0015] Figure 4is a flow chart of an optional voice interaction method of an intelligent device according to an embodiment of the present invention;

[0016] Figure 5 is a structural schematic diagram of an optional voice interaction device of an intelligent device according to an embodiment of the present invention;

[0017] Figure 6 It is a schematic diagram of the structure of an optional electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0019] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0020] According to one aspect of an embodiment of the present invention, a voice interaction method for an intelligent device is provided, and the voice interaction method for the intelligent device is widely used in smart home (Smart Home), smart home, smart home device ecology, smart residential (Intelligence House) ecology and other whole-house intelligent digital control application scenarios. Optionally, in this embodiment, the voice interaction method of the above-mentioned intelligent device can be applied to Figure 1 In the hardware environment composed of the terminal device 102 and the server 104 shown in FIG. Figure 1As shown, the server 104 is connected to the terminal device 102 via a network, and can be used to provide services (such as application services, etc.) for the terminal or a client installed on the terminal. A database can be set on the server or independently of the server to provide data storage services for the server 104. Cloud computing and / or edge computing services can be configured on the server or independently of the server to provide data computing services for the server 104.

[0021] The terminal device 102 is an intelligent terminal capable of acquiring and replying to interactive voices. The interactive voice is sent to the server 104 through the network, so that the interactive data for replying to the interactive voice is determined by the server 104, and the interactive data is interacted with the user through the terminal device 102. The server 104 determines the interactive data based on the interactive voice, which is not limited to being implemented by executing S102 to S108 in sequence. S102, obtain the target semantics. When the target voice is acquired, semantic recognition is performed on the target voice to obtain the target semantics, and the target voice is the interactive voice emitted by the target object in the target environment. S104, obtain correction information. Correction information associated with the target voice is acquired, and the correction information includes object information generated by the target object in the target environment and / or environmental information of the target environment. S106, obtain the target interactive semantics. Correct the target semantics using the correction information to obtain the target interactive semantics. S108, reply to the target voice using the target interactive data. Determine the target interactive data that matches the target interactive semantics, and reply to the target voice using the target interactive data.

[0022] The server may be a single server, or a server cluster consisting of multiple servers, or a cloud server. The network may include but is not limited to at least one of the following: a wired network, a wireless network. The wired network may include but is not limited to at least one of the following: a wide area network, a metropolitan area network, a local area network, and the wireless network may include but is not limited to at least one of the following: WIFI (Wireless Fidelity), Bluetooth. The terminal device 102 may be but is not limited to a PC, a mobile phone, a tablet computer, a smart air conditioner, a smart range hood, a smart refrigerator, a smart oven, a smart stove, a smart washing machine, a smart water heater, a smart washing device, a smart dishwasher, a smart projection device, a smart TV, a smart clothes drying rack, a smart curtain, a smart audio and video, a smart socket, a smart speaker, a smart speaker, a smart fresh air device, a smart kitchen and bathroom device, a smart bathroom device, a smart sweeping robot, a smart window cleaning robot, a smart mopping robot, a smart air purification device, a smart steamer, a smart microwave oven, a smart kitchen treasure, a smart purifier, a smart water dispenser, a smart door lock, etc. The above is only an example, and no limitation is made in this embodiment.

[0023] As an optional implementation, Figure 2As shown, the voice interaction method of the above-mentioned smart device includes:

[0024] S202, when the target speech is acquired, semantic recognition is performed on the target speech to obtain target semantics, wherein the target speech is the interactive speech uttered by the target object in the target environment;

[0025] S204, acquiring correction information associated with the target speech, wherein the correction information includes object information generated by the target object in the target environment and / or environmental information of the target environment;

[0026] S206, correcting the target semantics using the correction information to obtain the target interaction semantics;

[0027] S208, determining target interaction data that matches the target interaction semantics, and using the target interaction data to reply to the target voice.

[0028] The target speech is the interactive speech emitted by the target object collected by the terminal in the target environment. The interactive speech indicates that the target object and the terminal interact through speech to obtain interactive data. Correction information is information associated with the target speech and used to correct the target semantics. In the case where the target speech is emitted by the target object in the target environment, the correction information is the object information of the target object, or the environmental information of the target environment, or a combination of the two.

[0029] The object information of the target object is not limited to information related to the target object emitting the target voice, such as the expression information, posture information, intonation information, and voice information of the target object. The expression information and posture information of the target object are not limited to being obtained through images including the target object, and the intonation information and voice information of the target object are not limited to being obtained through audio including the target voice. The image including the target object and the audio including the target voice are not limited to being obtained through a video of the target object in the target environment, and can also be obtained based on images and audio. The environmental information of the target environment is not limited to being obtained through environmental images or environmental audio and environmental video including the target environment, and is not limited to including information such as the type of environment and the location of the environment.

[0030] Semantic recognition of the target speech is used to determine the target semantics of the target speech, and the interaction intention included in the target speech is determined based on the target semantics. Correcting the target semantics using correction information is not limited to further determining the interaction intention indicated by the target semantics, thereby obtaining more accurate target interaction semantics.

[0031] The target interaction data determined based on the target interaction semantics is data used to reply to the target speech, and is not limited to speech data and non-speech data. The form in which the target interaction data replies to the target speech is not displayed and is determined according to the interaction type of the target interaction data.

[0032] As an optional implementation, using target interaction data to reply to a target voice includes: when the interaction type of the target interaction data is voice interaction, converting the target interaction data into a target reply voice; and playing the target reply voice.

[0033] When the target interaction data indicates to reply the target voice with voice, it is not limited to converting the target interaction data into the target voice. For example, the target interaction data is converted into the target reply voice by using TTS technology, and the target voice is replied by playing the target reply voice.

[0034] As an optional implementation, using target interaction data to reply to a target voice includes: when the interaction type of the target interaction data is non-voice interaction, determining target display content corresponding to the target interaction data; and displaying the target display content.

[0035] When the target interaction data indicates that the target voice is to be answered with non-voice, it is not limited to determining the target display content indicated by the target interaction data for visual display, so as to answer the target voice by displaying the target display content. The specific form of the display content is not limited here, such as any form or combination of text, image, video, audio, web page, map, etc.

[0036] In an embodiment of the present application, when a target speech emitted by a target object in a target environment is acquired, semantic recognition is performed on the target speech to obtain target semantics, and correction information associated with the target speech is acquired, wherein the correction information includes object information generated by the target object in the target environment and / or environmental information of the target environment, the target semantics is corrected using the correction information to obtain target interaction semantics, target interaction data matching the target interaction semantics is determined, and the target speech is replied using the target interaction data. After semantic recognition is performed on the target speech emitted by the target object, the target semantics is corrected based on the correction information associated with the target speech to obtain target interaction semantics, and the target interaction data for replying to the target speech is determined based on the target interaction semantics, thereby achieving the purpose of correcting the semantics of the interactive speech to obtain more accurate target interaction semantics, thereby replying to the target speech based on the target interaction data determined by the target interaction semantics, thereby achieving the technical effect of obtaining more accurate interaction semantics through semantic correction based on the environmental information and object information associated with the interactive speech, thereby solving the technical problem of low interaction satisfaction caused by the inability to correctly understand the interactive speech.

[0037] As an optional implementation manner, obtaining correction information associated with the target speech includes at least one of the following:

[0038] Acquire environmental correction information indicated by a target environment image, wherein the target environment image is an environment image collected by a terminal device located in a target environment, and the environmental correction information is an environment type of the target environment determined based on the target environment image;

[0039] Acquire expression correction information of a target object indicated by the target object image, wherein the target object is an object that emits a target voice, and the expression correction information is expression information of the target object determined according to the target object image;

[0040] Acquire body posture correction information of a target object indicated by the target image, wherein the body posture correction information is body posture information of the target object determined according to the target object image;

[0041] Acquiring intonation correction information of the target speech indication, wherein the intonation correction information is used to determine the intonation information of the target speech indicated by the target object;

[0042] Acquire speech correction information indicated by the target speech, wherein the speech correction information is object sound information carried in the target speech.

[0043] The target environment image is not limited to images captured by any terminal device located in the target environment and having an image capture function, including images captured by a terminal device that captures target voices. Any images captured by a terminal device located in the target environment, including target environment information, can be used as the target environment image. The target environment image is used to determine the environment type of the target environment, such as determining whether the target environment is an indoor environment or an outdoor environment, determining whether the target environment is a home environment or a shopping mall environment, determining whether the target environment is a daytime environment or a nighttime environment, etc. Determining the environment type of the target environment based on the target environment image is not limited to determining the environment type corresponding to the current target environment from the candidate environment types based on the target environment image. The target semantics are further corrected based on the environment correction information to obtain the target interaction semantics.

[0044] The target object image is not limited to any image including the target object collected by any terminal device with image collection function located in the target environment, including the image including the target object collected by the terminal device collecting the target voice, and is used to indicate the behavior state of the target object when the target voice is uttered, and is not limited to including expression information and body posture information, so as to determine the expression correction information and / or body posture correction information of the target object based on the target object image. The expression correction information is used to indicate the facial expression of the target object when the target voice is uttered, and the body posture correction information is used to indicate the body posture information of the target object when the target voice is uttered, and is not limited to including gestures, postures, etc.

[0045] The intonation correction information is not limited to the intonation of the target object uttering the target speech, and the speech correction is not limited to the object sound information other than the target semantics in the target speech, such as coughing, wheezing, etc. The correction information is not limited to including any number of the above information and any number of combinations of the above correction information.

[0046] As an optional implementation, Figure 3 As shown, after obtaining the correction information associated with the target speech, the above also includes:

[0047] S302, determining the information confidence of the correction information;

[0048] S304: When the information confidence is greater than the confidence threshold, the target semantics is corrected using the correction information.

[0049] When correction information is obtained, the information confidence of the correction information is determined. When the number of correction information is greater than 1, the information confidence of each correction information is determined in turn. When the information confidence of the correction information is greater than the confidence threshold, the correction information is used to perform semantic correction on the target semantics. When the information confidence of the correction information is less than or equal to the information confidence, it is not limited to determining whether the correction information matches the target semantics. When the correction semantics indicated by the correction information is consistent with the target semantics, the correction information is used to correct the target semantics.

[0050] As an optional implementation, Figure 4 As shown, the information confidence level in determining the correction information includes:

[0051] S402, when the information confidence of the correction information is less than the confidence threshold and the target semantics are mutually exclusive, determining target reply data matching the correction information, wherein the target reply data is used to request to determine whether the correction information is correct;

[0052] S404, using the target reply data to reply to the target voice.

[0053] When the information confidence of the correction information is less than the confidence threshold and the target semantics are mutually exclusive, target reply data is obtained for determining whether the correction information is correct, thereby replying to the target voice through the target reply data, so as to further interact through the target reply data to determine the interaction intention of the target voice.

[0054] As an optional implementation, the above-mentioned use of correction information to correct the target semantics to obtain the target interaction semantics includes: when the target semantics indicates a query target route and the correction information includes environmental correction information, the target semantics are corrected using the target environment type indicated by the environmental correction information to obtain the target interaction semantics including the target environment type, wherein the target interaction semantics is used to indicate a query target route that matches the target environment type.

[0055] The starting point of the target route is not limited to the location of the terminal for collecting the target voice, and the end point is not limited to the target location. The environmental correction information is not limited to the environment type indicated by the environmental image collected for the terminal. Take the target semantics to indicate the query of the target route, and the environment type is divided into indoor and outdoor as an example. When the environmental correction information indicates that the environment type is indoor, the target interaction semantics is determined to query the indoor traffic route map from the indoor starting point to the end point, so that the map including the indoor traffic route map is displayed through the terminal. If there is no environmental correction information, then it is not known that the indoor traffic route map needs to be obtained based on the target semantics alone. It is very likely that the outdoor traffic route map from the starting point to the end point is directly retrieved. Then it is still unknown how to travel to the outdoor starting point indicated by the traffic route map based on the current indoor position. It is also possible that when the end point can be reached directly from indoors, an outdoor traffic route map is indicated, resulting in an interactive understanding deviation.

[0056] Similarly, when the environmental correction information indicates that the environment type is outdoor, the target interaction semantics is determined to be a query of an outdoor traffic route map from an outdoor starting point to an end point, so that a map including an outdoor traffic route map is displayed through the terminal. The end point of the target route is not limited to being determined by the target voice. For example, taking the target voice as "How do I get to XXX subway station", the end point can be determined to be XXX subway station through the target voice. The above target semantics of querying routes is only an example, and it can also be a query of any other information, such as knowledge, images, text, etc.

[0057] As an optional implementation, the above-mentioned use of correction information to correct the target semantics to obtain the target interaction semantics includes: when the target semantics indicates obtaining the target information, the target semantics is corrected using the information identifier contained in the correction information to obtain the target interaction semantics including the information identifier, wherein the target interaction semantics is used to indicate obtaining the target information corresponding to the information identifier.

[0058] Taking the target speech as "What medicine should I take" as an example, semantic recognition can determine that the interaction intention is to obtain medication. Without obtaining correction information, it is not known which medicine to obtain for treating the disease. Taking the correction information including speech correction information and expression correction information as an example, through the cough sound recognized in the speech and the facial expression recognized in the object image, it is determined that the information contained in the correction information is identified as cough, so that the target semantics is corrected using "cough", and the target interaction semantics is determined to be "obtain cough medication", and the recommended medication information for cough is displayed through the terminal.

[0059] Taking the target voice as "what is this" as an example, semantic recognition can determine that the interaction intention is to determine the object. Without obtaining the correction information, it is unknown what object the interactive voice indicates. Taking the correction information including posture correction information as an example, the posture information such as the gesture of the target object recognized by the object image can be used to determine the specific object referred to by the target object, such as a smart switch. Therefore, it is determined that the target interaction semantics is to ask what the smart switch is, so that the "smart switch" is displayed on the terminal or broadcasted by the terminal voice.

[0060] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0061] According to another aspect of an embodiment of the present invention, a voice interaction device for an intelligent device is provided for implementing the voice interaction method for the intelligent device. Figure 5 As shown, the device comprises:

[0062] The recognition unit 502 is used to perform semantic recognition on the target speech to obtain target semantics when the target speech is acquired, wherein the target speech is the interactive speech emitted by the target object in the target environment;

[0063] An acquisition unit 504 is configured to acquire correction information associated with the target speech, wherein the correction information includes object information generated by the target object in the target environment and / or environmental information of the target environment;

[0064] A correction unit 506, configured to correct the target semantics using the correction information to obtain the target interaction semantics;

[0065] The interaction unit 508 is used to determine the target interaction data that matches the target interaction semantics, and use the target interaction data to reply to the target speech.

[0066] Optionally, the above-mentioned interaction unit 508 includes a voice module, which is used to convert the target interaction data into a target reply voice when the interaction type of the target interaction data is voice interaction; and play the target reply voice.

[0067] Optionally, the above-mentioned interaction unit 508 includes a display module, which is used to determine the target display content corresponding to the target interaction data when the interaction type of the target interaction data is non-voice interaction; and display the target display content.

[0068] Optionally, obtaining correction information associated with the target voice comprises at least one of the following: obtaining environment correction information indicated by a target environment image, wherein the target environment image is an environment image captured by a terminal device located in the target environment, and the environment correction information is the environment type of the target environment determined based on the target environment image; obtaining expression correction information of a target object indicated by a target object image, wherein the target object is an object emitting the target voice, and the expression correction information is expression information of the target object determined based on the target object image; obtaining posture correction information of the target object indicated by the target image, wherein the posture correction information is posture information of the target object determined based on the target object image; obtaining intonation correction information indicated by the target voice, wherein the intonation correction information is used to determine the vocalization intonation information for the target voice emitted by the indicated target object; obtaining voice correction information indicated by the target voice, wherein the voice correction information is object sound information carried in the target voice.

[0069] Optionally, the voice interaction device of the above-mentioned smart device also includes a confidence unit, which is used to determine the information confidence of the correction information after obtaining the correction information associated with the target voice; when the information confidence is greater than the confidence threshold, the correction information is used to correct the target semantics.

[0070] Optionally, the above-mentioned confidence unit also includes determining target response data that matches the correction information when the information confidence of the correction information is less than a confidence threshold and the target semantics are mutually exclusive, wherein the target response data is used to request whether the correction information is correct; and using the target response data to respond to the target speech.

[0071] Optionally, the correction unit 506 is also used to correct the target semantics using the target environment type indicated by the environmental correction information when the target semantics indicates a query target route and the correction information includes environmental correction information, so as to obtain target interaction semantics including the target environment type, wherein the target interaction semantics is used to indicate a query target route that matches the target environment type.

[0072] Optionally, the correction unit 506 is also used to correct the target semantics using the information identifier contained in the correction information when the target semantics indicates obtaining target information, so as to obtain target interaction semantics including the information identifier, wherein the target interaction semantics is used to indicate obtaining target information corresponding to the information identifier.

[0073] In an embodiment of the present application, when a target speech emitted by a target object in a target environment is acquired, semantic recognition is performed on the target speech to obtain target semantics, and correction information associated with the target speech is acquired, wherein the correction information includes object information generated by the target object in the target environment and / or environmental information of the target environment, the target semantics is corrected using the correction information to obtain target interaction semantics, target interaction data matching the target interaction semantics is determined, and the target speech is replied using the target interaction data. After semantic recognition is performed on the target speech emitted by the target object, the target semantics is corrected based on the correction information associated with the target speech to obtain target interaction semantics, and the target interaction data for replying to the target speech is determined based on the target interaction semantics, thereby achieving the purpose of correcting the semantics of the interactive speech to obtain more accurate target interaction semantics, thereby replying to the target speech based on the target interaction data determined by the target interaction semantics, thereby achieving the technical effect of obtaining more accurate interaction semantics through semantic correction based on the environmental information and object information associated with the interactive speech, thereby solving the technical problem of low interaction satisfaction caused by the inability to correctly understand the interactive speech.

[0074] According to another aspect of the embodiment of the present invention, an electronic device for implementing the voice interaction method of the above-mentioned smart device is also provided. The electronic device may be Figure 1 The terminal device or server shown in the figure. This embodiment is described by taking the electronic device as a server as an example. Figure 6 As shown, the electronic device includes a memory 602 and a processor 604. The memory 602 stores a computer program, and the processor 604 is configured to execute the steps in any of the above method embodiments through the computer program.

[0075] Optionally, in this embodiment, the electronic device may be located in at least one network device among a plurality of network devices of a computer network.

[0076] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0077] S1, when a target speech is acquired, semantic recognition is performed on the target speech to obtain target semantics, wherein the target speech is an interactive speech emitted by a target object in a target environment;

[0078] S2, obtaining correction information associated with the target speech, wherein the correction information includes object information generated by the target object in the target environment and / or environmental information of the target environment;

[0079] S3, using the correction information to correct the target semantics to obtain the target interaction semantics;

[0080] S4, determining target interaction data that matches the target interaction semantics, and using the target interaction data to reply to the target voice.

[0081] Alternatively, a person skilled in the art may understand that: Figure 6 The structure shown is for illustration only, and the electronic device may also be any terminal device. Figure 6 The structure of the electronic device is not limited. Figure 6 More or fewer components (such as network interfaces, etc.) as shown in, or with Figure 6 Different configurations shown.

[0082] Among them, the memory 602 can be used to store software programs and modules, such as the program instructions / modules corresponding to the voice interaction method and device of the intelligent device in the embodiment of the present invention. The processor 604 executes various functional applications and data processing by running the software programs and modules stored in the memory 602, that is, realizing the above-mentioned voice interaction method of the intelligent device. The memory 602 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 602 may further include a memory remotely arranged relative to the processor 604, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned networks include but are not limited to the Internet, corporate intranets, local area networks, mobile communication networks and combinations thereof. Among them, the memory 602 can be specifically used for, but is not limited to, storing information such as target speech, target semantics, correction information, target interaction semantics, target interaction data, etc. As an example, such as Figure 6 As shown, the memory 602 may include, but is not limited to, the recognition unit 502, the acquisition unit 504, the correction unit 506, and the interaction unit 508 in the voice interaction device of the smart device. In addition, other module units in the voice interaction device of the smart device may also be included but are not limited to, which will not be repeated in this example.

[0083] Optionally, the transmission device 606 is used to receive or send data via a network. Specific examples of the network may include a wired network and a wireless network. In one example, the transmission device 606 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices and routers via a network cable so as to communicate with the Internet or a local area network. In one example, the transmission device 606 is a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0084] In addition, the electronic device further includes: a display 608 for displaying the target interaction data; and a connection bus 610 for connecting various module components in the electronic device.

[0085] In other embodiments, the terminal device or server may be a node in a distributed system, wherein the distributed system may be a blockchain system, and the blockchain system may be a distributed system formed by connecting the multiple nodes through network communication. Among them, the nodes may form a peer-to-peer (P2P, Peer To Peer) network, and any form of computing device, such as a server, terminal and other electronic devices, may become a node in the blockchain system by joining the peer-to-peer network.

[0086] According to one aspect of the present application, a computer program product or computer program is provided, the computer program product or computer program including computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method provided in various optional implementations of the voice interaction of the above-mentioned smart device. The computer program is configured to execute the steps of any of the above-mentioned method embodiments when it is run.

[0087] Optionally, in this embodiment, the computer-readable storage medium may be configured to store a computer program for performing the following steps:

[0088] S1, when a target speech is acquired, semantic recognition is performed on the target speech to obtain target semantics, wherein the target speech is an interactive speech emitted by a target object in a target environment;

[0089] S2, obtaining correction information associated with the target speech, wherein the correction information includes object information generated by the target object in the target environment and / or environmental information of the target environment;

[0090] S3, using the correction information to correct the target semantics to obtain the target interaction semantics;

[0091] S4, determining target interaction data that matches the target interaction semantics, and using the target interaction data to reply to the target voice.

[0092] Optionally, in this embodiment, a person of ordinary skill in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by instructing hardware related to the terminal device through a program, and the program may be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc.

[0093] 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.

[0094] If the integrated units in the above embodiments are implemented in the form of software functional units and sold or used as independent products, they can be stored in the above computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling one or more computer devices (which can be personal computers, servers or network devices, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention.

[0095] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0096] In the several embodiments provided in the present application, it should be understood that the disclosed client can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0097] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0098] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0099] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A voice interaction method for an intelligent device, characterized in that: include: When a target speech is acquired, semantic recognition is performed on the target speech to obtain target semantics, wherein the target speech is an interactive speech emitted by a target object in a target environment; Acquire correction information associated with the target speech, wherein the correction information includes object information generated by the target object in the target environment and environmental information of the target environment, and the environmental information of the target environment includes environmental correction information indicated by a target environmental image, and the target environmental image is an environmental image captured by a terminal device located in the target environment; Correcting the target semantics using the correction information to obtain target interaction semantics includes: In the case where the target semantics indicates a query target route and the environment correction information indicates an indoor environment type, the target semantics is corrected to obtain the target interaction semantics including the indoor environment type, wherein the target interaction semantics of the indoor environment type is used to indicate a query for an indoor traffic route map from an indoor starting point to an indoor end point; In the case where the target semantics indicates a query target route and the environment correction information indicates an outdoor environment type, the target semantics is corrected to obtain the target interaction semantics including the outdoor environment type, wherein the target interaction semantics of the outdoor environment type is used to indicate a query for an outdoor traffic route map from an outdoor starting point to an end point; In the case where the target semantics indicates obtaining target information, the target semantics is corrected using the information identifier included in the correction information to obtain the target interaction semantics including the information identifier, wherein the target interaction semantics is used to indicate obtaining the target information corresponding to the information identifier; Target interaction data matching the target interaction semantics is determined, and the target speech is replied using the target interaction data.

2. The method according to claim 1, characterized in that: The using the target interaction data to reply to the target voice comprises: In a case where the interaction type of the target interaction data is voice interaction, converting the target interaction data into a target reply voice; Play the target reply voice.

3. The method according to claim 1, characterized in that The using the target interaction data to reply to the target voice comprises: In a case where the interaction type of the target interaction data is non-voice interaction, determining target display content corresponding to the target interaction data; The target display content is displayed.

4. The method according to claim 1, characterized in that: The acquiring of correction information associated with the target speech comprises at least one of the following: Acquire expression correction information of a target object indicated by a target object image, wherein the target object is an object that emits the target voice, and the expression correction information is expression information of the target object determined according to the target object image; Acquire posture correction information of the target object indicated by the target object image, wherein the posture correction information is the posture information of the target object determined according to the target object image; Acquire intonation correction information indicated by the target speech, wherein the intonation correction information is intonation information determined according to the target speech; Acquire voice correction information indicated by the target voice, wherein the voice correction information is object sound information carried in the target voice.

5. The method according to claim 1, characterized in that After obtaining the correction information associated with the target speech, the method further includes: Determining information confidence of the correction information; In a case where the information confidence is greater than a confidence threshold, the target semantics is corrected using the correction information.

6. The method according to claim 5, characterized in that Determining the information confidence of the correction information includes: In a case where the information confidence of the correction information is less than the confidence threshold and the target semantics are mutually exclusive, determining target reply data matching the correction information, wherein the target reply data is used to request a determination of whether the correction information is correct; The target speech is responded to using the target response data.

7. A voice interaction device for an intelligent device, characterized in that: include: A recognition unit, configured to perform semantic recognition on the target speech to obtain target semantics when a target speech is acquired, wherein the target speech is an interactive speech emitted by a target object in a target environment; an acquisition unit, configured to acquire correction information associated with the target speech, wherein the correction information includes object information generated by the target object in the target environment and environmental information of the target environment, wherein the environmental information of the target environment includes environmental correction information indicated by a target environmental image, and the target environmental image is an environmental image captured by a terminal device located in the target environment; A correction unit, used to correct the target semantics using the correction information to obtain target interaction semantics, including: when the target semantics indicates querying a target route and the environmental correction information indicates an indoor environment type, correcting the target semantics to obtain the target interaction semantics including the indoor environment type, wherein the target interaction semantics of the indoor environment type is used to indicate querying an indoor traffic route map from an indoor starting point to an end point; when the target semantics indicates querying a target route and the environmental correction information indicates an outdoor environment type, correcting the target semantics to obtain the target interaction semantics including the outdoor environment type, wherein the target interaction semantics of the outdoor environment type is used to indicate querying an outdoor traffic route map from an outdoor starting point to an end point; when the target semantics indicates obtaining target information, correcting the target semantics using the information identifier contained in the correction information to obtain the target interaction semantics including the information identifier, wherein the target interaction semantics is used to indicate obtaining target information corresponding to the information identifier; The interaction unit is used to determine target interaction data that matches the target interaction semantics, and use the target interaction data to reply to the target voice.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the program executes the method described in any one of claims 1 to 6 when executed.

Images