Method, device, equipment and storage medium for intelligent voice interaction with virtual puppet

Abstract

The present invention belongs to the field of intelligent interaction technology, and discloses a method, device, equipment and storage medium for intelligent voice interaction with a virtual puppet. The method includes: when receiving a first voice message input by a user, querying a preset corpus according to the first voice message to obtain a target sentence; determining a target instruction according to the target sentence; determining a target guidance operation of a virtual 3D puppet according to the target instruction; and controlling the virtual 3D puppet to perform the target guidance operation in a virtual wedding scene to complete voice interaction with the user. In the above manner, the preset corpus can be queried according to the first voice message to obtain a target sentence, and then the target instruction can be determined according to the target sentence, and then the virtual 3D puppet can be guided to perform the target guidance operation in the virtual wedding scene according to the target instruction to complete voice interaction with the user, thereby realizing interaction with the user's voice through the target guidance operation of the 3D puppet, making the visual interaction between the user and the virtual puppet more intuitive and intelligent.

Description

Technical Field

[0001] The present invention relates to the field of intelligent interaction technology, and in particular to a method, device, equipment and storage medium for intelligent voice interaction with a virtual puppet. Background Art

[0002] Nowadays, with the rapid development of human-computer interaction, people can use smart devices to realize various human-computer interactions on the display screen. One of the most common ones is the interaction with intelligent AI, which involves various virtual scenes. However, the intelligent interaction in the existing virtual wedding scenes is often just the user commanding the intelligent AI or virtual puppets to act by clicking on the screen, and it cannot achieve automatic and humanized feedback of the virtual 3D puppet according to the information input by the user's voice, making the visual interaction with the virtual puppet not intuitive and intelligent enough.

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

[0004] The main purpose of the present invention is to provide a method, device, equipment and storage medium for intelligent voice interaction with a virtual doll, aiming to solve the technical problem of the prior art in making the visual interaction with a virtual doll in a virtual wedding scene more intuitive and intelligent.

[0005] To achieve the above object, the present invention provides a method for intelligent voice interaction with a virtual puppet, the method comprising the following steps:

[0006] When receiving a first voice message input by a user, querying a preset corpus according to the first voice message to obtain a target sentence;

[0007] Determining a target instruction according to the target sentence;

[0008] Determining a target guidance operation of the virtual 3D puppet according to the target instruction;

[0009] The virtual 3D doll is controlled to perform the target guidance operation in the virtual wedding scene to complete the voice interaction with the user.

[0010] Optionally, when receiving the first voice information input by the user, before searching the preset corpus according to the first voice information to obtain the target sentence, the method further includes:

[0011] Sending a puppet creation instruction to a user, and receiving puppet creation information uploaded by the user according to the puppet creation instruction;

[0012] Obtaining a puppet reference picture and puppet attribute parameters according to the puppet creation information;

[0013] A virtual 3D puppet matching the user is created according to the puppet reference picture and the puppet attribute parameters.

[0014] Optionally, when receiving the first voice information input by the user, before searching the preset corpus according to the first voice information to obtain the target sentence, the method further includes:

[0015] Obtain the corpus in the preset wedding virtual scene as the initial corpus;

[0016] Obtaining the correspondence between the initial corpus and the instruction terms in the virtual wedding scene;

[0017] A preset corpus is constructed according to the initial corpus and the corresponding relationship.

[0018] Optionally, when receiving the first voice information input by the user, querying a preset corpus according to the first voice information to obtain the target sentence includes:

[0019] When receiving a first voice message input by a user, obtaining a first text message according to the first voice message;

[0020] Acquire the first image information corresponding to the moment when the user inputs the first voice information;

[0021] Querying a preset corpus according to the first text information to obtain a first target sentence;

[0022] Determine a second target sentence according to the first image information;

[0023] A target sentence is determined according to the first target sentence and the second target sentence.

[0024] Optionally, determining a target guidance operation of the virtual 3D puppet according to the target instruction includes:

[0025] Determining an interaction mode of the virtual 3D puppet according to the target instruction;

[0026] When the interaction mode is the information reply mode, generating information reply text and information reply voice according to the target instruction;

[0027] The message reply text and the message reply voice are displayed as a target guidance operation.

[0028] Optionally, after determining the interaction mode of the virtual 3D puppet according to the target instruction, the method further includes:

[0029] When the interaction mode is the action reply mode, querying a preset instruction-action comparison table according to the target instruction;

[0030] Determine the target action corresponding to the target instruction according to the instruction-action comparison table;

[0031] Completing the target action is used as the target guiding operation.

[0032] Optionally, after determining the interaction mode of the virtual 3D puppet according to the target instruction, the method further includes:

[0033] When the interaction mode is a wedding execution mode, determining a target virtual 3D doll according to the target instruction;

[0034] Generate wedding target actions and wedding target voices;

[0035] The target virtual 3D doll is controlled to perform a wedding in the virtual wedding scene according to the target wedding actions and the target wedding voice.

[0036] In addition, to achieve the above-mentioned purpose, the present invention also proposes a voice intelligent interaction device with a virtual puppet, and the voice intelligent interaction device with a virtual puppet comprises:

[0037] A voice receiving module, configured to, when receiving a first voice message input by a user, query a preset corpus according to the first voice message to obtain a target sentence;

[0038] An instruction determination module, used to determine a target instruction according to the target statement;

[0039] A reply determination module, used for determining a target guidance operation of the virtual 3D puppet according to the target instruction;

[0040] The operation execution module is used to control the virtual 3D doll to perform the target guidance operation in the virtual wedding scene to complete the voice interaction with the user.

[0041] In addition, to achieve the above-mentioned purpose, the present invention also proposes a voice intelligent interaction device with a virtual puppet, the voice intelligent interaction device with a virtual puppet comprising: a memory, a processor, and a voice intelligent interaction program with a virtual puppet stored in the memory and executable on the processor, the voice intelligent interaction program with the virtual puppet being configured to implement the steps of the voice intelligent interaction method with a virtual puppet as described above.

[0042] In addition, to achieve the above-mentioned purpose, the present invention also proposes a storage medium, on which a voice intelligent interaction program with a virtual puppet is stored. When the voice intelligent interaction program with the virtual puppet is executed by a processor, the steps of the voice intelligent interaction method with the virtual puppet as described above are implemented.

[0043] When the present invention receives the first voice information input by the user, it queries the preset corpus according to the first voice information to obtain the target sentence; determines the target instruction according to the target sentence; determines the target guidance operation of the virtual 3D puppet according to the target instruction; and controls the virtual 3D puppet to perform the target guidance operation in the virtual wedding scene to complete the voice interaction with the user. Through the above method, when the first voice information input by the user is received, the preset corpus can be queried according to the first voice information to obtain the target sentence, and then the target instruction can be determined according to the target sentence, and then the virtual 3D puppet can be guided to perform the target guidance operation in the virtual wedding scene according to the target instruction to complete the voice interaction with the user, realizing the interaction between the 3D puppet's target guidance operation and the user's voice, making the visual interaction between the user and the virtual puppet more intuitive and intelligent. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a structural diagram of a voice intelligent interaction device with a virtual puppet in a hardware operating environment involved in an embodiment of the present invention;

[0045] Figure 2 It is a flowchart of a first embodiment of the method for intelligent voice interaction with a virtual puppet of the present invention;

[0046] Figure 3 It is a flow chart of a second embodiment of the method for intelligent voice interaction with a virtual puppet of the present invention;

[0047] Figure 4 This is a structural block diagram of the first embodiment of the voice intelligent interaction device with a virtual puppet of the present invention.

[0048] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0049] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0050] Reference Figure 1 , Figure 1 This is a schematic diagram of the structure of a voice intelligent interaction device with a virtual puppet in the hardware operating environment involved in an embodiment of the present invention.

[0051] like Figure 1As shown, the voice intelligent interaction device with the virtual doll may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) memory, or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0052] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the voice intelligent interaction device with the virtual puppet, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0053] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a voice intelligent interaction program with a virtual puppet.

[0054] exist Figure 1 In the voice intelligent interaction device with a virtual puppet shown, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the voice intelligent interaction device with a virtual puppet of the present invention can be set in the voice intelligent interaction device with a virtual puppet, and the voice intelligent interaction device with a virtual puppet calls the voice intelligent interaction program with a virtual puppet stored in the memory 1005 through the processor 1001, and executes the voice intelligent interaction method with a virtual puppet provided in an embodiment of the present invention.

[0055] The embodiment of the present invention provides a method for intelligent voice interaction with a virtual puppet, referring to Figure 2 , Figure 2 The figure is a flow chart of a first embodiment of a method for intelligent voice interaction with a virtual puppet according to the present invention.

[0056] In this embodiment, the method for intelligent voice interaction with a virtual puppet includes the following steps:

[0057] Step S10: When a first voice message input by a user is received, a preset corpus is queried according to the first voice message to obtain a target sentence.

[0058] It should be noted that the execution subject of this embodiment is a user terminal, which can be a personal computer, a smart phone, a tablet computer, etc., or other devices or equipment that can achieve this function, and this embodiment does not limit this. And the execution of this embodiment is realized on the APP on the user terminal.

[0059] It should be understood that, generally, the interaction between a user and a virtual 3D doll is based on gesture instructions generated by the user clicking or sliding on the screen, and then the virtual 3D doll gives feedback through display on the screen. However, this interaction method can only be achieved by clicking on the screen, which is not smart enough, and the virtual 3D doll cannot give feedback to the user's personalized instructions, making the interaction with the virtual doll not intuitive enough. Therefore, this embodiment is proposed so that the interaction with the virtual doll can be achieved through user input voice, and the virtual doll can automatically and humanely give feedback to the user's voice.

[0060] In a specific implementation, the first voice information refers to the voice information spoken by the user collected by the sound collection function of the smart device, such as a microphone or other device.

[0061] It should be noted that the preset corpus is a pre-established corpus, which is used to store corpora and can query text sentences corresponding to voice information based on voice information.

[0062] It should be understood that the target sentence is a sentence stored in text form, and the target sentence is the sentence that is finally matched with the content and meaning of the first voice information by comparing the first voice information with the corpus stored in the preset corpus. Figure 1 The text sentence is consistent with the original text.

[0063] In a specific implementation, when a first voice message input by a user is received, a preset corpus is queried based on the first voice message to obtain a target sentence, which means: when an APP on a smart terminal is opened and a first voice message input by a user through a voice input module of the smart terminal is received, a pre-established preset corpus is queried based on the first voice message, the first voice message is compared one by one with the corpus in the preset corpus, and finally the target sentence in text form is obtained.

[0064] Furthermore, the image of the existing virtual 3D puppet can often only be obtained by combining image modules provided in advance, and is not personalized enough. In order to pre-establish a virtual 3D puppet image that matches the user's needs before the user interacts with the virtual 3D puppet, before step S10, it also includes: sending a puppet creation instruction to the user, and receiving puppet creation information uploaded by the user according to the puppet creation instruction; obtaining a puppet reference picture and puppet attribute parameters according to the puppet creation information; and creating a virtual 3D puppet that matches the user according to the puppet reference picture and the puppet attribute parameters.

[0065] It should be noted that the puppet creation instruction is an instruction displayed to the user through the smart terminal, which is used to prompt the user to upload the puppet creation information required to create a virtual 3D puppet. The puppet creation instruction can be an instruction in any form that can achieve this function, and this embodiment does not limit this.

[0066] It should be understood that the puppet creation information includes all information for creating a virtual 3D puppet, such as a puppet reference image and puppet attribute parameters.

[0067] In a specific implementation, the puppet reference picture is a picture uploaded by the user for shaping the facial features of the virtual 3D puppet created by the user. The picture can be a picture containing the user's facial features taken by the user using a camera, or a picture containing the facial features of any portrait selected by the user from the system album.

[0068] It should be noted that the puppet attribute parameters are parameters set by the user for controlling various body data of the virtual 3D puppet. The puppet attribute parameters may include: puppet's height, body shape, clothing, gender and other parameters related to the puppet's body data, which are not limited in this embodiment.

[0069] It should be understood that creating a virtual 3D doll matching the user based on the doll reference picture and the doll attribute parameters means: after obtaining the doll reference picture and the doll attribute parameters, automatically generating a virtual 3D doll based on the doll reference picture and the doll attribute parameters, the facial features of the generated virtual 3D doll are generated according to the doll reference picture, and various body data are generated according to the doll attribute parameters, and the finally obtained virtual 3D doll is bound to the account logged in by the current user, and can only be used and edited by the user of the currently logged in account.

[0070] In this way, the user can fully customize the virtual 3D doll bound to him / her, making the interaction with the virtual doll more personalized.

[0071] Furthermore, in order to be more adaptable to the corpus and interaction in the virtual wedding scene, it is necessary to construct a corpus for the virtual wedding scene to adapt to the interaction between the user and the virtual 3D doll in the APP. Before step S10, it also includes: obtaining the corpus in the preset virtual wedding scene as the initial corpus; obtaining the correspondence between the initial corpus and the instruction terms in the virtual wedding scene; and constructing a preset corpus based on the initial corpus and the correspondence.

[0072] In a specific implementation, the wedding virtual scene refers to a virtual wedding scene that is pre-set in the APP and displayed on a smart terminal, and may include all virtual scenes related to the wedding, which is not limited in this embodiment.

[0073] It should be noted that obtaining the corpus in the preset wedding virtual scene as the initial corpus means: obtaining wedding corpus such as wedding terms, idioms and common expressions preset in the wedding virtual scene, and then using these wedding terms as the initial corpus.

[0074] It should be understood that the correspondence between the initial corpus and the instruction terms in the virtual wedding scene refers to: the correspondence between a certain specific instruction term corresponding to a number of pre-stored initial corpora, and the corresponding instruction term can be queried according to the initial corpus through the correspondence.

[0075] In a specific implementation, the smart terminal and the APP can identify the corresponding instructions that need to be executed based on the instruction terms.

[0076] It should be noted that, after the initial corpus and the corresponding relationship are determined, the initial corpus is stored according to the corresponding relationship to form a preset corpus, and the corresponding instruction terms can be found in the preset corpus according to the corpus.

[0077] In this way, a specific preset corpus can be constructed for the virtual wedding scene, so that the user's intention can be more accurately determined in the APP based on the first voice information input by the user, making the interaction with the virtual doll more accurate.

[0078] Furthermore, in order to be able to more accurately identify the target sentence, step S10 includes: when receiving a first voice message input by a user, obtaining a first text message based on the first voice message; obtaining the first image information corresponding to the moment when the user inputs the first voice message; querying a preset corpus based on the first text information to obtain a first target sentence; determining a second target sentence based on the first image information; and determining a target sentence based on the first target sentence and the second target sentence.

[0079] In a specific implementation, the first text information is text information obtained by directly processing the first voice information through a voice recognition function. Since voice recognition may be affected by the user's accent or other factors, the first text information may be a plurality of text information with different recognition matching degrees.

[0080] It should be noted that obtaining the first image information corresponding to the moment when the user inputs the first voice information means: obtaining the image information during the period when the user inputs the first voice information through the front camera of the smart terminal as the first image information. The first image information mainly includes the image information of the user's lip movement.

[0081] It should be understood that querying the preset corpus according to the first text information to obtain the first target sentence means: bringing the first text information into the preset corpus and matching it with the initial corpus stored in the preset corpus, and finally combining the successfully matched corpus and instruction terms to obtain the first target sentence.

[0082] In a specific implementation, determining the second target sentence based on the first image information refers to performing image recognition on the user's lip image information in the first image information, and combining a preset comparison table that stores the correspondence between lip images and sentences to obtain the text of the sentence spoken by the user that matches the first image information as the second target sentence.

[0083] It should be noted that the first target sentence is obtained by querying a preset corpus with first text information. There may be multiple first text information, so there may be multiple first target sentences. The second target sentence is text information obtained through image recognition, so it can be several text sentences with a decreasing degree of match with the sentence.

[0084] It should be noted that determining the target sentence based on the first target sentence and the second target sentence means: matching the first target sentence and the second target sentence, selecting the first target sentence and the second target sentence with the highest similarity, and combining them to obtain a sentence with overlapping intentions, which is the target sentence.

[0085] In this way, the target sentence can be determined by combining speech recognition and image recognition at the same time, making the determination of the target sentence more accurate.

[0086] Step S20: Determine a target instruction according to the target statement.

[0087] It should be understood that the target instruction refers to an instruction corresponding to the user's intention determined based on the target sentence.

[0088] In a specific implementation, determining the target instruction according to the target sentence means that after the target sentence is determined, the APP or the smart terminal automatically identifies the user instruction corresponding to the target sentence according to the target sentence.

[0089] Step S30: determining a target guidance operation of the virtual 3D puppet according to the target instruction.

[0090] It should be noted that determining the target guidance operation of the virtual 3D puppet according to the target instruction means: after the target instruction is determined, determining the response action that the virtual 3D puppet needs to perform according to the target instruction, and the response operation is the target guidance operation.

[0091] Step S40: controlling the virtual 3D doll to perform the target guidance operation in the virtual wedding scene to complete voice interaction with the user.

[0092] It should be understood that controlling the virtual 3D doll to perform the target guidance operation in the virtual wedding scene to complete the voice interaction with the user means that after the target guidance operation is determined, the APP program automatically controls the virtual 3D doll to perform the target guidance operation in the preset virtual wedding scene according to the target guidance operation.

[0093] This embodiment, when receiving the first voice information input by the user, queries the preset corpus according to the first voice information to obtain the target sentence; determines the target instruction according to the target sentence; determines the target guidance operation of the virtual 3D puppet according to the target instruction; controls the virtual 3D puppet to perform the target guidance operation in the virtual wedding scene to complete the voice interaction with the user. Through the above method, when receiving the first voice information input by the user, the preset corpus can be queried according to the first voice information to obtain the target sentence, and then the target instruction can be determined according to the target sentence, and then the virtual 3D puppet can be guided to perform the target guidance operation in the virtual wedding scene according to the target instruction to complete the voice interaction with the user, so as to realize the interaction between the target guidance operation of the 3D puppet and the user's voice, making the visual interaction between the user and the virtual puppet more intuitive and intelligent.

[0094] refer to Figure 3 , Figure 3 The figure is a flow chart of a second embodiment of a method for intelligent voice interaction with a virtual puppet according to the present invention.

[0095] Based on the first embodiment, step S30 in the method for intelligent voice interaction with a virtual puppet in this embodiment includes:

[0096] Step S301: determining the interaction mode of the virtual 3D puppet according to the target instruction.

[0097] It should be noted that the interaction mode refers to the action mode taken by the virtual 3D doll in response to the user's first voice message, including but not limited to: action reply mode, information reply mode and wedding execution mode.

[0098] It should be understood that determining the interaction mode of the virtual 3D puppet according to the target instruction means querying a preset instruction-mode comparison table according to the target instruction. The instruction-mode comparison table stores a comparison table of all target instructions and interaction modes. The corresponding interaction mode can be queried in the instruction-mode comparison table according to the target instruction.

[0099] Furthermore, in order to enable the virtual 3D doll to respond to the user through actions, after step S301, it also includes: when the interaction mode is the action response mode, querying a preset instruction-action comparison table according to the target instruction; determining the target action corresponding to the target instruction according to the instruction-action comparison table; and completing the target action as the target guidance operation.

[0100] In a specific implementation, the action response mode is a mode in which the simulated 3D puppet is controlled to respond to the user by completing a target action.

[0101] It should be noted that the instruction-action comparison table is pre-set and stored, and is used to find the target action corresponding to the target instruction. In the instruction-action comparison table, instructions and actions are stored in correspondence according to the corresponding relationship.

[0102] It should be understood that determining the target action corresponding to the target instruction according to the instruction-action comparison table means that the instruction-action comparison table is queried according to the target instruction, and the action of the query result is used as the target action.

[0103] In a specific implementation, the target action may be a human action pre-stored in the instruction-action comparison table, such as changing clothes, dancing, moving, squatting, etc., which are performed by a virtual 3D doll, and this embodiment does not limit this.

[0104] In this way, the virtual 3D puppet can respond and interact with the user by completing the target action, making the visual interaction more intuitive and intelligent.

[0105] Furthermore, in order to complete the virtual wedding according to the user's first voice information, after step S301, it also includes: when the interaction mode is the wedding execution mode, determining the target virtual 3D doll according to the target instruction; generating a wedding target action and a wedding target voice; controlling the target virtual 3D doll to perform the wedding in the wedding virtual scene according to the wedding target action and the wedding target voice.

[0106] It should be noted that the wedding execution mode is an interactive mode for controlling the virtual 3D doll to complete the virtual wedding in the wedding virtual scene in the APP.

[0107] It should be understood that the target virtual 3D doll is a virtual 3D doll used for the wedding in the wedding execution mode, one of which is the virtual 3D doll corresponding to the current user's login account, and the other is a virtual 3D doll determined according to the user's target instruction. It can be a virtual 3D doll of the account of any user using this APP, and this embodiment does not limit this.

[0108] In a specific implementation, the wedding target voice and wedding target action are pre-stored in the APP or smart terminal, and are used to control the target virtual 3D doll to complete the wedding. The wedding target action may include: wedding action, proposal action, etc., and the wedding target voice may include: proposal voice, wedding voice, etc., which are not limited in this embodiment.

[0109] It should be noted that controlling the target virtual 3D doll to perform a wedding in the virtual wedding scene according to the wedding target action and the wedding target voice means: controlling the virtual 3D doll to complete the wedding target action, and then playing the wedding target voice, so as to enable the target virtual 3D doll to perform a wedding in the virtual wedding scene.

[0110] In this way, the user's virtual 3D puppet can interact with other users' virtual 3D puppets in the APP, which makes the visual interaction with the virtual puppet more interesting and more intelligent.

[0111] Step S302: When the interaction mode is the information reply mode, an information reply text and an information reply voice are generated according to the target instruction.

[0112] In a specific implementation, the information reply mode is that the virtual 3D puppet replies to the user through voice or text messages.

[0113] It should be noted that the information reply text and the correspondence between the information reply text and the target instruction are stored in a preset instruction-information comparison table. The information reply text corresponding to the target instruction can be queried through the instruction-information comparison table, and then the information reply voice can be automatically generated based on the information reply text.

[0114] Step S303: displaying the message reply text and the message reply voice as a target guidance operation.

[0115] It should be understood that displaying the message reply text and the message reply voice as a target guidance operation means using the message reply text and the message reply voice as a target guidance operation. When the virtual 3D doll is controlled to perform the target guidance operation, the message reply text will be displayed to the user and the message reply voice will be played to the user.

[0116] This embodiment determines the interaction mode of the virtual 3D doll according to the target instruction; when the interaction mode is the information reply mode, generates the information reply text and the information reply voice according to the target instruction; and displays the information reply text and the information reply voice as the target guidance operation. In this way, it is possible to determine the interaction mode according to the target instruction, and then automatically generate voice and text in the information reply mode to reply to the user's words, making the visual interaction with the virtual doll in the virtual wedding scene more intuitive and intelligent.

[0117] In addition, an embodiment of the present invention further proposes a storage medium, on which a voice intelligent interaction program with a virtual puppet is stored. When the voice intelligent interaction program with the virtual puppet is executed by a processor, the steps of the voice intelligent interaction method with the virtual puppet as described above are implemented.

[0118] Since the storage medium adopts all the technical solutions of all the above embodiments, it has at least all the beneficial effects brought by the technical solutions of the above embodiments, which will not be described one by one here.

[0119] Reference Figure 4 , Figure 4 This is a structural block diagram of the first embodiment of the voice intelligent interaction device with a virtual puppet of the present invention.

[0120] like Figure 4 As shown, the voice intelligent interaction device with a virtual puppet proposed in an embodiment of the present invention includes:

[0121] The voice receiving module 10 is used to query a preset corpus according to the first voice information to obtain a target sentence when receiving the first voice information input by the user.

[0122] The instruction determination module 20 is used to determine a target instruction according to the target statement.

[0123] The reply determination module 30 is used to determine the target guidance operation of the virtual 3D puppet according to the target instruction.

[0124] The operation execution module 40 is used to control the virtual 3D doll to perform the target guidance operation in the virtual wedding scene to complete the voice interaction with the user.

[0125] This embodiment, when receiving the first voice information input by the user, queries the preset corpus according to the first voice information to obtain the target sentence; determines the target instruction according to the target sentence; determines the target guidance operation of the virtual 3D puppet according to the target instruction; controls the virtual 3D puppet to perform the target guidance operation in the virtual wedding scene to complete the voice interaction with the user. Through the above method, when receiving the first voice information input by the user, the preset corpus can be queried according to the first voice information to obtain the target sentence, and then the target instruction can be determined according to the target sentence, and then the virtual 3D puppet can be guided to perform the target guidance operation in the virtual wedding scene according to the target instruction to complete the voice interaction with the user, so as to realize the interaction between the target guidance operation of the 3D puppet and the user's voice, making the visual interaction between the user and the virtual puppet more intuitive and intelligent.

[0126] In one embodiment, the voice receiving module 10 is further used to send a puppet creation instruction to the user, and receive the puppet creation information uploaded by the user according to the puppet creation instruction; obtain a puppet reference picture and puppet attribute parameters according to the puppet creation information; and create a virtual 3D puppet matching the user according to the puppet reference picture and the puppet attribute parameters.

[0127] In one embodiment, the voice receiving module 10 is further used to obtain corpus in a preset wedding virtual scene as initial corpus; obtain the correspondence between the initial corpus in the wedding virtual scene and instruction terms; and construct a preset corpus based on the initial corpus and the correspondence.

[0128] In one embodiment, the voice receiving module 10 is also used to obtain first text information based on the first voice information when receiving the first voice information input by the user; obtain the first image information corresponding to the moment when the user inputs the first voice information; query the preset corpus according to the first text information to obtain the first target sentence; determine the second target sentence according to the first image information; determine the target sentence according to the first target sentence and the second target sentence.

[0129] In one embodiment, the reply determination module 30 is also used to determine the interaction mode of the virtual 3D puppet according to the target instruction; when the interaction mode is the information reply mode, generate information reply text and information reply voice according to the target instruction; and display the information reply text and the information reply voice as a target guidance operation.

[0130] In one embodiment, the reply determination module 30 is also used to query a preset instruction-action comparison table according to the target instruction when the interaction mode is an action reply mode; determine the target action corresponding to the target instruction according to the instruction-action comparison table; and use the completion of the target action as the target guidance operation.

[0131] In one embodiment, the reply determination module 30 is also used to determine the target virtual 3D puppet according to the target instruction when the interaction mode is the wedding execution mode; generate wedding target actions and wedding target voices; and control the target virtual 3D puppet to perform the wedding in the wedding virtual scene according to the wedding target actions and the wedding target voices.

[0132] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of them according to actual needs to achieve the purpose of the present embodiment, and no limitation is made here.

[0133] In addition, for technical details not described in detail in this embodiment, reference can be made to the voice intelligent interaction method with a virtual puppet provided in any embodiment of the present invention, and will not be repeated here.

[0134] It should be understood that the above is only an example and does not constitute any limitation on the technical solution of the present invention. In specific applications, technicians in this field can make settings as needed, and the present invention does not limit this.

[0135] In addition, it should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0136] 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.

[0137] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory (ROM) / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0138] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for intelligent voice interaction with a virtual puppet, characterized in that: The method for intelligent voice interaction with a virtual puppet comprises: When receiving a first voice message input by a user, obtaining a first text message according to the first voice message, wherein the first text message is a plurality of text messages with different recognition matching degrees; Acquire first image information corresponding to the moment when the user inputs the first voice information, wherein the first image information includes image information of the user's lip movement; Querying a preset corpus according to the first text information to obtain a first target sentence; Determine a second target sentence according to the first image information; determining a target sentence according to the first target sentence and the second target sentence; Determining a target instruction according to the target sentence; Determining an interaction mode of the virtual 3D puppet according to the target instruction; When the interaction mode is the information reply mode, generating information reply text and information reply voice according to the target instruction; Displaying the message reply text and the message reply voice as a target guidance operation; Wherein, when the interaction mode is a wedding execution mode, a target virtual 3D doll is determined according to the target instruction; Generate wedding target actions and wedding target voices; Control the target virtual 3D doll to perform the wedding in the wedding virtual scene according to the wedding target action and the wedding target voice; The virtual 3D doll is controlled to perform the target guidance operation in the virtual wedding scene to complete the voice interaction with the user.

2. The method for intelligent voice interaction with a virtual puppet as claimed in claim 1, characterized in that: When receiving the first voice information input by the user, before searching the preset corpus according to the first voice information to obtain the target sentence, the method further includes: Sending a puppet creation instruction to a user, and receiving puppet creation information uploaded by the user according to the puppet creation instruction; Obtaining a puppet reference picture and puppet attribute parameters according to the puppet creation information; A virtual 3D puppet matching the user is created according to the puppet reference picture and the puppet attribute parameters.

3. The method for intelligent voice interaction with a virtual puppet as claimed in claim 1, characterized in that: When receiving the first voice information input by the user, before searching the preset corpus according to the first voice information to obtain the target sentence, the method further includes: Obtain the corpus in the preset wedding virtual scene as the initial corpus; Obtaining the correspondence between the initial corpus and the instruction terms in the virtual wedding scene; A preset corpus is constructed according to the initial corpus and the corresponding relationship.

4. The method for intelligent voice interaction with a virtual puppet as claimed in claim 1, characterized in that: After determining the interaction mode of the virtual 3D puppet according to the target instruction, the method further includes: When the interaction mode is the action reply mode, querying a preset instruction-action comparison table according to the target instruction; Determine the target action corresponding to the target instruction according to the instruction-action comparison table; Completing the target action is used as the target guiding operation.

5. A voice intelligent interaction device with a virtual puppet, characterized in that: The voice intelligent interaction device with the virtual puppet comprises: A voice receiving module is used to obtain first text information according to the first voice information when receiving the first voice information input by the user, wherein the first text information is a plurality of text information with different recognition matching degrees; obtain first image information corresponding to the moment when the user inputs the first voice information, wherein the first image information includes image information of the user's lip movement; query a preset corpus according to the first text information to obtain a first target sentence; determine a second target sentence according to the first image information; and determine a target sentence according to the first target sentence and the second target sentence; An instruction determination module, used to determine a target instruction according to the target statement; A reply determination module is used to determine the interaction mode of the virtual 3D puppet according to the target instruction; when the interaction mode is the information reply mode, generate an information reply text and an information reply voice according to the target instruction; and display the information reply text and the information reply voice as a target guidance operation; The reply determination module is further used to, when the interaction mode is the wedding execution mode, determine the target virtual 3D puppet according to the target instruction; generate a wedding target action and a wedding target voice; and control the target virtual 3D puppet to perform the wedding in the wedding virtual scene according to the wedding target action and the wedding target voice; The operation execution module is used to control the virtual 3D doll to perform the target guidance operation in the virtual wedding scene to complete the voice interaction with the user.

6. A voice intelligent interaction device with a virtual puppet, characterized in that: The device includes: a memory, a processor, and a voice intelligent interaction program with a virtual puppet stored in the memory and executable on the processor, wherein the voice intelligent interaction program with the virtual puppet is configured to implement the voice intelligent interaction method with a virtual puppet as described in any one of claims 1 to 4.

7. A storage medium, characterized in that: The storage medium stores a program for intelligent voice interaction with a virtual puppet. When the program for intelligent voice interaction with a virtual puppet is executed by a processor, the method for intelligent voice interaction with a virtual puppet as described in any one of claims 1 to 4 is implemented.

Images