A dialogue processing method and device, electronic equipment and storage medium

Abstract

The application provides a dialogue processing method and device, electronic equipment and a computer readable storage medium; applied to a server; the method comprises the following steps: receiving the first voice dialogue information of a user sent by an intelligent voice device, wherein the first voice dialogue information is used to instruct a virtual character to execute a target task initiated by the user; obtaining an initial activity state of the virtual character when the user initiates the target task; determining a target activity state of the virtual character according to the target task and the initial activity state; sending first dialogue reply information of the target task to the intelligent voice device, wherein the first dialogue reply information comprises information obtained by the server by analyzing at least the target activity state through a large language model. Through the application, a dynamic narrative space can be created through generative content creation of the large language model, and the dynamic state analysis result driven by the large language model is fed back to the intelligent voice device, so that the intelligent voice device presents the generative chat feedback to the user.

Description

Technical Field

[0001] This application relates to the field of data processing, and more particularly to a dialogue processing method, apparatus, electronic device, and computer-readable storage medium. Background Technology

[0002] With the advancement of artificial intelligence technology, the demand for human-computer interaction systems in various application scenarios is gradually increasing, such as voice assistants and virtual agents. With the rapid development of deep learning technology, data-driven dialogue systems are emerging. Among related technologies, smart hardware products centered on voice dialogue primarily employ menu-based interaction via a Voice User Interface (VUI) to complete mechanical response interactions. Currently, with the increasing demands for user interaction experience, there is an urgent need to improve dialogue processing methods. Summary of the Invention

[0003] This application provides a dialogue processing method, apparatus, electronic device, and computer-readable storage medium that can create a dynamic narrative space through LLM generative content and feed back the results of LLM-driven dynamic state analysis to an intelligent voice device so that the intelligent voice device can present generative chat feedback to the user.

[0004] The technical solution of this application embodiment is implemented as follows:

[0005] This application provides a dialogue processing method applied to a server, including:

[0006] Receive first voice dialogue information from a user sent by a smart voice device, wherein the first voice dialogue information is used to instruct a virtual character to perform a target task initiated by the user;

[0007] Obtain the initial activity state of the virtual character when the user initiates the target task;

[0008] Based on the target task and the initial activity state, determine the target activity state of the virtual character;

[0009] Sending first dialogue response information for the target task to the intelligent voice device, wherein the first dialogue response information includes information obtained by the server through analysis of at least the target activity state using a large language model.

[0010] This application also provides a dialogue processing method applied to a smart voice device, including:

[0011] Obtain the user's first voice dialogue information, wherein the first voice dialogue information is used to instruct the virtual character to perform the target task initiated by the user;

[0012] Send the first voice dialogue information to the server;

[0013] The server receives a first dialogue response message for the target task, wherein the first dialogue response message includes information obtained by the server through analysis of the target activity state of the virtual character using a large language model.

[0014] This application provides a dialogue processing apparatus, which is applied to a server and includes:

[0015] The first receiving module is used to receive first voice dialogue information of a user sent by a smart voice device, wherein the first voice dialogue information is used to instruct a virtual character to perform the target task initiated by the user.

[0016] The first acquisition module is used to acquire the initial activity state of the virtual character when the user initiates the target task;

[0017] The first processing module is used to determine the target activity state based on the target task and the initial activity state;

[0018] The first sending module is used to send the first dialogue response information of the target task to the intelligent voice device, wherein the first dialogue response information includes information obtained by the server through analysis of the target activity state using a large language model.

[0019] In the above scheme, the first processing module is used to control the activity state of the virtual character to change from the initial activity state to the activity state indicated by the state identifier when the activity state indicated by the state identifier included in the target task is different from the initial activity state, and the initial activity state and the activity event included in the target task satisfy the state transition condition. The target activity state includes the activity state indicated by the state identifier.

[0020] In the above scheme, the first processing module is used to perform one of the following:

[0021] When the target activity status is in transit, after a first period of time, the activity status of the virtual character is controlled to change from the transit status to the on-site status. The transit status indicates that the virtual character is performing activities according to the activity event, but has not yet reached the destination included in the target task. The on-site status indicates that the virtual character has reached the destination.

[0022] When the target activity state is the on-site state, after a second period of time, the activity state of the virtual character is controlled to change from the on-site state to the en route state;

[0023] When the target activity state is the "on-site state", after a third period of time, the activity state of the virtual character is controlled to change from the "on-site state" to the "at-home state", wherein the "at-home state" indicates that the virtual character is located at the departure point.

[0024] In the above scheme, the first acquisition module is used to acquire the real-time activity status and real-time location information of the virtual character, wherein the real-time activity status includes being in transit or being on the ground.

[0025] The first processing module is used to analyze the real-time activity state and the real-time location information through the large language model to generate the first dialogue response information, wherein the real-time activity state includes the target activity state and / or the activity state after the target activity state has been transformed.

[0026] In the above scheme, the first dialogue reply information includes postcard text, wherein the postcard text includes one or more of the following: text corresponding to the real-time activity status and / or the real-time location information, and postcard images corresponding to the real-time location information.

[0027] In the above scheme, the first sending module is used to send the postcard text to the smart voice device in response to the virtual character's activity state being in transit and the virtual character leaving the scenic spot along the route to go to the destination included in the target task, or in response to the virtual character's activity state being in transit and the virtual character leaving the scenic spot along the route to go to the departure point.

[0028] In the above scheme, the first receiving module is used to receive the user's second voice dialogue information sent by the intelligent voice device;

[0029] The first processing module is configured to generate second dialogue response information based on the content indexed by the key information corresponding to the location information in the location information in the attraction list when the real-time location information of the virtual character is obtained in the location information included in the attraction list, and the key information of the user intent contained in the second voice dialogue information is the same as the key information corresponding to the location information included in the attraction list.

[0030] The first sending module is used to send the second dialogue response information to the intelligent voice device.

[0031] This application embodiment also provides a dialogue processing apparatus, which is applied to an intelligent voice device, including:

[0032] The second acquisition module is used to acquire the user's first voice dialogue information, wherein the first voice dialogue information is used to instruct the virtual character to perform the target task initiated by the user.

[0033] The second sending module is used to send the first voice dialogue information to the server;

[0034] The second receiving module is used to receive the first dialogue response information of the target task sent by the server, wherein the first dialogue response information includes information obtained by the server through analysis of the target activity state of the virtual character at least by a large language model.

[0035] In the above scheme, the first dialogue reply information includes postcard text, wherein the postcard text includes one or more of the following: text corresponding to the real-time activity status and / or real-time location information of the virtual character, and postcard images corresponding to the real-time location information.

[0036] In the above scheme, the second acquisition module is used to acquire the user's third voice dialogue information, and the third voice dialogue information is used to display the postcard text;

[0037] The presentation module is used to display the postcard image, which includes the postcard text, on the human-computer interaction interface of the smart voice device, and the output device is used to read the text aloud through speech synthesis.

[0038] In the above scheme, the second acquisition module is used to acquire the user's second voice dialogue information;

[0039] The second sending module is used to send the second voice dialogue information to the server;

[0040] The second receiving module is used to receive the second dialogue response information sent by the server, wherein the second dialogue response information includes information generated by the server through the large language model based on the content of the key information index corresponding to the location information contained in the attraction list, and the key information corresponding to the location information contained in the attraction list is the same as the key information of the user intent contained in the second voice dialogue information.

[0041] This application provides an electronic device, including:

[0042] Memory is used to store executable instructions or computer programs.

[0043] When a processor executes computer-executable instructions or computer programs stored in the memory, it implements a dialogue processing method provided in the embodiments of this application.

[0044] This application provides a computer-readable storage medium storing a computer program or computer-executable instructions, which, when executed by a processor, implements a dialogue processing method provided in this application.

[0045] This application provides a computer program product, including a computer program or computer executable instructions. When the computer program or computer executable instructions are executed by a processor, they implement a dialogue processing method provided in this application.

[0046] The embodiments of this application have the following beneficial effects:

[0047] The server receives the first voice dialogue information from the user sent by the intelligent voice device. This first voice dialogue information instructs the virtual character to perform the target task initiated by the user. The server then obtains the initial activity state of the virtual character when the user initiates the target task. Based on the target task and the initial activity state, the server determines the target activity state of the virtual character. Finally, the server sends the first dialogue response information for the target task to the intelligent voice device. This first dialogue response information includes information obtained by the server through analysis of the target activity state using a Large Language Model (LLM). Thus, in a voice interaction scenario, the server obtains the first dialogue response information by analyzing the target activity state of the virtual character through a Large Language Model (LLM). This first dialogue response information is the result of dynamic state analysis driven by a Large Language Model (LLM), giving the virtual character continuously evolving "digital life" characteristics and opening a new paradigm for emotional human-computer interaction. In this application, the intelligent voice device receives the first voice dialogue information initiated by the user and forwards it to the server. The server, based on the target task initiated by the user in the first voice dialogue information, creates a dynamic narrative space through LLM generative content and feeds back the dynamic state analysis results driven by LLM to the intelligent voice device, so that the intelligent voice device can present generative chat feedback to the user. In this way, in products with AI voice interaction intelligent hardware as the main body, the limitations of traditional VUI menu-style interaction and the limitations of traditional voice assistant mechanical response are broken through, realizing an emotional immersive experience that surpasses the GUI graphical interaction product. A deep gaming experience is achieved through multimodal perception and generative narrative. Attached Figure Description

[0048] Figure 1 This is a schematic diagram of the architecture of the dialogue processing system 100 provided in an embodiment of this application;

[0049] Figure 2A This is a schematic diagram of the structure of the electronic device 600 provided in the embodiments of this application;

[0050] Figure 2B This is a schematic diagram of the structure of the electronic device 700 provided in the embodiments of this application;

[0051] Figure 3 This is a flowchart illustrating the dialogue processing method provided in the embodiments of this application. Figure 1 ;

[0052] Figure 4 This is a second flowchart illustrating the dialogue processing method provided in the embodiments of this application;

[0053] Figure 5 This is a timing flowchart of the dialogue processing method provided in the embodiments of this application;

[0054] Figure 6 This is a schematic diagram of the dialogue processing architecture provided in an embodiment of this application;

[0055] Figure 7 This is a schematic diagram illustrating the content pushed by the server to MengUU as provided in this embodiment of the application.

[0056] Figure 8 This is a schematic diagram illustrating how a terminal device receives and displays content pushed by a server, as provided in an embodiment of this application.

[0057] Figure 9 This is a schematic diagram of the interface display of MengUU in different states provided in the embodiments of this application;

[0058] Figure 10 This is a schematic diagram of message push provided by the MengUU in the embodiments of this application. Detailed Implementation

[0059] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0060] In the following description, references are made to “some embodiments,” which describe a subset of all possible embodiments. However, it is understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0061] In this application embodiment, the terms "module" or "unit" refer to a computer program or part of a computer program that has a predetermined function and works with other related parts to achieve a predetermined goal, and can be implemented wholly or partially using software, hardware (such as processing circuitry or memory), or a combination thereof. Similarly, a processor (or multiple processors or memory) can be used to implement one or more modules or units. Furthermore, each module or unit can be part of an overall module or unit that includes the functionality of that module or unit.

[0062] In the following description, the terms “first, second, ...” are used merely to distinguish similar objects and do not represent a specific ordering of objects. It is understood that “first, second, ...” may be interchanged in a specific order or sequence where permitted, so that the embodiments of this application described herein can be implemented in an order other than that illustrated or described herein.

[0063] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0064] In related technologies, the current interaction method of game systems is mainly based on graphical user interface (GUI), including all mainstream personal computer (PC) games, mobile games, and console games. With the development and application of natural language processing (NLP) and LLM, some smart hardware will also realize conversational gameplay through VUI voice interaction. For example, many smart speakers or artificial intelligence (AI) conversational toys have built-in games such as idiom chain, werewolf game script murder, and role-playing games.

[0065] GUI-based game interaction can more fully and vividly showcase game visuals and effects, and better spread game content within communities through sharing methods such as pages / images, thereby achieving better dissemination, stickiness, and topicality. Therefore, compared to the abstract and difficult-to-spread VUI interaction, game systems will adopt GUI interaction more often.

[0066] For AI smart hardware products that primarily use voice dialogue, it is necessary to move beyond the limitations of VUI-based game interaction and incorporate the most mainstream GUI-based game interaction methods. This would allow the games on voice-interactive smart hardware products to move beyond basic stages such as word games and expand to a wider variety, similar to mobile games and computer games.

[0067] In view of this, embodiments of this application provide a dialogue processing method, apparatus, electronic device, and computer-readable storage medium, which can create a dynamic narrative space through LLM-generated content and feed back the LLM-driven dynamic state analysis results to an intelligent voice device for the intelligent voice device to present generative chat feedback to the user. The electronic device provided in this application embodiment can be implemented as a server or as an intelligent voice device. The following description uses an example of a server implementing the dialogue processing method provided in this application embodiment.

[0068] For example, see Figure 1 , Figure 1 This is a schematic diagram of the architecture of the dialogue processing system 100 provided in this application embodiment. To support a dialogue processing application, such as... Figure 1 As shown, the dialogue processing system 100 includes: a server 200, a network 300, an intelligent voice device 400 (e.g., various types of robots, voice assistants), and a terminal device 500. The intelligent voice device 400 and the terminal device 500 are connected to the server 200 through the network 300, which can be a local area network (LAN), a wide area network (WAN), or a combination of both. The terminal device 500 is a terminal associated with the user. Clients run on the intelligent voice device 400 and the terminal device 500. The clients can be of various types, such as clients related to real-time video display or browsers.

[0069] It should be noted that the technical solution provided in this application can be applied to various scenarios, such as AI voice dialogue scenarios like VUI intelligent interaction and smart speaker interaction.

[0070] Example, Figure 1 The server 200 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms. The intelligent voice device 400 can be various types of robots (e.g., remote-controlled robots, home intelligent robots, etc.) or smart speakers. The terminal device 500 can be a smartphone, tablet, laptop, desktop computer, smartwatch, in-vehicle terminal, etc., but is not limited to these. The intelligent voice device 400, terminal device 500, and server 200 can be directly or indirectly connected via wired or wireless communication, which is not limited in this embodiment.

[0071] The structure of the electronic device provided in the embodiments of this application will be described below. Taking the electronic device as a server as an example, see... Figure 2A , Figure 2A This is a schematic diagram of the structure of the electronic device 600 provided in the embodiments of this application. Figure 2A The illustrated electronic device 600 includes at least one processor 610, a memory 640, and at least one network interface 620. The various components in the electronic device 600 are coupled together via a bus system 630. It is understood that the bus system 630 is used to implement communication between these components. In addition to a data bus, the bus system 630 also includes a power bus, a control bus, and a status signal bus. However, for clarity, all buses are labeled as bus system 630 in Figure 2.

[0072] The processor 610 can be an integrated circuit chip with signal processing capabilities, such as a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc.

[0073] The memory 640 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid-state storage, hard disk drives, optical disk drives, etc. The memory 640 may optionally include one or more storage devices physically located away from the processor 610.

[0074] The memory 640 may include volatile memory or non-volatile memory, or both. The non-volatile memory may be read-only memory (ROM), and the volatile memory may be random access memory (RAM). The memory 640 described in this application embodiment is intended to include any suitable type of memory.

[0075] In some embodiments, memory 640 is capable of storing data to support various operations, examples of which include programs, modules, and data structures or subsets or supersets thereof, as illustrated below.

[0076] Operating system 641 includes system programs for handling various basic system services and performing hardware-related tasks, such as the framework layer, core library layer, and driver layer, for implementing various basic business functions and handling hardware-based tasks.

[0077] The network communication module 642 is used to reach other computing devices via one or more (wired or wireless) network interfaces 620, exemplary network interfaces 620 including: Bluetooth, WiFi, and Universal Serial Bus (USB), etc.

[0078] In some embodiments, the apparatus provided in this application can be implemented in software. Figure 2A A dialogue processing device 643 stored in memory 640 is shown. This device can be software in the form of programs and plug-ins, and includes the following software modules: a first receiving module 6431, a first sending module 6432, a first acquiring module 6433, and a first processing module 6434. These modules are logically linked and can therefore be arbitrarily combined or further separated according to the functions they implement. It should be noted that... Figure 2A For ease of explanation, all the above modules are shown at once, but this should not be construed as excluding the implementation of the dialogue processing device 643 which may only include the first receiving module 6431, the first sending module 6432, the first acquiring module 6433, and the first processing module 6434. The functions of each module will be described below.

[0079] The structure of the electronic device for implementing the dialogue processing method provided in the embodiments of this application will be further described below. Taking the electronic device 700 as an example, which is an intelligent voice device, see below. Figure 2B , Figure 2B This is a schematic diagram of the structure of the electronic device 700 provided in the embodiments of this application. Figure 2B The illustrated electronic device 700 includes a dialogue processing unit 755, which can be software in the form of programs and plug-ins, including the following software modules: a second acquisition module 7551, a second transmission module 7552, and a second receiving module 7553. These modules are logically linked and can therefore be arbitrarily combined or further separated according to the functions implemented. It should be noted that in Figure 2B For ease of explanation, all the above modules are shown at once, but this should not be construed as excluding the implementation of the dialogue processing device 755 which may only include the second acquisition module 7551, the second sending module 7552 and the second receiving module 7553. The functions of each module will be described below.

[0080] It should be noted that, Figure 2B The illustrated electronic device 700 includes a processor 710, a network interface 720, a bus system 740, an operating system 751, and a network communication module 752, all of which are related to... Figure 2A The corresponding modules contained therein have the same structure and the same function, and will not be described again in the embodiments of this application.

[0081] also, Figure 2B The illustrated electronic device 700 also includes a user interface 730. The user interface 730 includes one or more output devices 731 that enable the presentation of media content, including one or more speakers and / or one or more visual displays. The user interface 730 also includes one or more input devices 732, including user interface components that facilitate user input, such as a keyboard, mouse, microphone, touchscreen display, camera, other input buttons, and controls.

[0082] Figure 2B The memory 750 in the illustrated electronic device 700 also includes a presentation module 753 (e.g., a display screen) and an input processing module 754.

[0083] The presentation module 753 is configured to enable the output of information (e.g., a user interface for operating peripheral devices and displaying content and information) via one or more output devices 731 (e.g., speakers) associated with the user interface 730;

[0084] The input processing module 754 is used to detect and translate one or more user inputs or interactions from one or more input devices 732.

[0085] The dialogue processing method provided in this application will be specifically described below with reference to exemplary applications and implementations of the server provided in the embodiments of this application.

[0086] See Figure 3 , Figure 3 This is a flowchart illustrating the dialogue processing method provided in this application embodiment. The dialogue processing method described above is applied to a server and will be combined with... Figure 3 The steps shown are explained.

[0087] In step 101, the user's first voice dialogue information sent by the intelligent voice device is received, wherein the first voice dialogue information is used to instruct the virtual character to perform the target task initiated by the user.

[0088] Here, users interact with intelligent voice devices (such as MengUU, an intelligent voice dialogue device) through a client. MengUU communicates with a server, which executes the dialogue processing method. MengUU deploys virtual characters, which users can interact with through MengUU.

[0089] Here, the target task includes, but is not limited to, one or more of the following: activity events, destinations, location reporting, and information presentation. Activity events include, but are not limited to, travel events, such as "Let's go on a trip," "End the trip and go home," or "End the trip and go home after passing through one more attraction." Destinations include the destinations the activity events indicate the virtual character should reach. Location reporting includes real-time location reporting, such as voice location reporting commands like "Where are you?" or "Where to next?". Information presentation includes the presentation of relevant information during the virtual character's activities, and the presentation of relevant information before and / or after the virtual character's activities.

[0090] In step 102, the initial activity state of the virtual character when the user initiates the target task is obtained.

[0091] Here, when the user initiates the target task, that is, when the server receives the first voice dialogue information sent by the smart voice device, it checks the initial activity state (i.e., the current state) of the virtual character.

[0092] In step 103, the target activity state of the virtual character is determined based on the target task and the initial activity state.

[0093] Here, the initial activity state is determined based on the user-initiated target task to determine whether a state machine change is required. Finally, when a state change is needed, the target activity state is determined; otherwise, the initial activity state is maintained. This allows the LLM to generate voice chat feedback based on dynamic states, overcoming the limitations of traditional voice assistants' mechanical responses.

[0094] In step 104, the first dialogue response information of the target task is sent to the intelligent voice device, wherein the first dialogue response information includes information obtained by the server through analysis of the target activity state of the virtual character by the large language model.

[0095] Here, in a voice interaction scenario, the server analyzes the target activity state of the virtual character using a large language model to obtain the first dialogue response information. This first dialogue response information, driven by LLM-based dynamic state analysis, endows the virtual character with continuously evolving "digital life" characteristics, opening a new paradigm for emotional human-computer interaction. In this application, the intelligent voice device receives the first voice dialogue information initiated by the user and forwards it to the server. The server, based on the user's target task in the first voice dialogue information, creates a dynamic narrative space through LLM-based generative content and feeds back the LLM-driven dynamic state analysis results to the intelligent voice device, allowing the device to present generative chat feedback to the user. Thus, in products primarily based on AI voice interaction intelligent hardware, the limitations of traditional VUI's menu-style interaction and the mechanical responses of traditional voice assistants are overcome, achieving an emotionally immersive experience that surpasses GUI graphical interaction products. A deep gaming experience is achieved through multimodal perception and generative narrative.

[0096] In some embodiments, step 103 described above can be implemented as follows: when the activity state indicated by the status identifier contained in the target task is different from the initial activity state, and the initial activity state and the activity event contained in the target task satisfy the state transition condition, the activity state of the virtual character is controlled to change from the initial activity state to the activity state indicated by the status identifier, wherein the target activity state includes the activity state indicated by the status identifier.

[0097] Here, the state transition condition between the initial activity state and the activity events contained in the target task means that if both the event triggering and the condition verification are detected, then the state transition is executed.

[0098] The activity status of virtual characters includes: on the go, on the ground, and at home.

[0099] The "on the way" state indicates that the virtual character is performing an activity according to the event, but has not yet reached the destination included in the target task. For example, when MengUU selects a destination to travel, has left the body, but has not yet arrived at the destination, the state of MengUU on the way is MengUU's state.

[0100] The "on-site status" indicates the state in which the virtual character has arrived at its destination. For example, the state in which MengUU has arrived at the selected destination and is staying there to play is the "on-site status" of MengUU.

[0101] The "at-home" status indicates the virtual character's location at the point of origin. For example, when MengUU's inspiration has not left her body and she is not traveling, her status is "at-home".

[0102] Example 1: When the activity state (e.g., on the way) indicated by the status identifier of the target task (e.g., go on a trip) is different from the initial activity state (at home), and the state transition condition is met between the initial activity state (at home) and the activity event (e.g., go on a trip) included in the target task, control the virtual character's activity state to change from the at home state to the on the way state indicated by the status identifier.

[0103] Example 2: When the activity state (e.g., at home) indicated by the status identifier in the target task (e.g., returning home after a trip) is different from the initial activity state (on the way / on the ground), and the state transition condition is met between the initial activity state (on the way / on the ground) and the activity event (e.g., returning home after a trip) in the target task, the activity state of the virtual character is changed from the on the way / on the ground state to the at home state indicated by the status identifier.

[0104] Example 3: When the activity state indicated by the status identifier in the target task is the same as the initial activity state, the activity state of the virtual character remains unchanged.

[0105] Here, the state machine changes are controlled according to the current state. This condition-driven state transition mechanism not only ensures the logical rigor of the game world, but also creates a deep strategy space through structured event relationships. Based on this, the dialogue processing method provided in this application can be explored and evolved in more mainstream games.

[0106] In some embodiments, after controlling the virtual character's activity state to change from an initial activity state to an activity state indicated by a status identifier, one of the following may also be performed:

[0107] When the target activity status is in transit, after a first period of time, the virtual character's activity status is controlled to change from transit to on-site. The transit status indicates that the virtual character is performing activities according to the activity event, but has not yet reached the destination included in the target task. The on-site status indicates that the virtual character has reached the destination.

[0108] When the target activity status is in the on-site state, after the second time period, the virtual character's activity status is changed from the on-site state to the en route state.

[0109] When the target activity status is "on-site", after the third time period, the activity status of the virtual character is changed from "on-site" to "at home". The "at home" status indicates that the virtual character is located at the departure point.

[0110] Here, a state machine transition mechanism based on a timer algorithm is implemented to control state machine changes. This mechanism, based on strict timing control, ensures timing accuracy and improves synchronization and coordination capabilities. It should be noted that this application controls state machine changes by first controlling the state machine based on the current state, and then further incorporating a timer algorithm to continue controlling the state machine transition. This achieves an optimal balance between condition-driven and timing-driven approaches.

[0111] In some embodiments, before performing step 104 above, the process can also be carried out in the following manner:

[0112] Obtain the real-time activity status and real-time location information of the virtual character, wherein the real-time activity status includes being in transit or being on the ground;

[0113] The real-time activity status and real-time location information are analyzed by a large language model to generate the first dialogue response information. The real-time activity status includes the target activity status and / or the activity status after the target activity status is transformed.

[0114] Here, real-time location information includes the virtual character's real-time location information when performing activity events, including but not limited to latitude and longitude. The real-time activity status and real-time location information are used by the LLM to determine the virtual character's location (or approximate location), thereby generating the first dialogue response information (one or more of the following related to the determined location: sightseeing, attraction recommendations, postcard text, etc.).

[0115] Here, the current location longitude = (destination longitude - departure longitude) × departure time / t + departure longitude; the current location latitude = (destination latitude - departure latitude) × departure time / t + departure latitude.

[0116] In some embodiments, the first dialogue response information includes postcard text, wherein the postcard text includes one or more of the following: text corresponding to real-time activity status and / or real-time location information, and postcard images corresponding to real-time location information.

[0117] Here, the text on the postcard can be generated by the server by extracting key content from the set "Postcard Master List" and passing it through LLM; the Postcard Master List includes, but is not limited to: postcard name, postcard description text, postcard image, and the destination to which the image belongs.

[0118] Thus, based on the structured constraints of the "Postcard Master List" and the generative innovation of LLM, multimodal feature fusion was achieved, improving the personalized customization effect of postcards.

[0119] In some embodiments, step 104 described above can be implemented as follows: in response to the virtual character's activity state being in transit and the virtual character leaving the transit attractions to go to the destination included in the target task, or in response to the virtual character's activity state being in transit and the virtual character leaving the transit attractions to go to the departure point, a postcard text is sent to the smart voice device.

[0120] In some embodiments, the following process may also be performed: sending postcard text to a terminal device associated with the smart voice device so that the terminal device displays the postcard text.

[0121] Here, users interact with intelligent voice devices (such as MengUU, an intelligent voice dialogue device) through a client. MengUU communicates with the server and with the terminal device. When the service generates postcard text, users can send postcard text to MengUU and to the terminal device.

[0122] In some embodiments, after performing step 104 as described above, the process can also be carried out in the following manner:

[0123] Receive second voice dialogue information from the user sent by the intelligent voice device;

[0124] When the real-time location information of the acquired virtual character is in the location information contained in the attraction list, and the key information of the user intent contained in the second voice dialogue information is the same as the key information corresponding to the location information contained in the attraction list, the second dialogue response information is generated by the large language model based on the content indexed by the key information corresponding to the location information contained in the attraction list.

[0125] Send a second dialogue response to the smart voice device.

[0126] For example, in a voice interaction scenario, after the server receives the user's first voice dialogue information from the smart voice device, the user might chat with MengUU about travel-related experiences. When the user's voice conversation with MengUU touches on content that triggers travel-related intentions, the server extracts key content from the "Master Attractions List" / "List of Attractions" and generates real-time chat feedback through LLM. The Master Attractions List includes, but is not limited to: attractions, and the following information corresponding to each attraction: destination, distinctive description, and special events.

[0127] This application uses a list of attractions and an LLM (Local Management Model) to construct structured knowledge constraints and generative creative solutions, generating real-time travel dialogue feedback to enhance the real-time interactive experience.

[0128] See Figure 4 , Figure 4This is a flowchart illustrating the dialogue processing method provided in this application embodiment. The dialogue processing method described above is applied to intelligent voice devices and will be combined with... Figure 4 The steps shown are explained.

[0129] In step 201, the user's first voice dialogue information is obtained, wherein the first voice dialogue information is used to instruct the virtual character to perform the target task initiated by the user.

[0130] Here, users interact with intelligent voice devices (such as MengUU, an intelligent voice dialogue device) through a client. MengUU communicates with the server and executes the dialogue processing method. MengUU deploys virtual characters, which users can interact with through MengUU.

[0131] In step 202, the first voice dialogue information is sent to the server.

[0132] Here, after receiving the first voice dialogue information initiated by the user, MengUU can send the obtained first voice dialogue information to the server. The server uses a large language model to analyze at least the target activity state of the virtual character to obtain the first dialogue response information.

[0133] In step 203, the server receives the first dialogue response information of the target task, wherein the first dialogue response information includes information obtained by the server through analysis of the target activity state of the virtual character using a large language model.

[0134] Here, the server feeds back the first dialogue response information to MengUU. This first dialogue response information is the result of dynamic state analysis driven by LLM, which endows the virtual character with continuously evolving "digital life" characteristics, opening up a new paradigm for emotional human-computer interaction. In this application, the intelligent voice device receives the first voice dialogue information initiated by the user and forwards it to the server. Based on the target task initiated by the user in the first voice dialogue information, the server creates a dynamic narrative space through generative content of LLM and feeds back the dynamic state analysis results driven by LLM to the intelligent voice device, so that the intelligent voice device can present generative chat feedback to the user. In this way, in products with AI voice interaction intelligent hardware as the main body, the limitations of traditional VUI menu-style interaction and the limitations of traditional voice assistant mechanical response are broken through, realizing an emotional immersive experience that surpasses the GUI graphical interaction product, and achieving a deep gaming experience through multimodal perception and generative narrative.

[0135] In some embodiments, the first dialogue response information includes postcard text, wherein the postcard text includes one or more of the following: text corresponding to the virtual character's real-time activity status and / or real-time location information, and postcard images corresponding to the real-time location information.

[0136] In some embodiments, after performing step 203 above, the following processing may also be performed:

[0137] Obtain the user's third voice dialogue information, which is used to display the postcard text;

[0138] Display the postcard text, including the postcard image, on the human-computer interaction interface of the smart voice device; read the text aloud through speech synthesis.

[0139] Here, when a smart voice device displays information fed back from the server, the display of the information can be triggered by the user's voice.

[0140] For example, the text of the postcard can be converted into speech output through a text-to-speech (TTS) controller, and the image of the postcard can be displayed on the human-computer interaction interface of a smart voice device.

[0141] In some embodiments, after performing step 203 above, the following processing may also be performed:

[0142] Obtain the user's second voice conversation information;

[0143] Send a second voice dialogue message to the server;

[0144] The server receives a second dialogue response message, which includes information generated by the server using a large language model based on the key information index corresponding to the location information contained in the attraction list. The key information corresponding to the location information contained in the attraction list is the same as the key information of the user intent contained in the second voice dialogue message.

[0145] Here, in a voice interaction scenario, after MengUU sends the user's first voice dialogue information to the server, the user may chat with MengUU about travel-related experiences. At this time, MengUU obtains the user's second voice dialogue information and sends it to the server. When the user and MengUU discuss content that triggers travel-related intentions, the server extracts key content from the "Overall Attractions List" / "Attractions List" and generates real-time chat feedback through LLM. At this point, MengUU receives the second dialogue response information from the server. This application constructs a structured knowledge constraint + generative creative solution based on the attraction list and LLM to generate real-time travel dialogue feedback, improving the real-time interactive experience.

[0146] The following describes an exemplary application of the embodiments of this application in a real-world application scenario. This exemplary application describes the specific implementation process of the dialogue processing method in a voice interaction scenario.

[0147] In some embodiments, see Figure 5 , Figure 5 This is a timing flowchart of the dialogue processing method provided in the embodiments of this application. The following will be combined with... Figure 5 Explain the specific implementation process.

[0148] Phase 1: MengUU receives the first voice dialogue information input by the user and sends it to the server. Here, the first voice dialogue information includes the user's voice commands.

[0149] For example, the first voice dialogue information includes, but is not limited to: "Let's go on a trip", "Where are you traveling?", "Going home after the trip", "Other gameplay dialogues", etc.

[0150] Phase 2: The server receives the first voice dialogue information, generates the first dialogue response information through LLM, and sends the first dialogue response information back to MengUU.

[0151] For example, after receiving the first voice dialogue information, the server checks the current status of the virtual character (e.g., at home, on the go, or on the spot).

[0152] Here, when the target task carried by the first voice dialogue information (such as "Let's go on a trip") and Meng UU's current state is at home, if Meng UU hears "Let's go on a trip" at home, the state transition condition is met. Then, the game state machine is activated to switch Meng UU's activity state from at home to on the way.

[0153] Here, when the target task carried by the first voice dialogue information (such as ending the trip and going home) and Meng UU's current state is on the way / on the ground, if Meng UU hears "ending the trip and going home" while on the way / on the ground, the state transition condition is met. Then, the game state machine is activated to switch Meng UU's activity state from on the way / on the ground to the home state, and the state switch is completed.

[0154] Here, when the target task carried by the first voice dialogue information (such as "Let's go on a trip") and MengUU's current state is "on the way", if MengUU hears "Let's go on a trip" while on the way, the state transition condition is not met, so the activity state of MengUU is kept unchanged.

[0155] The system analyzes real-time activity status and location information using LLM to generate a first dialogue response (one or more of the following related to the determined location: sightseeing, attraction recommendations, postcard text, etc.). This first dialogue response is then sent to MengUU. Upon receiving the response, MengUU responds to the user's commands via TTS and displays the status on the screen.

[0156] In some embodiments, the state machine changes can be further controlled according to a timer algorithm.

[0157] The dwell time t1 of MengUU satisfies the following formula: minimum dwell time < t1 < maximum dwell time.

[0158] The duration t of the en route state satisfies the following formula: t = straight-line distance between the starting point and the destination / current speed. The latitude and longitude of the starting point and the destination can be extracted from the set "Destination Master Table" to calculate the distance between them.

[0159] While en route, users might chat with MengUU about their travel experiences. When a user's voice conversation with MengUU touches on topics that trigger travel-related intentions, MengUU needs to know its approximate location. This current location needs to be obtained as latitude and longitude coordinates so that the LLM (Local Management Module) can determine its approximate location and generate related responses.

[0160] In some embodiments, the parameters involved in MengUU's travel process can be extracted from a predefined "Variable Summary Table". For example, the Variable Summary Table is as follows:

[0161]

[0162]

[0163] Variable Summary Table

[0164] This application uses a table configuration method to allocate the extraction of various data. The parameters of the table configuration can be flexibly set according to actual needs. This application does not specifically limit them. In this way, not only can the content of each attribute parameter be flexibly configured, but the data acquisition efficiency is also improved.

[0165] In some embodiments, the destination selection formula is: range radius r = current vitality value × vitality value range.

[0166] In some embodiments, the destinations encountered by MengUU during her travels can be extracted from a predefined "Destination Master Table". The Destination Master Table includes, but is not limited to, locations and the following information corresponding to those locations: location (latitude and longitude), level requirements, affiliated unit, and weight.

[0167] Here, vitality can be understood as an attribute that affects the flight distance of MengUU's inspiration. Each point of vitality represents a fixed flight distance that MengUU can fly.

[0168] In some embodiments, the vitality value consumption formula is as follows: starting from the start of MengUU, 1 vitality value is consumed every n minutes, where n = vitality value range / current speed, and the timer stops when the destination is reached.

[0169] In some embodiments, the formula for the current speed of the UU in transit is: v = initial speed × (1 - fatigue level × fatigue level decay).

[0170] Here, the initial speed can be understood as a hidden attribute, a fixed value, which affects the duration of MengUU's on-the-go state after departure.

[0171] Here, fatigue can be understood as a parameter that affects the actual speed of MengUU's flight. The actual speed will decrease as MengUU's fatigue increases from the initial speed.

[0172] This application controls state machine changes by first controlling the state machine changes based on the current state, and then further incorporating a timer algorithm to continue controlling the state machine changes. In this way, an optimal balance between condition-driven and time-driven approaches is achieved.

[0173] Phase 3: The server indexes the corresponding postcard image, generates the postcard text through LLM, obtains the postcard text, and sends the postcard text to MengUU and to the terminal device.

[0174] Here, the server sends a postcard text to MengUU. After receiving the postcard text, MengUU reads the postcard text aloud via TTS and displays the postcard image on the screen. The server then sends a postcard text to the terminal device. After receiving the postcard text, the terminal device displays the postcard image and text on the screen.

[0175] In a feasible dialogue processing architecture, see Figure 6 , Figure 6 This is a schematic diagram of the dialogue processing architecture provided in the embodiments of this application. The following will combine... Figure 6 Explain the specific implementation process.

[0176] MengUU side: It serves as an entry point for voice command interaction, supports game screen presentation, and also serves as a voice output for LLM-generated content.

[0177] Server-side: Supports game system algorithm calculation, game state machine operation, and generation and feedback of game interactive content.

[0178] Terminal devices such as mobile phones: support auxiliary presentation of game screen.

[0179] In a feasible scenario, MengUU receives voice commands from users and sends them to the server. It then receives postcard text from the server, enabling a GUI display of the postcard image and text read aloud via TTS. The server can also send the postcard text back to the mobile phone, allowing users to see game-related visuals on their devices.

[0180] In a feasible scenario, see Figure 7 , Figure 7This is a schematic diagram illustrating how MengUU receives and presents content pushed by the server, as provided in an embodiment of this application. The following will be combined with... Figure 7 Explain the specific implementation process.

[0181] MengUU receives postcard text pushed by the server. Users can trigger the display of the postcard text by using voice commands (such as "open push content"). At this time, MengUU displays the postcard image on the screen and reads the postcard text through TTS.

[0182] In a feasible scenario, see Figure 8 , Figure 8 This is a schematic diagram illustrating how a terminal device receives and displays content pushed by a server, as provided in an embodiment of this application. The following will be combined with... Figure 8 Explain the specific implementation process.

[0183] Users can see the game's visual aids on their mobile devices. The first area of ​​the screen displays a postcard image, while the second area displays the postcard text generated by LLM based on key information from the game system's postcard configuration table.

[0184] In a feasible scenario, see Figure 9 , Figure 9 This is a schematic diagram illustrating the interface display of the cute UU in different states according to an embodiment of this application. The following will be combined with... Figure 9 Explain the specific implementation process.

[0185] For example, while en route, a user might chat with MengUU about their travel experiences. When the user's voice conversation with MengUU touches on content that triggers travel-related intentions, MengUU needs to know its approximate location at that moment. For example, the server would provide MengUU's activity status and approximate location. Figure 9 Image A shows the interface indicator for MengUU when it's in transit. MengUU can play TTS voice messages (the server generates chat feedback via LLM, including but not limited to approximate location and transit status). After 3 seconds, it redirects to the dual-view interface (MengUU's default display interface), enabling navigation to the travel page.

[0186] For example, when in a local state, a user may chat with MengUU about travel-related experiences. When the user and MengUU have a voice conversation that triggers travel-related intentions, the game system will extract the key content from the set "Attractions List" and generate chat feedback through LLM. Figure 9 Image B in the image shows the interface icon for MengUU's location status. MengUU can play TTS voice messages (the server generates chat feedback via LLM, including but not limited to destination, location status, etc.). After 3 seconds, it redirects to the dual-view interface (MengUU's default display interface), enabling navigation to the travel page.

[0187] For example, when the "on the go / on the ground" status changes to "at home" status, the user asks MengUU where she is currently. Figure 9 Image C in the image shows the interface icon for MengUU in a "at home" state. MengUU can play TTS voice messages (including but not limited to "at home" status). After 3 seconds, it will redirect to the dual-view interface (MengUU's default display interface).

[0188] It should be noted that all information on the interface is provided by the backend server and is information that already exists in the backend. Here, the content displayed on the interface is explained based on whether there are unread messages when the device is in the local state. Figure 9 The diagram in Figure D shows the interface display when there are unread messages. Figure 9 The diagram E shows the interface when there are no unread messages. Whether there are unread messages can be indicated by the message / gift icon on the interface.

[0189] In a feasible scenario, see Figure 10 , Figure 10 This is a schematic diagram of message push notification provided by the MengUU app in this embodiment of the application. The following will combine... Figure 10 Explain the specific implementation process.

[0190] Postcard push notifications are an important part of the user experience on MengUU, and this application includes a series of animated emoticons. Other push notifications are sent silently in the background and read by the user with a short press.

[0191] MengUU's work status includes, but is not limited to: active, on standby, and dormant.

[0192] When a new message arrives, the system enters an active state; it then checks if the message is a postcard. If so, it proceeds with the notification interaction process; otherwise, it waits in standby mode for the user to read the message.

[0193] The reminder interaction flow is as follows: MessageB (without sound) plays in a loop while vibrating for 0.5 seconds, then enters standby mode after 5 minutes. In standby mode, messageB.Bin (the aforementioned emoticon) continues to play in a loop, then enters sleep mode. In sleep mode, a static wallpaper of messageB is displayed. Each playback / display in the reminder interaction flow is followed by a waiting phase for user interaction.

[0194] User operations include, but are not limited to, operations on the following components of the MengUU: AI dialogue button, intercom button, power button, and inertial measurement unit (IMU).

[0195] A short press of the AI ​​dialogue button triggers a check to determine if it's a postcard. If it is, the user proceeds to display the postcard; otherwise, they proceed to determine if a payment reminder message has been sent. Here, only the first short press of the AI ​​dialogue button after a message arrives "reads the message"; the rest of the user's interaction logic remains consistent with the original.

[0196] Postcard display process: Play the messageA.bin emoticon (the emoticon of an opened letter). The local TTS message reads, "I prepared a little gift for you while we were apart~", accompanied by the audio [postcard.mp3]. This is followed by a 0.5-second vibration, displaying the postcard image pushed from the backend, and playing the background TTS voice message. If the user does not interact, it automatically switches to the next postcard; alternatively, the user can short-press the AI ​​dialogue button to "skip the song" and play the next postcard. When there are multiple postcards, they are played one at a time according to the rules. If the user does not interact during this time, it automatically switches to the next postcard; alternatively, the user can short-press the AI ​​dialogue button to "skip the song" until all postcards have been read.

[0197] Payment Reminder Message Determination Process: If it's a paid reminder message, it will remind you that your pet's pass needs renewal. Expiration date: YYYY-MM-DD. After this sequence finishes playing, the number of paid messages in stock will decrease by 1. The app download QR code will be displayed. You can also play the audio [renew.mp3] at this time, for example, "Without a pass, my pet can't travel in the human world. Quickly scan the QR code below to renew my pass, Master!"

[0198] After the above message is played, the last page will still be displayed for 5 minutes before entering active mode; then, when entering standby mode, the default standby animation wallpaper will be restored.

[0199] The message push process provided in this application for MengUU enables dynamic information delivery and transforms abstract notifications into concrete emotional expressions (such as different emoticons), reducing the time users spend understanding the push intent. This dynamic feedback + emotional expression approach achieves a balance between functionality and emotionality, improving the efficiency of user interaction perception.

[0200] The dialogue processing method provided in this application, through VUI voice interaction combined with LLM generative content, enables gameplay similar to that of complex traditional graphical interface games like "Travel Frog" on products primarily based on AI voice interaction smart hardware. MengUU, as a smart hardware product focused on AI voice dialogue, is not limited to the traditional VUI interactive games like idiom relay games. Instead, it incorporates gameplay elements from mainstream mobile games. Through state machines, algorithmic formulas, LLM prompt control, and various device-side displays and accompanying applications (Apps), it fully explores the scalability and possibilities of large-scale voice smart hardware in game interaction and game systems, and can be used to explore and evolve towards more mainstream game types in the future.

[0201] The following description continues to illustrate the exemplary structure of the dialogue processing device 643 provided in the embodiments of this application as a software module. In some embodiments, such as Figure 2A As shown, the software modules stored in the dialogue processing device 643 in the memory 640 may include: a first receiving module 6431, a first sending module 6432, a first acquiring module 6433, and a first processing module 6434. The first receiving module 6431 is used to receive first voice dialogue information from a user sent by a smart voice device, wherein the first voice dialogue information is used to instruct a virtual character to perform a target task initiated by the user; the first acquiring module 6433 is used to acquire the initial activity state of the virtual character when the user initiates the target task; the first processing module 6434 is used to determine the target activity state of the virtual character based on the target task and the initial activity state; the first sending module 6432 is used to send first dialogue response information of the target task to the smart voice device, wherein the first dialogue response information includes information obtained by the server through analysis of at least the target activity state using a large language model.

[0202] In some embodiments, the first processing module 6434 is configured to control the activity state of the virtual character to change from the initial activity state to the activity state indicated by the state identifier when the activity state indicated by the state identifier contained in the target task is different from the initial activity state, and the initial activity state and the activity event contained in the target task satisfy the state transition condition, wherein the target activity state includes the activity state indicated by the state identifier.

[0203] In some embodiments, the first processing module 6434 is configured to perform one of the following:

[0204] When the target activity status is in transit, after a first period of time, the virtual character's activity status is controlled to change from transit to on-site. The transit status indicates that the virtual character is performing activities according to the activity event, but has not yet reached the destination included in the target task. The on-site status indicates that the virtual character has reached the destination.

[0205] When the target activity status is in the on-site state, after the second time period, the virtual character's activity status is changed from the on-site state to the en route state.

[0206] When the target activity status is "on-site", after the third time period, the activity status of the virtual character is changed from "on-site" to "at home". The "at home" status indicates that the virtual character is located at the departure point.

[0207] In some embodiments, the first acquisition module 6433 is used to acquire the real-time activity status and real-time location information of the virtual character, wherein the real-time activity status includes being in transit or being on the ground.

[0208] The first processing module 6434 is used to analyze the real-time activity status and real-time location information through a large language model and generate the first dialogue response information, wherein the real-time activity status includes the target activity status and / or the activity status after the target activity status is transformed.

[0209] In some embodiments, the first dialogue response information includes postcard text, wherein the postcard text includes one or more of the following: text corresponding to real-time activity status and / or real-time location information, and postcard images corresponding to real-time location information.

[0210] In some embodiments, the first sending module 6432 is configured to send postcard text to a smart voice device in response to the virtual character's activity state being in transit and the virtual character leaving a scenic spot along the route to go to the destination included in the target task, or in response to the virtual character's activity state being in transit and the virtual character leaving a scenic spot along the route to go to the departure point.

[0211] In some embodiments, the first sending module 6432 is used to send postcard text to a terminal device associated with the smart voice device so that the terminal device displays the postcard text.

[0212] In some embodiments, the first receiving module 6431 is used to receive second voice dialogue information of the user sent by the intelligent voice device; the first processing module 6434 is used to generate second dialogue response information based on the content of the index of the key information corresponding to the location information in the location information in the attraction list when the real-time location information of the acquired virtual character is in the location information contained in the attraction list, and the key information of the user's intent contained in the second voice dialogue information is the same as the key information corresponding to the location information contained in the attraction list through a large language model; the first sending module 6432 is used to send the second dialogue response information to the intelligent voice device.

[0213] The following description continues to illustrate the exemplary structure of the dialogue processing device 755 provided in the embodiments of this application as a software module. In some embodiments, such as Figure 2B As shown, the software modules stored in the dialogue processing device 755 in the memory 750 may include: a second acquisition module 7551, a second sending module 7552, and a second receiving module 7553.

[0214] The second acquisition module 7551 is used to acquire the user's first voice dialogue information, wherein the first voice dialogue information is used to instruct the virtual character to perform the target task initiated by the user.

[0215] The second sending module 7552 is used to send the first voice dialogue information to the server;

[0216] The second receiving module 7553 is used to receive the first dialogue response information of the target task sent by the server, wherein the first dialogue response information includes information obtained by the server through analysis of the target activity state of the virtual character at least by a large language model.

[0217] In some embodiments, the first dialogue response information includes postcard text, wherein the postcard text includes one or more of the following: text corresponding to the virtual character's real-time activity status and / or real-time location information, and postcard images corresponding to the real-time location information.

[0218] In some embodiments, the second acquisition module 7551 is used to acquire the user's third voice dialogue information, which is used to display the postcard text.

[0219] The device also includes: a presentation module 753 for displaying the postcard image, which is part of the postcard text, on the human-computer interaction interface of the smart voice device; and an output device 731 for broadcasting the text via speech synthesis.

[0220] In some embodiments, the second acquisition module 7551 is used to acquire the user's second voice dialogue information; the second sending module 7552 is used to send the second voice dialogue information to the server; and the second receiving module 7553 is used to receive the second dialogue response information sent by the server, wherein the second dialogue response information includes information generated by the server through a large language model based on the content of the key information index corresponding to the location information contained in the attraction list, and the key information corresponding to the location information contained in the attraction list is the same as the key information of the user's intent contained in the second voice dialogue information.

[0221] It should be noted that the description of the apparatus in this application is similar to the description of the method embodiments described above, and has similar beneficial effects as the method embodiments; therefore, it will not be repeated. For any technical details not covered in the dialogue processing apparatus provided in this application, please refer to... Figure 3 ,or Figure 4 The meaning is understood in accordance with the description of any of the accompanying drawings.

[0222] This application provides a computer program product, which includes a computer program or computer-executable instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer-executable instructions from the computer-readable storage medium and executes the computer-executable instructions, causing the electronic device to perform the dialogue processing method described above in this application.

[0223] This application provides a computer-readable storage medium storing computer-executable instructions or a computer program. When the computer-executable instructions or the computer program are executed by a processor, the processor will execute the dialogue processing method provided in this application. For example, ... Figure 3 ,or Figure 4 The dialogue processing method is shown.

[0224] In some embodiments, the computer-readable storage medium may be a memory such as ferroelectric random access memory (FRAM), ROM, programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), flash memory, magnetic surface memory, optical disc, or compact disc read-only memory (CD-ROM); or it may be a device that includes one or any combination of the above-mentioned memories.

[0225] In some embodiments, computer-executable instructions may take the form of programs, software, software modules, scripts, or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as stand-alone programs or as modules, components, subroutines, or other units suitable for use in a computing environment.

[0226] As an example, computer-executable instructions may, but do not necessarily, correspond to files in a file system. They may be stored as part of a file that holds other programs or data, for example, in one or more scripts in a Hyper Text Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple co-located files (e.g., files that store one or more modules, subroutines, or code sections).

[0227] As an example, computer-executable instructions can be deployed to execute on a single electronic device, or on multiple electronic devices located at one location, or on multiple electronic devices distributed across multiple locations and interconnected via a communication network.

[0228] The above are merely embodiments of this application and are not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, and improvements made within the spirit and scope of this application are included within the scope of protection of this application.

Claims

1. A dialog processing method characterized by, The method is applied to a server, and the method includes: Receive first voice dialogue information from a user sent by a smart voice device, wherein the first voice dialogue information is used to instruct a virtual character to perform a target task initiated by the user; Obtain the initial activity state of the virtual character when the user initiates the target task; Based on the target task and the initial activity state, determine the target activity state of the virtual character; The real-time activity status and real-time location information of the virtual character are obtained, wherein the real-time activity status includes being in transit or on the ground, and the real-time activity status includes the target activity status and / or the activity status after the target activity status is transformed. The server sends a first dialogue response message for the target task to the intelligent voice device, wherein the first dialogue response message includes information obtained by the server through analysis of the real-time activity status and real-time location information using a large language model.

2. The method of claim 1, wherein, Determining the target activity state of the virtual character based on the target task and the initial activity state includes: When the activity state indicated by the status identifier contained in the target task is different from the initial activity state, and the initial activity state and the activity event contained in the target task satisfy the state transition condition, the activity state of the virtual character is controlled to change from the initial activity state to the activity state indicated by the status identifier, wherein the target activity state includes the activity state indicated by the status identifier.

3. The method of claim 2, wherein, After the virtual character's activity state is changed from the initial activity state to the activity state indicated by the state identifier, it includes one of the following: When the target activity status is in transit, after a first period of time, the activity status of the virtual character is controlled to change from the transit status to the on-site status. The transit status indicates that the virtual character is performing activities according to the activity event, but has not yet reached the destination included in the target task. The on-site status indicates that the virtual character has reached the destination. When the target activity state is the on-site state, after a second period of time, the activity state of the virtual character is controlled to change from the on-site state to the en route state; When the target activity state is the "on-site state", after a third period of time, the activity state of the virtual character is controlled to change from the "on-site state" to the "at-home state", wherein the "at-home state" indicates that the virtual character is located at the departure point.

4. The method according to claim 1, characterized in that, The first dialogue response information includes postcard text, wherein the postcard text includes one or more of the following: text corresponding to the real-time activity status and / or the real-time location information, and postcard images corresponding to the real-time location information.

5. The method according to claim 4, characterized in that, Sending the first dialogue response information for the target task to the intelligent voice device includes: In response to the virtual character's activity status being "on the way" and the virtual character leaving the scenic spot along the way to head to the destination included in the target task, or in response to the virtual character's activity status being "on the way" and the virtual character leaving the scenic spot along the way to head to the departure point, the postcard text is sent to the smart voice device.

6. The method according to claim 1, characterized in that, After sending the first dialogue response information for the target task to the intelligent voice device, the process includes: Receive the user's second voice dialogue information sent by the intelligent voice device; When the real-time location information of the virtual character is within the location information contained in the attraction list, and the key information of the user intent contained in the second voice dialogue information is the same as the key information corresponding to the location information contained in the attraction list, the second dialogue response information is generated by the large language model based on the content indexed by the key information corresponding to the location information contained in the attraction list. Send the second dialogue response information to the intelligent voice device.

7. A dialogue processing method, characterized in that, The method is applied to a smart voice device, and the method includes: Obtain the user's first voice dialogue information, wherein the first voice dialogue information is used to instruct the virtual character to perform the target task initiated by the user; Send the first voice dialogue information to the server; The server receives a first dialogue response message for the target task, wherein the first dialogue response message includes information obtained by the server through analysis of the real-time activity status and real-time location information of the virtual character using a large language model, wherein the real-time activity status includes a state in transit or a state on the ground, and the real-time activity status includes the target activity status of the virtual character and / or the activity status after the target activity status has been converted.

8. The method according to claim 7, characterized in that, The first dialogue response information includes postcard text, wherein the postcard text includes one or more of the following: text corresponding to the virtual character's real-time activity status and / or real-time location information, and postcard images corresponding to the real-time location information.

9. The method according to claim 8, characterized in that, After receiving the first dialogue response information for the target task sent by the server, the process includes: Obtain the user's third voice dialogue information, which is used to display the postcard text; The postcard image, including the postcard text, is displayed on the human-computer interaction interface of the intelligent voice device; The text is read aloud using speech synthesis.

10. The method according to claim 9, characterized in that, After receiving the first dialogue response information for the target task sent by the server, the process includes: Obtain the user's second voice dialogue information; Send the second voice dialogue information to the server; The server receives a second dialogue response message, wherein the second dialogue response message includes information generated by the server based on the key information index corresponding to the location information contained in the attraction list through the large language model, and the key information corresponding to the location information contained in the attraction list is the same as the key information of the user intent contained in the second voice dialogue message.

11. A dialogue processing apparatus, characterized in that, The device is used in a server, and the device includes: The first receiving module is used to receive first voice dialogue information of a user sent by a smart voice device, wherein the first voice dialogue information is used to instruct a virtual character to perform the target task initiated by the user. The first acquisition module is used to acquire the initial activity state of the virtual character when the user initiates the target task; The first processing module is used to determine the target activity state of the virtual character based on the target task and the initial activity state; The first acquisition module is further configured to acquire the real-time activity status and real-time location information of the virtual character, wherein the real-time activity status includes a state in transit or a state on the ground, and the real-time activity status includes the target activity status and / or the activity status after the target activity status has been converted. The first sending module is used to send the first dialogue response information of the target task to the intelligent voice device, wherein the first dialogue response information includes information obtained by the server through analysis of the real-time activity status and real-time location information by a large language model.

12. A dialogue processing device, characterized in that, The device is used in a smart voice device, and the device includes: The second acquisition module is used to acquire the user's first voice dialogue information, wherein the first voice dialogue information is used to instruct the virtual character to perform the target task initiated by the user. The second sending module is used to send the first voice dialogue information to the server; The second receiving module is used to receive the first dialogue response information of the target task sent by the server, wherein the first dialogue response information includes information obtained by the server through analysis of the real-time activity status and real-time location information of the virtual character by a large language model, wherein the real-time activity status includes a state in transit or a state on the ground, and the real-time activity status includes the target activity status of the virtual character and / or the activity status after the target activity status has been converted.

13. An electronic device, characterized in that, include: Memory is used to store executable instructions or computer programs. A processor, when executing computer-executable instructions or computer programs stored in the memory, implements the dialogue processing method according to any one of claims 1 to 10.

14. A computer-readable storage medium storing computer-executable instructions or a computer program, characterized in that, When the computer-executable instructions or computer program are executed by a processor, the dialogue processing method according to any one of claims 1 to 10 is implemented.

Images