Digital entertainment interaction method and device based on intelligent agent and storage medium

Abstract

The invention discloses an agent-based digital entertainment terminal interaction method and device and a storage medium, and the method comprises the steps: creating an agent with a semantic analysis function, and setting the agent as an access point for controlling a large model of a digital entertainment terminal; the digital entertainment terminal obtains a voice instruction, identifies the voice instruction as a corresponding broadcast control text, and uploads the broadcast control text to the large model; the large model calls the intelligent agent to perform semantic analysis on the broadcast control text and generates corresponding return information according to a semantic analysis result, and the large model controls the digital entertainment terminal to execute corresponding operation according to the return information. According to the invention, the intention of the voice instruction of the user can be accurately recognized, continuous voice interaction and voice fuzzy request can be realized, and the user experience is greatly improved.

Description

Technical Field

[0001] This application relates to the field of digital entertainment technologies, and specifically relates to an agent-based digital entertainment interaction method, apparatus, and storage medium. Background Art

[0002] With the rapid development of artificial intelligence technologies, voice interaction has been widely applied in multiple fields such as song ordering in digital entertainment venues, intelligent services in bank lobbies, and online intelligent customer service. Currently, the commonly adopted fixed-form voice interaction in the industry is to first systematically classify the problems and human-computer interaction scenarios involved in the industry, customize fixed-form templates, and then convert the voice into text through automatic speech recognition (ASR) technology. Based on the matching degree between the text and the preset sentences, a feedback result with a relatively high matching degree is output.

[0003] Existing voice interaction methods also have significant limitations when applied to digital entertainment venues. First, the voice recognition accuracy is low, sensitive to accents, dialects, or background noise, and keywords are easily misrecognized (e.g., "Qilixiang" misrecognized as "Qilixiang"), resulting in failed song ordering. Second, the multi-round interaction experience is poor. The user's dialogue with the system can only issue clear instructions sentence by sentence, and the system cannot optimize subsequent responses based on historical interaction content, resulting in a mechanical and rigid interaction process and making it difficult to form a smooth and natural dialogue experience. In addition, the ability to handle fuzzy requests is weak. When the user makes some expressions lacking clear song information, the system can only match fixed sentences, cannot understand the ambiguity of semantics, and cannot accurately respond, and must rely on the user to supplement precise information to complete the song ordering operation, greatly limiting the convenience and intelligence of the user experience. Summary of the Invention

[0004] In view of the above problems, this application provides an agent-based digital entertainment terminal interaction method for solving the technical problem of weak voice interaction processing ability of the above digital entertainment terminal.

[0005] To achieve the above object, this application provides an agent-based digital entertainment terminal interaction method, including the following steps:

[0006] Create and define an agent, and associate the agent with the access point of the large model;

[0007] The digital entertainment terminal obtains a voice instruction from the user and sends the voice instruction to the agent or the voice conversion module;

[0008] The agent or the voice conversion module recognizes the voice instruction as a corresponding instruction text, the agent calls the large model to perform semantic analysis on the instruction text, and the agent generates a return message according to its definition and the semantic analysis result and sends it to the digital entertainment terminal;

[0009] The digital entertainment terminal performs corresponding operations based on the returned information.

[0010] Furthermore, defining the intelligent agent includes: defining the identification domain of the intelligent agent as the digital entertainment domain, defining the triggering style and return information format of the intelligent agent, wherein the triggering style includes broadcast control requests and on-demand requests.

[0011] Furthermore, defining the recognition domain of the intelligent agent as the digital entertainment domain includes: optimizing the recognition domain of the intelligent agent through prompt words, and optimizing the recognition domain of the intelligent agent through prompt words includes at least: excluding or transforming semantics that are prone to errors in the digital entertainment domain.

[0012] Furthermore, the returned information format includes a list of selected multimedia resources and identifiers for different broadcast control functions; each identifier corresponds to a broadcast control instruction in the digital entertainment terminal.

[0013] Furthermore, the broadcast control commands include any one or more of the following: play, pause, skip song, and repeat.

[0014] Furthermore, the intelligent agent or speech conversion module recognizes the voice command as the corresponding command text, including the following steps:

[0015] The intelligent agent or speech conversion module preprocesses the speech command. The preprocessing includes scaling the volume of the speech command to a preset volume value and merging or splitting adjacent audio segments in the speech command according to a preset time interval threshold.

[0016] The preprocessed voice command is resampled according to the sampling frequency adapted to the automatic speech recognition technology;

[0017] The resampled audio data is identified using automatic speech recognition technology, and the voice command is recognized as the corresponding command text.

[0018] Furthermore, it also includes the following steps:

[0019] The intelligent agent generates a corresponding response audio based on the returned information and sends the response audio to the digital entertainment terminal for playback.

[0020] To address the aforementioned technical problems, this application also provides another technical solution:

[0021] A digital entertainment interactive device based on intelligent agents, comprising:

[0022] Create a module for creating and defining intelligent agents, and associating intelligent agents with the access points of the larger model;

[0023] The acquisition module is used to acquire the user's voice commands for the digital entertainment terminal and send the voice commands to the intelligent agent or the voice conversion module;

[0024] The recognition module is used to control the intelligent agent or the speech conversion module to recognize the speech command as the corresponding command text. The intelligent agent calls a large model to perform semantic analysis on the command text. The intelligent agent generates return information based on its definition and the semantic analysis results and sends it to the digital entertainment terminal.

[0025] The execution module is used to control the digital entertainment terminal to perform corresponding operations based on the returned information.

[0026] Furthermore, defining the intelligent agent includes: defining the identification domain of the intelligent agent as the digital entertainment domain, defining the triggering style and return information format of the intelligent agent, wherein the triggering style includes broadcast control requests and on-demand requests.

[0027] To address the aforementioned technical problems, this application also provides another technical solution:

[0028] A computer-readable storage medium storing a computer program, which, when executed, performs the agent-based digital entertainment interaction method according to any one of the technical solutions.

[0029] Unlike existing technologies, the above technical solution employs an intelligent agent for digital entertainment voice interaction. The intelligent agent is created and defined; the digital entertainment terminal acquires voice commands and sends them to the intelligent agent or a voice conversion module; the intelligent agent or voice conversion module recognizes the voice commands as corresponding command text; the intelligent agent invokes the large-scale model to perform semantic analysis on the command text; the intelligent agent generates corresponding return information based on the semantic analysis results; and the intelligent agent sends the return information to the digital entertainment terminal, which then executes the corresponding operation. Therefore, the intelligent agent is no longer limited to fixed-phrase voice interaction; it can accurately understand the user's input intent through the semantic analysis of the large-scale model, thereby achieving continuous voice interaction control and fuzzy requests that do not rely on precise information.

[0030] The above description of the invention is merely an overview of the technical solution of this application. In order to enable those skilled in the art to better understand the technical solution of this application and to implement it based on the description and drawings, and to make the above-mentioned objectives and other objectives, features and advantages of this application easier to understand, the following description is provided in conjunction with the specific embodiments and drawings of this application. Attached Figure Description

[0031] The accompanying drawings are only used to illustrate the principles, implementation methods, applications, features, and effects of specific embodiments of the present invention and other related contents, and should not be considered as limitations on this application.

[0032] In the accompanying drawings of the instruction manual:

[0033] Figure 1 A flowchart illustrating the agent-based digital entertainment interaction method described in a specific implementation;

[0034] Figure 2 This is a diagram illustrating the interaction process between the digital entertainment terminal and the intelligent agent in a specific implementation method.

[0035] Figure 3 This is a flowchart illustrating the voice recognition and control text implementation process.

[0036] Figure 4 This is a block diagram of the agent-based digital entertainment interactive device described in a specific embodiment;

[0037] Figure 5 A schematic diagram of the computer-readable storage medium described in a specific embodiment;

[0038] The reference numerals used in the above figures are explained as follows:

[0039] 400. A digital entertainment interactive device based on intelligent agents; 401. Creation module; 402. Acquisition module; 403. Recognition module; 404. Execution module;

[0040] 500. Computer-readable storage medium; Detailed Implementation

[0041] To illustrate the possible application scenarios, technical principles, implementable specific solutions, and achievable objectives and effects of this application in detail, the following description, in conjunction with the listed specific embodiments and accompanying drawings, provides a detailed explanation. The embodiments described herein are merely illustrative of the technical solutions of this application and are therefore intended to limit the scope of protection of this application.

[0042] In this document, the term "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The term "embodiment" appearing in various places throughout the specification does not necessarily refer to the same embodiment, nor does it specifically limit its independence or connection with other embodiments. In principle, in this application, as long as there are no technical contradictions or conflicts, the technical features mentioned in each embodiment can be combined in any way to form corresponding implementable technical solutions.

[0043] Unless otherwise defined, the technical terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the use of related terms herein is merely for the purpose of describing particular embodiments and is not intended to limit this application.

[0044] In the description of this application, the term "and / or" is used to describe the logical relationship between objects, indicating that three relationships can exist. For example, A and / or B means: A exists, B exists, and A and B exist simultaneously. Additionally, the character " / " in this document generally indicates that the preceding and following objects have an "or" logical relationship.

[0045] In this application, terms such as “first” and “second” are used only to distinguish one entity or operation from another, and do not necessarily require or imply any actual quantity, hierarchy or order relationship between these entities or operations.

[0046] Without further limitations, the use of terms such as “comprising,” “including,” “having,” or other similar open-ended expressions in this application is intended to cover non-exclusive inclusion, which does not exclude the presence of additional elements in a process, method, or product that includes the stated elements, such that a process, method, or product that includes a list of elements may include not only those defined elements but also other elements not expressly listed, or elements inherent to such a process, method, or product.

[0047] Similar to the understanding in the Examination Guidelines, in this application, expressions such as "greater than," "less than," and "exceeding" are understood to exclude the stated number; expressions such as "above," "below," and "within" are understood to include the stated number. Furthermore, in the description of the embodiments in this application, "multiple" means two or more (including two), and similar expressions related to "multiple" are also understood in this way, such as "multiple groups" and "multiple times," unless otherwise explicitly specified.

[0048] In the description of the embodiments of this application, the space-related expressions used, such as "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "vertical," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," and "circumferential," indicate the orientation or positional relationship based on the orientation or positional relationship shown in the specific embodiments or drawings. They are only for the purpose of describing the specific embodiments of this application or for the reader's understanding, and do not indicate or imply that the device or component referred to must have a specific position, a specific orientation, or be constructed or operated in a specific orientation. Therefore, they should not be construed as limitations on the embodiments of this application.

[0049] Unless otherwise expressly specified or limited, the terms "installation," "connection," "linking," "fixing," and "setting," as used in the description of the embodiments of this application, should be interpreted broadly. For example, "connection" can be a fixed connection, a detachable connection, or an integral setting; it can be a mechanical connection, an electrical connection, or a communication connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be the internal connection of two components or the interaction between two components. For those skilled in the art to which this application pertains, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0050] Please see Figure 1 This embodiment provides a digital entertainment interaction method based on intelligent agents. This method enables voice interaction with digital entertainment terminals, allowing for functions such as voice-activated song selection and voice-controlled playback. Furthermore, through the intelligent agent, this method can accurately understand the user's intent, enabling continuous interaction and fuzzy requests.

[0051] like Figure 1 As shown, in this embodiment, the agent-based digital entertainment interaction method includes the following steps:

[0052] S101. Create and define intelligent agents, and associate the intelligent agents with the access points of the large model;

[0053] S102. The digital entertainment terminal acquires the user's voice command and sends the voice command to the intelligent agent or voice conversion module;

[0054] S103. The intelligent agent or speech conversion module recognizes the speech command as the corresponding command text. The intelligent agent calls the large model to perform semantic analysis on the command text. The intelligent agent generates return information based on its definition and semantic analysis results and sends it to the digital entertainment terminal.

[0055] S104. The digital entertainment terminal performs corresponding operations based on the returned information.

[0056] In step S101, the agent is a goal-based agent that also possesses characteristics of an interactive agent. This agent combines the semantic analysis capabilities of a large model to analyze the input text, understand the user's intent, and plan a path to achieve the goal. This agent has strong decision-making capabilities and can respond by combining semantic understanding and contextual analysis; therefore, it goes beyond simple reflective rule matching. Furthermore, in step S101, the agent is associated with the access point of the large model; therefore, when the agent receives voice commands uploaded from the digital entertainment terminal, it can invoke the large model for semantic analysis. When creating the agent, the recognition domain, the tasks to be completed, and the format of the returned information need to be defined.

[0057] In this embodiment, the intelligent agent is directly defined as belonging to the digital entertainment field, and the tasks it needs to complete are defined as intelligent on-demand and intelligent playback control, that is, helping users to on-demand and control the playback of multimedia resources, thereby realizing intelligent on-demand and playback control commands. The playback control commands of the digital entertainment terminal include: skipping songs, pausing, replaying, muting, switching between original and backing vocals, etc.; the on-demand command is to select a song or other multimedia resource that matches the input for playback. Input methods for on-demand songs may include: I want to sing XXX song, I want to sing XXX song, recommend XXX song, request a XXX song, etc.

[0058] In step S102, the digital entertainment terminal can acquire voice commands input by the user via a microphone. This microphone can be used for both singing and acquiring voice commands. In some embodiments, a voice interaction mode can be entered by preseting a specific voice. For example, when the user says "Xiao Yi" or "Xiao Yi, Xiao Yi," the digital entertainment terminal enters the voice interaction mode, where voice-activated song selection, song skipping, pausing, and other voice-controlled functions can be implemented. In other embodiments, a physical button can be provided on the microphone or the digital entertainment terminal, and the voice interaction mode can be entered by triggering the physical button.

[0059] In step S103, the intelligent agent or speech conversion module recognizes the voice command as the corresponding command text. Next, in step S103, the intelligent agent invokes a large model to perform semantic analysis on the command text. Based on its definition and the semantic analysis results, the intelligent agent generates return information and sends it to the digital entertainment terminal.

[0060] When the large model receives the instruction text corresponding to the aforementioned on-demand or broadcast control instructions, it uses Natural Language Processing (NLP) to parse the semantics of the broadcast control text and combines it with data such as a knowledge base to perform semantic expansion and other semantic analyses, thereby accurately grasping the meaning of the user's instruction text. Then, the intelligent agent generates return information based on its definition and the semantic analysis results of the large model and sends it to the digital entertainment terminal.

[0061] In step S104, the digital entertainment terminal performs the corresponding on-demand and playback control operations.

[0062] like Figure 2 The diagram shown illustrates the interaction process between the digital entertainment terminal and the intelligent agent in this embodiment.

[0063] First, the intelligent agent is created and defined, and then associated with the access point of the large model. The intelligent agent is defined as follows: its recognition domain is defined as the digital entertainment domain; its triggering style and return information format are defined; the triggering style includes broadcast control requests and on-demand requests.

[0064] The definition of the intelligent agent's recognition domain as the digital entertainment domain includes: optimizing the intelligent agent's recognition domain through prompt words; this optimization includes at least: excluding or converting semantics prone to errors in the digital entertainment domain. For example, a user's voice input "volume 8" is easily recognized as "volume bar" after text conversion, or a user's voice input "switch songs" is easily recognized as the similar-sounding "cut" after text conversion. Therefore, when defining the intelligent agent's recognition domain, it is necessary to enhance relevant optimization schemes through prompt words, emphasizing that the intelligent agent needs to make correct conversions when similar sounds exist. For example, if the instruction text is "cut," the intelligent agent needs to recognize it as "switch songs" in the digital entertainment domain when analyzing the user's intent; and if the instruction text is "volume bar," the intelligent agent needs to recognize it as "volume 8" in the digital entertainment domain when analyzing the user's intent.

[0065] In actual voice interaction, the digital entertainment terminal acquires voice commands through the microphone and uploads the voice commands to the intelligent agent or voice conversion module.

[0066] The intelligent agent or speech conversion module recognizes the voice commands as corresponding instruction text.

[0067] The agent invokes a large model, which performs semantic analysis on the instruction text and sends the results back to the agent. Then, based on its definition and the semantic analysis results from the large model, the agent further understands the user's true intent and generates response information to send to the digital entertainment terminal.

[0068] The digital entertainment terminal performs functions such as on-demand playback, song skipping, and pausing based on the returned information. In the above embodiment, the format of the returned information from the intelligent agent can first determine whether the user sent a playback control command or an on-demand command. If it is an on-demand command, the intelligent agent identifies the type or specific multimedia resource that the user needs to select, and then returns a list of multimedia resources to the user for selection. The selected multimedia resource can be displayed as a multimedia resource list, such as a song list. In this embodiment, the intelligent agent can accurately understand the user's intention to select multimedia resources through semantic analysis of a large model. For example, if the user's voice command is: "Help me select the theme song of Tian Long Ba Bu," then the intelligent agent, based on its definition and semantic analysis of the large model, returns the following information to the digital entertainment terminal: "Singer: Wakin Chau; Song: Difficult to Recite Sutras."

[0069] If the user sends a voice command such as skipping a song or pausing, the intelligent agent directly returns the playback control command to the digital entertainment terminal to control the playback of the song. The playback control command includes any one or more of the following: play, pause, skip a song, and repeat.

[0070] Since the standard output format of large models and intelligent agents is plain text, and playback, pause, song skipping, and replay functions on digital entertainment terminals are controlled by playback control commands, which are defined by the manufacturer and semantically unrelated to their corresponding functions. For example, the playback control command for "play" is "0001", the song skipping command is "0002", and the pause command is "0003". Therefore, the format of the returned information from the intelligent agent includes a list of selected multimedia resources and identifiers for different playback control functions; each identifier corresponds to a playback control command in the digital entertainment terminal. That is, in the returned information to the intelligent agent, in addition to returning semantic information corresponding to different playback control functions, it is also necessary to set identifiers for different playback control functions, so that each identifier corresponds to a playback control command in the digital entertainment terminal. These identifiers can be directly associated with the corresponding playback control commands in the digital entertainment terminal. For example, when a user inputs the voice command "pause song," the intelligent agent analyzes and determines that the user wants to pause the song in the playback control function. Therefore, the intelligent agent returns information including "playback control: pause; identifier: 0003," where the identifier "0003" is the playback control command for the "pause" playback control function in the digital entertainment terminal. The identifier described in this application is not limited to the corresponding playback control command.

[0071] In some embodiments, step S103 further includes the step of:

[0072] The intelligent agent generates a corresponding response audio based on the returned information and sends the response audio to the digital entertainment terminal for playback.

[0073] Therefore, in this embodiment, the intelligent agent can not only assist the digital entertainment terminal in completing the corresponding song selection and playback control functions, but also respond to the user through audio replies. For example, when a user selects a song via voice, the intelligent agent can not only add the selected song to the digital entertainment terminal's list of selected songs by returning a message, but also play a reply audio message on the digital entertainment terminal saying "Your selected song XXX has been added to the playlist," thus improving the user's voice interaction experience. The reply audio can be generated using TTS technology, and the monochrome reply audio also carries rich emotional nuances. TTS technology is short for Text-to-Speech technology, which refers to the technology of converting text content into natural and fluent speech output.

[0074] like Figure 3 As shown, in one embodiment, recognizing the voice command as the corresponding broadcast control text includes the following steps:

[0075] S301. Preprocess the voice command, the preprocessing including scaling the volume of the voice command to a preset volume value, and performing sentence merging or sentence splitting on adjacent audio segments in the voice command according to a preset time interval threshold.

[0076] S302. Resample the preprocessed voice command according to the sampling frequency adapted to the automatic speech recognition technology;

[0077] S03. The audio data obtained by resampling is identified by automatic speech recognition technology to obtain the broadcast control text corresponding to the voice command.

[0078] In step S301, the volume of the voice command input from the microphone can be amplified in advance (by a factor of 1.2). The amplification factor can be dynamically configured so that the digital entertainment terminal can clearly recognize the voice command. In some cases, if the volume of the voice command acquired by the microphone is too high, the volume of the voice command can also be reduced.

[0079] The rational processing involves fitting two or more adjacent audio segments in a voice command into a complete sentence; conversely, sentence segmentation processing splits two or more adjacent audio segments in a voice command into independent sentences. The preset time interval threshold can be set based on the pause duration of normal human speech, and this threshold can be adjusted according to actual conditions. For example, the time interval threshold is 2 seconds. If the time interval (i.e., pause) between two adjacent audio segments in a user-input voice command is less than or equal to 2 seconds, these two audio segments are considered as one sentence, thus maintaining the continuity of audio input; if the time interval between two adjacent audio segments is greater than 2 seconds, the two adjacent audio segments are segmented, and these two adjacent audio segments are considered as two separate sentences. In this embodiment, volume scaling prevents the loss of voice commands in noisy environments; sentence merging and sentence segmentation prevent semantic analysis deviations caused by short pauses during voice command input.

[0080] In steps S302 and S303, the English abbreviation for the automatic speech recognition technology is ASR (Automatic Speech Recognition), which refers to the core technology of converting speech signals into text.

[0081] like Figure 4 As shown, in one embodiment, an agent-based digital entertainment interactive device 400 is provided. The agent-based digital entertainment interactive device 400 includes: a creation module 401, an acquisition module 402, an identification module 403, and an execution module 404.

[0082] The creation module 401 is used to create and define intelligent agents and associate intelligent agents with the access points of the large model.

[0083] The acquisition module 402 is used to acquire the user's voice commands for the digital entertainment terminal and send the voice commands to the intelligent agent or voice conversion module.

[0084] The recognition module 403 is used to control the intelligent agent or the speech conversion module to recognize the speech command as the corresponding command text. The intelligent agent calls the big model to perform semantic analysis on the command text. The intelligent agent generates return information based on its definition and semantic analysis results and sends it to the digital entertainment terminal.

[0085] The execution module 404 is used to control the digital entertainment terminal to perform corresponding operations based on the returned information.

[0086] In this embodiment, the broadcast control commands include any one or more of the following: play, pause, skip song, repeat, mute, and switch between original and backing vocals.

[0087] The large model and the intelligent agent mentioned are both part of the large model and intelligent agent in the embodiment of the digital entertainment interaction method based on intelligent agents, and therefore will not be described again in this embodiment. When creating the intelligent agent, it is necessary to define the recognition domain, the tasks to be completed, and the format of the returned information for the created intelligent agent. In this embodiment, the intelligent agent is directly defined as the digital entertainment terminal domain, and the tasks to be completed are defined as intelligent on-demand and intelligent playback control, that is, helping users to on-demand and control the playback of songs, thereby realizing intelligent on-demand and playback control commands. On-demand commands are to select songs or other multimedia resources that match the input for playback. The input methods for on-demanding songs may include: I want to sing XXX song, I want to sing XXX song, recommend XXX song, request a XXX song, etc. In this embodiment, the intelligent agent is no longer limited to fixed sentence-based voice interaction, and can accurately understand the user's input intent through semantic analysis of the large model, thereby realizing continuous voice interaction control and fuzzy requests that do not rely on precise information.

[0088] In this embodiment, the large model in the agent-based digital entertainment interactive device 400 and the process of voice interaction between the agent and the digital entertainment terminal are as follows: Figure 2 As shown in the previous embodiment, and as has been specifically described in the previous embodiment, it will not be repeated in this embodiment.

[0089] Since the standard output format of large models and intelligent agents is plain text, and playback, pause, song skipping, and replay functions on digital entertainment terminals are controlled by playback control commands, which are defined by the manufacturer and semantically unrelated to their corresponding functions. For example, the playback control command for "play" is "0001", the song skipping command is "0002", and the pause command is "0003". Therefore, the format of the returned information from the intelligent agent includes a list of selected multimedia resources and identifiers for different playback control functions; each identifier corresponds to a playback control command in the digital entertainment terminal. That is, in the returned information to the intelligent agent, in addition to returning semantic information corresponding to different playback control functions, it is also necessary to set identifiers for different playback control functions, so that each identifier corresponds to a playback control command in the digital entertainment terminal. These identifiers can be directly associated with the corresponding playback control commands in the digital entertainment terminal. For example, when a user inputs the voice command "pause song," the intelligent agent analyzes and determines that the user wants to pause the song in the playback control function. Therefore, the intelligent agent returns information including "playback control: pause; identifier: 0003," where the identifier "0003" is the playback control command for the "pause" playback control function in the digital entertainment terminal. The identifier described in this application is not limited to the corresponding playback control command.

[0090] In this embodiment, the intelligent agent is also used to generate a corresponding response audio based on the returned information and send the response audio to the digital entertainment terminal for playback. For example, when a user requests a song via voice, the intelligent agent can not only add the requested song to the digital entertainment terminal's list of requested songs based on the returned information, but also play the response audio "Your requested song XXX has been added to the playlist" through the digital entertainment terminal, thus improving the user's voice interaction experience. The response audio can be generated using TTS technology, and the monochrome response audio also carries rich emotional nuances. TTS technology is short for Text-to-Speech technology, which refers to the technology of converting text content into natural and fluent speech output.

[0091] like Figure 5 As shown, in another embodiment, a computer-readable storage medium 500 is provided, which stores a computer program. When the computer program is run, it executes the agent-based digital entertainment terminal interaction method described in any of the above embodiments.

[0092] The computer-readable storage medium may be volatile memory or non-volatile memory, or both. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), ferromagnetic random access memory (FRAM), flash memory, magnetic surface memory, optical disc, or compact disc read-only memory (CD-ROM); the magnetic surface memory may be disk storage or magnetic tape storage.

[0093] The volatile memory may be random access memory (RAM), which serves as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synclink dynamic random access memory (SLDRAM), and direct memory bus random access memory (DRRAM). The computer-readable storage media described in the embodiments of the present invention are intended to include these and any other suitable types of memory.

[0094] In some embodiments, the processor may be implemented by software, hardware, firmware, or a combination thereof, and may use at least one of the following: circuit, single or multiple application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), central processing units (CPUs), controllers, microcontrollers, and microprocessors, thereby enabling the processor to execute some or all of the steps or any combination of the steps in the agent-based digital entertainment interaction method in the various embodiments of this application.

[0095] Finally, it should be noted that although the above embodiments have been described in the text and drawings of this application, this should not limit the scope of patent protection of this application. Any technical solutions that are based on the essential concept of this application and utilize the content described in the text and drawings of this application, resulting in equivalent structural or procedural substitutions or modifications, as well as the direct or indirect application of the technical solutions of the above embodiments to other related technical fields, are all included within the scope of patent protection of this application.

Claims

1. A digital entertainment interaction method based on intelligent agents, characterized in that, Includes the following steps: Create and define intelligent agents, and associate the intelligent agents with the access points of the large model; The digital entertainment terminal acquires the user's voice commands and sends the voice commands to the intelligent agent or voice conversion module; The intelligent agent or speech conversion module recognizes the speech command as the corresponding command text. The intelligent agent calls a large model to perform semantic analysis on the command text. The intelligent agent generates return information based on its definition and semantic analysis results and sends it to the digital entertainment terminal. The digital entertainment terminal performs corresponding operations based on the returned information.

2. The digital entertainment interaction method based on intelligent agents according to claim 1, characterized in that, The definition of the intelligent agent includes: defining the identification domain of the intelligent agent as the digital entertainment domain, defining the triggering style and return information format of the intelligent agent, wherein the triggering style includes broadcast control request and on-demand request.

3. The digital entertainment interaction method based on intelligent agents according to claim 2, characterized in that, The definition of the intelligent agent's recognition domain as the digital entertainment domain includes: optimizing the intelligent agent's recognition domain through prompt words; The optimization of the intelligent agent's recognition domain through prompt words includes at least: excluding or converting semantics that are prone to errors in the digital entertainment field.

4. The digital entertainment interaction method based on intelligent agents according to claim 2, characterized in that, The returned information format includes a list of selected multimedia resources and identifiers for different broadcast control functions; each identifier corresponds to a broadcast control instruction in the digital entertainment terminal.

5. The digital entertainment interaction method based on intelligent agents according to claim 4, characterized in that, The broadcast control commands include any one or more of the following: play, pause, skip to the next song, and repeat.

6. The digital entertainment interaction method based on intelligent agents according to claim 1, characterized in that, The intelligent agent or speech conversion module recognizes the speech command as the corresponding command text, including the following steps: The intelligent agent or speech conversion module preprocesses the speech command. The preprocessing includes scaling the volume of the speech command to a preset volume value and merging or splitting adjacent audio segments in the speech command according to a preset time interval threshold. The preprocessed voice command is resampled according to the sampling frequency adapted to the automatic speech recognition technology; The resampled audio data is identified using automatic speech recognition technology, and the voice command is recognized as the corresponding command text.

7. The agent-based digital entertainment interaction method according to any one of claims 1-6, characterized in that, It also includes the following steps: The intelligent agent generates a corresponding response audio based on the returned information and sends the response audio to the digital entertainment terminal for playback.

8. A digital entertainment interactive device based on an intelligent agent, characterized in that, include: Create a module for creating and defining intelligent agents, and associating intelligent agents with the access points of the larger model; The acquisition module is used to acquire the user's voice commands for the digital entertainment terminal and send the voice commands to the intelligent agent or the voice conversion module; The recognition module is used to control the intelligent agent or the speech conversion module to recognize the speech command as the corresponding command text. The intelligent agent calls a large model to perform semantic analysis on the command text. The intelligent agent generates return information based on its definition and the semantic analysis results and sends it to the digital entertainment terminal. The execution module is used to control the digital entertainment terminal to perform corresponding operations based on the returned information.

9. The digital entertainment interactive device based on an intelligent agent according to claim 8, characterized in that, The definition of the intelligent agent includes: defining the identification domain of the intelligent agent as the digital entertainment domain, defining the triggering style and return information format of the intelligent agent, wherein the triggering style includes broadcast control request and on-demand request.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is run, it executes the agent-based digital entertainment interaction method according to any one of claims 1 to 7.

Images