Algorithm and system for matching tail action of digital animal image through voice

Abstract

The invention relates to an algorithm and a system for matching tail actions of a digital animal image through voice. The system comprises a voice recognition module, an emotion analysis server, an action generation module, a real-time monitoring module, a user terminal and a visual signal acquisition module. The voice recognition module receives a voice instruction and converts the voice instruction into text information, the sentiment analysis server extracts sentiment characteristics, and the action generation module generates an initial tail action according to the sentiment characteristics. And the real-time monitoring module monitors the action effect and the environment change, and when the offset of the action parameter reaches a preset threshold value, the tail action parameter is dynamically adjusted. The visual signal acquisition module captures actual motion data of the tail of an animal through an unmarked motion tracking technology, and provides reference for motion adjustment. Through multi-modal data fusion and a dynamic adjustment mechanism, accurate and natural tail action mapping is realized, multi-scene requirements are met, and user experience is improved.

Description

Technical Field

[0001] The present invention relates to the technical fields of computer artificial intelligence, computer graphics and robotics, and in particular to an algorithm and system for matching the tail movements of digital animal images through voice. Background Art

[0002] Currently, technologies for matching digital animal images with voice and mapping their tail movements are mostly based on foundational technologies such as speech recognition, sentiment analysis, and multimodal interaction. In practice, these technologies are combined to analyze human voice commands and match them with the movements of digital animal images. However, the matching process fails to fully consider the complexity of voice commands, the diversity of animal behavior, and the challenges of multimodal data fusion. This results in inaccurate and in-time matching results, which in turn affects the user experience. Summary of the Invention

[0003] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an algorithm and system for matching the tail movements of digital animal images through voice.

[0004] To achieve the above object, the present invention adopts the following technical solution: an algorithm for matching the tail movement of a digital animal image through voice, comprising the following steps:

[0005] Step S1: receiving a voice command input by a user, performing sentiment analysis on the voice command, and extracting the sentiment features therein;

[0006] Step S2: Based on the extracted emotional features, a list of full action parameters corresponding to the emotional features is searched from the database;

[0007] Step S3: selecting a tail action parameter to generate an initial tail action according to the action full parameter list, and caching the tail action parameter as current action information;

[0008] Step S4: Monitor the current action effect and environmental changes in real time to obtain the actual parameters of the current action; calculate the offset between the actual parameters of the current action and the tail action parameters in the cached current action information, and use the offset as the trigger condition for action adjustment. When the action adjustment condition is triggered, the tail action parameters are dynamically adjusted according to the new emotional characteristics and environmental information.

[0009] Preferably, step S1 includes the following sub-steps:

[0010] Sub-step S11: the voice recognition module receives the voice command input by the user;

[0011] Sub-step S12: the speech recognition module performs emotion negotiation with the emotion analysis server;

[0012] Sub-step S13: The sentiment analysis server caches the negotiation result information into a local database and records it as sentiment information. The sentiment information includes the emotional features in the voice command and the key action information in the negotiation result.

[0013] Preferably, step S2 includes the following sub-steps:

[0014] Sub-step S21: The action generation module searches the action pattern table in the database for a list of all action parameters corresponding to the emotion based on the emotion feature information returned by the emotion analysis server, and caches the list of all action parameters in the local database as a tail action parameter list, while initializing the action adjustment flag.

[0015] Sub-step S22: the action generation module selects a tail action parameter index ID and corresponding tail action parameter information that matches the closest emotion from the tail action parameter list according to the emotion feature in the emotion information;

[0016] Sub-step S23: The action generation module generates an initial tail action according to the parameter information, and caches the tail action parameters corresponding to the action generation to the local database, and records them as current action information.

[0017] Preferably, step S3 includes the following sub-steps:

[0018] Sub-step S31: After the action generation module starts generating actions, a new sub-thread is started, and the sub-thread detects the current environment changes and collects the actual effect information of the tail action in real time;

[0019] Sub-step S32: The background thread obtains the actual parameters of the current action, compares them with the tail action parameters in the cached current action information, and calculates the offset between the two. If the tail action parameter offset reaches a preset threshold, the background thread finds the tail action parameter index ID and corresponding tail action parameter that is closest to the current action requirement from the cached tail action parameter list, updates the tail action parameter in the current action information, and changes the action adjustment flag.

[0020] Sub-step S33: the action generation module dynamically adjusts the parameters of the tail action according to the updated tail action parameters;

[0021] Sub-step S34: When the background thread detects that the action adjustment flag has changed, the action generation module initiates an action update notification to the user terminal and resets the action adjustment flag;

[0022] Sub-step S35: The user terminal re-initiates a sentiment analysis request to the sentiment analysis server and jumps back to step S1 to complete an update of the tail action.

[0023] Preferably, the digital animal is a digital dog puppet or a digital fish puppet, and the digital fish puppet swims on the water surface.

[0024] The present invention also provides a system for matching the tail movements of digital animal images through voice, characterized in that the system includes: a voice recognition module, an emotion analysis server, an action generation module, a real-time monitoring module, a visual signal acquisition module, and a user terminal;

[0025] The speech recognition module is used to receive a voice command input by a user and convert the voice command into text information;

[0026] The sentiment analysis server is used to perform sentiment analysis on text information, extract emotional features from voice commands, and return emotional feature information;

[0027] The action generation module is used to select tail action parameters that match the emotional characteristics from the action parameter list according to the emotional characteristic information, and generate an initial tail action;

[0028] The real-time monitoring module is used to monitor the current action effect and environmental changes, and trigger an action update when the action parameter offset reaches a preset threshold;

[0029] The visual signal acquisition module is used to capture the actual movement data of the animal's tail;

[0030] The user terminal is used to receive the action update notification and regenerate the tail action according to the updated action parameters;

[0031] The present invention has the following beneficial effects:

[0032] 1. This invention combines emotional analysis of voice commands with real-time capture of visual signals, combined with multimodal data fusion technology, to dynamically adjust tail movement parameters based on the emotional characteristics of voice commands and the actual movement data of the animal's tail. This method addresses the problem of traditional movement mapping in accurately reflecting emotional states and behavioral intentions, making the generated tail movements more realistic and natural, enhancing the authenticity and naturalness of the movements.

[0033] 2. This invention supports dynamic optimization of movement performance based on the characteristics of different dog breeds and their current emotional state. Through personalized processing and dynamic adjustment mechanisms, the system can generate tail movements that match the characteristics of specific dog breeds based on their tail movement characteristics and emotional expressions, achieving personalized movement mapping to meet diverse user needs.

[0034] 3. This invention incorporates a real-time feedback mechanism that dynamically adjusts tail movement parameters by monitoring the current movement effect and emotional changes. When voice commands or environmental factors change, the system can respond in real time, adjusting the swing speed, amplitude, and direction of the movement to meet the needs of movement generation in multiple scenarios, ensuring the accuracy and real-time performance of the movement. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 The present invention provides a flow chart of an algorithm for matching the tail movements of a digital animal image through voice; DETAILED DESCRIPTION

[0036] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. Figure 1 The present invention provides a system for matching the tail movement of a digital animal image through voice. The digital animal image is such as a digital dog puppet image or a digital fish puppet image swimming on the water surface. The system includes: a voice recognition module, an emotion analysis server, an action generation module, a real-time monitoring module, a user terminal, and a visual signal acquisition module; the voice recognition module is used to receive voice instructions input by the user and convert the voice instructions into text information; the emotion analysis server is used to perform emotion analysis on the text information, extract emotional features in the voice instructions, and return the emotional feature information; the action generation module is used to select tail action parameters that match the emotional features from an action parameter list based on the emotional feature information, and generate an initial tail action; the real-time monitoring module is used to monitor the current action effect and environmental changes, and trigger an action update when the action parameter offset reaches a preset threshold; the user terminal is used to receive an action update notification and regenerate the tail action according to the updated action parameters; the visual signal acquisition module is used to capture the actual motion data of the animal's tail through markerless motion tracking technology, and use the data as a reference for action adjustment.

[0037] The present invention also provides an algorithm for matching the tail movements of digital animal images through voice, comprising the following steps:

[0038] Step S1: receiving a voice command input by a user, performing sentiment analysis on the voice command, and extracting the sentiment features therein;

[0039] Step S2: Based on the extracted emotional features, a list of full action parameters corresponding to the emotional features is searched from the database;

[0040] Step S3: selecting a tail action parameter to generate an initial tail action according to the action full parameter list, and caching the tail action parameter as current action information;

[0041] Step S4: Monitor the current action effect and environmental changes in real time to obtain the actual parameters of the current action; calculate the offset between the actual parameters of the current action and the tail action parameters in the cached current action information, and use the offset as the trigger condition for action adjustment. When the action adjustment condition is triggered, the tail action parameters are dynamically adjusted according to the new emotional characteristics and environmental information.

[0042] In the present invention, preferably, step S1 includes the following sub-steps:

[0043] Sub-step S11: the voice recognition module receives the voice command input by the user;

[0044] Sub-step S12: the speech recognition module performs emotion negotiation with the emotion analysis server;

[0045] Sub-step S13: The emotion analysis server caches the negotiation result information into the local database and records it as emotion information (Emotion_Info); the emotion information includes the emotion characteristics (emotion category, emotion intensity) in the voice command, the key action information in the negotiation result (including the tail action type, action amplitude, and swing frequency corresponding to the emotion) and part of the voice command information (including the text content of the voice command). This step ensures the matching of action patterns and emotion characteristics.

[0046] In step 1, the user inputs a voice command, the voice recognition module analyzes the command and extracts emotional features, while the visual signal acquisition module captures the actual movement data of the animal's tail through markerless motion tracking technology and uses this data as a reference for the motion model.

[0047] In the present invention, preferably, step S2 includes the following sub-steps:

[0048] Sub-step S21: The action generation module searches for a full parameter list of all actions corresponding to the emotion from the action pattern table in the database based on the emotional feature information returned by the emotion analysis server, and caches the full parameter list in the local database, recording it as a tail action parameter list (Tail_Action_List), and at the same time initializes the action adjustment flag.

[0049] Sub-step S22: The action generation module selects a tail action parameter index ID and corresponding tail action parameter information with the closest emotion matching from the tail action parameter list (Tail_Action_List) based on the emotional features in the emotion information (Emotion_Info) to generate personalized action. This step supports dynamic optimization of action performance based on the characteristics of different dog breeds.

[0050] Sub-step S23: The action generation module generates an initial tail action based on the parameter information, and caches the tail action parameters corresponding to this action generation to the local database, and records it as the current action information (Current_Action_Info). The above steps support dynamic optimization of action performance according to the characteristics of different dog breeds and current emotional states. Through personalized processing and dynamic adjustment mechanisms, the system can generate tail actions that meet the characteristics of specific dog breeds based on the tail movement characteristics and emotional expressions of different dog breeds, realize personalized action mapping, and meet diverse user needs.

[0051] In the present invention, preferably, step S3 includes the following sub-steps:

[0052] Sub-step S31: After the action generation module starts generating actions, a new sub-thread is started. The sub-thread detects the current environmental changes (such as emotional changes, external interference) in real time and collects the actual effect information of the tail action through the visual signal acquisition module;

[0053] Sub-step S32: While capturing the tail movement, the visual signal acquisition module will start a background thread. The background thread uses a real-time monitoring mechanism to detect current environmental changes and collect information on the actual effects of the tail action. When the action adjustment condition is triggered, the tail action parameters are dynamically adjusted according to the new emotional characteristics and environmental information to achieve an accurate and natural action mapping effect. Specifically, the background thread obtains the actual parameters of the current action, and compares them with the tail action parameters in the cached current action information (Current_Action_Info), and calculates the offset between the two; if the tail action parameter offset reaches the preset threshold, the background thread will find the tail action parameter index ID and the corresponding tail action parameter closest to the current action requirement from the cached tail action parameter list (Tail_Action_List), update the tail action parameters in the current action information (Current_Action_Info), and modify the action adjustment flag to `changeflag=1`;

[0054] Sub-step S33: The action generation module dynamically adjusts the parameters of the tail action (such as swing speed, amplitude, and direction) according to the updated tail action parameters to ensure that the generated action can accurately reflect the animal's emotional state and behavioral intention;

[0055] Sub-step S34: When the background thread detects a change in the action adjustment flag (`changeflag = 1`), the action generation module initiates an action update notification to the user terminal and resets the action adjustment flag `changeflag = 0`. These steps dynamically adjust tail action parameters (such as swing speed, amplitude, and direction) by monitoring the current action effect and emotional changes to ensure that the action accurately reflects the animal's emotional state and behavioral intentions. These steps implement a dynamic adjustment mechanism based on real-time feedback and propose a real-time feedback-driven tail action mapping method to adapt to action generation requirements in multiple scenarios.

[0056] Sub-step S35: The user terminal re-initiates a sentiment analysis request to the sentiment analysis server, and jumps back to step S1 to complete the update of the tail action. This step ensures that the system can adapt to the action generation requirements in multiple scenarios.

[0057] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An algorithm for matching the tail movements of digital animal images through voice, characterized in that: The following steps are involved: Step S1: receiving a voice command input by a user, performing sentiment analysis on the voice command, and extracting the sentiment features therein; Step S2: Based on the extracted emotional features, a list of full action parameters corresponding to the emotional features is searched from the database; Step S3: selecting a tail action parameter to generate an initial tail action according to the action full parameter list, and caching the tail action parameter as current action information; Step S4: Monitor the current action effect and environmental changes in real time to obtain the actual parameters of the current action; calculate the offset between the actual parameters of the current action and the tail action parameters in the cached current action information, and use the offset as the trigger condition for action adjustment. When the action adjustment condition is triggered, the tail action parameters are dynamically adjusted according to the new emotional characteristics and environmental information.

2. The algorithm for matching the tail movement of a digital animal image by voice according to claim 1, characterized in that: The step S1 includes the following sub-steps: Sub-step S11: the voice recognition module receives the voice command input by the user; Sub-step S12: the speech recognition module performs emotion negotiation with the emotion analysis server; Sub-step S13: The sentiment analysis server caches the negotiation result information into a local database and records it as sentiment information. The sentiment information includes the emotional features in the voice command and the key action information in the negotiation result.

3. The algorithm for matching the tail movement of a digital animal image by voice according to claim 1, characterized in that: The step S2 includes the following sub-steps: Sub-step S21: The action generation module searches the action pattern table in the database for a list of all action parameters corresponding to the emotion based on the emotion feature information returned by the emotion analysis server, and caches the list of all action parameters in the local database as a tail action parameter list, while initializing the action adjustment flag. Sub-step S22: the action generation module selects a tail action parameter index ID and corresponding tail action parameter information that matches the closest emotion from the tail action parameter list according to the emotion feature in the emotion information; Sub-step S23: The action generation module generates an initial tail action according to the parameter information, and caches the tail action parameters corresponding to the action generation to the local database, and records them as current action information.

4. The algorithm for matching the tail movement of a digital animal image by voice according to claim 1, characterized in that: The step S3 includes the following sub-steps: Sub-step S31: After the action generation module starts generating actions, a new sub-thread is started, and the sub-thread detects the current environment changes and collects the actual effect information of the tail action in real time; Sub-step S32: The background thread obtains the actual parameters of the current action, compares them with the tail action parameters in the cached current action information, and calculates the offset between the two. If the tail action parameter offset reaches a preset threshold, the background thread finds the tail action parameter index ID and corresponding tail action parameter that is closest to the current action requirement from the cached tail action parameter list, updates the tail action parameter in the current action information, and changes the action adjustment flag. Sub-step S33: the action generation module dynamically adjusts the parameters of the tail action according to the updated tail action parameters; Sub-step S34: When the background thread detects that the action adjustment flag has changed, the action generation module initiates an action update notification to the user terminal and resets the action adjustment flag; Sub-step S35: The user terminal re-initiates a sentiment analysis request to the sentiment analysis server and jumps back to step S1 to complete an update of the tail action.

5. The algorithm for matching the tail movement of a digital animal image by voice according to claim 1, characterized in that: The digital animal is a digital dog puppet or a digital fish puppet, and the digital fish puppet swims on the water surface.

6. A system for matching the tail movements of digital animal images through voice, characterized in that: The system includes: a speech recognition module, an emotion analysis server, an action generation module, a real-time monitoring module, a visual signal acquisition module, and a user terminal; The speech recognition module is used to receive a voice command input by a user and convert the voice command into text information; The sentiment analysis server is used to perform sentiment analysis on text information, extract emotional features from voice commands, and return emotional feature information; The action generation module is used to select tail action parameters that match the emotional characteristics from the action parameter list according to the emotional characteristic information, and generate an initial tail action; The real-time monitoring module is used to monitor the current action effect and environmental changes, and trigger an action update when the action parameter offset reaches a preset threshold; The visual signal acquisition module is used to capture the actual movement data of the animal's tail; The user terminal is used to receive the action update notification and regenerate the tail action according to the updated action parameters.

Images