CN-121983033-A - Intelligent toy control method based on semantic risk detection and related equipment

Abstract

The application is applicable to the technical field of artificial intelligence, and provides an intelligent toy control method based on semantic risk detection, which comprises the steps of obtaining voice data of a target user, and performing voice-to-text processing on the voice data to obtain corresponding target text data; carrying out semantic risk analysis on the target text data through a preset semantic risk detection model, and outputting a semantic risk analysis result corresponding to the target text data and a corresponding risk level label; and determining a target safety response strategy in a preset safety response strategy library based on the semantic risk analysis result and the corresponding risk grade label, and controlling the intelligent toy to execute the target safety response strategy. The application solves the problems that the existing method depends on a general semantic recognition and content filtering algorithm, is easy to generate semantic misjudgment or missed judgment under the condition of irregular language expression, lacks a real-time detection and intervention mechanism for the voice behavior, and cannot actively recognize potential risk behaviors in the interaction process.

Inventors

• ZHAO PINLONG
• Kuang Zhemin

Assignees

• 深圳市噜咔博士科技有限公司

Dates

Publication Date

20260505

Application Date

20251224

Claims (10)

1. 1. An intelligent toy control method based on semantic risk detection is characterized by comprising the following steps: Acquiring voice data of a target user, and performing voice-to-text processing on the voice data to obtain corresponding target text data; Carrying out semantic risk analysis on the target text data through a preset semantic risk detection model, and outputting a semantic risk analysis result corresponding to the target text data and a corresponding risk level label; And determining a target safety response strategy in a preset safety response strategy library based on the semantic risk analysis result and the corresponding risk grade label, and controlling the intelligent toy to execute the target safety response strategy.
2. 2. The intelligent toy control method based on semantic risk detection according to claim 1, wherein the performing voice-to-text processing on the voice data to obtain corresponding text data includes: performing voice-to-text processing on the voice data through a preset voice recognition model to obtain initial text data; and carrying out standardization processing on the initial text data to obtain target text data.
3. 3. The intelligent toy control method based on semantic risk detection according to claim 1, wherein the semantic risk analysis is performed on the target text data through a preset semantic risk detection model, and a semantic risk analysis result and a corresponding risk level label corresponding to the target text data are output, and the intelligent toy control method comprises the following steps: Performing first semantic risk analysis on the target text data through a preset semantic risk detection model to obtain a first semantic risk analysis result and a corresponding first risk level label; when the first semantic risk analysis result is a risk miss, performing second semantic risk analysis on the target text data to obtain a second semantic risk analysis result and a corresponding second risk level label; And when the second semantic risk analysis result is a risk miss, combining the context information and the emotion dictionary, and performing third semantic risk analysis processing on the target text data to obtain a third semantic risk analysis result and a corresponding third risk level label.
4. 4. The intelligent toy control method based on semantic risk detection according to claim 3, wherein the performing a second semantic risk analysis on the target text data to obtain a second semantic risk analysis result and a corresponding second risk level tag includes: carrying out semantic extraction processing on the target text data to obtain text semantic features corresponding to the target text data; and carrying out second semantic risk analysis on the text semantic features to obtain a second semantic risk analysis result and a corresponding second risk level label.
5. 5. The intelligent toy control method based on semantic risk detection according to claim 3, wherein the combining the context information and the emotion dictionary performs a third semantic risk analysis process on the target text data to obtain a third semantic risk analysis result and a corresponding third risk level label, and the method comprises: Calculating emotion change data of the target text data in combination with an emotion dictionary; Analyzing the context semantic features of the target text data in combination with the context information; and carrying out third semantic risk analysis processing on the target text data based on the emotion change data and the context semantic features to obtain a third semantic risk analysis result and a corresponding third risk level label.
6. 6. The intelligent toy control method based on semantic risk detection according to claim 1, wherein the determining a target safety response policy in a preset safety response policy library based on the semantic risk analysis result and a corresponding risk level label comprises: when the semantic risk analysis result is a risk hit, selecting a plurality of candidate safety response strategies from a preset safety response strategy library according to the risk grade label; and combining the cache management library, and determining a target security response strategy from the plurality of candidate security response strategies.
7. 7. A method of controlling a smart toy based on semantic risk detection according to any of claims 1-6, wherein after the controlling smart toy performs the target safety response strategy, the method further comprises: recording current session data; and generating log data and reporting the log data to a cloud end according to the current session data, the semantic risk analysis result and the corresponding risk level label.
8. 8. An intelligent toy control device based on semantic risk detection, characterized in that the intelligent toy control device based on semantic risk detection comprises: the first processing module is used for acquiring voice data of a target user, and performing voice-to-text processing on the voice data to obtain corresponding target text data; the second processing module is used for carrying out semantic risk analysis on the target text data through a preset semantic risk detection model and outputting a semantic risk analysis result corresponding to the target text data and a corresponding risk level label; and the control module is used for determining a target safety response strategy in a preset safety response strategy library based on the semantic risk analysis result and the corresponding risk grade label, and controlling the intelligent toy to execute the target safety response strategy.
9. 9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps in the intelligent toy control method based on semantic risk detection according to any one of claims 1 to 7 when the computer program is executed by the processor.
10. 10. A computer readable storage medium, characterized in that it has stored thereon a computer program which, when executed by a processor, implements the steps of the semantic risk detection based intelligent toy control method according to any of claims 1 to 7.

Description

Intelligent toy control method based on semantic risk detection and related equipment Technical Field The application belongs to the technical field of artificial intelligence, and particularly relates to an intelligent toy control method based on semantic risk detection and related equipment. Background In a child voice interaction scenario, plush toys are typically used to accompany a child for a natural voice conversation. However, the existing voice dialogue system for children mainly depends on a general semantic recognition and content filtering algorithm, has weak recognition capability on sensitive contents related to violence, pornography, frightening, induction and the like, and is easy to generate semantic misjudgment or missed judgment under the conditions of multi-turn dialogue, fuzzy context or irregular language expression of children, so that unsafe contents are output by the system, and physical and mental health of the children is influenced. In addition, the existing schemes generally lack real-time detection and intervention mechanisms for voice behaviors (such as abnormal emotion, dialogue induction, risk imitation and the like) of children, and potential risk behaviors cannot be actively identified in the interaction process. Therefore, there is a need for an intelligent toy control method combining semantic risk analysis and emotion analysis to solve the problems that the existing method relies on a general semantic recognition and content filtering algorithm, semantic misjudgment or missed judgment easily occurs under the condition that language expression of children is not standard, a real-time detection and intervention mechanism for voice behaviors of children is lacking, and potential risk behaviors cannot be actively recognized in the interaction process. Disclosure of Invention The embodiment of the application provides an intelligent toy control method based on semantic risk detection, which can solve the problems that the existing method depends on a general semantic recognition and content filtering algorithm, semantic misjudgment or missed judgment easily occurs under the condition of irregular language expression of children, a real-time detection and intervention mechanism for voice behaviors of the children is lacking, and potential risk behaviors cannot be actively recognized in the interaction process. The method comprises the steps of carrying out semantic risk analysis on target text data through a preset semantic risk detection model, outputting a semantic risk analysis result and a corresponding risk level label corresponding to the target text data, determining a target safety response strategy in a preset safety response strategy library according to the semantic risk analysis result and the corresponding risk level label, and controlling an intelligent toy to execute the target safety response strategy, thereby solving the problems that the existing method depends on a general semantic recognition and content filtering algorithm, is prone to semantic misjudgment or missed judgment under the condition of irregular language expression of children, lacks a real-time detection and intervention mechanism for voice behaviors of the children, and cannot actively recognize potential risk behaviors in the interaction process. In a first aspect, an embodiment of the present application provides a method for controlling an intelligent toy based on semantic risk detection, the method including the steps of: Acquiring voice data of a target user, and performing voice-to-text processing on the voice data to obtain corresponding target text data; Carrying out semantic risk analysis on the target text data through a preset semantic risk detection model, and outputting a semantic risk analysis result corresponding to the target text data and a corresponding risk level label; And determining a target safety response strategy in a preset safety response strategy library based on the semantic risk analysis result and the corresponding risk grade label, and controlling the intelligent toy to execute the target safety response strategy. Optionally, the performing voice-to-text processing on the voice data to obtain corresponding text data includes: performing voice-to-text processing on the voice data through a preset voice recognition model to obtain initial text data; and carrying out standardization processing on the initial text data to obtain target text data. Optionally, the performing semantic risk analysis on the target text data through a preset semantic risk detection model, and outputting a semantic risk analysis result corresponding to the target text data and a corresponding risk level label, includes: Performing first semantic risk analysis on the target text data through a preset semantic risk detection model to obtain a first semantic risk analysis result and a corresponding first risk level label; when the first semantic risk analysis result is a risk miss, performi