Infant dialogue system based on artificial intelligence technology

Abstract

The invention discloses an infant dialogue system based on an artificial intelligence technology. The infant dialogue system comprises a system front-end user interface, a first service module, a data storage module and a second service module. The system front-end user interface is used for realizing interaction with children; the first service module is used for realizing data interaction between the system front-end user interface and the second service module; the data storage module is used for storing various data related to children; and the second service module is used for realizing intelligent communication of the system. According to the invention, the problem of insufficient communication time between the teacher and the child can be solved, the conversation time of the child is obviously prolonged on the premise of ensuring the conversation quality, and abundant resources can be provided to broaden the view of the child; besides, dialogue content and activity process taking the infant as a main body can be recorded and analyzed, so that the workload of teachers can be reduced, the infant can be objectively evaluated, the development level of the infant can be accurately reflected in real time, and the education efficiency and quality are further improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence natural language dialogue and speech recognition, and in particular to an infant dialogue system based on artificial intelligence technology. Background Art

[0002] At present, children’s communication partners in kindergarten are mainly teachers and other children. Teachers need to balance teaching and administrative work, which to a certain extent limits the time and depth of their interaction with children. Children are still in the growth stage in terms of cognition and language expression, which makes it difficult for them to provide effective feedback when communicating with their peers.

[0003] At the same time, in kindergarten education, teachers are responsible for promoting the cognitive development of children. Given that children's language ability is still in the development stage, teachers often use pictures to help children understand various things in detail. However, the picture resources in kindergarten teaching materials may be limited in number and may not be updated in a timely manner, limiting children's opportunities to contact and understand new things. In addition, the evaluation of children is often based on the subjective judgment of teachers. Due to the differences in each teacher's understanding of the evaluation criteria, coupled with busy work, personal business capabilities and sense of responsibility, the evaluation results cannot reflect the children's true development level in real time and accurately. Summary of the invention

[0004] The purpose of the present invention is to provide a children's dialogue system based on artificial intelligence technology to solve the problems of limited interaction time between teachers and children and relatively subjective evaluation by teachers.

[0005] In order to solve the above technical problems, the present invention provides a child dialogue system based on artificial intelligence technology, including a system front-end user interface, a first service module, a data storage module and a second service module.

[0006] The system front-end user interface is used to achieve interaction with young children;

[0007] The first service module is used to implement data interaction between the system front-end user interface and the second service module;

[0008] The data storage module is used to store various data related to the child;

[0009] The second service module is used to realize intelligent communication of the system.

[0010] Furthermore, the system front-end user interface includes a deep dialogue module and a cognitive assistance module; the deep dialogue module is capable of communicating with young children; and the cognitive assistance module enriches young children's cognition through visual display.

[0011] Furthermore, the deep dialogue module includes a one-to-one listening unit; the one-to-one listening unit conducts personalized communication with the children through different topics, and the content of the dialogue serves as the basis for evaluating the development level of the children.

[0012] Furthermore, the cognitive assistance module includes a "you say, I draw" unit; the "you say, I draw" unit generates a picture according to the content expressed by the child.

[0013] Furthermore, the cognitive assistance module also includes a creative thinking unit; the creative thinking unit communicates with the child based on the child's ideas.

[0014] Furthermore, the cognitive assistance module also includes a "take a picture and say it" unit; the "take a picture and say it" unit converts the image content taken by the child into a voice description.

[0015] Furthermore, the first service module includes artificial intelligence interaction service, video storage and playback service and dialogue and video content analysis service; the artificial intelligence interaction service module is used to process the interaction between the system front-end user interface and the children; the video storage and playback service module is used for teachers to observe the activities of the children; the dialogue and video content analysis service module is used to analyze the dialogue content between the children and the system, as well as analyze the behaviors and reactions in the children's videos.

[0016] Furthermore, the data storage module includes a child and parent information module, a teacher information module, a conversation record module, a child activity video record module, a policy document module and an evaluation and analysis result module; the child and parent information module is used to store and manage the information of the children and their parents; the teacher information module is used to store the teacher's personal information; the conversation record module serves as a repository for saving the conversation content of each child; the child activity video record module saves video records of children participating in activities; the policy document module is used to store policy documents related to early childhood education and evaluation; the evaluation result module displays the evaluation results based on the policy documents and the conversation content and the children's reactions.

[0017] Furthermore, the second service module includes a large language model, voice service, image generation model, image content recognition model and video storage and broadcasting service; the large language model module is used to summarize, conclude and evaluate the text content; the voice service module is used to process voice signals; the image generation model is used to convert the child's language description or idea into an image; the image content recognition model is used to recognize and understand the image content; the video storage and broadcasting service is used to save the video content of the child's activity process and play it.

[0018] Furthermore, the system front-end user interface can be applicable to the artificial intelligence robot terminal, the parent / teacher mobile terminal, and the teacher's web page terminal; the artificial intelligence robot terminal is used to interact with the children; the teacher mobile terminal and the teacher's web page terminal are used for teachers to view the records and evaluations of the children's interactions with the artificial intelligence robot terminal, and to guide the teachers' teaching and educational work; the parent mobile terminal is used to view the interaction records between the children and the artificial intelligence robot terminal, the children's activity videos, and the system's analysis and evaluation of the children.

[0019] Compared with the prior art, the present invention has at least the following beneficial effects:

[0020] The present invention can solve the problem of insufficient communication time between teachers and children through the system front-end user interface, and significantly prolong the children's dialogue practice time while ensuring the quality of the dialogue. In addition, the system front-end user interface can also provide rich picture resources for kindergarten teaching materials, broadening the children's horizons. At the same time, the children's dialogue system can record and analyze the dialogue content and activity process with children as the main body through the first service module, which can not only reduce the workload of teachers, but also objectively evaluate children, reflect the development level of children in real time and accurately, and further improve the efficiency and quality of education. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is the overall module block diagram of the child dialogue system of the present invention;

[0022] Figure 2 It is a block diagram of the front-end user interface of the child dialogue system of the present invention;

[0023] Figure 3 It is a principle block diagram of the basic dialogue of the present invention;

[0024] Figure 4 It is a functional block diagram of a one-to-one listening unit of the present invention;

[0025] Figure 5 The functional block diagram of the unit of the present invention;

[0026] Figure 6 It is a functional block diagram of the video analysis of the present invention. DETAILED DESCRIPTION

[0027] The following will be described in more detail with reference to a schematic diagram of a child dialogue system based on artificial intelligence technology of the present invention, wherein a preferred embodiment of the present invention is shown, and it should be understood that those skilled in the art can modify the present invention described herein while still achieving the advantageous effects of the present invention. Therefore, the following description should be understood as being widely known to those skilled in the art, and not as a limitation of the present invention.

[0028] The present invention is described in more detail in the following paragraphs by way of example with reference to the accompanying drawings. The advantages and features of the present invention will become more apparent from the following description. It should be noted that the accompanying drawings are in very simplified form and are not in exact proportions, and are only used to facilitate and clearly assist in illustrating the purpose of the embodiments of the present invention.

[0029] like Figure 1 As shown, an embodiment of the present invention proposes a child dialogue system based on artificial intelligence technology, including a system front-end user interface, a first service module, a data storage module and a second service module.

[0030] The system front-end user interface is used to achieve interaction with young children;

[0031] The first service module is used to implement data interaction between the system front-end user interface and the second service module;

[0032] The data storage module is used to store various data related to the child;

[0033] The second service module is used to realize intelligent communication of the system, and adopts existing technologies to realize such as speech recognition, text-speech conversion, text-image conversion, image recognition and video analysis.

[0034] Among them, the system front-end user interface includes a deep dialogue module and a cognitive assistance module, which can be applied to the system front-end user interface and can be applied to artificial intelligence robot terminals, parent / teacher mobile terminals, and teacher web pages.

[0035] The artificial intelligence robot terminal is used to interact with young children and is usually used by young children.

[0036] The teacher mobile terminal and the teacher web page terminal are used by teachers to view the records and evaluations of the interactions between children and the artificial intelligence robot terminal, and can guide teachers' teaching and educational work. Teachers can communicate with artificial intelligence in the corresponding interface, add or modify topics, add or improve children's information, view children's dialogue records, upload policy documents, view evaluation results, etc., thereby facilitating teachers to more effectively manage and participate in children's learning process in daily teaching, and at the same time facilitating teachers to adjust teaching strategies according to children's needs and policy requirements.

[0037] The parent mobile terminal is used to view the interaction records between the child and the artificial intelligence robot terminal, the child's activity video and the system's analysis and evaluation of the child, which facilitates parents to participate in the child's education process and can also promptly discover the child's growth and progress.

[0038] In this embodiment, the first service module includes artificial intelligence interaction service, video storage and playback service, and conversation and video content analysis service.

[0039] The artificial intelligence interactive service module is used to process the interaction between the system front-end user interface and the children, understand and respond to the children's voice input and picture taking through artificial intelligence technology, generate appropriate answers, and convert these answers into voice output or picture output for the children to understand.

[0040] The video storage and playback service module is used by teachers to observe children's activities and can show teachers the process of children's daily life and play and entertainment.

[0041] The dialogue and video content analysis service module is used to analyze the dialogue content between the child and the system, as well as the behavior and reaction of the child in the video, and generate corresponding analysis and evaluation results, so as to facilitate parents and teachers to understand the development level of the child.

[0042] In this embodiment, the second service module includes a large language model and a voice service. The large language model module is used to summarize, conclude, evaluate and analyze text content; and the voice service module is used to process voice signals.

[0043] like Figure 3 As shown, taking the machine end as an example, the child's words are captured by the machine end and an audio file is generated. The audio file is transmitted to the voice service through the first service module. The voice service processes the child's voice and converts it into text; the text content is transmitted to the large language model through the first service module. The large language model makes a corresponding reply based on the received text content, and converts the reply content into audio through the voice service. The audio is transmitted to the machine end through the first service module and played to the child. This process not only realizes the conversion of the child's voice to text, but also completes the re-conversion of text to voice, ensuring effective communication between the child and the machine.

[0044] In a specific embodiment, the deep dialogue module can communicate with the child, thereby meeting the child's unique learning needs, emotional needs and interests; the cognitive assistance module enriches the child's cognition through visual display and other forms.

[0045] like Figure 2 As shown, the deep dialogue module includes a one-to-one listening unit; the one-to-one listening unit conducts personalized communication with the children through different topics, and the content of the dialogue is used as the basis for evaluating the development level of the children. The topics of the communication include but are not limited to the twenty-four solar terms, gardens, food, animals, etc.

[0046] like Figure 4As shown, the teacher clicks on the one-to-one listening unit on the interface to enter the unit. The teacher can use the listening mode in the one-to-one listening unit to personally talk to the child, and based on the child's response, talk around the topic or freely, and save the corresponding conversation record. Alternatively, the child can determine personal information through the guidance of the device without a teacher's conversation, and select a topic to start a conversation; or, the child can choose other topics and start a conversation according to his or her own wishes. If he or she is not satisfied, he or she can reselect the topic on the current page and start a new conversation. After the conversation is completed, you can choose to end it manually or wait for the timeout to end automatically. After the conversation ends, the content of the conversation will be automatically saved.

[0047] In a preferred embodiment, the second service module further includes a picture generation model and a picture content recognition model. The picture generation model is used to convert the child's language description or idea into an image; the picture content recognition model is used to recognize and understand the picture content.

[0048] Continue to refer Figure 2 The cognitive assistance module includes a "you say, I draw" unit, a "wonderful thinking" unit and a "you shoot, I say" unit. The "you say, I draw" unit converts the content expressed by the child into pictures and shows them to the child; the "wonderful thinking" unit communicates with the child based on the child's ideas, which can cultivate the child's imagination and satisfy the child's curiosity and interest; the "you shoot, I say" unit converts the image content taken by the child into voice description, which can improve the child's cognitive level and promote the development of the child's language system.

[0049] like Figure 5 As shown, the child enters the "You Take Photos, I Say" unit, and the child takes a photo through the machine end, which then saves the photo and sends it to the picture content recognition model via the first service module, which analyzes the picture content. At the same time, the child can have a conversation with the machine end based on the content of the photo, and the conversation content is recorded and saved; the conversation content is sent to the voice service via the first service module, and the voice service converts the voice into text. The text is sent to the picture content recognition model via the backend service, and the picture content recognition model generates an appropriate reply based on the picture and text information, and then sends the reply text to the voice service via the first service module to be converted into audio, which is transmitted back to the machine end via the first service module and played to the child.

[0050] In this embodiment, the second service module also includes a video storage and broadcast service, and the video storage and broadcast service is used to save and play video content of children's activities.

[0051] The system is connected to an external camera device, which can be used to record children's activities. Teachers can watch the video on a mobile terminal or a web page. When watching the video, if the teacher thinks that the children's activities and behaviors being played are worth recording, he or she can select the start and end time points, initially save the video of this time period to the system, and use the video content analysis service and evaluation criteria to analyze the children's behavior, and further understand the children through the analysis results.

[0052] Specific as Figure 6 As shown, the video of the children's activities shot by the external camera device is transmitted and saved to the video server. The teacher can watch the video through the teacher's mobile terminal and the Web page terminal, and select some clips to be transmitted to the video content analysis service. The video content analysis service will automatically extract key frames, which are then transmitted to the picture content recognition model for content recognition. The picture content recognition model recognizes the content of each frame and transmits the recognition result to the video content analysis service. The video content analysis service merges the content recognized by each frame and transmits the merged content to the large language model. The large language model summarizes the content and transmits the summary result to the video content analysis service. At this time, the teacher can view the summary result in the corresponding interface of the teacher's mobile terminal and the Web page terminal. The video content analysis service transmits the summarized content and analysis criteria to the large language model, and the large language model analyzes the summarized content and transmits the analysis result to the video content analysis service. The video content analysis service saves the analysis result, and the teacher can view the analysis result in the corresponding interface of the teacher's mobile terminal and the Web page terminal.

[0053] Continue to refer Figure 1 The data storage module includes a child and parent information module, a teacher information module, a conversation record module, a child activity video record module, a policy document module and an evaluation and analysis result module.

[0054] The child and parent information module is used to store and manage the information of the child and his / her parents. The child's personal information includes but is not limited to the child's name, age, gender, hobbies, development level, etc.

[0055] The teacher information module is used to store the teacher's personal information, including but not limited to name, age, gender, education level and teaching classes.

[0056] The conversation record module is used as a repository to store the conversation content of each child, including the child's voice input, the system-generated responses, the pictures generated based on the child's expression, and any related interactions. The teacher can determine whether it is always the same person through the voice files of the conversation record module, and can correct the incorrect recognition content of the device and generate a more accurate evaluation through the corrected content.

[0057] The child activity video recording module is used to save the behaviors and performances of children in different activities captured by external cameras. The system can analyze the children's social interactions, motor skills, learning behaviors, etc. based on the video content to help teachers and parents understand the development of children.

[0058] The policy document module is used to store policy documents related to early childhood education and assessment. Policy documents include but are not limited to the "Guidelines for Learning and Development of Children Aged 3-6", "Guidelines for Observing Developmental Behaviors of Children Aged 3-6", etc.

[0059] The evaluation result module is based on the policy document, and scores and displays the evaluation results according to the conversation content and the children's reactions.

[0060] In summary, with the support of the second service module, the system front-end user interface can solve the problem of insufficient communication time between teachers and children, and significantly extend the children's dialogue practice time while ensuring the quality of the dialogue. In addition, the cognitive auxiliary module provides rich picture resources for kindergarten teaching materials, broadening the children's horizons. At the same time, the children's dialogue system can record and analyze the content of dialogues with children as the main body, and use external cameras to record the children's activities, summarize and analyze the children's behavior, which can not only reduce the workload of teachers, but also objectively evaluate children through artificial intelligence technology, and accurately reflect the children's development level in real time, and further improve the efficiency and quality of education.

[0061] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A children's dialogue system based on artificial intelligence technology, characterized in that: It includes a system front-end user interface, a first service module, a data storage module, and a second service module; The system front-end user interface is used to achieve interaction with young children; The first service module is used to implement data interaction between the system front-end user interface and the second service module; The data storage module is used to store various data related to the child; The second service module is used to realize intelligent communication of the system.

2. The child dialogue system according to claim 1, characterized in that: The system front-end user interface includes a deep dialogue module and a cognitive assistance module; the deep dialogue module can communicate with young children; the cognitive assistance module enriches young children's cognition through visual display.

3. The child dialogue system according to claim 2, characterized in that: The in-depth dialogue module includes a one-to-one listening unit; the one-to-one listening unit conducts personalized communication with children through different topics, and the content of the dialogue serves as the basis for evaluating the development level of the children.

4. The child dialogue system according to claim 2, characterized in that: The cognitive assistance module includes a "you say, I draw" unit; the "you say, I draw" unit generates a picture according to the content expressed by the child.

5. The child dialogue system according to claim 2, characterized in that: The cognitive assistance module also includes a creative thinking unit; the creative thinking unit communicates with the child based on the child's ideas.

6. The child dialogue system according to claim 2, characterized in that: The cognitive assistance module also includes a "take a picture and tell me" unit; the "take a picture and tell me" unit converts the image content taken by the child into a voice description.

7. The child dialogue system according to claim 1, characterized in that: The first service module includes artificial intelligence interaction service, video storage and playback service and dialogue and video content analysis service; the artificial intelligence interaction service module is used to process the interaction between the system front-end user interface and the children; the video storage and playback service module is used for teachers to observe the activities of the children; the dialogue and video content analysis service module is used to analyze the content of the dialogue between the children and the system, as well as to analyze the behaviors and reactions in the children's videos.

8. The child dialogue system according to claim 7, characterized in that: The data storage module includes a child and parent information module, a teacher information module, a conversation record module, a child activity video record module, a policy document module and an evaluation and analysis result module; the child and parent information module is used to store and manage the information of the children and their parents; the teacher information module is used to store the teacher's personal information; the conversation record module serves as a repository for saving the conversation content of each child; the child activity video record module saves video records of children participating in activities; the policy document module is used to store policy documents related to early childhood education and evaluation; the evaluation result module displays the evaluation results based on the policy documents and the conversation content and the children's reactions.

9. The child dialogue system according to claim 1, characterized in that: The second service module includes a large language model, a voice service, an image generation model, an image content recognition model, and a video storage and broadcasting service; The large language model module is used to summarize, conclude, evaluate and analyze the text content; the voice service module is used to process voice signals; the image generation model is used to convert the child's language description or ideas into images; the image content recognition model is used to recognize and understand the image content; the video storage and broadcast service is used to save the video content of the child's activities and play it.

10. The child dialogue system according to claim 1, characterized in that: The system front-end user interface can be applied to the artificial intelligence robot terminal, the parent / teacher mobile terminal, and the teacher Web page terminal; the artificial intelligence robot terminal is used to interact with the children; the teacher mobile terminal and the teacher Web page terminal are used by the teacher to view the records and evaluations of the children's interaction with the artificial intelligence robot terminal, and guide the teacher's teaching and education work; The parent mobile terminal is used to view the interaction records between the child and the artificial intelligence robot terminal, the child's activity video and the system's analysis and evaluation of the child.

Images