WO2020221142A1

WO2020221142A1 - Picture book-based question and answer interaction method and electronic device

Info

Publication number: WO2020221142A1
Application number: PCT/CN2020/086872
Authority: WO
Inventors: 李荣军; 郭文峰; 娄旭芳; 黄雪妍; 董明杰; 刘祖齐
Original assignee: 华为技术有限公司
Priority date: 2019-04-28
Filing date: 2020-04-24
Publication date: 2020-11-05
Also published as: CN111858861B; CN111858861A

Abstract

A picture book-based question and answer interaction method and an electronic device, which relate to the field of artificial intelligence, wherein intelligent interaction with a user is carried out when an electronic device reads a picture book. The question and answer interaction method comprises: an electronic device loading a database related to a target picture book (401); and after receiving a question asked by a user, determining an answer to be responded on the basis of an entity attribute library, a question template library, a call function library, an answer template library, and a word set that are comprised in the database, and outputting the answer to the user. As such, the electronic device can flexibly and automatically determine an answer, and questions and answers do not need to be manually preset; the user does not need to ask questions according to preset questions and can flexibly ask questions, and the electronic device can answer more questions, thus the interaction between the electronic device and the user when reading a picture book may be more intelligent, and the effectiveness of reading the picture book can be improved.

Description

A question and answer interactive method and electronic device based on picture book

This application claims the priority of a Chinese patent application filed with the Chinese Patent Office on April 28, 2019, the application number is 201910349961.6, and the application name is "a method for interactive question and answer and electronic equipment based on picture books", the entire content of which is incorporated by reference In this application.

Technical field

This application relates to the field of artificial intelligence, and in particular to a question and answer interactive method and electronic equipment based on picture books.

Background technique

Artificial intelligence (AI) is a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to obtain the best results. In other words, artificial intelligence is a branch of computer science that attempts to understand the essence of intelligence and produce a new kind of intelligent machine that can react in a similar way to human intelligence. Artificial intelligence is to study the design principles and implementation methods of various intelligent machines, so that the machines have the functions of perception, reasoning and decision-making. Research in the field of artificial intelligence includes robotics, natural language processing, computer vision, decision-making and reasoning, human-computer interaction, recommendation and search, and basic AI theories.

Currently, artificial intelligence is widely used in electronic devices with the function of reading picture books, such as smart speakers, smart robots, smart learning machines, and so on. For example, when the electronic device reads a picture book, it will ask children questions based on preset questions and answers.

However, the current electronic equipment mechanically asks the user based on the preset question and answer pair. The order of the questions asked to the user is preset, the answer is also preset, and it can only ask questions to children. To answer children’s questions, the interactivity is greatly reduced, and it cannot achieve the effect of replacing parents with storytelling.

Therefore, there is an urgent need for a method and electronic device that can flexibly implement question and answer interactions with users, especially in the process of reading picture books by electronic devices that can intelligently perform question and answer interactions with users (such as children).

Summary of the invention

This application provides a question and answer interaction method based on a picture book and an electronic device, which can intelligently interact with the user during the process of reading the picture book by the electronic device.

In the first aspect, this application provides a question and answer interaction method based on picture books. The method includes: an electronic device loads a database related to a target picture book, wherein the database includes an entity attribute library, a question template library, a calling function library, An answer template library and a word set, the entity attribute library includes multiple entity names and multiple entity attributes, the multiple entity names correspond to the multiple entity attributes one-to-one, and the question template database includes at least one A question template, the call function library includes at least one call function, each question template in the question template library corresponds to one or more call functions in the call function library, and each question template library The question template includes a plurality of slots, the answer template library includes at least one answer template, the answer templates in the answer template library correspond to the calling functions in the calling function library, and the word set indicates Correspondence between multiple keywords and generalized words, the generalized words include entities; the electronic device receives the user's question; the electronic device performs word segmentation processing on the user's question to obtain word segmentation Word string, the word segmentation string is a plurality of keyword text sequences; then the electronic device obtains a generalized question according to the word segmentation string and the word set, and the generalized question is multiple A generalized word text sequence; the electronic device extracts the entity name corresponding to the question posed by the user from the generalized question, and the entity name corresponding to the question posed by the user is the generalized The question in the question is generalized into an entity keyword; the electronic device obtains the question template to be asked from the question template library according to the text similarity between the generalized question and the question template in the question template library; The electronic device obtains the questioned calling function from the calling function library according to the degree of matching between the slot of the question template being asked and the parameter of the calling function in the calling function library; The question call function and the entity name corresponding to the question posed by the user are obtained from the entity attribute library and the entity attribute corresponding to the entity name corresponding to the question posed by the user is obtained; and finally the electronic device is based on the question The calling function obtains an answer template to be answered from the answer template library, the answer template to be answered is an answer template in the answer template library corresponding to the called function of the question, and based on the answer template to be answered The entity name corresponding to the question posed by the user and the entity attribute corresponding to the entity name corresponding to the question posed by the user generate an answer to be answered, and output the answer to be answered to the user.

Through the above method, the electronic device can flexibly determine the answer based on the user’s question based on the database related to the target picture book. It does not need to mechanically preset the question and answer. The user does not need to ask the question according to the preset question, but can ask the question flexibly , The electronic device can also answer more questions, so that the interaction between the electronic device and the user during the picture book reading process can be more intelligent, and the effectiveness of reading picture books can be improved.

In a possible design, the number and types of the parameters of the questioned calling function have the highest matching degree with the number and types of slots of the question template. In this way, the function called by the questioned question can be accurately determined, so that the answer to be answered can be accurately determined subsequently.

In a possible design, the electronic device updates the entity attribute database according to the entity name and entity attributes contained in the interaction history information; wherein, the interaction history information is the result of reading the target picture book on the electronic device In the process, the electronic device receives speech information input by the user or action information of the user.

Through the above method, the electronic device can make the updated entity attribute library more in line with user needs, make human-computer interaction more targeted, and make reading deeper.

In a possible design, before the electronic device loads the database related to the target picture book, the electronic device collects the image of the picture book displayed by the user through a camera; the electronic device collects The image of the picture book is analyzed to determine the target picture book.

Through the above method, the electronic device can flexibly and accurately obtain the target picture book, so that the subsequent electronic device can accurately obtain the database related to the target picture book and enter the subsequent question and answer interaction process with the user.

In a possible design, when the electronic device includes a display screen, when the electronic device outputs the answer to be answered to the user, it may also display the answer to be answered through the display screen.

Through the above method, the electronic device can output the answer to the user more flexibly, and the answer can be displayed on the display screen while answering the user by voice, making the output of the electronic device more intuitive, making the user easier to understand, and improving user acceptance degree.

In a possible design, when the electronic device further includes a movable component, when the electronic device outputs the answer to be answered to the user, the electronic device may also control the movable component to perform outputting. Describe the action to be answered.

Through the above method, the electronic device can output the answer to the user more flexibly, and the answer can be indicated by performing an action while answering the user by voice, so that the output of the electronic device is more diversified and the user's acceptance is improved.

In the second aspect, this application provides a question and answer interaction method based on picture books. The method includes: an electronic device loads a database related to a target picture book, wherein the database includes an entity attribute library, a question template library, and a calling function library, The entity attribute library includes multiple entity names and multiple entity attributes, the multiple entity names correspond to the multiple entity attributes one-to-one, the question template library includes at least one question template, and the calling function library Contains at least one calling function, each question template in the question template library corresponds to one or more calling functions in the call function library, and each question template in the question template library includes multiple slots; The electronic device obtains a question template to be asked from the question template library according to question template information, the question template information is a transition probability set or a question template type, and the transition probability set includes a historical question template and the question template library The transition probability between other question templates in the above, the historical question template is a question template obtained by the electronic device in the process of generating the last question posed to the user, and the question template type is related to the age of the user; The electronic device obtains the calling function to be asked from the calling function library according to the degree of matching between the slot of the question template to be asked and the parameter of the calling function in the calling function library; The question calling function obtains the entity name corresponding to the question template to be asked and/or the entity attribute corresponding to the question template to be asked from the entity attribute library; based on the question template to be asked, the electronic device The entity name corresponding to the question template to be asked and/or the entity attribute corresponding to the question template to be asked generates the question to be asked; finally, the electronic device outputs the question to be asked to the user.

Through the above method, the electronic device can automatically generate questions to be asked according to the database related to the target picture book, and does not need to preset the questions, and does not mechanically ask the user according to the preset questions, so that the picture book can be read In the process, the interaction between electronic devices and users is more intelligent, which can improve the effectiveness of reading picture books.

In a possible design, the database further includes an answer template library, the answer template library contains at least one answer template, and the answer templates in the answer template library are one-to-one with the calling functions in the calling function library. Corresponding; the electronic device extracts the entity name corresponding to the question to be asked and/or the entity attribute corresponding to the question to be asked from the question to be asked; then, the electronic device calls according to the question to be asked Function and the entity name corresponding to the question to be asked, the entity attribute corresponding to the entity name corresponding to the question to be asked is obtained from the entity attribute library, or the electronic device calls the function and The entity attribute corresponding to the question to be asked is obtained from the entity attribute library and the entity name corresponding to the entity attribute corresponding to the question to be asked is obtained; finally, the electronic device calls the function according to the question to be asked from the answer A to-be-determined answer template is obtained from a template library, where the to-be-determined answer template is an answer template in the answer template library that corresponds to the call function to be asked, and based on the to-be-determined answer template, the electronic device will A keyword generates a to-be-determined answer, and the keyword of the to-be-determined answer is any one of the following: the entity attribute corresponding to the entity name corresponding to the question to be asked, the entity name corresponding to the question to be asked, and the question to be asked The entity attribute corresponding to the entity name corresponding to the question, the entity attribute corresponding to the question to be asked, the entity attribute corresponding to the question to be asked, and the entity name corresponding to the entity attribute corresponding to the question to be asked.

Through the above method, the electronic device can automatically generate the answers to the questions to be asked according to the database related to the target picture book, and does not need to mechanically preset the question answer pairs, which can make the electronic device ask questions and user answers more during the picture book reading process. Flexible, so that the interaction between the electronic device and the user in the picture book reading process can be more intelligent, and the effectiveness of reading picture books can be improved.

In a possible design, the electronic device receives the user's answer to the question to be asked, and compares the user's answer to the question to be asked with the answer to be determined to obtain the user According to the result of judging whether the answer is correct, corresponding operations are made to the user according to the judgment result.

Through the above method, the electronic device can accurately determine whether the user's answer is correct, and perform corresponding operations to the user to directly or indirectly prompt the user whether the answer is correct, which can improve the user's acceptance of the answer.

In a possible design, the number and types of parameters of the calling function to be asked have the highest matching degree with the number and types of slots of the template of the question to be asked. In this way, the function to be called can be accurately determined, so that the answer to be determined can be accurately determined subsequently.

In a possible design, when the question template information is the transition probability set, the electronic device obtains the question template to be asked from the question template library according to the question template information, and the specific method may be: The electronic device determines the target transition probability from the set of transition probabilities according to a predetermined random value; the electronic device obtains the question template to be asked from the question template library according to the target transition probability.

Through the above method, the electronic device can make more diversified questions, prevent the user from feeling bored, and increase the user's interest in picture book reading.

In a possible design, when the question template information is the question template type, the electronic device obtains the question template to be asked from the question template library according to the question template information. The specific method may be: The electronic device determines the target question template type according to the user’s age and the corresponding relationship between the age and the question template type; the corresponding relationship indicates that the user’s age corresponds to at least one of the following question template types: space, detail, society, color, number, Text and nature; the electronic device obtains a question template that meets the target question template type from the question template library as the question template to be asked.

Through the above method, a question template that is more suitable for the user's cognitive ability can be selected, so that subsequent questions are more targeted, and the user's reading is more effective.

In the third aspect, the embodiments of the present application also provide an electronic device, which has the function of implementing the behavior of the electronic device in the method example of the first aspect. The function can be realized by hardware, or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above-mentioned functions.

In a possible design, the structure of the electronic device includes a processing unit, an input unit, and an output unit. These units can perform the corresponding functions in the method example of the first aspect. For details, please refer to the detailed description in the method example. Do not repeat it.

In a possible design, the structure of the electronic device includes a processor and a communication unit, and may also include a memory. The communication unit is used to interact with a user; the processor is configured to support the electronic device to perform the corresponding function in the above-mentioned method in the first aspect. The memory is coupled with the processor, and stores the necessary program instructions and data of the electronic device.

In a possible design, the electronic device includes a processor and a memory connected to each other, and the processor is configured to read and execute program instructions stored in the memory, and execute any one of the possible options in the first aspect. The methods mentioned in the design.

In a fourth aspect, an embodiment of the present application also provides an electronic device that has a function of implementing the behavior of the electronic device in the method example of the second aspect. The function can be realized by hardware, or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above-mentioned functions.

In a possible design, the structure of the electronic device includes a processing unit and an output unit, and may also include an input unit. These units can perform the corresponding functions in the method example of the second aspect. For details, please refer to the detailed description in the method example , Do not repeat it here.

In a possible design, the structure of the electronic device includes a processor and a communication unit, and may also include a memory. The communication unit is used to interact with a user; the processor is configured to support the electronic device to perform the corresponding function in the method of the second aspect. The memory is coupled with the processor, and stores the necessary program instructions and data of the electronic device.

In a possible design, the electronic device includes a processor and a memory connected to each other, and the processor is configured to read and execute program instructions stored in the memory, and execute any one of the possible options in the second aspect. The methods mentioned in the design.

In a fifth aspect, the embodiments of the present application also provide a computer-readable storage medium in which computer-executable instructions are stored, and the computer-executable instructions are used to make the computer executable when called by the computer. The computer executes the method mentioned in any possible design in the first aspect or the second aspect.

In the sixth aspect, the embodiments of the present application also provide a computer program product containing instructions, which when run on an electronic device, causes the electronic device to execute any of the possible designs in the first aspect or the second aspect. The mentioned method.

In a seventh aspect, an embodiment of the present application also provides an electronic device. The electronic device may be a chip, and the chip is connected to a memory, and is used to read and execute the program instructions stored in the memory to implement the above-mentioned The method mentioned in any possible design in one aspect or in the second aspect.

Description of the drawings

Figure 1 is a schematic diagram of a main artificial intelligence framework provided by this application;

Figure 2 is a schematic diagram of an application scenario provided by this application;

Figure 3 is a schematic structural diagram of an electronic device provided by this application;

FIG. 4 is a flowchart of a question and answer interaction method based on picture books provided by this application;

FIG. 5 is a flowchart of another question and answer interaction method based on picture books provided by this application;

FIG. 6 is a schematic diagram of the transition probability between question templates provided by this application;

Figure 7 is a flow chart for updating the entity attribute database provided by this application;

Figure 8 is another flow chart for updating the entity attribute database provided by this application;

FIG. 9 is a schematic diagram of identifying a position in a picture book provided by this application;

FIG. 10 is a schematic diagram of a question and answer interaction process provided by this application;

Figure 11 is a schematic diagram of another question and answer interaction process provided by this application;

Figure 12 is a schematic diagram of a child's intention provided in this application;

FIG. 13 is a schematic diagram of a picture book provided by this application;

Figure 14 is a flow chart of a method for inquiring about purchasing goods provided by this application;

FIG. 15 is a schematic structural diagram of an electronic device provided by this application;

FIG. 16 is a structural diagram of an electronic device provided by this application.

Detailed ways

The application will be further described in detail below in conjunction with the accompanying drawings.

The embodiment of the present application provides a question and answer interaction method based on a picture book and an electronic device, which are used to intelligently interact with a user during the process of reading the picture book by the electronic device. Among them, the method and the electronic device described in this application are based on the same inventive concept. Since the method and the principle of the electronic device to solve the problem are similar, the implementation of the electronic device and the method can be referred to each other, and the repetition will not be repeated.

Figure 1 shows a schematic diagram of an artificial intelligence main framework, which describes the overall workflow of the artificial intelligence system and is suitable for general artificial intelligence field requirements.

The following describes the above-mentioned artificial intelligence theme framework from the two dimensions of "intelligent information chain" (horizontal axis) and "IT value chain" (vertical axis).

"Intelligent Information Chain" reflects a series of processes from data acquisition to processing. For example, it can be the general process of intelligent information perception, intelligent information representation and formation, intelligent reasoning, intelligent decision-making, intelligent execution and output. In this process, the data has gone through the condensing process of "data-information-knowledge-wisdom". The "IT value chain" from the underlying infrastructure of human intelligence, information (providing and processing technology realization) to the system's industrial ecological process, reflects the value that artificial intelligence brings to the information technology industry.

(1) Infrastructure: Infrastructure provides computing power support for artificial intelligence systems, realizes communication with the outside world, and realizes support through the basic platform. Communicate with the outside through sensors; computing capabilities are provided by smart chips (CPU, NPU, GPU, ASIC, FPGA and other hardware acceleration chips); the basic platform includes distributed computing framework and network related platform guarantees and support, which can include cloud storage and Computing, interconnection network, etc. For example, sensors communicate with the outside to obtain data, and these data are provided to the smart chip in the distributed computing system provided by the basic platform for calculation.

(2) Data: The data in the upper layer of the infrastructure is used to indicate the data source in the field of artificial intelligence. The data involves graphics, images, voice, and text, as well as IoT data of traditional devices, including business data of existing systems and sensory data such as force, displacement, liquid level, temperature, and humidity.

(3) Data processing: Data processing usually includes data training, machine learning, deep learning, search, reasoning, and decision-making. Among them, machine learning and deep learning can symbolize and formalize data for intelligent information modeling, extraction, preprocessing, training, etc. Reasoning refers to the process of simulating human intelligent reasoning in a computer or intelligent system, using formal information to conduct machine thinking and solving problems based on reasoning control strategies. The typical function is search and matching. Decision-making refers to the decision-making process of intelligent information after reasoning, and usually provides functions such as classification, ranking, and prediction.

(4) General capabilities: After the data is processed as mentioned above, some general capabilities can be formed based on the results of data processing, such as algorithms or a general system, for example, translation, text analysis, computer vision Processing, speech recognition, image recognition, etc.

(5) Smart products and industry applications: Smart products and industry applications refer to the products and applications of artificial intelligence systems in various fields. It is an encapsulation of the overall solution of artificial intelligence, productizing intelligent information decision-making and realizing landing applications. Its application fields Mainly include: smart manufacturing, smart transportation, smart home, smart medical, smart security, autonomous driving, safe city, smart terminal, etc.

Artificial intelligence has wide applications in many fields, such as human-computer question answering and interaction. The question and answer interactive method based on picture books provided in this application belongs to the field of artificial intelligence.

The picture book-based question and answer interaction method provided by the embodiment of the application is applied to a picture book question and answer system. It should be understood that question and answer are one question and one answer, and this type of question and answer usually includes two types: one is for people to ask the machine to answer, and the other is for machines to ask people to answer. However, the question and answer interaction method based on picture books provided by the embodiments of the present application is generally the question and answer interaction between the child and the machine that occurs when the machine is reading the picture book for the child (ie, the user).

FIG. 2 shows a possible application scenario to which the picture book-based question and answer interaction method provided by an embodiment of the present application is applicable, and the application scenario may include a user and an electronic device. among them:

In the embodiments of this application, users generally refer to children who need to listen to picture books and read. Therefore, in the embodiments of this application, the user is a child as an example for description. The electronic device may be a physical device with a voice output function. In a specific implementation, the electronic device may be a smart terminal, such as a smart phone or smart terminal shown in FIG. 2; the electronic device may also be The wearable terminal or robot shown in FIG. 2. Of course, the electronic device is not limited to the example shown in FIG. 2, but can also be other electronic devices, such as notebook computers, tablet computers, car computers, personal digital assistants (personal digital assistant, PDA), smart watches, personal computers ( (personal computer, PC), TV, etc. Of course, the electronic device is not limited to the above-listed devices, and this application does not limit it.

The electronic device has at least the functions of receiving sound and voice, and outputting sound and voice.

In an optional manner, in addition to the above-mentioned functions, the electronic device also has functions such as sound or voice analysis, semantic analysis, and speech synthesis. If the electronic device has the capabilities of data storage and data processing, in this application scenario Only the user and the electronic device can complete the question and answer interactive process on the picture book.

In another optional implementation manner, if the electronic device does not have data storage and data processing capabilities, the electronic device can be connected to a server through a network, and the server completes the storage and processing of data, as shown in FIG. 2 .

Of course, when the electronic device has the capability of data storage and data processing, in order to reduce the energy consumption of the electronic device, the electronic device can also be connected to a server via a network, and the server completes the storage and processing of data. There is no restriction on this.

Optionally, in addition to the above-mentioned functions, the electronic device may also include a camera, which can be used to take picture books for reading picture books, or take pictures of children for subsequent image analysis and so on.

Of course, when the electronic device is a robot or other device with movable parts, the electronic device can also interact with children more flexibly through limbs or movable parts, such as hugging, giving instructions and so on.

It should be noted that the application scenario diagram shown in FIG. 2 may also include other devices, which are not shown here.

Since the picture book-based question and answer interaction method provided by the embodiment of the present application is applicable to electronic equipment, the electronic equipment will be briefly introduced below. Fig. 3 shows a partial structural block diagram of the electronic device related to this embodiment. 3, the electronic device 300 may include: a communication unit 310, a power supply 320, a processor 330, a memory 340, an input unit 350, an output unit 360, an audio circuit 370 and other components. Those skilled in the art can understand that the structure of the electronic device shown in FIG. 3 does not constitute a limitation on the electronic device, and may include more or less components than shown in the figure, or a combination of certain components, or different component arrangements. .

Hereinafter, each component of the electronic device 300 will be specifically introduced with reference to FIG. 3:

The communication unit 310 may provide voice or data communication capabilities, and may provide a wired or wireless communication interface. Optionally, the communication unit 310 may include radio frequency (RF) transceiver components, global positioning system (global positioning system, GPS) transceiver components (for example, the RF circuit 311 shown in FIG. 3), and wireless fidelity (wireless fidelity, WiFi) components (for example, the WiFi module 312 shown in FIG. 3), some or all of other components, etc.; the communication unit 310 may also be software and hardware (for example, an antenna, a modulator/demodulator, an /Decoder, analog/digital processing circuit, etc.).

Wherein, the RF circuit 311 can be used for receiving and sending data in the process of sending and receiving information or talking. In particular, after the RF circuit 311 receives the downlink data from the base station, it sends it to the processor 330 for processing; in addition, it sends the uplink data to be sent to the base station. Generally, the RF circuit 311 includes but is not limited to an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier (LNA), a duplexer, and the like. In addition, the RF circuit 311 can also communicate with the network and other devices through wireless communication. The wireless communication may use any communication standard or protocol, including but not limited to the global system of mobile communication (GSM), general packet radio service (GPRS), code division multiple access (code division multiple access). division multiple access (CDMA), wideband code division multiple access (WCDMA), long term evolution (LTE), email, short messaging service (SMS), etc.

The audio circuit 370, the speaker 371, and the microphone 372 can provide an audio interface between the user and the electronic device 300. The audio circuit 370 can transmit the electrical signal converted from the received audio data to the speaker 371, and the speaker 371 converts it into a sound signal for output; on the other hand, the microphone 372 converts the collected sound signal It is an electrical signal that is received by the audio circuit 370 and converted into audio data, and then the audio data is output to the RF circuit 310 for sending to, for example, another electronic device, or the audio data is output to the memory 340 for further processing .

WiFi is a short-distance wireless transmission technology. The electronic device 300 can be connected to an access point (AP) through the WiFi module 312, thereby achieving data network access. The WiFi module 312 can be used to receive and send data during communication with other devices.

The memory 340 can be used to store software programs and modules. The processor 330 executes various functional applications and data processing of the electronic device 300 by running software programs and modules stored in the memory 340. Optionally, the memory 340 may mainly include a program storage area and a data storage area, where the program storage area may store an operating system, various application programs, etc.; the storage data area may store information according to the use of the electronic device 300 Data created, etc. Specifically, optionally, the processor 340 may also store static data (for example, images, etc.), rules, etc. required by the processor 330 and other modules. For example, in the embodiment of the present application, the memory 340 may store the content of a picture book and a database related to the picture book. In addition, the memory 340 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.

It should be noted that the function of the above-mentioned memory 340 may be embodied in the electronic device 300 as shown in FIG. 3, and may also be implemented in a server (for example, a cloud server), etc., and it is only exemplified here as a part of the electronic device 300. But not as a limitation on memory.

The input unit 350 can be used to receive input digital, sound or character information, and generate key signal input related to user settings and function control of the electronic device 300. For example, in this embodiment, the input unit 350 can receive and input a child's voice. Specifically, the input unit 350 may include a touch panel 351 and other input devices 352.

Wherein, the touch panel 351, which can also be called a touch screen, can collect user touch operations on or near it (for example, the user uses a finger, a stylus, or any other suitable object or accessory on the touch panel 351 or touches it. The operation near the control panel 351), and drive the corresponding connection device according to the preset program. Optionally, the touch panel 351 may include two parts: a touch detection device and a touch controller. Wherein, the touch detection device detects the user's touch position, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives touch information from the touch detection device, and It is converted into contact coordinates, and then transmitted to the processor 330, and can receive and execute the command sent by the processor 330. For example, when the user touches the picture book catalog displayed on the display panel 3611 on the touch panel 351 by hand, the touch detection device detects this signal brought about by this touch, and then transmits the signal to The touch controller, the touch controller then converts this signal into coordinates and sends it to the processor 330, and the processor 330 determines what is executed on the picture book catalog according to the coordinates and the type (touch) of the signal. Operate (select a picture book in the picture book catalog), and then the processor 330 will instruct to read the selected picture book.

In addition, the touch panel 351 can be implemented in multiple types such as resistive, capacitive, infrared, and surface acoustic wave.

Optionally, the other input device 352 may include, but is not limited to, one or more of a physical keyboard, function keys (such as volume control buttons, switch buttons, etc.), trackball, mouse, and joystick.

The output unit 360 may be used to output various information for user interaction or provided to the user. Optionally, the output unit 360 may include a display unit 361, a vibration motor (which can be used to provide vibration feedback), and so on.

Wherein, the display unit 361 can be used to display information input by the user, information provided to the user, and various menus of the electronic device 300. The display unit 361 is the display system of the electronic device 300 for The interface is presented to realize human-computer interaction. For example, when the input unit 350 receives a user's instruction requiring human-computer interaction, it transmits the instruction to the processor 330, and then the processor 330 displays the picture book through the display unit 361 according to the instruction ( Specifically, the picture book can be displayed through the display panel 3611, so that the user can see the picture book, and thus human-computer interaction can be realized.

The display unit 361 may include a display panel 3611. Optionally, the display panel 3611 may be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), etc. Further, the touch panel 351 can cover the display panel 3611, and when the touch panel 351 detects a touch operation on or near it, it is transmitted to the processor 330 to determine the type of touch event, Then the processor 330 provides corresponding visual output on the display panel 3611 according to the type of the touch event. For example, when the touch panel 351 detects that the user clicks on it to select a picture book, it transmits it to the processor 330, and the processor 330 determines that the type of the touch event is a click, and displays it on the display panel 3611 The content of the corresponding picture book after being selected, such as the picture in the selected picture book, etc., achieve the purpose of displaying the picture book.

Although in FIG. 3, the touch panel 351 and the display panel 3611 are used as two independent components to implement the input and input functions of the electronic device 300, but in some embodiments, the The touch panel 351 is integrated with the display panel 3611 to realize the input and output functions of the electronic device 300.

The processor 330 is the control center of the electronic device 300, and uses various interfaces and lines to connect various parts of the entire electronic device, and by running or executing software programs and/or modules stored in the memory 340, and calling The data stored in the memory 340 executes various functions of the electronic device 300 and processes data, thereby realizing various services based on the electronic device 300. Optionally, the processor 330 may include one or more processing units; specifically, the processor 330 may integrate an application processor and a modem processor, where the application processor mainly processes an operating system, User interface and application programs, etc., the modem processor mainly handles wireless communication. It can be understood that the foregoing modem processor may not be integrated into the processor 330. For example, in this application, the processor 330 may include a display driving unit, and after the processor 330 generates a picture book, the display driving unit may control the display panel 3611 to present the contents of the picture book through the display driving unit. For another example, a display driver program is stored in the memory 340, and the processor 330 may call the driver program in the memory 340 to control the display panel 3611 to present picture book content.

The electronic device 300 also includes the power source 320 (such as a battery) for supplying power to various components. Optionally, the power source 320 may be logically connected to the processor 330 through a power management system, so as to pass through the power management system. Realize the functions of managing charging, discharging, and power consumption.

It should be noted that, although not shown in FIG. 3, the electronic device 300 may also include a camera, a Bluetooth module, a sensor, etc., which will not be repeated here.

The picture book-based question and answer interaction method provided by the embodiment of the application mainly includes two interactive processes: the child asks the electronic device and the electronic device answers the child's question; and the electronic device actively asks the child and the child answers the electronic device’s question. The electronic device determines whether the child's answer is correct. Of course, there are other voice interactions between the child and the electronic device in the above two processes. Specifically, in the above-mentioned question and answer interaction process, data processing and data storage are required. The stored data involved in this embodiment is mainly a database related to picture books, and the specific database may include an entity attribute library, a grammar library, a word collection, and a calling function library. Wherein, further, the grammar library may also include a question template library and an answer template library. Exemplarily, the entity attribute library is used to store multiple entity names and multiple entity attributes related to the content of the picture book, and the multiple entity names correspond to the multiple entity attributes in a one-to-one correspondence, wherein the entity refers to the real world Objects or things that exist objectively and can be distinguished from each other. Concrete entities often refer to a collection of certain types of things, which can be concrete people, things, abstract concepts, connections, etc.; the problem template library is used to store A sentence template used to generate a question, that is, the question template library contains at least one question template, and each question template may include multiple slots; the calling function library is used to store calling functions for obtaining answers based on questions, Set functions and parameters for each question template, and the function defines the path and rules corresponding to the answer to the question template from the database. Each question template in the question template library may correspond to one or more calling functions in the calling function library; the answer templates in the answer template library correspond to the calling functions in the calling function library one-to-one The word set indicates the correspondence between a plurality of keywords and generalized words, and the generalized words include entities. The database needs to be pre-established, pre-stored in the electronic device, and data processing by the electronic device, or pre-stored in a server connected to the electronic device, and the server assists in data processing. The following briefly introduces the pre-establishment method of the database:

For example, the process of establishing the question template library can be as follows:

a1. Collect problem samples from data providers and other channels, extract key words, and compose simplified problem samples.

Take the picture book "Rose the Hen Going for a Walk" as an example, the collected questions can be "What color is the hen?", "What color is Rose?", "Is the hen yellow?", "This one What color is the hen?" Wait.

a2. Construct a problem template based on the problem sample.

Specifically, put words with the same meaning in the same set, and name each set; for example, among the keywords extracted from the sample question shown in a1 above, "hen", "Rose "Belongs to the same kind of words. Putting these similar words in the same set can be named "Entity"; the set of "What" and "Which" are located can be named "Common word (What)" ; The collection of "color", "red", "yellow", etc. can be named "Color" (where color is a specific entity attribute). Specifically, Entity, What, Color, etc. can be called generalized words. A set of words indicating the correspondence between multiple keywords and generalized words can be stored in the database. For example, the word set can be as shown in Table 1:

Table 1

泛化词Generalized words	关键词Key words
EntityEntity	母鸡、萝丝、母鸡萝丝Hen, rose, rose hen
WhatWhat	什么、哪种What, what

Color

Color, red, yellow, blue

Then, the generalized words in the word set are used to replace the specific words in the problem sample to obtain the generalized problem sample, that is, the generalized problem. Among them, generalization refers to the expansion of specific and individual to general, for example, generalization of hens to Entity.

Exemplarily, after the above question samples are generalized, the question template obtained can be (Entity)[是][What](Color), other question templates such as (Entity)[在][Where] and so on. The problem templates in the established problem template library are shown in Table 2:

Table 2

问题模板1Question template 1	(Entity)[是][What](Color)(Entity)[是][What](Color)
问题模板2Question template 2	(Entity)[在][Where](Entity)[在][Where]

Wherein, the question template is a combination of mandatory word set names, mandatory words, optional word set names, and optional words. Fill in the mandatory word set names or mandatory words in (), and fill in the optional word set names Or fill in the optional words in [], where the content in () and [] can be called the slots included in the question template.

For example, the process of establishing the calling function library may be as follows:

Set up a calling function for each question template. Wherein, the calling function may include functions and parameters, where the function defines the path and rules corresponding to the answer to the question template extracted from the entity attribute library, that is, the meaning of the function represented by the function, including the name of the table for extracting the answer. Extracted field names, etc. The function expresses the user's intention. The parameters correspond to the output of the problem template and provide constraints for the function. For example, the calling function corresponding to the above question template 1 can be:

getColor(Entity,What,Color): Get the color of the specified entity.

isExist(Entity,What): Determine whether the query entity exists.

isFact(Entity,Color): Determine whether the color of the entity matches the facts.

Exemplarily, the calling function corresponding to the question template 1 may be as shown in Table 3:

table 3

For example, the establishment process of the answer template library is to set an answer template for each calling function. For example, the answer template corresponding to each calling function can be as shown in Table 4:

Table 4

调用函数(函数+参数)Call function (function + parameter)	答案模板Answer template
1、getColor(Entity,What,Color)1.getColor(Entity,What,Color)	Entity是Color的Entity is Color
2、isExist(Entity,What)2. isExist(Entity,What)	有EntityEntity
3、isFact(Entity,Color)3. isFact(Entity,Color)	Entity是Color的Entity is Color

Based on the content in the established database, data processing in the question and answer interaction process between the child and the electronic device can be realized, thereby realizing human-computer interaction. The following uses a specific example to introduce the question and answer interaction method based on a picture book provided by the embodiment of the present application.

Embodiment 1: The child asks questions to the electronic device and the electronic device answers the specific method flow. The electronic device may be any device shown in FIG. 2 or not shown that can implement the picture book-based question and answer interaction method provided in the embodiment of the present application, and the electronic device is applied to the device shown in FIG. 3 Electronic equipment. Referring to Figure 4, the specific process of the method may include:

Step 401: The electronic device loads a database related to the target picture book.

Wherein, the database includes an entity attribute library, a question template library, a calling function library, an answer template library, and a word set. The entity attribute library includes multiple entity names and multiple entity attributes, and the multiple entity names are related to The multiple entity attributes are in one-to-one correspondence, the question template library includes at least one question template, the call function library includes at least one call function, and each question template in the question template library corresponds to the call function One or more calling functions in the library, each question template in the question template library includes multiple slots, the answer template library includes at least one answer template, and the answer template in the answer template library is consistent with all the The calling functions in the calling function library have a one-to-one correspondence, and the word set indicates the correspondence between a plurality of keywords and generalized words, and the generalized words include entities.

It should be understood that the target picture book is a picture book that needs to be read by children.

Exemplarily, before the electronic device loads the database related to the target picture book, the electronic device determines the target picture book based on a child's instruction. Specifically, the method for the electronic device to determine the target picture book may include Variety:

In one embodiment, the electronic device asks the child which picture book the child wants to listen to. For example, the electronic device asks the child "Shall we read a story?", and the child answers "OK, I want to listen to the hen "Silk", after receiving the user's answer, the electronic device determines that the target picture book is "Hen Rose Going for a Walk" according to semantic analysis and matching.

Optionally, when the electronic device cannot perform data processing, the electronic device sends the child's answer received to the server, and the server performs semantic analysis and matching, and then after determining the target picture book, it will determine The result of notifying the electronic device, and then the electronic device knows that the target picture book is "Rose the Hen Going for a Walk" according to the determined result.

In another embodiment, when the electronic device has a display touch screen, such as a mobile phone, a robot with a display touch screen, etc., a picture book catalog can be displayed on the display touch screen, that is, multiple picture books are displayed for children to choose. Click the selected picture book to confirm the target picture book. For example, if the child clicks "Rose the Hen Going for a Walk" on the display touch screen, the electronic device determines that the target picture book is "Rose the Hen Going for a Walk".

In another embodiment, when the electronic device has a camera, for example, when the electronic device is a mobile phone, a robot with a touch screen, etc., the electronic device can collect information of the picture book displayed by the child through the camera. Image, the image of the collected picture book is analyzed by image analysis technology to determine the target picture book.

Optionally, when the electronic device cannot perform data processing, the electronic device sends the image of the picture book collected by the camera to the server, and the server analyzes the collected image of the picture book through image analysis technology. , And then after determining the target picture book, notify the electronic device of the determined result, and then the electronic device learns the target picture book according to the determined result.

Of course, the electronic device may determine the target picture book in multiple ways other than the above methods, which will not be listed here.

In the following description, the target picture book is "Rose the Hen Going for a Walk" as an example.

In specific implementation, when the database is stored in the electronic device, the electronic device can directly load the database related to the target picture book from the memory or other modules of the electronic device; when the database is stored in the server In the middle, the electronic device needs to load the database related to the target picture book from the server.

Wherein, the database acquired by the electronic device includes the entity attribute database. For example, when the target picture book is "Hen Rose Going for a Walk", the entity attribute library loaded by the electronic device locally or from a server may be as shown in Table 5:

table 5

实体(Entity)Entity	实体属性(Color)Entity attributes (Color)
母鸡hen	红色red
小鸟Little bird	黄色yellow
狐狸fox	棕黄色Brownish yellow
……...	……...

Among them, the entity names of the entities in Table 5 can be hen, bird, fox..., and the corresponding entity attributes of each entity name are red, yellow, brown....

In an embodiment, the question template library and the calling function library included in the database related to the target picture book loaded by the electronic device may be as shown in Table 6:

Table 6

Step 402: The electronic device receives the question raised by the child.

Wherein, when the electronic device reads the target picture book, when the electronic device receives the question posed by the child, it defaults that the child asked based on the target picture book, that is, the The children’s questions are considered to be related to the target picture book.

Specifically, the electronic device may obtain the child's question through the input unit, and then transmit the child's question to the processor of the electronic device, so that the processor can analyze the child's question; or The processor of the electronic device transmits the question raised by the child to a server, so that the server analyzes the question raised by the child.

For example, the child inputs the question "What color is the hen?" to the electronic device through the microphone of the electronic device.

Step 403: The electronic device performs word segmentation processing on the question posed by the child to obtain a word segmentation string, and the word segmentation string is a plurality of keyword text sequences.

Specifically, the electronic device performs word segmentation processing on the child's question, and divides the child's question into five words: "hen", "yes", "what", "color", and "of". For example, the word segmentation can be obtained. String "what color is the hen".

Step 404: The electronic device obtains a generalized question according to the word segmentation word string and the word set, and the generalized question is a plurality of generalized word text sequences.

Specifically, the electronic device generalizes the word segmentation word string problem based on the word set.

First, the electronic device matches the keywords in the word segmentation string through the word set (for example, Table 1) obtained during the construction of the question template library corresponding to the target picture book. Among them, "hen" has a corresponding key word in the word set is "hen", "what" has a corresponding key word "what" in the word set, and "color" has a corresponding key in the word set The word is "color". For example, the marked keywords shown in Table 7:

Table 7

实体：EntityEntity: Entity	母鸡、萝丝、母鸡萝丝、狐狸、钉耙 Hen , rose, hen rose, fox, rake
属性：ColorProperty: Color	颜色、红色、黄色、蓝色 Color , red, yellow, blue
普通词：WhatCommon words: What	什么、哪种 What , what

Then, the electronic device determines a generalized word corresponding to each keyword in the word segmentation string according to the word set. For example, the generalized word corresponding to "hen" is "Entity", the generalized word corresponding to "What" is "What", and the generalized word corresponding to "Color" is "Color".

Through the above method, the generalized question obtained by the electronic device is "Entity is What Color".

Step 405: The electronic device extracts the entity name corresponding to the question posed by the child from the generalized question, and the entity name corresponding to the question posed by the child is in the generalized question Keywords that are generalized into entities.

For example, the entity name corresponding to the question asked by the child is extracted from the generalized question in step 404 as "hen".

Step 406: The electronic device obtains the question template to be asked from the question template library according to the text similarity between the generalized question and the question template in the question template library.

In an optional implementation manner, the electronic device may obtain the question template to be asked from the question template library according to the generalized question based on the method with the smallest edit distance. Wherein, the method for the smallest edit distance is: when the generalized question is modified into a question template, the question template with the least number of changes is the question template being asked.

Of course, in addition to the above method, the electronic device may also obtain the question template to be asked from the question template library in other ways, for example, matching the question template library according to the keywords in the generalized question As the question template in question, the question template with the highest matching rate is used as the question template.

Among them, the above methods are all implemented by using the text similarity between the generalized question and the question template in the question template library.

Through the above method, it is determined that the question template corresponding to the generalized question "Entity is What Color" is (Entity)[是][What](Color).

Step 407: The electronic device obtains the questioned call function from the call function library according to the matching degree between the slot of the question template and the parameter of the call function in the call function library.

Wherein, the number and types of parameters of the questioned calling function have the highest matching degree with the number and types of slots of the question template.

In an optional implementation manner, when the calling function library contains a calling function corresponding to the questioned question template, the electronic device directly uses this calling function as the calling function of the questioned. It should be understood here that the number and types of parameters of this calling function match the number and types of slots of the question template to the highest degree.

In another optional implementation manner, when the calling function library contains multiple calling functions corresponding to the question template, the electronic device compares the slots of the question template with the The matching degree of the parameters of the calling function in the calling function library is obtained, and the calling function in question is obtained from the calling function library. The specific method may be: the electronic device obtains the number and type of parameters from the calling function library and the The calling function with the highest matching degree between the number of slots and the type in the question template being asked determines the call function being questioned corresponding to the question template being asked.

Among them, the number and types of parameters of a calling function match the number and types of slots in the question template to the highest degree, specifically referring to the parameters and slots of the same type in the calling function and the question template. The number of bits is the largest.

For example, calling the function getColor(Entity,What,Color) matches the question template (Entity)[是][What](Color) with the same type of parameters and the largest number of slots (there are 3 types of parameters) Matches the slot), therefore, it is determined that the calling function is the called function being questioned. Specifically, the parameter Entity in the calling function and the slot Entity in the question template are all of the same type, and the parameter What in the calling function and the slot What in the question template are both of the same type. The parameter Color in the function and the slot Color in the question template are of the same type. There are 3 parameters and slots of the same type, which are the same types of parameters and slots as other calling functions and the question template. The number of bits is large.

Step 408: The electronic device obtains the entity attribute corresponding to the entity name corresponding to the question posed by the child from the entity attribute library according to the called function being asked and the entity name corresponding to the question posed by the child .

Exemplarily, the entity name corresponding to the question posed by the child and the entity attribute corresponding to the entity name corresponding to the question posed by the child acquired by the electronic device may be used as the answer keywords to be answered.

Specifically, the electronic device obtains the entity attribute corresponding to the entity name corresponding to the question posed by the child from the entity attribute library according to the called function being asked and the entity name corresponding to the question posed by the child At the time, it is necessary to combine the meaning of the function represented by the function called by the question and the entity name corresponding to the question posed by the child, and obtain the entity attribute corresponding to the entity name corresponding to the question posed by the child from the entity attribute library . For example, the electronic device substitutes the name of the entity corresponding to the question posed by the child into the questioned calling function to obtain getColor (hen, what, color). The meaning of the getColor function is to query an entity in the entity attribute library. s color. According to the aforementioned example of the entity attribute library, the color attribute of the entity name "hen" is "red", so the entity attribute corresponding to the entity name corresponding to the question asked by the child is "red", that is, to be answered The answer key word (entity name + entity attribute corresponding to the entity name) is "hen" and "red".

Step 409: The electronic device obtains an answer template to be answered from the answer template library according to the called function of the question, where the answer template to be answered is an answer corresponding to the function of the question called in the answer template library template.

For example, the electronic device may obtain from the answer template library that the answer template to be answered corresponding to the function called by the question is that the Entity is Color.

Step 410: Based on the answer template, the electronic device generates an answer to be answered by using the entity name corresponding to the question asked by the child and the entity attribute corresponding to the entity name corresponding to the question asked by the user.

Wherein, the electronic device generates the answer to be answered by the entity name and entity attribute corresponding to the question asked by the child, that is, the electronic device generates the answer to be answered by the keyword of the answer to be answered.

For example, the answer template for the answer to be answered is Entity is Color, and the electronic device converts the entity name corresponding to the question posed by the child and the entity attribute corresponding to the entity name corresponding to the question posed by the user. Answer key word) "hen" and "red" are combined into a sentence "hen is red" according to the answer template to be answered, that is, the answer to be answered is generated.

Step 411: The electronic device outputs the answer to be answered to the child.

In an optional implementation manner, the electronic device first synthesizes the answer to be answered into a voice, and plays the answer to be answered through the voice.

Specifically, the electronic device plays the voice corresponding to the answer to be answered through a speaker.

It should be noted that the execution of the above steps 403 to 410 by the electronic device is based on the premise that the electronic device has data storage and data processing capabilities. When the electronic device does not have data storage and data processing capabilities, After the electronic device receives the child's question, it transmits the child's question to the server connected to the electronic device, and the server performs the operation of the electronic device in the above steps 403 to 410, Then, the server transmits the answer to be answered to the electronic device, so that the electronic device directly executes step 411.

Using the picture book-based question and answer interactive method provided by the embodiment of the present application, the electronic device or server can flexibly determine the answer based on the database related to the target picture book according to the question asked by the child, and does not need to preset the answer to the question mechanically. You need to ask questions according to preset questions, you can ask questions flexibly, and the electronic device can answer more questions, so that the interaction between the electronic device and the child during the picture book reading process can be more intelligent, which can improve the effectiveness of reading picture books and enhance the children’s experience .

Embodiment 2: The electronic device asks the child a question and the child answers the specific method flow. The electronic device may be any device shown in FIG. 2 or not shown that can implement the picture book-based question and answer interaction method provided in the embodiment of the present application, and the electronic device is applied to the device shown in FIG. 3 Electronic equipment. Referring to Figure 5, the specific process of the method may include:

Step 501: The electronic device loads a database related to the target picture book.

Wherein, the database includes an entity attribute library, a question template library, and a calling function library. The entity attribute library includes multiple entity names and multiple entity attributes, and the multiple entity names are one-to-one with the multiple entity attributes. Correspondingly, the question template library includes at least one question template, the call function library includes at least one call function, and each question template in the question template library corresponds to one or more calls in the call function library Function, each question template in the question template library includes multiple slots.

Specifically, step 501 is similar to step 401 in the foregoing embodiment, and reference may be made to each other for details, and details are not repeated here.

Step 502: The electronic device obtains a question template to be asked from the question template library according to the question template information, where the question template information is a transition probability set or a question template type, and the transition probability set includes historical question templates and all questions. The transition probability between other question templates in the question template library, the historical question template is the question template acquired by the electronic device in the process of generating the last question posed to the user, and the historical question template is used to generate the upper A question template of a question posed to the user at a time, and the type of the question template is related to the age of the user.

In real life, when parents tell a story for their children, usually after telling a story, parents will ask their children some questions to understand the children's understanding of the story. Based on this, the electronic device replaces the role of parents. In the process of reading a picture book, when a story is finished or a highlight is read, the electronic device can recognize that it is necessary to ask the child a question, and the electronic device will execute the subsequent Questioning process.

When the electronic device asks the child a question for the first time, the electronic device may randomly select a question template from the question template library as the question template to be asked. In the process of the electronic device asking the child questions for the second or more times, the electronic device may still randomly select a question template from the question template library as the question template to be asked, or the The electronic device obtains the question template to be asked by the method in step 502.

Example 1: When the question template information is the transition probability set, the electronic device obtains the question template to be asked from the question template library according to the question template information. The specific method may be: the electronic device The determined random value determines the target transition probability from the transition probability set; the electronic device obtains the question template to be asked from the question template library according to the target transition probability.

Wherein, the random value is greater than a set threshold. The random value may be a random number that is currently determined when the question template to be asked needs to be obtained; the random value may also be a value that is randomly selected and determined from a plurality of preset values. Of course, it can also be in other situations, which are not limited in this application.

Example 2: When the question template information is the question template type, the electronic device obtains the question template to be asked from the question template library according to the question template information. The specific method may be: State the age of the user and the corresponding relationship between the age and the question template type to determine the target question template type; the correspondence indicates that the user's age corresponds to at least one of the following question template types: space, detail, society, color, number, text, nature; The electronic device obtains a question template that meets the target question template type from the question template library as the question template to be asked.

In the above example 1, in a scenario where the electronic device has already asked the child's question, the electronic device may use the question template acquired by the electronic device in the process of generating the last question posed to the child Obtaining the template of the question to be asked can achieve diversified questions, prevent children from feeling bored, and increase children's interest in picture book reading, thereby enhancing children's experience. For example, by setting the transition probability between question templates, the purpose of determining one question template based on another question template can be achieved. In this way, it is necessary to set the transition probability between question templates in advance when building the database. Among them, the transition probability between question templates with similar meanings is lower, and the transition probability between question templates with large meaning differences is higher. Wherein, optionally, the transition probability between every two question templates can be manually set in advance, and it can also be based on statistical methods to analyze the questions asked by the child, and calculate every two according to the number of question templates hit. Probability of transition between templates. For example, FIG. 6 shows a schematic diagram of transition probability between question templates.

For example, if the question template (ie, the historical question template) obtained by the electronic device in the process of generating the last question posed to the child is question template 1 in FIG. 6, the electronic device determines a random When the value is 0.34, the transition probability (that is, the target transition probability) close to 0.34 in the transition probability between the electronic device and the problem template 1 shown in FIG. 6 (that is, the transition probability set) is 0.34 ; Then the electronic device can determine a question template with a transition probability of 0.34 between the question template 1 and at this time, it can be seen from FIG. 6 that the question template 2 in FIG. 6 can be used as the question template to be asked.

Of course, the above process can also be implemented by a server connected to the electronic device, which is not limited in this application.

Questioning children through the above methods can make the questions more diverse, avoid children's boringness, mobilize children's enthusiasm, and increase children's interest in picture book reading.

In the above example 2, when the question template library is established in advance, the type setting for the question templates in the question template library can also be performed. Because a certain period in the process of children's psychological development is easier to learn certain knowledge and behavior than other periods, a certain aspect of the psychological process develops most rapidly, this period is called the "sensitive period". The sensitive period theory was put forward by the Italian educator Montaigne. The sensitive period is not only a critical period for children's learning, but also affects the development of their soul and personality. For example, the 31 sensitive periods experienced by children aged 0-9 include muscle sensitivity period: 1-3 years old; sensitive period interested in subtle things: 1.5-4 years old; language sensitivity period: 1.5-2.5 years old; society Standard sensitive period: 2 and a half to 4 years old; Space sensitive period: 3-4 years old; Color sensitive period: 3-4 years old; Mathematical concept sensitive period: 4.5 years old to 7 years old; Recognition sensitive period: 5 years old to 7 years old Years old; animals and plants, scientific experiments, collection sensitive period: 6-7 years old; cultural sensitive period: 6-9 years old, etc. Asking questions according to the developmental stage of children can more effectively promote the growth of children. Therefore, the question template type can be set for the question template, and the matching table between the question template type and the child’s age (also understood as the child’s development stage or the child’s age group) is stored in the database. When the child is at the corresponding age (development stage or Age group), increase the probability of the corresponding question type being selected.

For example, Table 8 shows the corresponding relationship between children's age (developmental stage or age group) and question template types:

Table 8

年龄(发展阶段或年龄段)Age (developmental stage or age group)	问题模板类型Question template type
11	空间、细节Space, details
22	空间、细节、社会Space, detail, society
33	空间、细节、社会、色彩Space, detail, society, color
44	空间、细节、社会、色彩、数字Space, detail, society, color, number
55	数字、文字Numbers, text
66	数字、文字、自然、文化Numbers, words, nature, culture
77	数字、文字、自然、文化Numbers, words, nature, culture
88	文化culture
99	文化culture

For example, Table 9 shows the type of question template, the corresponding relationship between examples of question templates and examples of questions:

Table 9

问题模板类型Question template type	问题模板的示例Example of question template	问题的示例Examples of problems
空间space	(Entity)[在][Where](Entity)[在][Where]	母鸡在哪里？Where is the hen?
细节detail	(Entity)(position)有[What](Entity)(position) has [What]	母鸡后面有什么？What's behind the hen?
社会society	(Entity)[和][Entity][是][What](Relation)(Entity)[and][Entity][是][What](Relation)	佩奇和乔治是什么关系？What is the relationship between Page and George?
色彩color	(Entity)[是][What](Color)(Entity)[是][What](Color)	狐狸是什么颜色？What color is a fox?
数字digital	有[数量词](Entity)Have [quantifier] (Entity)	有几只小猪？How many little pigs are there?
文字Text	[这是][What][This is][What]	这是什么字？What is this word?
自然natural	[这是][What][Entity][This is][What][Entity]	这是什么动物？What kind of animal is this?
文化culture	[你知道](Entity)[的历史吗][Do you know the history of](Entity)[]	你知道长城的历史吗？Do you know the history of the Great Wall?

Optionally, the age (or age group) of the child can be set through the setting software on the electronic device (for example, an App that controls the robot on a mobile phone) to determine the corresponding question template type. A man-machine interface for setting the problem template type can also be provided, so that parents can directly set the problem template type on the software.

Optionally, you can also use the history of human-machine conversations to tag the questions that children posed to electronic devices over a period of time, determine the child’s current age (developmental stage or age group), and continuously count the children’s questions on each type of question Ratio to determine the type of question template that the child currently fits.

In addition, in addition to the above-mentioned setting question template types, some children’s sensitive periods do not correspond to specific question template types, but can correspond to the frequency of questions asked by electronic devices, such as the language sensitive period of 1.5-2.5 years old, which can improve every page Or the frequency of questions in each picture book. Specifically, the method of determining the question template based on the frequency is similar to the method of determining the question template based on the type of the question template, and will not be described in detail here.

Through the above methods, selecting an appropriate question template according to the child's age (developmental stage or age group) can make the questioning more targeted and make the child's reading more effective.

Step 503: The electronic device obtains the calling function to be asked from the calling function library according to the matching degree between the slot of the question template to be asked and the parameter of the calling function in the calling function library.

Wherein, the number and types of parameters of the calling function to be asked have the highest matching degree with the number and types of slots of the template of the question to be asked.

In an optional implementation manner, when the calling function library contains a calling function corresponding to the question template to be asked, the electronic device directly uses this calling function as the calling function to be asked. It should be understood here that the number and types of parameters of this calling function match the number and types of slots of the question template to be asked to the highest degree.

In another optional implementation manner, when the calling function library contains multiple calling functions corresponding to the question template to be asked, the electronic device compares the slots of the question template with the The matching degree of the parameters of the calling function in the calling function library is obtained, and the calling function to be questioned is obtained from the calling function library. The specific method may be: the electronic device obtains the number and type of parameters from the calling function library and the The calling function with the highest matching degree between the number of slots and the type in the question template to be asked is determined, the calling function to be asked corresponding to the question template to be asked is determined.

Among them, the specific implementation method with the highest degree of matching between the number and type of parameters of a calling function and the number and types of parameters in the question template to be asked is the same as the number and types of parameters of a calling function in step 407 above. The number and type of the parameters in the question template have the highest degree of matching. The specific implementation methods are similar, and can be referred to each other, and will not be described in detail here.

Step 504: The electronic device obtains the entity name corresponding to the question template to be asked and/or the entity attribute corresponding to the question template to be asked from the entity attribute library according to the calling function to be asked.

Wherein, the entity name corresponding to the question template to be asked and/or the entity attribute corresponding to the question template to be asked can be understood as question keywords.

Specifically, when the electronic device obtains the entity name corresponding to the question template to be asked and/or the entity attribute corresponding to the question template to be asked from the entity attribute library according to the calling function to be asked, it needs to Combining the meaning of the function represented by the calling function to be asked, the entity name corresponding to the question template to be asked and/or the entity attribute corresponding to the question template to be asked are obtained from the entity attribute library.

For example, when the question template to be asked is (Entity)[在][Where], it is necessary to obtain the entity name corresponding to the question template to be asked; when the question template to be asked is (Entity)[是][ What] (Color), it is necessary to obtain the entity name corresponding to the question template to be asked and the entity attribute corresponding to the question template to be asked; when the question template to be asked is (Color)[有][What] At this time, the entity attribute corresponding to the question template to be asked needs to be obtained.

Step 505: Based on the question template to be asked, the electronic device generates the question to be asked by the entity name corresponding to the question template to be asked and/or the entity attribute corresponding to the question template to be asked.

That is, the electronic device generates the question to be asked based on the question key word template based on the question to be asked template.

For example, the electronic device generates, based on the question template to be asked, the entity name corresponding to the question template to be asked and/or the entity attribute corresponding to the question template to be asked (that is, the question keywords) The questions to be asked can be as shown in the questions in Table 10:

Table 10

(母鸡)[在][哪里](Hen) [at] [where]	只有实体名称Entity name only
(小鸟)[在][哪里](Little bird) [At] [Where]	只有实体名称Entity name only
(老虎)[在][哪里](Tiger) [at] [where]	只有实体名称Entity name only
(母鸡)[是][什么](颜色)(Hen) (is) (what) (color)	有实体名称和实体属性Has entity name and entity attributes
(小鸟)[是][什么](颜色)(Little bird) [Yes] [What] (Color)	有实体名称和实体属性Has entity name and entity attributes
(老虎)[是][什么](颜色)(Tiger) (yes) (what) (color)	有实体名称和实体属性Has entity name and entity attributes
(眉毛)[是][什么样子](Eyebrows) [Yes] [What is it like]	只有实体名称Entity name only

(玩具)[被抢走了](Toy) [stolen]	只有实体名称Entity name only
(辫子)[有][什么变化](Braid) [Yes] [What changes]	只有实体名称Entity name only
(红色的)[有][什么](Red) [Yes] [What]	只有实体属性Only entity attributes
(喷出来的)[是][什么](Squirting out) [is] [what]	只有实体属性Only entity attributes
[什么](颜色)[最多][What] (Color) [Max]	只有实体属性Only entity attributes
[这个](屋子)(温暖)[么][This] (house) (warm) [what]	有实体名称和实体属性Has entity name and entity attributes
(菲菲)[的](心情)[怎么样](Feifei) [of] (mood) [how]	有实体名称和实体属性Has entity name and entity attributes
(菲菲)[的](咆哮)[威力大么](Fei Fei) [的] (Roaring) [Is it powerful?]	有实体名称和实体属性Has entity name and entity attributes
(熊猫)[叫][什么](Panda) [Call] [What]	只有实体名称Entity name only
[这是][什么](树)[This is] [What] (Tree)	只有实体名称Entity name only
(果实)[是][什么](Fruit) [is] [what]	只有实体名称Entity name only
(狐狸)[怎么][不穿](衣服)(Fox) (How) (Don't wear) (Clothes)	有实体名称和实体属性Has entity name and entity attributes
(猴子)[是][什么](表情)(Monkey) (yes) (what) (emoji)	有实体名称和实体属性Has entity name and entity attributes

Step 506: The electronic device outputs the question to be asked to the child, that is, the electronic device asks the child a question.

In an optional implementation manner, the electronic device first synthesizes the question to be asked into a voice, and plays the question to be asked through the voice.

Specifically, the electronic device plays the voice corresponding to the question to be asked through a speaker.

Step 507: The electronic device extracts the entity name corresponding to the question to be asked and/or the entity attribute corresponding to the question to be asked from the question to be asked.

For example, the electronic device may extract the entity name corresponding to the question to be asked and/or the entity attribute corresponding to the question to be asked according to the question to be asked in the above table 10. For example, when the question to be asked is "(hen)[at][where]", the entity name "hen" corresponding to the question to be asked can be extracted. For another example, when the question to be asked is "(red)[Yes][what]", the entity attribute "red" corresponding to the question to be asked can be extracted. For another example, when the question to be asked is "(hen) [Yes] [what] (color)", the entity name "hen" corresponding to the question to be asked can be extracted. For another example, when the question to be asked is "(fox)[how][do not wear] (clothes)", the entity name "fox" corresponding to the question to be asked and the entity attribute "clothes" corresponding to the question to be asked can be extracted.

Step 508: The electronic device obtains the entity attribute corresponding to the entity name corresponding to the question to be asked from the entity attribute library according to the calling function to be asked and the entity name corresponding to the question to be asked, or The electronic device obtains the entity name corresponding to the entity attribute corresponding to the question to be asked from the entity attribute library according to the calling function to be asked and the entity attribute corresponding to the question to be asked.

For example, when the question to be asked is "(hen) [yes] [what] (color)", the entity name "hen" corresponding to the question to be asked is extracted, the electronic device may retrieve from the entity attribute database Obtain the entity attribute "red" corresponding to the entity name corresponding to the question to be asked. For another example, when the question to be asked is "(red) [Yes] [what]", when the entity attribute "red" corresponding to the question to be asked is extracted, the electronic device can obtain all the attributes from the entity attribute database. State the entity name "hen" corresponding to the entity attribute corresponding to the question to be asked. For another example, when the question to be asked is "(fox)[how][do not wear](clothes)", the entity name "fox" corresponding to the question to be asked and the entity attribute "clothes" corresponding to the question to be asked are extracted. The electronic device may obtain the entity attribute "full body plush" corresponding to the entity name corresponding to the question to be asked from the entity attribute database.

Step 509: The electronic device obtains an answer template to be determined from an answer template library according to the calling function to be asked, where the answer template to be determined is an answer template corresponding to the calling function to be asked in the answer template library.

Wherein, the database further includes an answer template library, the answer template library includes at least one answer template, and the answer templates in the answer template library correspond to the calling functions in the calling function library in a one-to-one correspondence.

Step 510: Based on the to-be-determined answer template, the electronic device generates the to-be-determined answer key word.

Wherein, the key of the answer to be determined is any one of the following: the entity attribute corresponding to the entity name corresponding to the question to be asked, the entity name corresponding to the question to be asked, and the entity corresponding to the question to be asked The entity attribute corresponding to the name, the entity attribute corresponding to the question to be asked, the entity attribute corresponding to the question to be asked, and the entity name corresponding to the entity attribute corresponding to the question to be asked.

For example, when the question to be asked is "(hen) [yes] [what] (color)", the electronic device will send the entity name "hen" corresponding to the question to be asked and the name of the entity to be asked The entity attribute “red” corresponding to the entity name corresponding to the question generates the answer to be determined “the hen is red”. For another example, when the question to be asked is "(red) [Yes] [what]", the electronic device generates the entity name "hen" corresponding to the entity attribute corresponding to the question to be asked to be determined The answer is "hen", or the electronic device generates the entity name "hen" corresponding to the entity attribute corresponding to the question to be asked and the entity attribute "red" corresponding to the question to be asked to generate the answer to be determined" The red ones have hens".

Step 511: The electronic device receives the child's answer to the question to be asked.

Step 512: The electronic device compares and analyzes the child's answer to the question to be asked and the answer to be determined to obtain a judgment result of whether the child's answer is correct.

Specifically, the electronic device compares the keywords in the child's answer with the keywords in the answer to be determined, and judges whether the child's answer is correct based on the comparison result, and obtains whether the judgment result is correct or incorrect.

Step 513: The electronic device performs a corresponding operation on the child according to the judgment result.

Specifically, the electronic device may play the judgment result through a loudspeaker. For example, when the judgment result is correct, the electronic device may play "correct answer", or it may also play a voice with the same meaning, such as "Too Okay, you got it right" Wait.

Similarly, the electronic device performing the above steps 502-505, 507-510, and 512 is based on the premise that the electronic device has data storage and data processing capabilities, when the electronic device does not have data storage And data processing capabilities, when the electronic device determines that it needs to ask a child a question, it triggers the server to perform the operations in step 502-step 505 and step 507-step 510, and the server transmits the determined question to be asked to the electronic device. Device, and then the electronic device asks the child a question. After receiving the child’s answer, it transmits the child’s answer to the server so that the server executes the judgment process in step 512, and then the server sends the judgment The result is transmitted to the electronic device, and the electronic device continues to perform step 513.

Using the picture book-based question and answer interaction method provided by the embodiment of this application, the electronic device or server can generate the questions and answers to be asked according to the database related to the target picture book, and there is no need to preset the question and answer pairs mechanically, and the electronic device does not Ask the user mechanically according to the preset questions, which can make the electronic device ask questions and the user's answer more flexibly during the picture book reading process, thereby making the interaction between the electronic device and the child smarter during the picture book reading process, and can improve the effectiveness of reading , To enhance children's experience.

Based on the above embodiment, the question and answer interaction process described in the above embodiment can be applied to the question and answer interaction between an electronic device and a child. However, in practical applications, there may be parents or teachers, children, and electronic devices in the scene of reading picture books. In an optional implementation, in a picture book reading scene where there are three of them, the electronic device may have a voiceprint recognition module, and a human-machine interface for user voiceprint recognition may be provided in the setting software of the electronic device. Through the input of voices by different users, the user specifies the user in which role the different voice corresponds to through the man-machine interface, and determines the corresponding relationship between the voiceprint and the role, such as the roles of parents, teachers, and children.

For the scenario of the electronic device in the embodiment shown in FIG. 5, you can wait for the parent or teacher role to issue an instruction (for example, electronic device (it can also be other pronouns), you can ask a question!), then start the electronic device to the child The process of asking questions.

It is understandable that in the process of using the question template, the electronic device can record a conversation history within a preset period of time. For questions that the parent or teacher has already asked, the corresponding question template is no longer selected.

For the scenario where the electronic device answers questions in the embodiment shown in FIG. 4, the electronic device can first continuously detect the user's voice input. Through voiceprint recognition and semantic analysis, the electronic device can determine whether the child’s questions have been answered by the parent or teacher. If the child’s question exceeds a certain time threshold and the parent or teacher has not received a valid answer (wrong answer or no answer), the electronic device will then execute the follow-up process of answering the user’s question.

It should be noted that the question and answer interaction process involved in the foregoing embodiment is generally established in a scenario where the entity attribute library of the stored picture book is fixed. Optionally, the electronic device may also update the (at least one) entity name and (at least one) entity attribute contained in the interaction history information between the electronic device and the child during the process of reading the target picture book by the electronic device The entity attribute library. For example, the electronic device updates the entity attribute database according to the entity name and entity attribute contained in the interaction history information, which can be divided into the following two cases: In the first case, the interaction history information is in the electronic When the device reads the target picture book, the electronic device receives the speech information input by the child; in the second case, the interaction history information is that the electronic device reads the target picture book during the process of reading the target picture book. The electronic device receives the action information of the child.

Specifically, in the first case described above, referring to FIG. 7, the specific method flow for updating the entity attribute database may include the following steps:

Step 701: The electronic device obtains the child's speech information received during the process of reading the target picture book by the electronic device, and extracts the entity name (at least one) and the entity ( At least one) attribute.

For example, in the process of interacting with the child’s question and answer, the electronic device recognizes that the child has said a sentence: “The rabbit of Tongtong’s family is called Xiaobei”. Through semantic analysis, the electronic device can determine that an entity name in the sentence is "rabbit" and the synonym of the entity name is "小贝".

Step 702: The electronic device judges whether there is a corresponding entity name in the existing entity attribute library, if there is a corresponding entity name, step 703 is executed, otherwise, step 704 is executed.

For example, the electronic device judges that there is an entity name "rabbit" in the existing entity attribute database, and it has a Food attribute of "green vegetables", for example, as shown in Table 11, the existing entity can be judged at this time A certain entity name exists in the property library.

Table 11

实体(Entity)Entity	实体属性：FoodEntity attribute: Food
兔子rabbit	青菜vegetables

Step 703: The electronic device judges whether there is an entity attribute corresponding to the entity name in the existing entity attribute database, if there is an entity attribute corresponding to the entity name, it ends, otherwise, step 705 is executed.

Step 704: The electronic device updates the entity name and entity attributes to the existing entity attribute database to obtain the updated entity attribute database.

For example, the electronic device updates the entity name "rabbit" and entity attribute (alias alias) "Xiaobei" into the existing entity attribute database. The updated entity attribute database may be as shown in Table 12:

Table 12

实体(Entity)Entity	实体属性：aliasEntity attributes: alias
兔子rabbit	小贝Beckham

Step 705: The electronic device updates the entity attribute to the existing entity attribute database to obtain the updated entity attribute database.

For example, the electronic device can obtain from Table 11 that the entity attribute (alias) "Xiaobei" does not exist in the existing entity attribute database, and the entity attribute is updated to the existing entity attribute database. In, the updated entity attribute library is shown in Table 13:

Table 13

实体(Entity)Entity	实体属性：FoodEntity attribute: Food	实体属性：aliasEntity attributes: alias
兔子rabbit	青菜vegetables	小贝Beckham

Based on the entity attribute database updated by the above method, when the electronic device asks the child again, it can generate a personalized question. For example, the question template (Entity)[吃][What](Food), if the existing entity attribute library is used, the generated question should be "What does the rabbit eat", and the updated entity attribute library is used to generate the question. It is "what does Beckham eat". The questions generated by the above methods, combined with the children’s question and answer interaction process, can effectively strengthen the children’s acceptance of the questions.

Specifically, in the second case described above, the electronic device may be an electronic device having a camera and a display screen. Because some children are accompanied by physical movements (for example, pointing their fingers at the content of the picture book) when they listen to the picture book and read. The electronic device can obtain the indicated position of the child's finger on the picture book, thereby obtaining the position attribute of the entity on the picture book. Through this process, the electronic device can establish the corresponding relationship between the entity and its position in the picture book, thereby updating the entity attribute database. Referring to Figure 8, the specific method flow for updating the entity attribute database may include the following steps:

Step 801: In the process of reading the target picture book, the electronic device receives the child's voice input and converts the voice into text.

For example, when a child is listening to the target picture book and sees a dragonfly in the target picture book displayed on the display screen of the electronic device, the child will input the voice "here is a dragonfly" into the electronic device.

Step 802: The electronic device extracts the entity name and entity attributes from the text.

For example, the electronic device extracts an entity name "Dragonfly" and an entity attribute "here" from "Here is a dragonfly".

Step 803: The electronic device judges whether the entity attribute is a location pronoun, if it is, execute step 804, otherwise it ends.

Step 804: The electronic device recognizes the position where the child's finger points in the picture book, that is, the electronic device receives the child's action information.

For example, the electronic device can use the method of edge detection and closed figure detection to determine the range of drawing the pages of the book (for example, the left picture in Fig. 9), and establish the quadrants of the book pages to obtain the upper and lower edges of the book pages. , Left, right, top left, top right, bottom left, bottom right, etc. (for example, the middle image in Figure 9). Through image recognition, you can also determine the child's finger and the corresponding object on the book page (the right image in Figure 9 shows a dragonfly).

Through the above method, the electronic device can determine that the child is pointing below the picture book in the picture book, that is, there is a dragonfly under the picture book.

Step 805: The electronic device updates the determined position in the picture book as the orientation attribute of the entity to the existing entity attribute database to obtain the updated entity attribute database.

For example, the electronic device obtains the corresponding relationship between the entity name "Dragonfly" and "under the picture book", and then updates "under the picture book" as the orientation attribute to the existing entity attribute database. For example, the updated entity attribute database can be as Table 14 shows:

Table 14

实体“Entity”Entity "Entity"	实体属性：positionEntity attribute: position
蜻蜓dragonfly	绘本下方Below the picture book

After obtaining the updated entity attribute database based on the above method, the subsequent electronic device can ask children questions flexibly. For example, after the electronic device recognizes the entity with the orientation attribute, it can be based on the question template [Let’s see See](where)[有](what) generates the question "Let's see what's below?". In this way, you can make more use of the information in the picture book and make reading more in-depth.

It should be noted that all of the above steps 701 to 705 can be implemented by a server connected to the electronic device; and the electronic device in the embodiment shown in FIG. 8 can transmit the voice to the server after receiving the user's voice, and The acquired images of children pointing to the picture book are transmitted to the server, and the server completes the data processing process to update the entity attribute database.

Based on the updated entity attribute database in the above embodiment, the electronic device can further update the entity attribute database according to the life experience of the child. For example, when the electronic device has a camera, permission settings can be used to enable the setting software of the electronic device to obtain images/videos in the installed electronic device gallery, through image analysis, geographic location information carried by the image, etc. , Or get the notebooks related to parenting notes in electronic device note-taking software (such as Evernote) (which can be set by the user), etc., analyze the places that children have visited, what they have seen, and correspond to the question template.

For example, the electronic device determines that the child has gone to the xx science and technology museum based on the geographic location carried in the photo in the today's gallery (of course it can be another name, here is just an example), and further determines that the child takes a photo with the dinosaur (model) through image analysis. This can update the entity attribute database as shown in Table 15:

Table 15

实体(Entity)Entity	实体属性：experience(Place)Entity attribute: experience(Place)	实体属性：experience(Entity)Entity attributes: experience(Entity)
恐龙dinosaur	XX科技馆XX Science and Technology Museum	腕龙Brachiosaurus

Further, for example, when the electronic device reads the picture book "Dinosaur Land", the electronic device (or server) can select the problem template related to the experience attribute in step 503 according to the updated entity attribute library, [ The baby has been to](Entity.position), [also seen](Entity), [is][What](Entity)? , And then asked the children, "The baby has also been to the xx science and technology museum and has seen dinosaurs. Which one is it?". When reading picture books are combined with children’s own life experiences, children’s understanding will be more effective because they have personal experience.

In the foregoing embodiments, only an example in which the electronic device is only output based on voice is briefly introduced. In practical applications, some electronic devices have display functions, such as electronic devices with display screens (mobile phones, etc.). At this time, while the electronic device is outputting voice, the text corresponding to the voice (that is, all the The electronic device displays the answer to be answered through the display screen); some electronic devices have movable parts, such as robots with limbs. In this case, the electronic device’s voice output can also add the action output of the movable parts ( That is, the electronic device controls the movable part to perform the action of outputting the answer to be answered); there are also some electronic devices that have both a display function and a movable part, for example, a robot with a display screen. At this time, the electronic device voices The output can also be combined with the display and the actions of movable parts.

The above-mentioned various outputs can be realized by the processor control of the electronic device, and can also be realized by establishing the display/action control instruction function of the calling function in the calling function library.

For example, when implemented by calling a function, the corresponding relationship between the specific question template and the calling function can be as shown in Table 16:

Table 16

As can be seen from Table 16, the calling function contains display/action control instructions.

For example, as shown in Table 16, the call function getColor(Entity,What,Color) used to answer the color further includes the control command display(Entity,Color) to display the color. The database can further store images/videos. By setting the entity name and entity attribute tags for these images/videos, the electronic device can display pictures related to the entity name and the entity attribute on the screen.

For example, in the schematic diagram of the question and answer interaction process shown in FIG. 10, the child asks the question "What color is the polar bear?". After the process of determining the answer to be answered described in the embodiment shown in FIG. 4, the electronic device obtains the answer to be answered. The polar bear is white", and the corresponding entity name is determined to be "polar bear", and the entity attribute is determined to be "white", and the corresponding entity name and entity attribute label are searched in the image/video stored in the database to obtain the result shown in Figure 10. The picture shown is displayed on the display screen of the electronic device.

For another example, as shown in Table 16 above, the call function (Entity)[在][Where] used to answer the position further includes the action control instruction raise_hand()point_to(Entity.position), which corresponds to the electronic device Movements of movable parts (such as robots) (such as body movements), such as raising hands, pointing (somewhere), etc. According to the entity attribute library with the orientation attribute described in the updated entity attribute library, the electronic device can determine the location of the entity name and point to the location with a limb.

For example, in the example shown in Figure 11, the child asks the question "Where is the dragonfly?", after the process of determining the answer to be answered described in the embodiment shown in Figure 4, and according to the determination that the corresponding entity name is "Dragonfly ", according to the confirmation question template (Entity) [in][Where], and according to the entity attribute library with orientation attribute described in the updated entity attribute library, the position of the entity name is determined to be "below", and then according to the answer The position call function (Entity)[in][Where] includes the action control instructions, the electronic device (robot) executes the control instructions of "raise hand" and "point to (below the picture book)" to move the movable parts (movable limbs) Point to the position of the dragonfly on the picture book.

Through the above methods, through display and action response methods, the functions that electronic devices can provide can be fully utilized, the responses are more diversified, and the attractiveness of the product is enhanced.

Based on the above embodiments, the robot can also be linked with other apps. For example, an interface with an e-commerce app can be provided in the setting software of an electronic device to call product search and purchase functions. For electronic devices with cameras and image analysis capabilities, products can be matched through image recognition. For example, the back cover of many picture books will have recommendations of other books in the same series, works by the same author, books from the same publisher, etc. When children are listening to electronic devices to read picture books, if they point their fingers to one of the books, or express "I want to For this "I can sleep by myself"", it is considered that the child has a purchase intention. For example, as shown in Figure 12, the child’s intention diagram is to determine the name of the book through product matching, and search for it through the product search interface provided by the e-commerce App Commodities, thus asking the user if they want to buy. For another example, in the picture book shown in Figure 13, there is a specific animated image on the cover. Through image recognition, it can be determined that the image is "Super Pan", and children’s voice input "I want a Super Pan toy" can be recognized. It is considered that the child has a purchase intention, the name of the product is determined through product matching, and the product is searched through the product search interface provided by the e-commerce App, thereby asking the user whether to buy.

Specifically, referring to the method implemented in the foregoing process shown in FIG. 14, the method may specifically include the following steps:

Step 1401: Determine the purchase intention.

Specifically, get children’s input, analyze the keywords and word combinations that appear in common purchase instructions, construct and store purchase-related grammar templates in the database, such as "I want to buy [Entity]" and "I want to buy [Entity]" and "I want to buy [Entity]" appear in the user input. Sentences such as "Want to buy [Entity]", "I want an [Entity]", and "Can you buy me an [Entity]" confirm that the child has a purchase intention.

Step 1402: Determine the product search keywords.

Specifically, [Entity] in children's input can be directly used as a search keyword. For example, in the above example, "I want a Super Flying Man toy", then "Super Flying Man toy" is determined as the product search key.

For example, for an electronic device with a camera, the camera can also obtain images, perform image analysis, and determine the objects that appear in the image. Books, characters, and animated images shown in dashed boxes in the two figures shown in Figure 12 and Figure 13 can also be It can be animals, plants, objects, etc. And through image recognition to determine the location of the child's finger, whether it points to the above object. This step can further enhance the accuracy of product keywords.

Step 1403: Search for the product, return the search result to the child, and ask the child if he wants to buy it.

In this step, it may be that the electronic device also provides a product purchase function to directly search for the product, or the electronic device calls the product search interface of the e-commerce App to search.

It should be noted that, in the embodiments of the present application, children are used for description. It is understandable that a child is only a user and is not limited to a child.

Based on the above embodiments, an embodiment of the present application also provides an electronic device. The electronic device is used to implement the picture book-based question and answer interaction method provided by the embodiment of the present application. Referring to FIG. 15, the electronic device 1500 may include: a processing unit 1501, an input unit 1502, and an output unit 1503.

In one embodiment, the electronic device shown in FIG. 15 may be used to perform operations of the electronic device in the picture book-based question and answer interaction method shown in FIG. 4. specific:

The processing unit 1501 is configured to load a database related to the target picture book, wherein the database includes an entity attribute library, a question template library, a calling function library, an answer template library, and a word set. The entity attribute library contains multiple Entity names and entity attributes, the multiple entity names correspond to the multiple entity attributes one-to-one, the question template library includes at least one question template, the call function library includes at least one call function, the Each question template in the question template library corresponds to one or more call functions in the call function library, each question template in the question template library includes multiple slots, and the answer template library includes at least one The answer template, the answer template in the answer template library corresponds to the call function in the call function library one-to-one, the word set indicates the correspondence between multiple keywords and generalized words, and the general Anagrams include entities;

The input unit 1502 is used to receive questions raised by users;

The processing unit 1501 is further configured to perform word segmentation processing on the question posed by the user to obtain a word segmentation string, the word segmentation string being a plurality of keyword text sequences;

Obtaining a generalized question according to the word segmentation string and the word set, and the generalized question is a plurality of generalized word text sequences;

The entity name corresponding to the question posed by the user is extracted from the generalized question, and the entity name corresponding to the question posed by the user is the keyword that is generalized to the entity in the generalized question ；

Acquiring the question template to be asked from the question template library according to the text similarity between the generalized question and the question template in the question template library;

Obtaining the questioned calling function from the calling function library according to the matching degree between the slot of the question template being asked and the parameters of the calling function in the calling function library;

Obtaining the entity attribute corresponding to the entity name corresponding to the question posed by the user from the entity attribute library according to the called function being asked and the entity name corresponding to the question posed by the user;

Acquiring an answer template to be answered from the answer template library according to the called function being asked, where the answer template to be answered is an answer template corresponding to the calling function of the question in the answer template library;

Based on the answer template, generating the answer to be answered by the entity name corresponding to the question asked by the user and the entity attribute corresponding to the entity name corresponding to the question asked by the user;

The output unit 1503 is configured to output the answer to be answered to the user.

Based on the above electronic equipment, the user can flexibly determine the answer based on the database related to the target picture book according to the user’s question. There is no need to mechanically preset the question and answer. The user does not need to ask the question according to the preset question, and can ask the question flexibly. The electronic device can also answer more questions, so that the interaction between the electronic device and the user during the picture book reading process can be more intelligent, and the effectiveness of reading can be improved.

In an optional implementation manner, the number and types of parameters of the questioned calling function have the highest matching degree with the number and types of slots of the question template.

In an optional implementation manner, the processing unit 1501 is further configured to: update the entity attribute database according to the entity name and entity attribute contained in the interaction history information; wherein, the interaction history information is In the process of the electronic device reading the target picture book, the electronic device receives speech information input by the user or action information of the user.

In an optional implementation manner, the electronic device further includes a camera for collecting images of the picture book displayed by the user, and the processing unit 1501 is further used for loading a database related to the target picture book Previously, the image of the picture book displayed by the user was collected through the camera, and the image of the collected picture book was analyzed by image analysis technology to determine the target picture book.

In an optional implementation manner, the electronic device further includes a display screen, and the processing unit 1501 is further configured to: when the output unit 1503 outputs the answer to be answered to the user, pass the The display screen displays the answer to be answered.

In an optional implementation manner, the electronic device further includes movable parts, and the processing unit 1501 is further configured to: when the output unit 1503 outputs the answer to be answered to the user, control the The movable component performs an action of outputting the answer to be answered.

In another embodiment, the electronic device shown in FIG. 15 may be used to perform operations of the electronic device in the picture book-based question and answer interaction method shown in FIG. 5. specific:

The processing unit 1501 is configured to load a database related to the target picture book, wherein the database includes an entity attribute library, a question template library, and a calling function library, and the entity attribute library includes multiple entity names and multiple entity attributes , The multiple entity names correspond to the multiple entity attributes one-to-one, the question template library includes at least one question template, the call function library includes at least one call function, and each question template library One question template corresponds to one or more call functions in the call function library, and each question template in the question template library includes multiple slots;

Acquire a question template to be asked from the question template library according to question template information, where the question template information is a transition probability set or a question template type, and the transition probability set includes historical question templates and other question templates in the question template library The historical question template is a question template obtained by the electronic device in the process of generating the question posed to the user last time, and the question template type is related to the age of the user;

Obtaining the calling function to be asked from the calling function library according to the degree of matching between the slot of the question template to be asked and the parameter of the calling function in the calling function library;

Obtaining the entity name corresponding to the question template to be asked and/or the entity attribute corresponding to the question template to be asked from the entity attribute library according to the calling function to be asked;

Based on the question template to be asked, the entity name corresponding to the question template to be asked and/or the entity attribute corresponding to the question template to be asked are generated to generate the question to be asked;

The output unit 1503 is configured to output the question to be asked to the user.

In an optional implementation manner, the database further includes an answer template library, the answer template library includes at least one answer template, the answer template in the answer template library and the call function in the call function library The numbers correspond to each other; the processing unit 1501 is also used for:

Extracting the entity name corresponding to the question to be asked and/or the entity attribute corresponding to the template of the question to be asked from the question to be asked;

According to the call function to be asked and the entity name corresponding to the question to be asked, obtain the entity attribute corresponding to the entity name corresponding to the question to be asked from the entity attribute library, or call according to the question to be asked Function and the entity attribute corresponding to the question to be asked, obtaining the entity name corresponding to the entity attribute corresponding to the question to be asked from the entity attribute library;

Obtaining an answer template to be determined from the answer template library according to the calling function to be asked, where the answer template to be determined is an answer template corresponding to the calling function to be asked in the answer template library;

Based on the to-be-determined answer template, the to-be-determined answer keyword is generated to generate a to-be-determined answer, and the to-be-determined answer keyword is any of the following: the entity attribute corresponding to the entity name corresponding to the question The entity name corresponding to the question to be asked and the entity attribute corresponding to the entity name corresponding to the question to be asked, the entity attribute corresponding to the question to be asked, the entity attribute corresponding to the question to be asked, and the question to be asked The entity name corresponding to the corresponding entity attribute.

In an example, the electronic device further includes:

The input unit 1502 is configured to receive the user's answer to the question to be asked;

The processing unit 1501 is further configured to: compare and analyze the user's answer to the question to be asked and the answer to be determined to obtain a judgment result of whether the user's answer is correct; The user makes the corresponding operation.

In an implementation manner, the number and types of parameters of the calling function to be asked have the highest matching degree with the number and types of slots of the template of the question to be asked.

In an exemplary manner, when the question template information is the transition probability set, the processing unit 1501 is specifically configured to obtain the question template to be asked from the question template library according to the question template information :

Determining the target transition probability from the transition probability set according to a predetermined random value;

Acquire the question template to be asked from the question template library according to the target transition probability.

In another exemplary manner, when the question template information is the question template type, the processing unit 1501 specifically uses the question template to be asked from the question template library according to the question template information. in:

Determine the target question template type according to the user’s age and the corresponding relationship between the age and the question template type; the corresponding relationship indicates that the user’s age corresponds to at least one of the following question template types: space, detail, society, color, number, text, natural;

Obtain a question template that meets the target question template type from the question template library as the question template to be asked.

In an optional implementation manner, the processing unit 1501 is further configured to: update the entity attribute database according to the entity name and entity attributes contained in the interaction history information; wherein, the interaction history information is in the In the process of the electronic device reading the target picture book, the electronic device receives speech information input by the user or action information of the user.

In a possible manner, the electronic device further includes: a camera for collecting images of the picture book displayed by the user;

The processing unit 1501 is further configured to collect an image of the picture book displayed by the user through a camera before loading the database related to the target picture book; analyze the collected image of the picture book by image analysis technology to determine the Target picture book.

It should be noted that the division of units in the embodiments of the present application is illustrative, and is only a logical function division, and there may be other division methods in actual implementation. The functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or software functional unit.

If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical solution of this application essentially or the part that contributes to the existing technology or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium , Including a number of instructions to make a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor (processor) execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (read-only memory, ROM), random access memory (random access memory, RAM), magnetic disk or optical disk and other media that can store program code .

Based on the above embodiments, the embodiments of the present application also provide an electronic device that can implement the picture book-based question and answer interaction method provided in the embodiments of the present application. As shown in FIG. 16, the electronic device 1600 includes a communication unit 1601 and a processor 1602, and optionally may also include a memory 1603, where:

The processor 1602 may be a central processing unit (CPU), a network processor (NP), or a combination of CPU and NP, and so on. The processor 1602 may further include a hardware chip. The aforementioned hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD) or a combination thereof. The above-mentioned PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL) or any combination thereof. When the processor 1602 realizes the above functions, it may be realized by hardware, and of course, it may also be realized by hardware executing corresponding software.

The communication unit 1601 and the processor 1602 are connected to each other. Optionally, the communication unit 1601 and the processor 1602 are connected to each other through a bus 1604; the bus 1604 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. . The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, only one thick line is used in FIG. 16, but it does not mean that there is only one bus or one type of bus.

In an optional implementation manner, the memory 1603 is coupled with the processor 1602 for storing programs and the like. Specifically, the program may include program code, and the program code includes computer operation instructions. The memory 1603 may include RAM, or may also include non-volatile memory, such as at least one disk memory. The processor 1602 executes the application program stored in the memory 1603 to realize the above-mentioned functions, thereby realizing the function of the electronic device, that is, realizing the question and answer interactive method based on the picture book.

In one embodiment, the electronic device shown in FIG. 16 may be used to perform operations of the electronic device in the embodiment shown in FIG. 4 above. specific:

The processor 1602 is configured to load a database related to the target picture book, wherein the database includes an entity attribute library, a question template library, a calling function library, an answer template library, and a word set. The entity attribute library includes multiple Entity names and multiple entity attributes, the multiple entity names correspond to the multiple entity attributes one-to-one, the question template library includes at least one question template, and the calling function library includes at least one calling function, Each question template in the question template library corresponds to one or more call functions in the call function library, each question template in the question template library includes a plurality of slots, and the answer template library contains At least one answer template, the answer templates in the answer template library correspond to the calling functions in the calling function library, and the word set indicates the correspondence between multiple keywords and generalized words, so The generalized words include entities;

The communication unit 1601 is configured to receive questions raised by the user;

The processor 1602 is further configured to perform word segmentation processing on the question posed by the user to obtain a word segmentation string, where the word segmentation string is a plurality of keyword text sequences;

The communication unit 1601 is also used to output the answer to be answered to the user.

Based on the above electronic equipment, the user can flexibly determine the answer based on the database related to the target picture book according to the user’s question. There is no need to mechanically preset the question and answer. The user does not need to ask the question according to the preset question, and can ask the question flexibly. The electronic device can also answer more questions, so that the interaction between the electronic device and the user during the picture book reading process can be more intelligent, and the effectiveness of reading picture books can be improved.

In an optional implementation manner, the processor 1602 is further configured to: update the entity attribute database according to the entity name and entity attribute contained in the interaction history information; wherein, the interaction history information is In the process of the electronic device reading the target picture book, the electronic device receives speech information input by the user or action information of the user.

In an optional implementation manner, the electronic device 1600 further includes a camera for collecting images of the picture book displayed by the user, and the processor 1602 is further used for loading a picture book related to the target Before the database, the image of the picture book displayed by the user is collected through the camera, and the collected image of the picture book is analyzed by image analysis technology to determine the target picture book.

In an optional implementation manner, the electronic device 1600 further includes a display screen, and the processor 1602 is further configured to: when the communication unit 1601 outputs the answer to be answered to the user, pass the The display screen displays the answer to be answered.

In an optional implementation manner, the electronic device 1600 further includes movable components, and the processor 1602 is further configured to: when the communication unit 1601 outputs the answer to be answered to the user, control The movable part performs an action of outputting the answer to be answered.

In another embodiment, the electronic device shown in FIG. 16 may be used to perform operations of the electronic device in the picture book-based question and answer interaction method shown in FIG. 5. specific:

The processor 1602 is configured to load a database related to the target picture book, wherein the database includes an entity attribute library, a question template library, and a calling function library, and the entity attribute library includes multiple entity names and multiple entity attributes , The multiple entity names correspond to the multiple entity attributes one-to-one, the question template library includes at least one question template, the call function library includes at least one call function, and each question template library One question template corresponds to one or more call functions in the call function library, and each question template in the question template library includes multiple slots;

Acquiring the calling function to be asked from the calling function library according to the degree of matching between the slot of the question template to be asked and the parameter of the calling function in the calling function library;

The communication unit 1601 is configured to output the question to be asked to the user.

In an optional implementation manner, the database further includes an answer template library, the answer template library includes at least one answer template, the answer template in the answer template library and the call function in the call function library The numbers correspond to each other; the processor 1602 is also used for:

In an example, the communication unit 1601 is further configured to receive the user's answer to the question to be asked;

The processor 1602 is further configured to: compare and analyze the user's answer to the question to be asked with the answer to be determined to obtain a judgment result of whether the user's answer is correct; The user makes the corresponding operation.

In an exemplary manner, when the question template information is the set of transition probabilities, the processor 1602 is specifically configured to obtain the question template to be asked from the question template library according to the question template information. :

In another exemplary manner, when the question template information is the question template type, the processor 1602 specifically uses the question template to be asked from the question template library according to the question template information. in:

In an optional implementation manner, the processor 1602 is further configured to: update the entity attribute database according to the entity name and entity attribute contained in the interaction history information; wherein, the interaction history information is in the In the process of the electronic device reading the target picture book, the electronic device receives speech information input by the user or action information of the user.

In a possible manner, the electronic device 1600 further includes: a camera for collecting images of the picture book displayed by the user; and the processor 1602 is also used for loading a database related to the target picture book, The image of the picture book displayed by the user is collected by a camera; the image of the collected picture book is analyzed by image analysis technology to determine the target picture book.

In summary, the embodiments of the present application provide a picture book-based question and answer interaction method and electronic device, so that the interaction between the electronic device and the user during the picture book reading process is more intelligent, which can improve efficiency and enhance user experience.

Those skilled in the art should understand that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

This application is described with reference to flowcharts and/or block diagrams of methods, equipment (systems), and computer program products according to the embodiments of this application. It should be understood that each process and/or block in the flowchart and/or block diagram, and the combination of processes and/or blocks in the flowchart and/or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing equipment to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing equipment are generated It is a device that realizes the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.

These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing equipment to work in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including the instruction device. The device implements the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.

These computer program instructions can also be loaded on a computer or other programmable data processing equipment, so that a series of operation steps are executed on the computer or other programmable equipment to produce computer-implemented processing, so as to execute on the computer or other programmable equipment. The instructions provide steps for implementing functions specified in a flow or multiple flows in the flowchart and/or a block or multiple blocks in the block diagram.

Obviously, those skilled in the art can make various changes and modifications to the embodiments of the present application without departing from the scope of the embodiments of the present application. In this way, if these modifications and variations of the embodiments of this application fall within the scope of the claims of this application and their equivalent technologies, this application is also intended to include these modifications and variations.

Claims

A question and answer interactive method based on picture books, which is characterized in that it includes:

The electronic device loads a database related to the target picture book, wherein the database includes an entity attribute library, a question template library, a calling function library, an answer template library, and a word set. The entity attribute library includes multiple entity names and multiple Entity attributes, the multiple entity names correspond to the multiple entity attributes one-to-one, the question template library contains at least one question template, the calling function library contains at least one calling function, and the question template library contains Each question template corresponds to one or more call functions in the call function library, each question template in the question template library includes multiple slots, and the answer template library includes at least one answer template, so The answer templates in the answer template library correspond to the call functions in the call function library one-to-one, the word set indicates the correspondence between multiple keywords and generalized words, and the generalized words include entities ；

The electronic device receives the question raised by the user;

The electronic device performs word segmentation processing on the question posed by the user to obtain a word segmentation string, and the word segmentation string is a plurality of keyword text sequences;

The electronic device obtains a generalized question according to the word segmentation string and the word set, and the generalized question is a plurality of generalized word text sequences;

The electronic device extracts the entity name corresponding to the question posed by the user from the generalized question, and the entity name corresponding to the question posed by the user is the generalized question which is generalized to Entity keywords;

The electronic device obtains the question template to be asked from the question template library according to the text similarity between the generalized question and the question template in the question template library;

The electronic device obtains the questioned call function from the call function library according to the degree of matching between the slot of the question template and the parameter of the call function in the call function library;

The electronic device obtains the entity attribute corresponding to the entity name corresponding to the question posed by the user from the entity attribute library according to the called function being asked and the entity name corresponding to the question posed by the user;

The electronic device obtains an answer template to be answered from the answer template library according to the called function being asked, where the answer template to be answered is an answer template corresponding to the called function being asked in the answer template library;

Based on the answer template, the electronic device generates the answer to be answered by the entity name corresponding to the question asked by the user and the entity attribute corresponding to the entity name corresponding to the question asked by the user;

The electronic device outputs the answer to be answered to the user.
The method according to claim 1, wherein the number and types of parameters of the function called by the question have the highest matching degree with the number and types of slots of the question template.
The method according to claim 1 or 2, wherein the method further comprises:

The electronic device updates the entity attribute database according to the entity name and entity attribute contained in the interaction history information;

Wherein, the interaction history information is the speech information input by the user or the action information of the user received by the electronic device during the process of reading the target picture book by the electronic device.
The method according to any one of claims 1 to 3, wherein before the electronic device loads the database related to the target picture book, the method further comprises:

The electronic device collects an image of the picture book displayed by the user through a camera;

The electronic device analyzes the collected image of the picture book by image analysis technology to determine the target picture book.
A question and answer interactive method based on picture books, which is characterized in that it includes:

The electronic device loads a database related to the target picture book, where the database includes an entity attribute library, a question template library, and a calling function library. The entity attribute library includes multiple entity names and multiple entity attributes, and the multiple entities The name corresponds to the multiple entity attributes one-to-one, the question template library contains at least one question template, the calling function library contains at least one calling function, and each question template in the question template library corresponds to the Calling one or more calling functions in the function library, and each question template in the question template library includes multiple slots;

The electronic device obtains a question template to be asked from the question template library according to question template information, the question template information is a transition probability set or a question template type, and the transition probability set includes a historical question template and the question template library The transition probability between other question templates in the above, the historical question template is a question template obtained by the electronic device in the process of generating the last question posed to the user, and the question template type is related to the age of the user;

The electronic device obtains the calling function to be asked from the calling function library according to the matching degree between the slot of the question template to be asked and the parameter of the calling function in the calling function library;

The electronic device obtains the entity name corresponding to the question template to be asked and/or the entity attribute corresponding to the question template to be asked from the entity attribute library according to the calling function to be asked;

Based on the question template to be asked, the electronic device generates the question to be asked by the entity name corresponding to the question template to be asked and/or the entity attribute corresponding to the question template to be asked;

The electronic device outputs the question to be asked to the user.
The method according to claim 5, wherein the database further comprises an answer template library, the answer template library contains at least one answer template, and the answer template in the answer template library and the calling function library are The calling function of is one-to-one correspondence; the method further includes:

The electronic device extracts the entity name corresponding to the question to be asked and/or the entity attribute corresponding to the question to be asked from the question to be asked;

The electronic device obtains the entity attribute corresponding to the entity name corresponding to the question to be asked from the entity attribute library according to the calling function to be asked and the entity name corresponding to the question to be asked, or the The electronic device obtains the entity name corresponding to the entity attribute corresponding to the question to be asked from the entity attribute library according to the calling function to be asked and the entity attribute corresponding to the question to be asked;

The electronic device obtains an answer template to be determined from the answer template library according to the call function to be asked, where the answer template to be determined is an answer template in the answer template library that corresponds to the call function to be asked;

Based on the to-be-determined answer template, the electronic device generates a to-be-determined answer keyword to be determined, and the to-be-determined answer keyword is any one of the following: the entity attribute corresponding to the entity name corresponding to the question to be asked , The entity name corresponding to the question to be asked and the entity attribute corresponding to the entity name corresponding to the question to be asked, the entity attribute corresponding to the question to be asked, the entity attribute corresponding to the question to be asked, and the State the entity name corresponding to the entity attribute corresponding to the question to be asked.
The method of claim 6, wherein the method further comprises:

Receiving, by the electronic device, the user's answer to the question to be asked;

The electronic device compares and analyzes the user's answer to the question to be asked and the answer to be determined to obtain a judgment result of whether the user's answer is correct;

The electronic device makes a corresponding operation to the user according to the judgment result.
The method according to any one of claims 5-7, wherein the number and types of parameters of the calling function to be asked have the highest matching degree with the number and types of slots of the question template to be asked.
The method according to any one of claims 5-8, wherein when the question template information is the set of transition probabilities, the electronic device obtains the pending question from the question template library according to the question template information. Question template, including:

The electronic device determines the target transition probability from the transition probability set according to a predetermined random value;

The electronic device obtains the question template to be asked from the question template library according to the target transition probability.
The method according to any one of claims 5-8, wherein when the question template information is the question template type, the electronic device obtains the pending question from the question template library according to the question template information. Question template, including:

The electronic device determines the target question template type according to the age of the user and the corresponding relationship between the age and the question template type; the corresponding relationship indicates that the user’s age corresponds to at least one of the following question template types: space, detail, society, color, Numbers, words, nature;

The electronic device obtains a question template that meets the target question template type from the question template library as the question template to be asked.
The method according to any one of claims 5-10, wherein the method further comprises:

The electronic device updates the entity attribute database according to the entity name and entity attribute contained in the interaction history information;

Wherein, the interaction history information is the speech information input by the user or the action information of the user received by the electronic device during the process of reading the target picture book by the electronic device.
The method according to any one of claims 5-11, wherein before the electronic device loads the database related to the target picture book, the method further comprises:

The electronic device collects an image of the picture book displayed by the user through a camera;

The electronic device analyzes the collected image of the picture book by image analysis technology to determine the target picture book.
An electronic device, characterized in that it comprises:

The processing unit is used to load a database related to the target picture book, wherein the database includes an entity attribute library, a question template library, a calling function library, an answer template library, and a word set, and the entity attribute library contains multiple entity names And multiple entity attributes, the multiple entity names correspond to the multiple entity attributes one-to-one, the question template library includes at least one question template, the calling function library includes at least one calling function, the question Each question template in the template library corresponds to one or more call functions in the call function library, each question template in the question template library includes multiple slots, and the answer template library includes at least one answer Template, the answer template in the answer template library corresponds to the call function in the call function library one-to-one, the word set indicates the correspondence between multiple keywords and generalized words, and the generalized Words include entities;

Input unit for receiving questions raised by users;

The processing unit is further configured to perform word segmentation processing on the question posed by the user to obtain a word segmentation string, and the word segmentation string is a plurality of keyword text sequences;

Obtaining a generalized question according to the word segmentation string and the word set, and the generalized question is a plurality of generalized word text sequences;

The entity name corresponding to the question posed by the user is extracted from the generalized question, and the entity name corresponding to the question posed by the user is the keyword that is generalized to the entity in the generalized question ；

Acquiring the question template to be asked from the question template library according to the text similarity between the generalized question and the question template in the question template library;

Obtaining the questioned calling function from the calling function library according to the matching degree between the slot of the question template being asked and the parameters of the calling function in the calling function library;

Obtaining the entity attribute corresponding to the entity name corresponding to the question posed by the user from the entity attribute library according to the called function being asked and the entity name corresponding to the question posed by the user;

Acquiring an answer template to be answered from the answer template library according to the called function being asked, where the answer template to be answered is an answer template corresponding to the calling function of the question in the answer template library;

Based on the answer template, generating the answer to be answered by the entity name corresponding to the question asked by the user and the entity attribute corresponding to the entity name corresponding to the question asked by the user;

The output unit is used to output the answer to be answered to the user.
The electronic device according to claim 13, wherein the number and types of parameters of the questioned calling function have the highest matching degree with the number and types of slots of the question template.
The electronic device according to claim 13 or 14, wherein the processing unit is further configured to:

Update the entity attribute database according to the entity name and entity attribute contained in the interaction history information;

Wherein, the interaction history information is the speech information input by the user or the action information of the user received by the electronic device during the process of reading the target picture book by the electronic device.
15. The electronic device according to any one of claims 13-15, wherein the electronic device further comprises:

A camera for collecting images of the picture book displayed by the user;

The processing unit is further configured to collect an image of the picture book displayed by the user through a camera before loading the database related to the target picture book;

The image of the collected picture book is analyzed by image analysis technology to determine the target picture book.
An electronic device, characterized in that it comprises:

The processing unit is used to load a database related to the target picture book, wherein the database includes an entity attribute library, a question template library, and a calling function library, and the entity attribute library includes multiple entity names and multiple entity attributes. The multiple entity names correspond to the multiple entity attributes one-to-one, the question template library contains at least one question template, the calling function library contains at least one calling function, and each question template in the question template library Corresponding to one or more calling functions in the calling function library, each question template in the question template library includes multiple slots;

Acquire a question template to be asked from the question template library according to question template information, where the question template information is a transition probability set or a question template type, and the transition probability set includes historical question templates and other question templates in the question template library The historical question template is a question template obtained by the electronic device in the process of generating the question posed to the user last time, and the question template type is related to the age of the user;

Acquiring the calling function to be asked from the calling function library according to the degree of matching between the slot of the question template to be asked and the parameter of the calling function in the calling function library;

Obtaining the entity name corresponding to the question template to be asked and/or the entity attribute corresponding to the question template to be asked from the entity attribute library according to the calling function to be asked;

Based on the question template to be asked, the entity name corresponding to the question template to be asked and/or the entity attribute corresponding to the question template to be asked are generated to generate the question to be asked;

The output unit is configured to output the question to be asked to the user.
The electronic device of claim 17, wherein the database further comprises an answer template library, the answer template library contains at least one answer template, the answer template in the answer template library and the calling function library The calling functions in the one-to-one correspondence; the processing unit is also used for:

Extracting the entity name corresponding to the question to be asked and/or the entity attribute corresponding to the template of the question to be asked from the question to be asked;

According to the call function to be asked and the entity name corresponding to the question to be asked, obtain the entity attribute corresponding to the entity name corresponding to the question to be asked from the entity attribute library, or call according to the question to be asked Function and the entity attribute corresponding to the question to be asked, obtaining the entity name corresponding to the entity attribute corresponding to the question to be asked from the entity attribute library;

Obtaining an answer template to be determined from the answer template library according to the calling function to be asked, where the answer template to be determined is an answer template corresponding to the calling function to be asked in the answer template library;

Based on the to-be-determined answer template, the to-be-determined answer keyword is generated to generate a to-be-determined answer, and the to-be-determined answer keyword is any of the following: the entity attribute corresponding to the entity name corresponding to the question The entity name corresponding to the question to be asked and the entity attribute corresponding to the entity name corresponding to the question to be asked, the entity attribute corresponding to the question to be asked, the entity attribute corresponding to the question to be asked, and the question to be asked The entity name corresponding to the corresponding entity attribute.
The electronic device of claim 18, wherein the electronic device further comprises:

An input unit, configured to receive the user's answer to the question to be asked;

The processing unit is also used for:

Comparing and analyzing the user's answer to the question to be asked and the answer to be determined to obtain a judgment result of whether the user's answer is correct;

Make a corresponding operation to the user according to the judgment result.
20. The electronic device according to any one of claims 17-19, wherein the number and types of parameters of the calling function to be asked have the highest matching degree with the number and types of slots of the question template to be asked.
The electronic device according to any one of claims 17-20, wherein when the question template information is the set of transition probabilities, the processing unit obtains information from the question template library according to the question template information. When obtaining the template of the question to be asked, it is specifically used for:

Determining the target transition probability from the transition probability set according to a predetermined random value;

Acquire the question template to be asked from the question template library according to the target transition probability.
The electronic device according to any one of claims 17-20, wherein when the question template information is the question template type, the processing unit obtains information from the question template library according to the question template information. When obtaining the template of the question to be asked, it is specifically used for:

Determine the target question template type according to the user’s age and the corresponding relationship between the age and the question template type; the corresponding relationship indicates that the user’s age corresponds to at least one of the following question template types: space, detail, society, color, number, text, natural;

Obtain a question template that meets the target question template type from the question template library as the question template to be asked.
The electronic device according to any one of claims 17-22, wherein the processing unit is further configured to:

Update the entity attribute database according to the entity name and entity attribute contained in the interaction history information;

Wherein, the interaction history information is the speech information input by the user or the action information of the user received by the electronic device in the process of reading the target picture book by the electronic device.
The electronic device according to any one of claims 17-23, wherein the electronic device further comprises:

A camera for collecting images of the picture book displayed by the user;

The processing unit is further configured to collect an image of the picture book displayed by the user through a camera before loading the database related to the target picture book;

The image of the collected picture book is analyzed by image analysis technology to determine the target picture book.
A computer-readable storage medium, characterized by comprising instructions, which when run on a computer, cause the computer to execute the method according to any one of claims 1-12.