Intelligent interaction system and method for education all-in-one machine

Abstract

The invention discloses an intelligent interaction system and method for an education all-in-one machine, relates to the technical field of intelligent interaction, and aims to solve the problem of low efficiency of an all-in-one machine application interface during user identity conversion. Setting detection time and an application combination scoring mechanism, introducing the user into the application combination scoring mechanism within the detection time, utilizing a multi-layer perceptron to imitate a user identity portrait, and calculating an identity recognition coefficient; judging whether the user is incorporated into an identity multi-library or not by using a geometric averaging method according to the application exploration condition of the user and the identity recognition coefficient; and when the all-in-one machine starts to work, popping up an application combination pop-up window to a user side and guiding a user to provide input, identifying a current identity state of the user according to a user input mode and an input result, judging whether the user interacts with the all-in-one machine in a single identity state or not, and providing different interaction interfaces for the user.

Description

Technical Field

[0001] The present invention relates to the field of intelligent interaction technology, and more specifically, to an intelligent interaction system and method for an all-in-one educational machine. Background Art

[0002] Intelligent interaction technology refers to the use of artificial intelligence, natural language processing, machine learning and other related technologies to enhance the interaction between people and computer systems. When intelligent interaction technology is applied to all-in-one educational machines, it can improve educational efficiency and reduce educational costs.

[0003] The existing technology has the following deficiencies: The all-in-one machine contains application software with different functions. When users interact with the all-in-one machine, they interact through preset function buttons. However, when users use the identity of the all-in-one machine to switch, they are not familiar with the function buttons in the application software when using unfamiliar application software, which affects the interaction effect and delays the learning or training progress. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an intelligent interaction method for an educational all-in-one machine, which analyzes user behavior, determines user identity and judges whether the user has a single identity, incorporates non-single identity users into the identity library, analyzes the current user status, matches in the identity library, determines the identity of the current user using the all-in-one machine and provides different operation interfaces to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions: An intelligent interaction method for an educational all-in-one machine, comprising the following steps: Step S1: Collect user behavior data to determine the user's exploration of various applications on the all-in-one machine, set the detection time and application combination scoring mechanism; Step S2: During the detection time, the user is passed through the application combination scoring mechanism to simulate the user's identity portrait and calculate the identity recognition coefficient. The user's application exploration and identity recognition coefficient are comprehensively considered to determine whether to include the user in the identity multi-database; Step S3: Pop up an application combination pop-up window to the user end and guide the user to make a selection. According to the user selection mode and input result, identify the user's current identity status and determine whether the user interacts with the all-in-one device in a single identity state; Step S4: providing different interactive interfaces to the user according to the user's current identity status and the single identity status judgment result.

[0006] In a preferred embodiment, in step S1, the user behavior data is the number of times the user has used the application and the duration of use in the application history. The user's exploration rate of each application is calculated based on the user behavior data as the user's exploration of each application on the all-in-one device. The application history is stored in the server database of the all-in-one machine. By calling the application history of each application in the server database of the all-in-one machine, the number of times and the duration of use in the history of each application are obtained.

[0007] In a preferred embodiment, in step S1, the number of times each application is used is combined into an application frequency dataset, and the usage duration of each application is combined into an application duration dataset. The application frequency dataset and the application duration dataset are used to construct a multi-layer perceptron model to calculate the exploration rate of each application. The specific steps are as follows: Data input: The application frequency dataset and application duration dataset are passed into the input layer as input features. The input layer normalizes the input features and then passes them into the hidden layer. Initialization parameters: Initialize the initial weights and bias parameters from the input layer to the hidden layer; Set the hidden layer processing algorithm: Set the hidden layer activation function to process the input features. Take the weighted function as an example to construct the activation function: , where T is the output of the hidden layer, is the result of data standardization in the application frequency dataset, and b is the result of data standardization in the application duration dataset. and are the two initial weights set in the input layer to the hidden layer, is the bias parameter set in the input layer to the hidden layer; Set the output layer processing algorithm: Set the activation function of the output layer: , is the output result of the output layer, i is the output result sequence number of different input features through the hidden layer, and n is the number of data in the application frequency dataset or application duration dataset; Propagation: The multi-layer perceptron passes the input features through the input layer, hidden layer, and output layer in sequence, and finally uses the output of the output layer as the user's application exploration reference ratio; Calculating the exploration rate: The data from the application frequency dataset and the application duration dataset of the same application are used as input features. The output of the hidden layer is calculated through the hidden layer. The ratio of the hidden layer output to the application exploration reference ratio is used as the exploration rate of the corresponding application. In the application combination scoring mechanism, different applications are assigned values and set with different identity information, where the identity information includes single identity information or multiple identity information.

[0008] In a preferred embodiment, in step S2, a period of time is selected as a detection period. When drawing a user identity profile, the applications opened by the user during the detection period are recorded, the number of repeated assignments of the opened applications is counted, and the identity corresponding to the application with the most repeated assignments is used as the current user identity. The user's identity recognition coefficient is obtained by accumulating the application assignment values with the most repetitions and dividing it by the accumulated sum of all application assignment values within the detection time.

[0009] In a preferred embodiment, in step S2, the application with the most repetitions within the detection time is marked, the exploration rate of the marked application by the user is called, and the exploration rate of the marked application and the identity recognition coefficient are used to determine whether to include the user in the identity multi-library using the geometric mean method. The geometric mean formula is: , where L is the exploration rate of the tag application, B is the user's identity recognition coefficient, and S is the identity cardinality obtained by calculation; When the tag application is used by multiple identities and the identity base calculated by the corresponding tag application exceeds the preset multi-identity threshold, the current user is included in the identity multi-library; otherwise, the current user is not included in the identity multi-library.

[0010] In a preferred embodiment, in step S3, when the user turns on the all-in-one machine, a combination pop-up window pops up to the user terminal and guides the user to make a selection. Single or multiple identity tags are set in different applications. Applications with a single and identical identity tag are combined. The corresponding application combination inherits the identity tag. The combination pop-up window includes multiple application combinations, and the user inputs in two modes, as shown below: Mode 1: Select the application combination provided in the pop-up window; Mode 2: Select a single app or multiple apps from the apps in the all-in-one device.

[0011] In a preferred embodiment, in step S3, when determining whether the user interacts with the all-in-one device in a single identity state, the following rules are used: Rule 1: When the user selects mode 1 for input, the user is judged to be in a single identity state, and the identity tag corresponding to the application combination selected by the user is used as the identity tag of the current user; Rule 2: When the user selects mode 2 for input, if the user selects a single application, the user is judged to be in a single identity state, and the identity tag corresponding to the single application selected by the user is used as the identity tag of the current user; Rule 3: When the user selects mode 2 for input, if the user selects a single application and the application has multiple identity tags, the user is judged to be in a multi-identity state, and the different identity tags corresponding to the application are all used as the identity tags of the current user; Rule 4: When the user selects mode 2 for input, if the user selects multiple applications and the identity tags corresponding to the multiple applications are the same, the user is judged to be in a single identity state, and the corresponding identity tag is used as the identity tag of the current user; Rule 5: When the user selects mode 2 for input, if the user selects multiple applications and the identity tags corresponding to the multiple applications are different, the user is judged to be in a multi-identity state, and the different identity tags corresponding to the applications are all used as the identity tags of the current user.

[0012] In a preferred embodiment, in step S4, if the current user is in a single identity state, the all-in-one machine enters a quick use interface; if the current user is in a multi-identity state, the all-in-one machine enters an auxiliary use interface; In the quick use interface, when the user interacts with the open application, no function guidance is provided. In the auxiliary use interface, when the user interacts with the open application, function application guidance is provided; Function application guidelines are semi-transparent function annotations next to the application interface buttons.

[0013] An intelligent interactive system for an all-in-one educational machine, used to implement the above-mentioned intelligent interactive method for an all-in-one educational machine, comprising a data acquisition module, an exploration and recording module, an identity confirmation module, and an interface providing module; The data collection module is used to collect user behavior data, set the detection time and application combination scoring mechanism based on the user behavior data, and pass the user behavior data, detection time and application combination scoring mechanism to the exploration recording module. When the user uses the all-in-one machine, the application combination pop-up window will pop up to the user end and obtain the user input result and pass it to the identity confirmation module; The exploration and recording module simulates the user's identity portrait according to the application combination scoring mechanism within the detection time, determines whether to include the user in the identity multi-database, and stores the user's identity information according to the judgment result; The identity confirmation module identifies the current user identity status based on the user input result and determines whether the user interacts with the all-in-one device in a single identity state, and transmits the interaction judgment result to the interface providing module; The interface providing module selects to provide different interaction interfaces to the current user based on the received interaction judgment results.

[0014] The technical effects and advantages of the intelligent interactive system and method for an all-in-one educational machine of the present invention are as follows: The present invention first collects user behavior, determines the user's exploration of various applications on the all-in-one machine, sets a detection time and an application combination scoring mechanism, and passes the user through the application combination scoring mechanism within the detection time to simulate the user's identity portrait and calculate the identity recognition coefficient, and comprehensively considers the user's exploration of various applications and the identity recognition coefficient to determine whether to include the user in the identity multiple library; the user's identity is preliminarily recorded to facilitate subsequent identification and call analysis, when the all-in-one machine starts working, an application combination pop-up window pops up to the user end and guides the user to provide input, and analysis is performed based on the user input to improve the accuracy of the analysis of the current user identity, and the user's current identity status is identified according to the user input mode and the input result, and it is determined whether the user interacts with the all-in-one machine in a single identity state, and different interaction interfaces are provided to the user according to the user's current identity status and the single identity status judgment result, thereby reducing the time cost of the user operating the all-in-one machine and improving the user's learning efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 The present invention is a schematic diagram of an intelligent interaction method for an all-in-one educational machine.

[0016] Figure 2 This is a flow chart of an intelligent interactive system for an all-in-one educational machine according to the present invention. DETAILED DESCRIPTION

[0017] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0018] The present invention first collects user behavior, determines the user's exploration of various applications on the all-in-one machine, sets a detection time and an application combination scoring mechanism, and passes the user through the application combination scoring mechanism within the detection time to simulate the user's identity portrait and calculate the identity recognition coefficient, and comprehensively considers the user's exploration of various applications and the identity recognition coefficient to determine whether to include the user in the identity multiple library; when the all-in-one machine starts working, an application combination pop-up window pops up to the user end and guides the user to provide input, identifies the user's current identity status according to the user's input mode and input results, and determines whether the user interacts with the all-in-one machine in a single identity state, and provides different interaction interfaces to the user according to the user's current identity status and the single identity status judgment result, thereby reducing the time cost of the user operating the all-in-one machine and improving the user's learning efficiency.

[0019] Example 1: An intelligent interaction method for an educational all-in-one machine, such as Figure 1 As shown, the following steps are included: Step S1: Collect user behavior data to determine the user's exploration of various applications on the all-in-one machine, set the detection time and application combination scoring mechanism; Step S2: During the detection time, the user is passed through the application combination scoring mechanism to simulate the user's identity portrait and calculate the identity recognition coefficient. The user's application exploration and identity recognition coefficient are comprehensively considered to determine whether to include the user in the identity multi-database; Step S3: Pop up an application combination pop-up window to the user end and guide the user to make a selection. According to the user selection mode and input result, identify the user's current identity status and determine whether the user interacts with the all-in-one device in a single identity state; Step S4: providing different interactive interfaces to the user according to the user's current identity status and the single identity status judgment result.

[0020] The specific implementation is as follows: In step S1, the user behavior data is the number of times the user has used the application and the duration of use in the application history. The user's exploration rate of each application is calculated based on the user behavior data as the user's exploration of each application on the all-in-one device. The application history is stored in the server database of the all-in-one machine. By calling the application history of each application in the server database of the all-in-one machine, the number of times and the duration of use in the history of each application are obtained.

[0021] It should be noted that the server database refers to a database system running on a remote server, which is used to store and manage data. The server database of the all-in-one machine records the usage of each application, including the number of times each application has been used in history and the duration of use, which can be called through the server database.

[0022] Combine the number of times each application is used into an application frequency dataset, and combine the usage time of each application into an application duration dataset. Use the application frequency dataset and the application duration dataset to build a multi-layer perceptron model to calculate the exploration rate of each application. The specific steps are as follows: Data input: The application frequency dataset and application duration dataset are passed into the input layer as input features. The input layer normalizes the input features and then passes them into the hidden layer. Initialization parameters: Initialize the initial weights and bias parameters from the input layer to the hidden layer; Set the hidden layer processing algorithm: Set the hidden layer activation function to process the input features. Take the weighted function as an example to construct the activation function: , where T is the output of the hidden layer, is the result of data standardization in the application frequency dataset, and b is the result of data standardization in the application duration dataset. and are the two initial weights set in the input layer to the hidden layer, is the bias parameter set in the input layer to the hidden layer; Set the output layer processing algorithm: Set the activation function of the output layer: , is the output result of the output layer, i is the output result sequence number of different input features through the hidden layer, and n is the number of data in the application frequency dataset or application duration dataset; Propagation: The multi-layer perceptron passes the input features through the input layer, hidden layer, and output layer in sequence, and finally uses the output of the output layer as the user's application exploration reference ratio; Calculating the exploration rate: The data in the application frequency dataset and the application duration dataset of the same application are used as input features. The output of the hidden layer is calculated through the hidden layer. The ratio of the hidden layer output to the application exploration reference ratio is used as the exploration rate of the corresponding application.

[0023] It should be explained that the activation functions of the hidden layers and output layers involved in the above-mentioned multi-layer perceptron are not unique. The higher the exploration rate of an application, the longer the number of times and duration of use of the corresponding application, and the higher the proficiency of the corresponding application.

[0024] Since different identities use different applications, this example uses two identities. In the application combination scoring mechanism, different applications are assigned values and different identity information is set, where the identity information includes single identity information or multiple identity information. For example, the two identities are marked as identity 1 and identity 2 respectively; a 1 to 3-point scale mechanism is used to assign identity scores to different applications. Applications used by both identities 1 and 2 are assigned a score of 2 points, applications used only by identity 1 are assigned a score of 1 point; and applications used only by identity 2 are assigned a score of 3 points.

[0025] It should be noted that in the application combination mechanism, the points assigned by the scale mechanism are not unique and can be adjusted according to the number of applications and other actual conditions. For example, a 1 to 5 point scale mechanism can be used to assign identity scores, etc., which will not be elaborated here.

[0026] In step S2, a period of time is selected as the detection time. When drawing the user identity portrait, the applications opened by the user are recorded during the detection time, the number of repeated assignments of the opened applications is counted, and the identity corresponding to the application with the most repeated assignments is used as the current user identity.

[0027] For example, if application 1 is assigned a score of 1, application 2 is assigned a score of 2, and application 3 is assigned a score of 3, and within the detection time, application 1 is opened once and application 3 is opened twice, the identity corresponding to application 3 is used as the current user identity.

[0028] The user's identity recognition coefficient is obtained by accumulating the application assignment values with the most repetitions and dividing it by the accumulated sum of all application assignment values within the detection time.

[0029] For example, during the detection time, application 1 is opened once, application 2 is opened once, and application 3 is opened twice. The user's identity recognition coefficient is (3*2) / (1+2+3*2)=2 / 3.

[0030] Mark the application with the most repetitions within the detection time, call the exploration rate of the user using the marked application, and use the geometric mean method to determine whether to include the user in the identity multi-library based on the exploration rate of the marked application and the identity recognition coefficient. The geometric mean formula is: , where L is the exploration rate of the tag application, B is the user's identity recognition coefficient, and S is the identity cardinality obtained by calculation.

[0031] When the tag application is used by multiple identities and the identity base calculated by the corresponding tag application exceeds the preset multi-identity threshold, the current user is included in the identity multi-library; otherwise, the current user is not included in the identity multi-library.

[0032] It should be noted that the identity multi-library is a database coefficient that stores and manages user identity information. It is used for identity storage, authentication and user management. In this case, it is used to store user identities and determine call permissions.

[0033] In step S3, when the user turns on the all-in-one machine, a combination pop-up window pops up to the user end and guides the user to make a selection. Single or multiple identity tags are set in different applications. Applications with a single and identical identity tag are combined. The corresponding application combination inherits the identity tag. The combination pop-up window includes multiple application combinations. The user enters in two modes, as shown below: Mode 1: Select the application combination provided in the pop-up window; Mode 2: Select a single app or multiple apps from the apps in the all-in-one device.

[0034] The following rules are used to determine whether a user is interacting with the all-in-one device in a single identity state: Rule 1: When the user selects mode 1 for input, the user is judged to be in a single identity state, and the identity tag corresponding to the application combination selected by the user is used as the identity tag of the current user; Rule 2: When the user selects mode 2 for input, if the user selects a single application, the user is judged to be in a single identity state, and the identity tag corresponding to the single application selected by the user is used as the identity tag of the current user; Rule 3: When the user selects mode 2 for input, if the user selects a single application and the application has multiple identity tags, the user is judged to be in a multi-identity state, and the different identity tags corresponding to the application are all used as the identity tags of the current user; Rule 4: When the user selects mode 2 for input, if the user selects multiple applications and the identity tags corresponding to the multiple applications are the same, the user is judged to be in a single identity state, and the corresponding identity tag is used as the identity tag of the current user; Rule 5: When the user selects mode 2 for input, if the user selects multiple applications and the identity tags corresponding to the multiple applications are different, the user is judged to be in a multi-identity state, and the different identity tags corresponding to the applications are all used as the identity tags of the current user.

[0035] It should be noted that the identity tag is set within the application through the application combination scoring mechanism.

[0036] In step S4, if the current user is in a single identity state, the all-in-one machine enters a quick use interface; if the current user is in a multi-identity state, the all-in-one machine enters an auxiliary use interface.

[0037] In the quick use interface, when the user interacts with an open application, no function guidance is provided. In the auxiliary use interface, when the user interacts with an open application, function application guidance is provided.

[0038] Determining the all-in-one machine application interface based on identity information improves the efficiency of different users in interactive operations using the all-in-one machine, and provides a guarantee for the expected completion of studies or achievement of training goals.

[0039] It should be noted that the functional application guide is a semi-transparent function annotation next to the interface button of the application.

[0040] Example 2: An intelligent interactive system for an educational all-in-one machine, such as Figure 2 As shown, it includes a data acquisition module, an exploration and recording module, an identity confirmation module, and an interface providing module, and each module is connected by electrical signals; The data collection module is used to collect user behavior data, set the detection time and application combination scoring mechanism based on the user behavior data, and pass the user behavior data, detection time and application combination scoring mechanism to the exploration recording module. When the user uses the all-in-one machine, the application combination pop-up window will pop up to the user end and obtain the user input result and pass it to the identity confirmation module; The exploration and recording module simulates the user's identity portrait according to the application combination scoring mechanism within the detection time, determines whether to include the user in the identity multi-database, and stores the user's identity information according to the judgment result; The identity confirmation module identifies the current user identity status based on the user input result and determines whether the user interacts with the all-in-one device in a single identity state, and transmits the interaction judgment result to the interface providing module; The interface providing module selects to provide different interaction interfaces to the current user based on the received interaction judgment results.

[0041] The above embodiments may be implemented in whole or in part through software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0042] Those skilled in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application of the technical solution and the invention constraints. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0043] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0044] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0045] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An intelligent interaction method for an educational all-in-one machine, characterized in that: The following steps are included: Step S1: Collect user behavior data to determine the user's exploration of various applications on the all-in-one machine, set the detection time and application combination scoring mechanism; Step S2: During the detection time, the user is passed through the application combination scoring mechanism to simulate the user's identity portrait and calculate the identity recognition coefficient. The user's application exploration and identity recognition coefficient are comprehensively considered to determine whether to include the user in the identity multi-database; Step S3: Pop up an application combination pop-up window to the user end and guide the user to make a selection. According to the user selection mode and input result, identify the user's current identity status and determine whether the user interacts with the all-in-one device in a single identity state; Step S4: providing different interactive interfaces to the user according to the user's current identity status and the single identity status judgment result.

2. The intelligent interaction method for an all-in-one educational machine according to claim 1, characterized in that: In step S1, the user behavior data is the number of times the user has used the application and the duration of use in the application history. The user's exploration rate of each application is calculated based on the user behavior data as the user's exploration of each application on the all-in-one device. The application history is stored in the server database of the all-in-one machine. By calling the application history of each application in the server database of the all-in-one machine, the number of times and the duration of use in the history of each application are obtained.

3. The intelligent interaction method for an all-in-one educational machine according to claim 2, characterized in that: In step S1, the number of times each application is used is combined into an application frequency dataset, and the usage time of each application is combined into an application time dataset. The application frequency dataset and the application time dataset are used to build a multi-layer perceptron model to calculate the exploration rate of each application. The specific steps are as follows: Data input: The application frequency dataset and application duration dataset are passed into the input layer as input features. The input layer normalizes the input features and then passes them into the hidden layer. Initialization parameters: Initialize the initial weights and bias parameters from the input layer to the hidden layer; Set the hidden layer processing algorithm: Set the hidden layer activation function to process the input features. Take the weighted function as an example to construct the activation function: , where T is the output of the hidden layer, is the result of data standardization in the application frequency dataset, and b is the result of data standardization in the application duration dataset. and are the two initial weights set in the input layer to the hidden layer, is the bias parameter set in the input layer to the hidden layer; Set the output layer processing algorithm: Set the activation function of the output layer: , is the output result of the output layer, i is the output result sequence number of different input features through the hidden layer, and n is the number of data in the application frequency dataset or application duration dataset; Propagation: The multi-layer perceptron passes the input features through the input layer, hidden layer, and output layer in sequence, and finally uses the output of the output layer as the user's application exploration reference ratio; Calculating the exploration rate: The data from the application frequency dataset and the application duration dataset of the same application are used as input features. The output of the hidden layer is calculated through the hidden layer. The ratio of the hidden layer output to the application exploration reference ratio is used as the exploration rate of the corresponding application. In the application combination scoring mechanism, different applications are assigned values and set with different identity information, where the identity information includes single identity information or multiple identity information.

4. The intelligent interaction method for an all-in-one educational machine according to claim 1, characterized in that: In step S2, a period of time is selected as the detection time. When drawing the user identity portrait, the applications opened by the user during the detection time are recorded, the number of repeated assignments of the opened applications is counted, and the identity corresponding to the application with the most repeated assignments is used as the current user identity; The user's identity recognition coefficient is obtained by accumulating the application assignment values with the most repetitions and dividing it by the accumulated sum of all application assignment values within the detection time.

5. The intelligent interaction method for an all-in-one educational machine according to claim 4, characterized in that: In step S2, the application with the most repetitions within the detection time is marked, and the exploration rate of the marked application is called. The exploration rate of the marked application and the identity recognition coefficient are used to determine whether to include the user in the identity multi-library using the geometric mean method. The geometric mean formula is: , where L is the exploration rate of the tag application, B is the user's identity recognition coefficient, and S is the identity cardinality obtained by calculation; When the tag application is used by multiple identities and the identity base calculated by the corresponding tag application exceeds the preset multi-identity threshold, the current user is included in the identity multi-library; otherwise, the current user is not included in the identity multi-library.

6. The intelligent interaction method for an all-in-one educational machine according to claim 1, characterized in that: In step S3, when the user turns on the all-in-one machine, a combination pop-up window pops up to the user end and guides the user to make a selection. Single or multiple identity tags are set in different applications. Applications with a single and identical identity tag are combined. The corresponding application combination inherits the identity tag. The combination pop-up window includes multiple application combinations. The user enters in two modes, as shown below: Mode 1: Select the application combination provided in the pop-up window; Mode 2: Select a single app or multiple apps from the apps in the all-in-one device.

7. The intelligent interaction method for an all-in-one educational machine according to claim 6, characterized in that: In step S3, when determining whether the user interacts with the all-in-one device in a single identity state, the following rules are used: Rule 1: When the user selects mode 1 for input, the user is judged to be in a single identity state, and the identity tag corresponding to the application combination selected by the user is used as the identity tag of the current user; Rule 2: When the user selects mode 2 for input, if the user selects a single application, the user is judged to be in a single identity state, and the identity tag corresponding to the single application selected by the user is used as the identity tag of the current user; Rule 3: When the user selects mode 2 for input, if the user selects a single application and the application has multiple identity tags, the user is judged to be in a multi-identity state, and the different identity tags corresponding to the application are all used as the identity tags of the current user; Rule 4: When the user selects mode 2 for input, if the user selects multiple applications and the identity tags corresponding to the multiple applications are the same, the user is judged to be in a single identity state, and the corresponding identity tag is used as the identity tag of the current user; Rule 5: When the user selects mode 2 for input, if the user selects multiple applications and the identity tags corresponding to the multiple applications are different, the user is judged to be in a multi-identity state, and the different identity tags corresponding to the applications are all used as the identity tags of the current user.

8. The intelligent interaction method for an all-in-one educational machine according to claim 7, characterized in that: In step S4, if the current user is in a single identity state, the all-in-one machine enters a quick use interface; if the current user is in a multi-identity state, the all-in-one machine enters an auxiliary use interface; In the quick use interface, when the user interacts with the open application, no function guidance is provided. In the auxiliary use interface, when the user interacts with the open application, function application guidance is provided. Function application guidelines are semi-transparent function annotations next to the application interface buttons.

9. An intelligent interactive system for an all-in-one educational machine, based on an intelligent interactive method for an all-in-one educational machine according to any one of claims 1 to 8, characterized in that: It includes data collection module, exploration record module, identity confirmation module and interface provision module; The data collection module is used to collect user behavior data, set the detection time and application combination scoring mechanism based on the user behavior data, and pass the user behavior data, detection time and application combination scoring mechanism to the exploration recording module. When the user uses the all-in-one machine, the application combination pop-up window will pop up to the user end and obtain the user input result and pass it to the identity confirmation module; The exploration and recording module simulates the user's identity portrait according to the application combination scoring mechanism within the detection time, determines whether to include the user in the identity multi-database, and stores the user's identity information according to the judgment result; The identity confirmation module identifies the current user identity status based on the user input result and determines whether the user interacts with the all-in-one device in a single identity state, and transmits the interaction judgment result to the interface providing module; The interface providing module selects to provide different interaction interfaces to the current user based on the received interaction judgment results.

Images