An intelligent interactive system and method for educational all-in-one machines

Abstract

This invention discloses an intelligent interactive system and method for educational all-in-one machines, relating to the field of intelligent interactive technology. It aims to improve the low efficiency of all-in-one machine application interfaces during user identity transitions. The system includes collecting user behavior data, determining the user's exploration of various applications on the all-in-one machine, setting a detection time and an application combination scoring mechanism. Within the detection time, the user is fed into the application combination scoring mechanism, which uses a multilayer perceptron to simulate the user's identity profile and calculate the identity recognition coefficient. The geometric mean method is used to determine whether to include the user in a multi-identity database, considering the user's exploration of various applications and the identity recognition coefficient. When the all-in-one machine starts working, an application combination pop-up window appears on the user's end, guiding the user to provide input. Based on the user's input pattern and input results, the system identifies the user's current identity state, determines whether the user is interacting with the all-in-one machine with a single identity state, and provides different interactive interfaces to the user.

Description

Technical Field

[0001] This invention relates to the field of intelligent interactive technology, and more specifically, to an intelligent interactive system and method for educational all-in-one machines. Background Technology

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

[0003] The existing technology has the following shortcomings:

[0004] All-in-one machines contain application software with different functions. When users interact with the all-in-one machine, they do so through preset function buttons. However, when users switch identities using the all-in-one machine, they may be unfamiliar with the function buttons in the application software, which may affect the interaction effect and delay the learning or training progress. Summary of the Invention

[0005] To overcome the aforementioned deficiencies of the prior art, embodiments of the present invention provide an intelligent interaction method for an educational all-in-one machine. By analyzing user behavior, the method determines the user's identity and whether the user has a single identity. Users with non-single identities are included in an identity database. The method analyzes the current user status, matches the user in the identity database, determines the current user's identity when using the all-in-one machine, and provides different operating interfaces to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] A smart interaction method for educational all-in-one machines includes the following steps:

[0008] Step S1: Collect user behavior data to determine the user's exploration of various applications on the all-in-one machine, and set the detection time and application combination scoring mechanism;

[0009] Step S2: During the detection period, the user is entered into the application combination scoring mechanism to simulate the user identity profile and calculate the identity recognition coefficient. Based on the user's exploration of various applications and the identity recognition coefficient, it is determined whether to include the user in the multi-identity database.

[0010] Step S3: Display an application combination pop-up window to the user and guide the user to make a selection. Based on the user's selection mode and input results, identify the user's current identity status and determine whether the user is interacting with the all-in-one machine in a single identity status.

[0011] Step S4: Provide different interactive interfaces to the user based on the user's current identity status and the single identity status judgment result.

[0012] In a preferred embodiment, in step S1, the user behavior data includes the number of times and duration of use of the user's application in history. The user's exploration rate for each application is calculated based on the user behavior data as the user's exploration status of each application on the all-in-one device.

[0013] 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 each application was used and the duration of use can be obtained.

[0014] In a preferred embodiment, in step S1, the usage frequency of each application is merged into an application frequency dataset, and the usage duration of each application is merged into an application duration dataset. A multilayer perceptron model is then constructed using the application frequency dataset and the application duration dataset to calculate the exploration rate of each application. The specific steps are as follows:

[0015] Data input: The application frequency dataset and application duration dataset are used as input features and fed into the input layer. The input layer standardizes the input features and then feeds them into the hidden layer.

[0016] Initialize parameters: Assign initial values ​​to the weights and biases from the input layer to the hidden layer;

[0017] Setting up the hidden layer processing algorithm: The hidden layer activation function is set to process the input features. Taking a weighted function as an example, the activation function is constructed as follows: Where T is the output of the hidden layer. b represents the result of standardized centralized data in the application frequency dataset, and b represents the result of standardized centralized data in the application duration dataset. and These are two initial weights set between the input layer and the hidden layer. These are the bias parameters set between the input layer and the hidden layer.

[0018] Set the output layer processing algorithm: Set the activation function of the output layer: , is the output of the output layer, i is the index of the output result of different input features through the hidden layer, and n is the number of data in the application frequency dataset or application duration dataset.

[0019] Propagation: The multilayer perceptron passes the input features sequentially through the input layer, hidden layer, and output layer, and finally uses the output of the output layer as a reference ratio for the user's application exploration;

[0020] Calculate the exploration rate: Take the data from the application frequency dataset and the application duration dataset of the same application as input features, calculate the output of the hidden layer through the hidden layer, and take the ratio of the output of the hidden layer to the application exploration reference ratio as the exploration rate of the corresponding application.

[0021] In the application combination scoring mechanism, different applications are assigned values ​​and set with different identity information, which includes single identity information or multiple identity information.

[0022] In a preferred embodiment, in step S2, a period of time is selected as the detection time. When drawing the user identity profile, the applications opened by the user are recorded during the detection time, the number of times the opened applications are assigned repeated values ​​is counted, and the identity corresponding to the application with the most repeated values ​​is taken as the current user identity.

[0023] The user's identity recognition coefficient is obtained by summing the values ​​assigned to the application with the most repetitions and dividing by the sum of all application values ​​assigned within the detection period.

[0024] In a preferred embodiment, in step S2, the application with the most repetitions within the detection time is marked. The user's exploration rate using the marked application is retrieved. 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-factor database. The geometric mean formula is: Where L is the exploration rate of the tagging application, B is the user's identity recognition coefficient, and S is the identity base obtained by calculation;

[0025] If a tagging application is used by multiple identities and the identity base calculated by the corresponding tagging application exceeds the preset multi-identity threshold, then the current user will be included in the multi-identity database; otherwise, the current user will not be included in the multi-identity database.

[0026] In a preferred embodiment, in step S3, when the user turns on the all-in-one device, a combined pop-up window is displayed to the user, guiding the user to make a selection. Different applications have one or more identity tags. Applications that all have a single and identical identity tag are combined, and the corresponding application combination inherits the identity tag. The combined pop-up window includes multiple application combinations, and the user inputs information in two modes, as shown below:

[0027] Mode 1: Select the application combination provided in the pop-up window;

[0028] Mode 2: Select one or more applications from the applications in the all-in-one machine.

[0029] In a preferred embodiment, in step S3, when determining whether a user interacts with the all-in-one machine in a single-identity state, the following rules are used:

[0030] Rule 1: When a user selects Mode 1 for input, the user is determined to be in a single identity state, and the identity tag corresponding to the application combination selected by the user is used as the current user's identity tag;

[0031] Rule 2: When a user selects Mode 2 for input, if the user selects a single application and the application corresponds to only a single identity tag, then the user is determined to be in a single identity state, and the identity tag corresponding to the single application selected by the user is taken as the current user's identity tag.

[0032] Rule 3: When a user selects mode 2 for input, if the user selects a single application and the application has multiple identity tags, the user is determined to be in a multi-identity state, and all the different identity tags corresponding to the application are used as the current user's identity tags.

[0033] Rule 4: When a user selects Mode 2 for input, if the user selects multiple applications and the identity tags corresponding to the multiple applications are the same, then the user is determined to be in a single identity state, and the corresponding identity tag is used as the current user's identity tag.

[0034] Rule 5: When a user selects Mode 2 for input, if the user selects multiple applications and the identity tags corresponding to the multiple applications are different, then the user is determined to be in a multi-identity state, and the different identity tags corresponding to the applications are all used as the current user's identity tags.

[0035] In a preferred embodiment, in step S4, if the current user is in a single identity state, the all-in-one machine enters the quick use interface; if the current user is in a multi-identity state, the all-in-one machine enters the auxiliary use interface.

[0036] In the quick access interface, no function guidance is provided when the user interacts with the opened application; in the accessibility interface, function application guidance is provided when the user interacts with the opened application.

[0037] Function application guidelines are semi-transparent annotations placed next to the application's interface buttons.

[0038] An intelligent interactive system for an educational all-in-one machine, used to implement the aforementioned intelligent interactive method for an educational all-in-one machine, includes a data acquisition module, an exploration record module, an identity verification module, and an interface provision module;

[0039] The data acquisition module is used to collect user behavior data and set the detection time and application combination scoring mechanism based on the user behavior data. The user behavior data, detection time and application combination scoring mechanism are then passed to the exploration record module. When the user uses the all-in-one machine, an application combination pop-up window is displayed to the user and the user input results are obtained and passed to the identity verification module.

[0040] The exploration and recording module simulates user identity profiles based on the application combination scoring mechanism within the detection period, determines whether to include the user in the multi-identity database, and stores the user identity information into the database based on the judgment result.

[0041] The identity verification module identifies the current user's identity status based on the user's input and determines whether the user is interacting with the all-in-one machine with a single identity status. The interaction judgment result is then passed to the interface provision module.

[0042] The interface providing module selects different interactive interfaces to provide to the current user based on the received interaction judgment results.

[0043] The technical effects and advantages of the intelligent interactive system and method for educational all-in-one machines of the present invention are as follows:

[0044] This invention first collects user behavior data to determine the user's exploration of various applications on the all-in-one machine. It then sets a detection time and an application combination scoring mechanism. Within the detection time, the user is fed into the application combination scoring mechanism to simulate a user identity profile and calculate an identity recognition coefficient. Based on the user's application exploration and the identity recognition coefficient, it determines whether to include the user in a multi-identity database. The user's identity is initially recorded for subsequent identification and analysis. When the all-in-one machine starts working, an application combination pop-up window appears on the user's end, guiding the user to provide input. Analysis is performed based on the user's input to improve the accuracy of current user identity analysis. The user's current identity state is identified based on the input pattern and results, and it is determined whether the user is interacting with the all-in-one machine with a single identity state. Different interactive interfaces are provided to the user based on the current identity state and the single identity state determination results, reducing the time cost of operating the all-in-one machine and improving user learning efficiency. Attached Figure Description

[0045] Figure 1 This is a schematic diagram of an intelligent interaction method for an educational all-in-one machine according to the present invention.

[0046] Figure 2 This is a flowchart of an intelligent interactive system for an educational all-in-one machine according to the present invention. Detailed Implementation

[0047] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0048] This invention first collects user behavior data to determine the user's exploration of various applications on the all-in-one machine. It then sets a detection time and an application combination scoring mechanism. During the detection time, the user is fed into the application combination scoring mechanism to simulate a user identity profile and calculate an identity recognition coefficient. Based on the user's application exploration and the identity recognition coefficient, it determines whether to include the user in a multi-identity database. When the all-in-one machine starts working, an application combination pop-up window appears on the user's end, guiding the user to provide input. Based on the user's input pattern and results, the invention identifies the user's current identity state and determines whether the user is interacting with the all-in-one machine with a single identity. Based on the user's current identity state and the single identity state determination result, different interactive interfaces are provided to the user, reducing the time cost of operating the all-in-one machine and improving user learning efficiency.

[0049] Example 1: An intelligent interaction method for educational all-in-one machines, such as... Figure 1 As shown, it includes the following steps:

[0050] Step S1: Collect user behavior data to determine the user's exploration of various applications on the all-in-one machine, and set the detection time and application combination scoring mechanism;

[0051] Step S2: During the detection period, the user is entered into the application combination scoring mechanism to simulate the user identity profile and calculate the identity recognition coefficient. Based on the user's exploration of various applications and the identity recognition coefficient, it is determined whether to include the user in the multi-identity database.

[0052] Step S3: Display an application combination pop-up window to the user and guide the user to make a selection. Based on the user's selection mode and input results, identify the user's current identity status and determine whether the user is interacting with the all-in-one machine in a single identity status.

[0053] Step S4: Provide different interactive interfaces to the user based on the user's current identity status and the single identity status judgment result.

[0054] The specific implementation is as follows:

[0055] In step S1, user behavior data includes the number of times and duration of use of the user's application in history. The user's exploration rate for each application is calculated based on the user behavior data as the user's exploration status of each application on the all-in-one device.

[0056] 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 each application was used and the duration of use can be obtained.

[0057] It should be noted that the server database refers to a database system running on a remote server, 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 accessed through the server database.

[0058] The usage frequency of each application is merged into an application frequency dataset, and the usage duration of each application is merged into an application duration dataset. A multilayer perceptron model is then constructed using the application frequency dataset and the application duration dataset to calculate the exploration rate of each application. The specific steps are as follows:

[0059] Data input: The application frequency dataset and application duration dataset are used as input features and fed into the input layer. The input layer standardizes the input features and then feeds them into the hidden layer.

[0060] Initialize parameters: Assign initial values ​​to the weights and biases from the input layer to the hidden layer;

[0061] Setting up the hidden layer processing algorithm: The hidden layer activation function is set to process the input features. Taking a weighted function as an example, the activation function is constructed as follows: Where T is the output of the hidden layer. b represents the result of standardized centralized data in the application frequency dataset, and b represents the result of standardized centralized data in the application duration dataset. and These are two initial weights set between the input layer and the hidden layer. These are the bias parameters set between the input layer and the hidden layer.

[0062] Set the output layer processing algorithm: Set the activation function of the output layer: , is the output of the output layer, i is the index of the output result of different input features through the hidden layer, and n is the number of data in the application frequency dataset or application duration dataset.

[0063] Propagation: The multilayer perceptron passes the input features sequentially through the input layer, hidden layer, and output layer, and finally uses the output of the output layer as a reference ratio for the user's application exploration;

[0064] Calculate the exploration rate: Take the data from the application frequency dataset and the application duration dataset of the same application as input features, calculate the output of the hidden layer, and take the ratio of the hidden layer output to the application exploration reference ratio as the exploration rate of the corresponding application.

[0065] It should be noted that the activation functions of the hidden and output layers involved in the above multilayer perceptron are not unique. The higher the exploration rate of the application, the more times and duration the application is used, and the higher the proficiency of the application.

[0066] 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. The identity information includes single identity information or multiple identity information. For example, the two identities are labeled 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 Identity 1 and Identity 2 are assigned 2 points, applications used only by Identity 1 are assigned 1 point, and applications used only by Identity 2 are assigned 3 points.

[0067] It should be noted that in the application combination mechanism, the number of scale points assigned is not unique and can be adjusted according to the number of applications and other actual situations. For example, a 1 to 5 point scale mechanism can be used for identity scoring, etc., which will not be elaborated here.

[0068] In step S2, a period of time is selected as the detection time. When drawing the user identity profile, the applications opened by the user are recorded during the detection time, the number of times the opened applications are assigned repeated values ​​is counted, and the identity corresponding to the application with the most repeated values ​​is taken as the current user identity.

[0069] For example, if application 1 is assigned a value of 1 point, application 2 is assigned a value of 2 points, and application 3 is assigned a value of 3 points, and application 1 is opened once and application 3 is opened twice within the detection time, then the identity corresponding to application 3 will be used as the current user's identity.

[0070] The user's identity recognition coefficient is obtained by summing the values ​​assigned to the application with the most repetitions and dividing by the sum of all application values ​​assigned within the detection period.

[0071] For example, if application 1 is opened once, application 2 is opened once, and application 3 is opened twice within the detection time, then the user's identity recognition coefficient is (3 2) / (1+2+3) 2) = 2 / 3.

[0072] The application with the highest frequency of repetition within the detection period is marked. The user's exploration rate using the marked application is then used to determine whether to include the user in the multi-identity database using the geometric mean method, which is based on the exploration rate of the marked application and the identity recognition coefficient. The geometric mean formula is as follows: Where L is the exploration rate of the tagging application, B is the user's identity recognition coefficient, and S is the identity base obtained by calculation.

[0073] If a tagging application is used by multiple identities and the identity base calculated by the corresponding tagging application exceeds the preset multi-identity threshold, then the current user will be included in the multi-identity database; otherwise, the current user will not be included in the multi-identity database.

[0074] It should be noted that a multi-identity database is a database system for storing and managing user identity information. It is used for identity storage, authentication, and user management. In this example, it is used to store user identities and determine access permissions.

[0075] In step S3, when the user turns on the all-in-one device, a combined pop-up window appears on the user's device, guiding the user to make a selection. Different applications have one or more identity tags set. Applications that all have a single and identical identity tag are grouped together, and the corresponding application group inherits the identity tag. The combined pop-up window includes multiple application groups, and the user can input in two modes, as shown below:

[0076] Mode 1: Select the application combination provided in the pop-up window;

[0077] Mode 2: Select one or more applications from the applications in the all-in-one machine.

[0078] The following rules are used to determine whether a user is interacting with the all-in-one machine in a single identity state:

[0079] Rule 1: When a user selects Mode 1 for input, the user is determined to be in a single identity state, and the identity tag corresponding to the application combination selected by the user is used as the current user's identity tag;

[0080] Rule 2: When a user selects Mode 2 for input, if the user selects a single application and the application corresponds to only a single identity tag, then the user is determined to be in a single identity state, and the identity tag corresponding to the single application selected by the user is taken as the current user's identity tag.

[0081] Rule 3: When a user selects mode 2 for input, if the user selects a single application and the application has multiple identity tags, the user is determined to be in a multi-identity state, and all the different identity tags corresponding to the application are used as the current user's identity tags.

[0082] Rule 4: When a user selects Mode 2 for input, if the user selects multiple applications and the identity tags corresponding to the multiple applications are the same, then the user is determined to be in a single identity state, and the corresponding identity tag is used as the current user's identity tag.

[0083] Rule 5: When a user selects Mode 2 for input, if the user selects multiple applications and the identity tags corresponding to the multiple applications are different, then the user is determined to be in a multi-identity state, and the different identity tags corresponding to the applications are all used as the current user's identity tags.

[0084] It should be noted that the identity tags set within the application are implemented through an application-based scoring mechanism.

[0085] In step S4, if the current user is in a single identity state, the all-in-one machine enters the quick use interface; if the current user is in a multi-identity state, the all-in-one machine enters the auxiliary use interface.

[0086] In the quick access interface, no function guidance is provided when the user interacts with the opened application. In the accessibility interface, function application guidance is provided when the user interacts with the opened application.

[0087] Determining the interface of the all-in-one machine based on identity information improves the efficiency of interactive work for different users, providing a guarantee for completing studies or achieving training goals.

[0088] It should be noted that the function application guide is a semi-transparent annotation next to the button on the application's interface.

[0089] Example 2: An intelligent interactive system for educational all-in-one machines, such as... Figure 2 As shown, it includes a data acquisition module, an exploration record module, an identity verification module, and an interface provision module, and the modules are connected by electrical signals.

[0090] The data acquisition module is used to collect user behavior data and set the detection time and application combination scoring mechanism based on the user behavior data. The user behavior data, detection time and application combination scoring mechanism are then passed to the exploration record module. When the user uses the all-in-one machine, an application combination pop-up window is displayed to the user and the user input results are obtained and passed to the identity verification module.

[0091] The exploration and recording module simulates user identity profiles based on the application combination scoring mechanism within the detection period, determines whether to include the user in the multi-identity database, and stores the user identity information into the database based on the judgment result.

[0092] The identity verification module identifies the current user's identity status based on the user's input and determines whether the user is interacting with the all-in-one machine with a single identity status. The interaction judgment result is then passed to the interface provision module.

[0093] The interface providing module selects different interactive interfaces to provide to the current user based on the received interaction judgment results.

[0094] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, in the form of a computer program product.

[0095] Those skilled in the art will recognize that the modules and algorithm steps of the various examples 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 implemented in hardware or software depends on the specific application and inventive constraints of the technical solution. Those skilled in the art 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.

[0096] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0097] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0098] In conclusion, 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 within the protection scope of the present invention.

Claims

1. An intelligent interaction method for an educational all-in-one machine, characterized in that, Includes the following steps, Step S1: Collect user behavior data to determine the user's exploration of various applications on the all-in-one machine, and set the detection time and application combination scoring mechanism; Step S2: During the detection period, users use the application combination scoring mechanism to simulate user identity profiles and calculate identity recognition coefficients. Based on the user's exploration of various applications and the identity recognition coefficients, it is determined whether to include the user in the multi-identity database. Step S3: Display an application combination pop-up window to the user and guide the user to make a selection. Based on the user's selection mode and input results, identify the user's current identity status and determine whether the user is interacting with the all-in-one machine in a single identity status. Step S4: Provide different interactive interfaces to the user based on the user's current identity status and the result of the single identity status judgment; In step S1, the usage frequency of each application is merged into an application frequency dataset, and the usage duration of each application is merged into an application duration dataset. A multilayer perceptron model is then constructed using the application frequency dataset and the application duration dataset 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 used as input features and fed into the input layer. The input layer standardizes the input features and then feeds them into the hidden layer. Initialize parameters: Assign initial values ​​to the weights and biases from the input layer to the hidden layer; Set up the hidden layer processing algorithm: Set the hidden layer activation function to process the input features, and construct the activation function: Where T is the output of the hidden layer. b represents the result of standardized centralized data in the application frequency dataset, and b represents the result of standardized centralized data in the application duration dataset. and These are two initial weights set between the input layer and the hidden layer. These are the bias parameters set between the input layer and the hidden layer. Set the output layer processing algorithm: Set the activation function of the output layer: , is the output of the output layer, i is the index of the output result 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 multilayer perceptron passes the input features sequentially through the input layer, hidden layer, and output layer, and finally uses the output of the output layer as a reference ratio for the user's application exploration; Calculate the exploration rate: Take the data from the application frequency dataset and the application duration dataset of the same application as input features, calculate the output of the hidden layer through the hidden layer, and take the ratio of the output of the hidden layer to the application exploration reference ratio 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, which includes single identity information or multiple identity information.

2. The intelligent interaction method for an educational all-in-one machine according to claim 1, characterized in that: In step S1, user behavior data includes the number of times and duration of use of the user's application in history. The user's exploration rate for each application is calculated based on the user behavior data as the user's exploration status 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 each application was used and the duration of use can be obtained.

3. The intelligent interaction method for an educational all-in-one 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 profile, the applications opened by the user are recorded during the detection time. The number of times the opened applications are assigned the identity is counted. The identity corresponding to the application with the most repetitions is taken as the current user identity. The user's identity recognition coefficient is obtained by summing the values ​​assigned to the application with the most repetitions and dividing by the sum of all application values ​​assigned within the detection period.

4. The intelligent interaction method for an educational all-in-one machine according to claim 3, characterized in that: In step S2, the application with the most repetitions within the detection time is marked. The user's exploration rate using the marked application is retrieved. 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-factor database. The geometric mean formula is: Where L is the exploration rate of the tagging application, B is the user's identity recognition coefficient, and S is the identity base obtained by calculation; If a tagging application is used by multiple identities and the identity base calculated by the corresponding tagging application exceeds the preset multi-identity threshold, then the current user will be included in the multi-identity database; otherwise, the current user will not be included in the multi-identity database.

5. The intelligent interaction method for an educational all-in-one machine according to claim 1, characterized in that: In step S3, when the user turns on the all-in-one device, a combined pop-up window appears on the user's device, guiding the user to make a selection. Different applications have one or more identity tags set. Applications that all have a single and identical identity tag are grouped together, and the corresponding application group inherits the identity tag. The combined pop-up window includes multiple application groups, and the user can input in two modes, as shown below: Mode 1: Select the application combination provided in the pop-up window; Mode 2: Select one or more applications from the applications in the all-in-one machine.

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

7. The intelligent interaction method for an educational all-in-one machine according to claim 6, characterized in that: In step S4, if the current user is in a single identity state, the all-in-one machine enters the quick use interface; if the current user is in a multi-identity state, the all-in-one machine enters the auxiliary use interface. In the quick access interface, no function guidance is provided when the user interacts with the opened application; in the accessibility interface, function application guidance is provided when the user interacts with the opened application. Function application guidelines are semi-transparent annotations placed next to the application's interface buttons.

8. An intelligent interactive system for an educational all-in-one machine, based on the intelligent interactive method for an educational all-in-one machine according to any one of claims 1-7, characterized in that, It includes a data acquisition module, an exploration record module, an identity verification module, and an interface provision module; The data acquisition module is used to collect user behavior data and set the detection time and application combination scoring mechanism based on the user behavior data. The user behavior data, detection time and application combination scoring mechanism are then passed to the exploration record module. When the user uses the all-in-one machine, an application combination pop-up window is displayed to the user and the user input results are obtained and passed to the identity verification module. The exploration and recording module simulates user identity profiles based on the application combination scoring mechanism within the detection period, determines whether to include the user in the multi-identity database, and stores the user identity information into the database based on the judgment result. The identity verification module identifies the current user's identity status based on the user's input and determines whether the user is interacting with the all-in-one machine with a single identity status, and then passes the interaction judgment result to the interface provision module. The interface providing module selects different interactive interfaces to provide to the current user based on the received interaction judgment results.

Images