Interaction control method and device, storage medium and electronic equipment

Abstract

The embodiment of the invention discloses an interaction control method and device, a storage medium and electronic equipment, and the method comprises the steps: displaying at least one preset debate theme, obtaining a target debate theme selected by a user for the preset debate theme, obtaining a target debate role selected by the user for the target debate theme, and displaying the target debate role. Obtaining debate interaction data input by the user based on the target debate role, performing debate processing based on the debate interaction data and the target debate theme through the large debate interaction model to obtain debate response content, outputting the debate response content, and when the target debate theme is in a debate completion state, outputting the debate response content. And performing debate evaluation processing based on the debate interaction data to obtain a debate feedback report, and displaying the debate feedback report to the user. Therefore, the debate interaction large model takes a debate role opposite to that of the user, so that the user can perform a debate process about the target debate theme with the large model in the intelligent wearable device, and the intelligent debate function of the intelligent wearable device is increased.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computers, and particularly relates to an interactive control method and device, a storage medium and an electronic device. BACKGROUND

[0002] With the rapid development of sensor technology, wireless communication and artificial intelligence technology, smart wearable devices have gradually become an important part of daily life. Smart wearable devices can monitor the physiological data of users in real time, such as heart rate, exercise amount, sleep quality, etc., by integrating various sensors, and transmit the data to smart phones or the cloud for processing and analysis. At the same time, the interactive technology of smart wearable devices is also constantly upgrading, from the initial button operation to today's touch, voice recognition and gesture control, so that users can interact with the device more conveniently and intuitively.

[0003] With the continuous progress of intelligent interaction technology, smart wearable devices can respond to user needs more naturally and efficiently, promoting the development of smart wearable devices in the direction of personalization and intelligence. Therefore, how to enrich the interactive functions of smart wearable devices is a technical problem that needs to be solved by those skilled in the art. SUMMARY

[0004] The embodiments of the present application provide an interactive control method and device, a storage medium and an electronic device. The technical solution is as follows:

[0005] In a first aspect, the embodiments of the present application provide an interactive control method applied to a smart wearable device, and the method comprises:

[0006] displaying at least one preset debate topic, obtaining a target debate topic selected by a user for the preset debate topic;

[0007] obtaining a target debate role selected by the user for the target debate topic, and obtaining debate interaction data input by the user based on the target debate role;

[0008] performing debate processing based on the debate interaction data and the target debate topic by a debate interaction large model to obtain debate response content, and outputting the debate response content;

[0009] when the target debate topic is in a complete debate state, performing debate evaluation processing based on the debate interaction data to obtain a debate feedback report, and displaying the debate feedback report to the user.

[0010] In combination with the first aspect, in some possible implementation manners, the performing debate processing based on the debate interaction data and the target debate topic by the debate interaction large model to obtain debate response content comprises:

[0011] determine a debate interaction text based on the debate interaction data;

[0012] perform debate processing on the debate interaction text based on the preset debate strategy and the target debate topic by the debate interaction large model to obtain debate response content.

[0013] In some possible implementation manners, in combination with the above implementation manners, the performing debate processing on the debate interaction text based on the preset debate strategy and the target debate topic by the debate interaction large model to obtain debate response content includes:

[0014] perform debate analysis processing on the user based on the debate interaction text and the target debate topic by the debate interaction large model to obtain debate performance analysis content corresponding to the user;

[0015] determine a reference debate strategy from the preset debate strategy based on the target debate topic by the debate interaction large model, and perform strategy adjustment processing on the reference debate strategy based on the debate performance analysis content to obtain a target debate strategy;

[0016] perform debate processing on the debate interaction text based on the debate performance analysis content, the target debate strategy, and the target debate topic by the debate interaction large model to obtain debate response content.

[0017] In some possible implementation manners, in combination with the above implementation manners, after the performing debate processing on the debate interaction text based on the target debate strategy and the target debate topic by the debate interaction large model to obtain debate response content, the method further includes:

[0018] determine debate suggestion content for the user based on the debate performance analysis content by the debate interaction large model, and output the debate suggestion content.

[0019] In some possible implementation manners, in combination with the above implementation manners, the performing debate processing on the debate interaction text based on the debate performance analysis content, the target debate strategy, and the target debate topic by the debate interaction large model to obtain debate response content includes:

[0020] perform debate processing on the debate interaction text based on the debate performance analysis content, the target debate strategy, and the target debate topic by the debate interaction large model to obtain initial debate response content;

[0021] obtain language capability information for the user by the debate interaction large model, and perform sentence adaptation adjustment processing on the initial debate response content based on the language capability information to obtain debate response content.

[0022] In some possible implementation manners, the argument evaluation processing based on the debate interaction data comprises:

[0023] The argument evaluation processing based on the debate interaction data comprises argument content evaluation, debate logic evaluation, and language expression evaluation;

[0024] The debate feedback report is generated based on the argument content evaluation, the debate logic evaluation, and the language expression evaluation.

[0025] In some possible implementation manners, the debate feedback report is generated based on the argument content evaluation, the debate logic evaluation, and the language expression evaluation, and the generating comprises:

[0026] Based on the argument content evaluation, the debate logic evaluation, and the language expression evaluation, debate improvement suggestions and knowledge expansion content for the target debate topic are determined;

[0027] The debate feedback report is generated based on the argument content evaluation, the debate logic evaluation, the language expression evaluation, the debate improvement suggestions, and the knowledge expansion content.

[0028] In some possible implementation manners, the debate processing based on the debate interaction data by the debate interaction large model comprises:

[0029] It is determined whether the debate round of the debate interaction large model is equal to a preset round;

[0030] If the debate round is less than the preset round, second-round debate interaction data input by the user for the debate response content is acquired, the second-round debate interaction data is taken as the debate interaction data, and the debate processing based on the debate interaction data and the target debate topic by the debate interaction large model to obtain debate response content, and the output of the debate response content are executed;

[0031] If the debate round is equal to the preset round, it is determined that the target debate topic is in a completed debate state.

[0032] In the second aspect, an interaction control apparatus is provided, which is applied to a smart wearable device, and the apparatus comprises:

[0033] The debate theme selection module is configured to display at least one preset debate theme, and obtain a target debate theme selected by a user from the preset debate themes.

[0034] The debate data acquisition module is configured to obtain a target debate role selected by the user from the target debate theme, and obtain debate interaction data input by the user based on the target debate role.

[0035] The debate interaction processing module is configured to perform debate processing based on the debate interaction data and the target debate theme by using a debate interaction large model to obtain debate response content, and output the debate response content.

[0036] The debate data evaluation module is configured to perform debate evaluation processing based on the debate interaction data to obtain a debate feedback report when the target debate theme is in a completed debate state, and display the debate feedback report to the user.

[0037] Optionally, the debate interaction processing module includes:

[0038] The data conversion unit is configured to determine debate interaction text based on the debate interaction data.

[0039] The debate response unit is configured to perform debate processing on the debate interaction text based on a preset debate strategy and the target debate theme by using a debate interaction large model to obtain debate response content.

[0040] Optionally, the debate response unit includes:

[0041] The first processing unit is configured to perform debate analysis processing on the user based on the debate interaction text and the target debate theme by using a debate interaction large model to obtain debate performance analysis content corresponding to the user.

[0042] The second processing unit is configured to determine a reference debate strategy from a preset debate strategy based on the target debate theme by using the debate interaction large model, and perform strategy adjustment processing on the reference debate strategy based on the debate performance analysis content to obtain a target debate strategy.

[0043] The third processing unit is configured to perform debate processing on the debate interaction text based on the debate performance analysis content, the target debate strategy, and the target debate theme by using the debate interaction large model to obtain debate response content.

[0044] Optionally, the debate response unit further includes:

[0045] The fourth processing unit is configured to determine debate suggestion content for the user based on the debate performance analysis content by using the debate interaction large model, and output the debate suggestion content.

[0046] Optionally, the third processing unit is specifically configured to:

[0047] The debate interaction model performs debate processing on the debate interaction text based on the debate performance analysis content, the target debate strategy and the target debate topic to obtain initial debate response content;

[0048] The language ability information of the user is obtained through the debate interaction model, and the initial debate response content is sentence-adapted and adjusted based on the language ability information to obtain the debate response content.

[0049] Optional, Debate Data Evaluation Module, including:

[0050] a first evaluation unit, configured to perform argument evaluation processing based on the debate interaction data to obtain argument evaluation content, perform debate logic evaluation processing based on the debate interaction data to obtain debate logic evaluation content, and perform language expression evaluation processing based on the debate interaction data to obtain language expression evaluation content;

[0051] The second evaluation unit is used to generate a debate feedback report based on the argument evaluation content, the debate logic evaluation content and the language expression evaluation content.

[0052] Optionally, the second evaluation unit is specifically configured to:

[0053] Determining debate improvement suggestions and knowledge expansion content for the target debate topic based on the argument evaluation content, the debate logic evaluation content, and the language expression evaluation content;

[0054] A debate feedback report is generated based on the argument evaluation content, the debate logic evaluation content, the language expression evaluation content, the debate improvement suggestions and the knowledge expansion content.

[0055] Optionally, the interactive control device is further used to:

[0056] Determining whether the debate rounds of the debate interaction model are equal to the preset rounds;

[0057] If the debate round is less than the preset round, obtaining the second round of debate interaction data input by the user for the debate response content, using the second round of debate interaction data as the debate interaction data, and executing the steps of performing debate processing based on the debate interaction data and the target debate topic through the debate interaction macro model to obtain debate response content, and outputting the debate response content;

[0058] If the debate round is equal to the preset round, the target debate topic is determined to be in a completed debate state.

[0059] In a third aspect, the embodiments of the present application provide a computer storage medium, which has a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method described above.

[0060] In a fourth aspect, the embodiments of the present application provide an electronic device, which can include a memory and a processor, wherein the memory stores a computer program, and the computer program is suitable for being loaded by the memory and executing the method described above.

[0061] The technical solutions provided by the embodiments of the present application have at least the following beneficial effects:

[0062] The interactive control method provided by the embodiments of the present application displays at least one preset debate topic, obtains a target debate topic selected by a user for the preset debate topic, obtains a target debate role selected by the user for the target debate topic, obtains debate interaction data input by the user based on the target debate role, obtains debate response content by performing debate processing on the debate interaction data and the target debate topic based on a debate interaction large model, outputs the debate response content, when the target debate topic is in a completed debate state, obtains a debate feedback report by performing debate evaluation processing based on the debate interaction data, and displays the debate feedback report to the user. Therefore, the debate interaction large model can play a debate role opposite to the user, so that the user can carry out a debate process on the target debate topic with the large model in the smart wearable device, the smart debate function of the smart wearable device is increased, the interactive function of the smart wearable device is enriched, and the user's logical thinking is also helped to be exercised. BRIEF DESCRIPTION OF DRAWINGS

[0063] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0064] Figure 1 is a flowchart of an interactive control method provided by the embodiments of the present application;

[0065] Figure 2 is a flowchart of another interactive control method provided by the embodiments of the present application;

[0066] Figure 3 is a structural schematic diagram of an interactive control device provided by the embodiments of the present application;

[0067] Figure 4 is a structural schematic diagram of a debate interaction processing module provided by the embodiments of the present application;

[0068] Figure 5 is a structural schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0069] In order to make the purposes, features and advantages of the embodiments of the present application more obvious and easy to understand, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0070] In the description of the present application, it should be understood that the terms "first", "second" and the like are only used for the purpose of description and should not be understood as indicating or implying relative importance. In the description of the present application, it should be noted that, unless otherwise explicitly specified and limited, "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but can optionally include steps or units not listed or can optionally include other steps or units inherent to the process, method, product or device. Those skilled in the art can understand the specific meaning of the above terms in the present application according to the specific circumstances. In addition, in the description of the present application, "multiple" means two or more, unless otherwise specified. "And / or" describes the relationship between the associated objects, which means that there can be three relationships, for example, A and / or B can mean that A exists alone, A and B exist together, and B exists alone. The character " / " generally represents a "or" relationship between the associated objects.

[0071] The present application will be described in detail below with reference to specific embodiments.

[0072] In one embodiment, as shown in Figure 1 a kind of interactive control method is specially proposed, which can be realized by computer program, and can be run on interactive control device based on von Neumann system. The computer program can be integrated in application, or can be run as independent tool class application. The interactive control method can be applied to smart wearable device, and the smart wearable device can include but not limited to smart watch, smart bracelet.

[0073] Specifically, the interactive control method includes:

[0074] S101, at least one preset debate theme is displayed, and a target debate theme selected by a user for the preset debate theme is obtained.

[0075] The preset debate topic refers to a central issue used for carrying out a debate activity. The preset debate topic can be an explicit, controversial question or statement. The smart wearable device can configure at least one preset debate topic through Internet collection, manual setting, etc. When receiving a debate topic display operation input by a user, the smart wearable device displays at least one preset debate topic on the display screen in response to the debate topic display operation.

[0076] For example, the user opens an application named "AI Debate Competition" in the smart wearable device. The interface of the application can display at least one preset debate topic.

[0077] The target debate topic refers to a preset debate topic selected by the user from at least one preset debate topic. The display screen of the smart wearable device displays at least one preset debate topic. The smart wearable device can receive a debate topic selection operation input by the user. According to the debate topic selection operation, the target debate topic selected by the user for the preset debate topic can be obtained. Specifically, the preset debate topic indicated by the debate topic selection operation can be determined as the target debate topic. Alternatively, the smart wearable device can receive a topic selection voice instruction input by the user. According to the topic selection voice instruction, the target debate topic selected by the user for the preset debate topic can be obtained.

[0078] It can be understood that the debate topic selection operation described above can be an operation of the user touching any one of the preset debate topics on the display screen. The debate topic selection operation described above can also be a pressing operation or a rotating operation performed by the user on the physical control of the smart display device.

[0079] S102, obtaining a target debate role selected by the user for the target debate topic, and obtaining debate interaction data input by the user based on the target debate role.

[0080] The target debate role refers to a pro-debate role or a con-debate role for the target debate topic. After the user selects the target debate topic, the smart wearable device displays preset debate roles for the target debate topic on the display screen. The preset debate roles can include a pro-debate role and a con-debate role. The smart wearable device can also display role selection prompt information for reminding the user. Subsequently, the smart wearable device can receive a debate role selection operation input by the user for the preset debate role. According to the debate role selection operation, the target debate role selected by the user for the target debate topic can be obtained. Specifically, the preset debate role indicated by the debate role selection operation can be determined as the target debate role. Alternatively, the smart wearable device can receive a role selection voice instruction input by the user. According to the role selection voice instruction, the target debate role selected by the user for the target debate topic can be obtained.

[0081] The debate interaction data can be voice interaction data input by the user on the smart wearable device, or video interaction data recorded by the user on the smart wearable device. The debate interaction data specifically can include voice of the user inputting a debate viewpoint on the target debate topic in the identity of the target debate role. Specifically, obtaining the debate interaction data input by the user based on the target debate role can be: after the user selects the target debate role, monitoring whether the user starts a voice recording operation or a video recording operation, and when the user starts the voice recording operation or the video recording operation, collecting the debate interaction data recorded by the user.

[0082] In S103, debate response content is obtained by performing debate processing on the debate interaction data and the target debate topic based on the debate interaction large model, and the debate response content is output.

[0083] The debate interaction large model can be obtained based on a basic large language model and model training for a debate interaction scene.

[0084] The debate response content refers to a debate viewpoint obtained by a corresponding opposite debate role of the debate interaction large model acting as the target debate role, debating the viewpoint input by the user acting as the target debate role.

[0085] In some embodiments, performing step S103 can specifically include: when the debate interaction data is voice interaction data, performing voice-to-text conversion on the voice interaction data to obtain first input text, and performing text cleaning processing on the first input text to obtain debate interaction text; when the debate interaction data is video interaction data, extracting user voice data from the video interaction data, performing voice-to-text conversion on the user voice data to obtain second input text, and performing text cleaning processing on the second input text to obtain debate interaction text; inputting the debate interaction text and the target debate topic to the debate interaction large model, performing debate processing by using the debate interaction large model to obtain the debate response content; and outputting the debate response content.

[0086] In the embodiments of the present application, the debate interaction large model can be obtained based on a multi-modal large model.

[0087] Optionally, the training process of the debate interaction large model can be: creating an initial debate interaction large model based on a multi-modal large model; obtaining sample data of a sample user, the sample data including a sample debate topic of the sample user, sample debate interaction data input by the sample user based on a sample debate role, and labeling debate response content labels on the sample data; performing at least one round of model training on the initial debate interaction large model using the sample data; in the model forward propagation training process, calling the initial debate interaction large model to perform debate interaction processing based on the sample debate interaction data and the sample debate topic to obtain predicted debate response content; in the model backward propagation training process, determining a model loss value based on the predicted debate response content and the debate response content labels; and adjusting model parameters of the initial debate interaction large model based on the model loss value to obtain a debate interaction large model after model training.

[0088] Optionally, the model loss value can be determined using any one of hinge loss functions, contrast loss functions, Euclidean distance loss functions, or cross-entropy loss functions in related technologies.

[0089] Optionally, the model end training condition for obtaining the debate interaction large model can include a loss function value less than or equal to a preset loss function threshold, an iteration number reaching a preset number threshold, and the like. The model end training condition can be determined based on actual conditions, which is not limited here.

[0090] Optionally, creating the initial debate interaction large model based on the multi-modal large model can be: obtaining the multi-modal large model, creating an initial debate interaction scene adaptation module and a large language generation module based on the multi-modal large model, and composing the initial debate interaction large model based on the large language generation module and the initial debate interaction scene adaptation module.

[0091] Performing model parameter adjustment on the initial debate interaction scene adaptation module in the debate interaction large model based on the model loss value, and controlling the model parameters of the large language generation module to be unchanged, until the model training end condition is met to obtain the large language generation module and the debate interaction scene adaptation module, complete model fusion of the large language generation module and the debate interaction scene adaptation module, and obtain the trained debate interaction large model.

[0092] Optionally, the model fusion of the large language generation module and the debate interaction scene adaptation module can be that the model structure layer weight of the debate interaction scene adaptation module is fused with the large language generation module, a corresponding target model structure layer of the model structure layer weight in the large language generation module is determined, the model structure layer parameters of the target model structure layer are fused with the model structure layer weight, the model structure layer weight of the debate interaction scene adaptation module can only correspond to part of the model structure layers in the basic large language model and exist in the model structure layer weight, the parameter updating of the model structure layer based on the model structure layer weight is completed for the part of the target model structure layers, and the reference updating process of all the model structure layer weights is completed in this way, so as to obtain the debate interaction large model.

[0093] S104, when the target debate topic is in a completed debate state, a debate feedback report is obtained by performing debate evaluation processing based on the debate interaction data, and the debate feedback report is displayed to the user.

[0094] It can be understood that the determination that the target debate topic is in a completed debate state can be based on a debate end operation initiated by the user, or can be determined by detecting that the debate round reaches a preset round.

[0095] The debate feedback report can include multi-angle evaluation contents such as argument evaluation, debate logic evaluation, and language expression evaluation on the multi-round debate interaction data of the user, and improvement suggestions corresponding to each evaluation content.

[0096] Specifically, the multi-round debate interaction data of the user and the debate feedback task description information can be input into the debate interaction large model, and the debate interaction large model generates the debate feedback report according to the debate feedback task description information.

[0097] The interaction control method provided by the embodiment of the application displays at least one preset debate topic, obtains a target debate topic selected by a user for the preset debate topic, obtains a target debate role selected by the user for the target debate topic, obtains debate interaction data input by the user based on the target debate role, obtains debate response content by performing debate processing on the debate interaction data and the target debate topic based on a debate interaction large model, outputs the debate response content, obtains a debate feedback report by performing debate evaluation processing based on the debate interaction data when the target debate topic is in a completed debate state, and displays the debate feedback report to the user. Therefore, the debate interaction large model can play a debate role opposite to that of the user, so that the user can carry out a debate process on the target debate topic with the large model in the smart wearable device, the intelligent debate function of the smart wearable device is increased, the interaction function of the smart wearable device is enriched, and the user's logical thinking is also helped to be exercised.

[0098] Next, please see Figure 2A flowchart of another embodiment of an interactive control method proposed in the present application.

[0099] Specifically, the interactive control method comprises:

[0100] S201, at least one preset debate topic is displayed, and a target debate topic selected by a user for the preset debate topic is obtained.

[0101] S202, a target debate role selected by the user for the target debate topic is obtained, and debate interaction data input by the user based on the target debate role is obtained.

[0102] Specifically, the implementation manners of steps S201-S202 can be specifically referred to the descriptions of the related parts in the embodiments shown in Figure 1 The descriptions of the related parts in the embodiments shown in the foregoing are not repeated here.

[0103] S203, debate response content is obtained by performing debate processing on the debate interaction data and the target debate topic based on a debate interaction large model, and the debate response content is output.

[0104] In some embodiments, the debate response content is obtained by performing debate processing on the debate interaction data and the target debate topic based on a debate interaction large model, and the debate response content is output.

[0105] A1: debate interaction text is determined based on the debate interaction data;

[0106] A2: debate response content is obtained by performing debate processing on the debate interaction text based on a preset debate strategy and the target debate topic through a debate interaction large model.

[0107] In step A1, the debate interaction text refers to the text of the debate viewpoint of the user based on the target debate topic in the role of the target debate role extracted from the debate interaction data. Specifically, when the debate interaction data is voice interaction data of a voice type, a voice-to-text tool is used to convert the voice interaction data into initial input text, and text cleaning processing such as de-duplication and punctuation modification is performed on the initial input text to obtain the debate interaction text.

[0108] Step A2 is performed, which can include the following steps:

[0109] A21: debate performance analysis content corresponding to the user is obtained by performing debate analysis processing on the user based on the debate interaction text and the target debate topic through a debate interaction large model;

[0110] A22: a reference debate strategy is determined from the preset debate strategy based on the target debate topic through a debate interaction large model, and the target debate strategy is obtained by performing strategy adjustment processing on the reference debate strategy based on the debate performance analysis content;

[0111] A23: obtaining, by the debate interaction large model, a debate response content based on the target debate strategy and the target debate topic, by performing debate processing on the debate interaction text.

[0112] In step A21, the debate performance analysis content can be understood as content for representing the argument logical strength, the theme focus strength, the argument innovation strength, and the language expression evaluation result obtained by performing multi-angle analysis on the debate interaction text. Specifically, the debate interaction text, the target debate topic, and the debate analysis task description information are input into the debate interaction large model. The debate analysis task description information is used to instruct the debate interaction large model to determine the argument logical strength, the theme focus strength, the argument innovation strength, and the language expression evaluation result based on the target debate topic and the debate interaction text. The debate interaction large model determines the argument clarity, the argument completeness, and the logical coherence of the debate interaction text, determines the argument logical strength based on the argument clarity, the argument completeness, and the logical coherence, performs theme deviation identification processing on the debate interaction text to obtain the theme focus strength, determines the argument innovation strength based on argument novelty evaluation and argument perspective evaluation of the debate interaction text, and determines the language expression evaluation result based on syntax evaluation, vocabulary evaluation, language fluency evaluation, and rhetoric type evaluation of the debate interaction text. The debate performance analysis content is generated based on the argument logical strength, the theme focus strength, the argument innovation strength, and the language expression evaluation result.

[0113] It can be understood that the argument logical strength is used to represent whether the argument logic of the debate interaction text is correct or rigorous, the theme focus strength is used to represent whether the debate interaction text deviates from the target debate topic, the argument innovation strength is used to represent the innovation of the debate interaction text, and the language expression evaluation result is used to represent the language expression ability of the user.

[0114] It can be understood that the argument logical strength, the theme focus strength, the argument innovation strength, and the language expression evaluation result can all be represented by scores. For example, the greater the score of the argument logical strength, the stronger the logicality of the argument, the greater the score of the theme focus strength, the stronger the theme focus of the argument, the greater the score of the argument innovation strength, the higher the innovation of the argument, and the greater the score of the language expression evaluation result, the stronger the language expression ability, and vice versa.

[0115] In step A22, the preset argument strategy can be understood as an argument strategy stored in an argument strategy library, which can be constructed based on a knowledge graph and related knowledge of various argument topics. The reference argument strategy can be an argument strategy selected from the preset argument strategies that is adapted to the target argument topic. Specifically, the target argument topic, argument performance analysis content, and strategy adjustment task description information are input into the argument interaction large model. The strategy adjustment task description information is used to instruct the argument interaction large model to first select a reference argument strategy adapted to the target argument topic, and then adjust the reference argument strategy based on the argument performance analysis content. The argument interaction large model obtains the preset argument strategy from the argument strategy library, performs strategy adaptation detection processing based on the preset argument strategy and the target argument topic to determine the reference argument strategy, and adjusts the argument difficulty, argument depth, and argument angle of the reference argument strategy based on the argument performance analysis content to obtain the target argument strategy.

[0116] For example, the argument difficulty of the reference argument strategy can be adjusted according to the argument point logical strength and language expression evaluation result in the argument performance analysis content, the argument depth of the reference argument strategy can be adjusted according to the topic focus strength and language expression evaluation result in the argument performance analysis content, and the argument angle of the reference argument strategy can be adjusted according to the argument point innovation strength and language expression evaluation result in the argument performance analysis content.

[0117] For example, in the argument performance analysis content, the score of the argument point logical strength is 85 (the upper limit of the score is 100 and the lower limit is 0), and the score of the language expression evaluation result is 90 (the upper limit of the score is 100 and the lower limit is 0). Therefore, the argument difficulty of the reference argument strategy can be increased.

[0118] For another example, in the argument performance analysis content, the topic focus strength is 30 (the upper limit of the score is 100 and the lower limit is 0), and the score of the language expression evaluation result is 60 (the upper limit of the score is 100 and the lower limit is 0). Therefore, the argument depth of the reference argument strategy can be reduced.

[0119] For another example, in the argument performance analysis content, the argument point innovation strength is 40 (the upper limit of the score is 100 and the lower limit is 0), and the score of the language expression evaluation result is 80 (the upper limit of the score is 100 and the lower limit is 0). Therefore, the argument angle of the reference argument strategy can be changed.

[0120] Step A23 is performed, which can specifically include: inputting the argument performance analysis content, the target argument strategy, the target argument topic, the argument interaction text, and the argument task description information into the argument interaction large model. The argument task description information is used to instruct the argument interaction large model to generate argument response content for the argument interaction text based on the argument performance analysis content, the target argument strategy, the target argument topic, and the argument interaction text. The argument interaction large model generates the argument response content for the argument interaction text.

[0121] The step A23 can further include: performing, by the debate interactive large model, debate processing on the debate interactive text based on the debate performance analysis content, the target debate strategy and the target debate topic to obtain initial debate response content; and obtaining, by the debate interactive large model, language ability information of the user, and performing sentence adaptation adjustment processing on the initial debate response content based on the language ability information to obtain the debate response content.

[0122] Specifically, the debate performance analysis content, the target debate strategy, the target debate topic, the debate interactive text and debate response task description information are input into the debate interactive large model, and the debate response task description information is used to instruct the debate interactive large model to generate response content for the debate interactive text according to the debate performance analysis content, the target debate strategy, the target debate topic and the debate interactive text; then, the initial debate response content and sentence adaptation task description information are input into the debate interactive large model, and the sentence adaptation task description information is used to instruct the debate interactive large model to determine the language ability information of the user according to the debate performance analysis content, and to generate the debate response content by performing sentence adaptation adjustment on the initial debate response content according to the language ability information.

[0123] It can be understood that the debate interactive large model can determine the language ability information of the user according to the language expression evaluation result in the debate performance analysis content.

[0124] After the step A23 is performed, the step A24 can be further performed: determining, by the debate interactive large model, debate suggestion content for the user based on the debate performance analysis content, and outputting the debate suggestion content.

[0125] Specifically, the debate suggestion content can include at least one of suggestion content for debate logic, suggestion content for debate topic focus, suggestion content for debate topic innovation, and suggestion content for language expression. In this way, by outputting the debate suggestion content, the user can understand the shortcomings in the debate process, which helps the user to improve the debate ability.

[0126] S204, determining whether the debate round of the debate interactive large model is equal to a preset round.

[0127] It can be understood that the debate round of the debate interactive large model can be understood as the number of times of generating the debate response content by the debate interactive large model.

[0128] S205, if the debate round is less than the preset round, obtaining two-round debate interactive data input by the user for the debate response content, and taking the two-round debate interactive data as the debate interactive data.

[0129] It can be understood that when the debate round is less than the preset round, the interaction data collected by the smart wearable device after outputting the debate response content is determined as the second round debate interaction data. The second round debate interaction data can be voice interaction data input by the user after the smart wearable device outputs the debate response content. The second round debate interaction data can also be video interaction data recorded by the user after the smart wearable device outputs the debate response content. Then, the second round debate interaction data is returned to step S203 as the debate interaction data to obtain the debate response content for the second round debate interaction data and output the debate response content of the second round debate interaction data, realizing the second round debate interaction process between the debate interaction large model and the user. After the second round debate interaction process is performed through step S203, steps S204 and S205 are continuously performed. When the debate round is less than the preset round, the second round debate interaction data obtained at this time is the debate interaction data input by the user to start the third round debate interaction process, and then the third round debate interaction process between the debate interaction large model and the user is realized. In this way, steps S203-S205 are circularly performed to realize the multi-round debate interaction between the user and the debate interaction large model.

[0130] S206, if the debate round is equal to the preset round, the target debate topic is determined to be in a completed debate state.

[0131] It can be understood that when the debate round is equal to the preset round, the debate interaction process between the user and the debate interaction large model is stopped, and the target debate topic is determined to be in a completed debate state. It can be understood that when the debate round is less than the preset round, the target debate topic is in an incomplete debate state.

[0132] S207, when the target debate topic is in a completed debate state, argument evaluation content is obtained based on the debate interaction data, debate logic evaluation content is obtained based on the debate interaction data, and language expression evaluation content is obtained based on the debate interaction data.

[0133] It can be understood that the argument evaluation content is obtained by evaluating the rationality of the argument put forward by the user in each round of the debate process of the target debate topic. The debate logic evaluation content is obtained by evaluating the debate logic of the user in each round of the debate process of the target debate topic. The language expression evaluation content is obtained by evaluating the language expression (including vocabulary, grammar, sentence pattern, etc.) in each round of the debate process of the target debate topic.

[0134] Specifically, when the target debate topic is a completion of a debate state, all debate interaction data input by a user for the target debate topic is obtained, a target debate text corresponding to all the debate interaction data is obtained, the target debate text includes debate interaction text corresponding to each debate interaction, a target prompt word is generated according to the target debate text and evaluation task description information, the evaluation task description information is used to indicate that the debate interaction large model evaluates the argument rationality, debate logic and language expression of the target debate text, the target prompt word is input into the debate interaction large model, the debate interaction large model is used to evaluate the argument rationality of the target debate text, and an argument evaluation content is obtained by enumerating and discussing unreasonable arguments, the debate logic of the target debate text is evaluated, and a debate logic evaluation content is obtained by enumerating and discussing logically incorrect arguments, and the language expression of the target debate text is evaluated, and a language expression evaluation content is obtained by enumerating and discussing language expression errors.

[0135] In S208, a debate feedback report is generated based on the argument evaluation content, the debate logic evaluation content and the language expression evaluation content.

[0136] In some embodiments, S208 is performed, specifically including: obtaining a preset report template, filling the argument evaluation content, the debate logic evaluation content and the language expression evaluation content in the preset report template, and generating the debate feedback report.

[0137] In yet some embodiments, S208 is performed, and can include: determining a debate improvement suggestion and knowledge expansion content for the target debate topic based on the argument evaluation content, the debate logic evaluation content and the language expression evaluation content; and generating the debate feedback report based on the argument evaluation content, the debate logic evaluation content, the language expression evaluation content, the debate improvement suggestion and the knowledge expansion content.

[0138] The debate improvement suggestion can include an improvement suggestion for the argument evaluation content, an improvement suggestion for the debate logic evaluation content, and an improvement suggestion for the language expression evaluation content, the improvement suggestion for the argument evaluation content can be an improvement suggestion based on an unreasonable argument, the improvement suggestion for the debate logic evaluation content can be an improvement suggestion based on a logically incorrect argument, and the improvement suggestion for the language expression evaluation content can be an improvement suggestion based on a language expression error.

[0139] The knowledge expansion content can be a reference argument discussed by an excellent debater when carrying out a debate activity for the target debate topic.

[0140] In this way, the argument feedback report is generated by evaluating the content of the argument, evaluating the content of the debate logic, evaluating the content of the language expression, providing the argument improvement suggestion, and expanding the knowledge, so that the user can quickly understand the argument performance and the argument improvement suggestion in the argument process through the argument feedback report, which helps the user to improve the argument level based on the argument feedback report, and the user can also learn the extended knowledge related to the target argument topic without searching the extended knowledge related to the target argument topic by himself / herself, thereby increasing the convenience of the user to learn the extended knowledge related to the argument topic.

[0141] In S209, the argument feedback report is displayed to the user.

[0142] Specifically, the smart wearable device displays the argument feedback report in the form of text on the display screen, that is, displays the text of the argument feedback report on the display screen, can output the argument feedback report in the form of voice, that is, generates voice data of the argument feedback report, plays the voice data of the argument feedback report, or can output the argument feedback report in the form of text and voice at the same time, that is, displays the text of the argument feedback report on the display screen and plays the voice data of the argument feedback report at the same time.

[0143] In the interactive control method provided by the embodiments of the present application, at least one preset debate topic is displayed, a target debate topic selected by a user for the preset debate topic is obtained, a target debate role selected by the user for the target debate topic is obtained, debate interaction data input by the user based on the target debate role is obtained, debate response content is obtained by performing debate processing on the debate interaction data and the target debate topic based on a debate interaction large model, the debate response content is output, it is judged whether the debate round of the debate interaction large model is equal to a preset round, if the debate round is less than the preset round, second-round debate interaction data input by the user for the debate response content is obtained, the second-round debate interaction data is taken as the debate interaction data, and the steps of obtaining the debate response content by performing debate processing on the debate interaction data and the target debate topic based on the debate interaction large model and outputting the debate response content are executed, and if the debate round is equal to the preset round, it is determined that the target debate topic is in a completed debate state; in this way, the function of a multi-round debate process between the user and the large model is realized; then, when the target debate topic is in the completed debate state, argument evaluation content is obtained by performing argument evaluation processing based on the debate interaction data, debate logic evaluation content is obtained by performing debate logic evaluation processing based on the debate interaction data, language expression evaluation content is obtained by performing language expression evaluation processing based on the debate interaction data, a debate feedback report is generated based on the argument evaluation content, the debate logic evaluation content and the language expression evaluation content, the debate feedback report is displayed to the user, and in this way, by generating the debate feedback report, it is helpful for the user to improve the debate level of the user based on the debate feedback report, and the user can also learn the extended knowledge related to the target debate topic without searching for the extended knowledge related to the target debate topic by the user himself / herself, thereby increasing the convenience of the user in learning the extended knowledge related to the debate topic.

[0144] The embodiments of the present application will be described below in conjunction with Figure 3 The interactive control device provided by the embodiments of the present application will be described in detail. It should be noted that Figure 3 The interactive control device shown in the figure is used to execute the method of the embodiments of the present application. Figures 1-2 The method of the embodiments shown in the figure is only used to show the parts related to the embodiments of the present application, and the specific technical details are not disclosed, please refer to the embodiments shown in the figure. Figures 1-2 The embodiments shown in the figure.

[0145] Please refer to Figure 3 which shows the structure schematic diagram of the interactive control device of the embodiments of the present application. The interactive control device 1 can be realized by software, hardware or a combination of the two to become all or part of the device. According to some embodiments, the interactive control device 1 includes a debate topic selection module 11, a debate data selection module 12, a debate interaction processing module 13 and a debate data evaluation module 14, which are specifically used for:

[0146] The debate theme selection module 11 is configured to display at least one preset debate theme, and obtain a target debate theme selected by a user for the preset debate theme.

[0147] The debate data selection module 12 is configured to obtain a target debate role selected by the user for the target debate theme, and obtain debate interaction data input by the user based on the target debate role.

[0148] The debate interaction processing module 13 is configured to perform debate processing based on the debate interaction data and the target debate theme by using a debate interaction large model to obtain debate response content, and output the debate response content.

[0149] The debate data evaluation module 14 is configured to perform debate evaluation processing based on the debate interaction data to obtain a debate feedback report when the target debate theme is in a completed debate state, and display the debate feedback report to the user.

[0150] Optionally, referring to Figure 4 FIG. 13 shows a structural schematic diagram of a debate interaction processing module 13. The debate interaction processing module 13 includes a data conversion unit 131 and a debate response unit 132, and is specifically configured to:

[0151] The data conversion unit 131 is configured to determine debate interaction text based on the debate interaction data.

[0152] The debate response unit 132 is configured to perform debate processing on the debate interaction text based on a preset debate strategy and the target debate theme by using a debate interaction large model to obtain debate response content.

[0153] Optionally, the debate response unit 132 includes:

[0154] The first processing unit is configured to perform debate analysis processing on the user based on the debate interaction text and the target debate theme by using a debate interaction large model to obtain debate performance analysis content corresponding to the user.

[0155] The second processing unit is configured to determine a reference debate strategy from a preset debate strategy based on the target debate theme by using the debate interaction large model, and perform strategy adjustment processing on the reference debate strategy based on the debate performance analysis content to obtain a target debate strategy.

[0156] The third processing unit is configured to perform debate processing on the debate interaction text based on the debate performance analysis content, the target debate strategy, and the target debate theme by using the debate interaction large model to obtain debate response content.

[0157] Optionally, the debate response unit 132 further includes:

[0158] a fourth processing unit configured to determine, by the debate interactive large model, debate suggestion content for the user based on the debate performance analysis content, and output the debate suggestion content.

[0159] Optionally, the third processing unit is specifically configured to:

[0160] perform debate processing on the debate interactive text based on the debate performance analysis content, the target debate strategy, and the target debate topic by the debate interactive large model to obtain initial debate response content;

[0161] obtain language ability information for the user by the debate interactive large model, and perform sentence adaptation adjustment processing on the initial debate response content based on the language ability information to obtain debate response content.

[0162] Optionally, the debate data evaluation module 14 comprises:

[0163] a first evaluation unit configured to perform argument evaluation processing based on the debate interactive data to obtain argument evaluation content, perform debate logic evaluation processing based on the debate interactive data to obtain debate logic evaluation content, and perform language expression evaluation processing based on the debate interactive data to obtain language expression evaluation content;

[0164] a second evaluation unit configured to generate a debate feedback report based on the argument evaluation content, the debate logic evaluation content, and the language expression evaluation content.

[0165] Optionally, the second evaluation unit is specifically configured to:

[0166] determine debate improvement suggestions and knowledge expansion content for the target debate topic based on the argument evaluation content, the debate logic evaluation content, and the language expression evaluation content;

[0167] generate a debate feedback report based on the argument evaluation content, the debate logic evaluation content, the language expression evaluation content, the debate improvement suggestions, and the knowledge expansion content.

[0168] Optionally, the interactive control apparatus 1 is further configured to:

[0169] determine whether the debate round of the debate interactive large model is equal to a preset round;

[0170] if the debate round is less than the preset round, obtain second-round debate interactive data input by the user for the debate response content, take the second-round debate interactive data as the debate interactive data, and perform the steps of performing debate processing based on the debate interactive data and the target debate topic by the debate interactive large model to obtain debate response content, and outputting the debate response content.

[0171] If the debate round is equal to the preset round, it is determined that the target debate topic is in a completed debate state.

[0172] The interaction control apparatus provided by the embodiments of the present application displays at least one preset debate topic, obtains a target debate topic selected by a user for the preset debate topic, obtains a target debate role selected by the user for the target debate topic, obtains debate interaction data input by the user based on the target debate role, obtains debate response content by performing debate processing on the debate interaction data and the target debate topic based on a debate interaction large model, and outputs the debate response content. When the target debate topic is in a completed debate state, the debate evaluation processing is performed based on the debate interaction data to obtain a debate feedback report, and the debate feedback report is displayed to the user. In this way, the debate interaction large model can play a debate role opposite to the user, so that the user can carry out a debate process on the target debate topic with the large model in the smart wearable device, the smart debate function of the smart wearable device is increased, the interaction function of the smart wearable device is enriched, and the user's logical thinking can also be helped to be exercised.

[0173] Please refer to Figure 5 , Figure 5 A structural schematic diagram of an electronic device is provided for the embodiments of the present application. For example, the electronic device in the embodiments of the present application can be specifically a smart wearable device. The electronic device can include one or more of the following components: a processor 110, a memory 120, an input device 130, an output device 140, and a bus 150. The processor 110, the memory 120, the input device 130, and the output device 140 can be connected through the bus 150.

[0174] The processor 110 can include one or more processing cores. The processor 110 connects various parts within the entire electronic device by various interfaces and lines, performs various functions of the electronic device and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 120, and calling data stored in the memory 120. Alternatively, the processor 110 can be implemented in at least one of a hardware form of a digital signal processing (DSP), a field-programmable gate array (FPGA), a programmable logic array (PLA). The processor 110 can integrate a combination of one or several of a central processing unit (CPU), a graphics processing unit (GPU), and a modem, etc. Among them, the CPU mainly processes an operating system, a user interface, and an application program, etc.; the GPU is responsible for rendering and drawing display content; and the modem is used for processing wireless communication. It can be understood that the above-mentioned modem can also not be integrated into the processor 110, but be implemented by a separate communication chip.

[0175] The memory 120 can include a random access memory (RAM) and can also include a read-only memory (ROM). Optionally, the memory 120 includes a non-transitory computer-readable storage medium. The memory 120 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 120 can include a program storage area and a data storage area, wherein the program storage area can store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing each of the following method embodiments, etc., and the operating system can be an Android system, an IOS system developed by Apple Inc., a system developed based on the Android system or other systems.

[0176] In order to enable the operating system to distinguish the specific application scenarios of the third-party application, it is necessary to open up the data communication between the third-party application and the operating system, so that the operating system can obtain the current scenario information of the third-party application at any time, and then perform targeted system resource adaptation based on the current scenario.

[0177] The input device 130 is configured to receive input instructions or data, and the input device 130 includes but is not limited to a keyboard, a mouse, a camera, a microphone, or a touch device. The output device 140 is configured to output instructions or data, and the output device 140 includes but is not limited to a display device and a speaker. In an example, the input device 130 and the output device 140 can be combined, and the input device 130 and the output device 140 are a touch display screen.

[0178] The touch display screen can be designed as a full screen, a curved screen, or a special-shaped screen. The touch display screen can also be designed as a combination of a full screen and a curved screen, a combination of a special-shaped screen and a curved screen, and the present application does not limit this.

[0179] In addition, those skilled in the art can understand that the structure of the electronic device shown in the above-mentioned drawings does not constitute a limitation on the electronic device, and the electronic device can include more or fewer components than the drawings, or combine certain components, or different component arrangements. For example, the electronic device also includes radio frequency circuitry, an input unit, a sensor, audio circuitry, a wireless fidelity (WiFi) module, a power supply, a Bluetooth module, and the like, which are not described here.

[0180] In Figure 5 In the electronic device shown, the processor 110 can be configured to call the program of the interaction control method stored in the memory 120, and specifically perform the following operations:

[0181] At least one preset debate topic is displayed, and a target debate topic selected by a user for the preset debate topic is obtained;

[0182] A target debate role selected by the user for the target debate topic is obtained, and debate interaction data input by the user based on the target debate role is obtained;

[0183] Debate response content is obtained by a debate interaction large model based on the debate interaction data and the target debate topic, and the debate response content is output;

[0184] When the target debate topic is a complete debate state, debate evaluation processing is performed based on the debate interaction data to obtain a debate feedback report, and the debate feedback report is displayed to the user.

[0185] In some embodiments, when the processor 110 performs the step of obtaining debate response content by a debate interaction large model based on the debate interaction data and the target debate topic, the processor 110 specifically performs the following operations:

[0186] Debate interaction text is determined based on the debate interaction data;

[0187] The argument interaction large model performs argument processing on the argument interaction text based on the preset argument strategy and the target argument topic to obtain argument response content.

[0188] In some embodiments, when performing the step of performing argument processing on the argument interaction text based on the target argument strategy and the target argument topic by the argument interaction large model to obtain argument response content, the processor 110 specifically performs the following operations:

[0189] The argument interaction large model performs argument analysis processing on the user based on the argument interaction text and the target argument topic to obtain argument performance analysis content corresponding to the user;

[0190] The argument interaction large model determines a reference argument strategy from the preset argument strategy based on the target argument topic, and performs strategy adjustment processing on the reference argument strategy based on the argument performance analysis content to obtain a target argument strategy.

[0191] The argument interaction large model performs argument processing on the argument interaction text based on the argument performance analysis content, the target argument strategy, and the target argument topic to obtain argument response content.

[0192] In some embodiments, after performing the argument processing on the argument interaction text based on the target argument strategy and the target argument topic by the argument interaction large model to obtain argument response content, the processor 110 further performs the following operations:

[0193] The argument interaction large model determines argument suggestion content for the user based on the argument performance analysis content, and outputs the argument suggestion content.

[0194] In some embodiments, when performing the step of performing argument processing on the argument interaction text based on the argument performance analysis content, the target argument strategy, and the target argument topic by the argument interaction large model to obtain argument response content, the processor 110 specifically performs the following operations:

[0195] The argument interaction large model performs argument processing on the argument interaction text based on the argument performance analysis content, the target argument strategy, and the target argument topic to obtain initial argument response content.

[0196] The argument interaction large model obtains language ability information for the user, and performs sentence adaptation adjustment processing on the initial argument response content based on the language ability information to obtain argument response content.

[0197] In some embodiments, when performing the step of generating the debate feedback report based on the argument evaluation content, the debate logic evaluation content, and the language expression evaluation content, the processor 110 specifically performs the following operations:

[0198] performing argument evaluation processing based on the debate interaction data to obtain argument evaluation content, performing debate logic evaluation processing based on the debate interaction data to obtain debate logic evaluation content, and performing language expression evaluation processing based on the debate interaction data to obtain language expression evaluation content;

[0199] generating a debate feedback report based on the argument evaluation content, the debate logic evaluation content, and the language expression evaluation content.

[0200] In some embodiments, when performing the step of generating the debate feedback report based on the argument evaluation content, the debate logic evaluation content, and the language expression evaluation content, the processor 110 specifically performs the following operations:

[0201] determining debate improvement suggestions and knowledge expansion content for the target debate topic based on the argument evaluation content, the debate logic evaluation content, and the language expression evaluation content;

[0202] generating a debate feedback report based on the argument evaluation content, the debate logic evaluation content, the language expression evaluation content, the debate improvement suggestions, and the knowledge expansion content.

[0203] In some embodiments, when performing the step of obtaining debate response content by performing debate processing on the debate interaction data based on the debate interaction large model, outputting the debate response content, the processor 110 further performs the following operations:

[0204] determining whether the debate round of the debate interaction large model is equal to a preset round;

[0205] if the debate round is less than the preset round, obtaining second-round debate interaction data input by the user for the debate response content, taking the second-round debate interaction data as the debate interaction data, and performing the steps of obtaining debate response content by performing debate processing on the debate interaction data based on the debate interaction large model and the target debate topic, and outputting the debate response content;

[0206] if the debate round is equal to the preset round, determining that the target debate topic is in a completed debate state.

[0207] The embodiments of the present application also provide a computer readable storage medium, which stores at least one instruction for being executed by a processor to implement the interactive control method according to the above various embodiments.

[0208] The embodiments of the present application also provide a computer program product, which stores at least one instruction, and the at least one instruction is loaded and executed by the processor to implement the interaction control method according to the above various embodiments.

[0209] Those skilled in the art should be aware that, in the above one or more examples, the functions described in the embodiments of the present application can be implemented in hardware, software, firmware or any combination thereof. When implemented in software, the functions can be stored in a computer readable medium or transmitted as one or more instructions or codes on a computer readable medium. The computer readable medium includes computer storage medium and communication medium, and the communication medium includes any medium that facilitates the transfer of computer programs from one place to another. The storage medium can be any available medium accessible by a general or special purpose computer.

[0210] The above description is only optional embodiments of the present application, and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. An interactive control method, characterized in that: Applied to a smart wearable device, the method includes: Displaying at least one preset debate topic, and obtaining a target debate topic selected by a user for the preset debate topic; Acquire a target debate role selected by the user for the target debate topic, and acquire debate interaction data input by the user based on the target debate role; Performing debate processing based on the debate interaction data and the target debate topic through a debate interaction macro model to obtain debate response content, and outputting the debate response content; When the target debate topic is in a debate completion state, a debate evaluation process is performed based on the debate interaction data to obtain a debate feedback report, and the debate feedback report is displayed to the user.

2. The method according to claim 1, characterized in that The debate interaction model performs debate processing based on the debate interaction data and the target debate topic to obtain debate response content, including: determining a debate interaction text based on the debate interaction data; The debate interaction model performs debate processing on the debate interaction text based on the preset debate strategy and the target debate topic to obtain the debate response content.

3. The method according to claim 2, characterized in that The debate interaction model performs debate processing on the debate interaction text based on the preset debate strategy and the target debate topic to obtain debate response content, including: Performing debate analysis on the user based on the debate interaction text and the target debate topic through a debate interaction macro model to obtain debate performance analysis content corresponding to the user; Determining a reference debate strategy from preset debate strategies based on the target debate topic through the debate interaction macro model, and performing strategy adjustment processing on the reference debate strategy based on the debate performance analysis content to obtain a target debate strategy; The debate interaction model performs debate processing on the debate interaction text based on the debate performance analysis content, the target debate strategy and the target debate topic to obtain debate response content.

4. The method according to claim 3, characterized in that After the debate interaction text is subjected to debate processing based on the target debate strategy and the target debate topic by the debate interaction macro model to obtain debate response content, the method further includes: Debate suggestion content for the user is determined based on the debate performance analysis content through the debate interaction model, and the debate suggestion content is output.

5. The method according to claim 3, characterized in that The step of performing debate processing on the debate interaction text based on the debate performance analysis content, the target debate strategy, and the target debate topic by the debate interaction macro model to obtain debate response content includes: The debate interaction model performs debate processing on the debate interaction text based on the debate performance analysis content, the target debate strategy and the target debate topic to obtain initial debate response content; The language ability information of the user is obtained through the debate interaction model, and the initial debate response content is sentence-adapted and adjusted based on the language ability information to obtain the debate response content.

6. The method according to claim 1, characterized in that The debate evaluation process based on the debate interaction data to obtain a debate feedback report includes: Performing argument evaluation processing based on the debate interaction data to obtain argument evaluation content, performing debate logic evaluation processing based on the debate interaction data to obtain debate logic evaluation content, and performing language expression evaluation processing based on the debate interaction data to obtain language expression evaluation content; A debate feedback report is generated based on the argument evaluation content, the debate logic evaluation content and the language expression evaluation content.

7. The method according to claim 6, characterized in that The generating of the debate feedback report based on the argument evaluation content, the debate logic evaluation content and the language expression evaluation content includes: Determining debate improvement suggestions and knowledge expansion content for the target debate topic based on the argument evaluation content, the debate logic evaluation content, and the language expression evaluation content; A debate feedback report is generated based on the argument evaluation content, the debate logic evaluation content, the language expression evaluation content, the debate improvement suggestions and the knowledge expansion content.

8. An interactive control device, characterized in that: Applied to smart wearable devices, the device includes: A debate topic selection module is used to display at least one preset debate topic and obtain a target debate topic selected by a user based on the preset debate topic; A debate data selection module, configured to obtain a target debate role selected by the user for the target debate topic, and obtain debate interaction data input by the user based on the target debate role; a debate interaction processing module, configured to perform debate processing based on the debate interaction data and the target debate topic through a debate interaction macro model to obtain debate response content, and output the debate response content; The debate data evaluation module is used to perform debate evaluation processing based on the debate interaction data to obtain a debate feedback report when the target debate topic is in a completed debate state, and to display the debate feedback report to the user.

9. A computer storage medium, characterized in that The computer storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: include: A processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the method according to any one of claims 1 to 7.

Images