Teaching methods, devices, equipment, and media for finance based on digital human agents

Abstract

This application discloses a financial teaching method, apparatus, device, and medium based on a digital human agent. In this method, a digital human begins interacting with the student upon detecting an interactive trigger event. Specifically, the digital human collects teaching context data, including student operation data, market data, and student profile data, and analyzes this data to obtain behavioral analysis data. Based on the behavioral analysis data, market data, and student profile data, the student's intention is determined. A suitable teaching strategy is then determined based on the student's intention, and a corresponding teaching plan is generated. The corresponding teaching plan is executed, allowing the student to output corresponding operation messages based on the teaching plan. The digital human then executes the corresponding trading operations based on these operation messages. By generating a corresponding teaching plan through a suitable teaching strategy, the student gains a deeper understanding of financial knowledge. The student outputs corresponding operation messages based on the teaching plan and continuously interacts with the digital human.

Description

Technical Field

[0001] This application relates to the field of digital human technology, and more particularly to a financial teaching method, apparatus, device, and medium based on digital human agents. Background Technology

[0002] Traditional finance education relies heavily on theoretical lectures, case studies, and simple simulated trading software, lacking interactivity with students and failing to cultivate their practical skills and complex decision-making abilities. Therefore, improving student interactivity in finance education has become a pressing technical challenge for those in the field. Summary of the Invention

[0003] This application provides a financial teaching method, apparatus, device, and medium based on a digital human agent. In this method, the digital human begins interacting with the student upon detecting an interactive trigger event. Specifically, the digital human collects teaching context data, including student operation data, market data, and student profile data, and analyzes this data to obtain behavioral analysis data. Based on the behavioral analysis data, market data, and student profile data, the student's intention is determined. A suitable teaching strategy is then determined based on the student's intention, and a corresponding teaching plan is generated. The corresponding teaching plan is executed, at which point the student can output corresponding operation messages based on the teaching plan. The digital human executes the corresponding trading operations based on these operation messages. By generating a corresponding teaching plan through a teaching strategy suitable for the student, the student gains a deep understanding of financial knowledge. The student outputs corresponding operation messages based on the teaching plan and continuously interacts with the digital human.

[0004] This application provides a financial teaching method based on digital human agents, including: When an interactive trigger event is detected, teaching context data is collected; wherein, the interactive trigger event includes a student submitting a transaction operation; the teaching context data includes student operation data, market data, and student profile data; The student operation data and market data are analyzed to obtain behavioral analysis data; Based on the behavioral analysis data, the market data, and the student profile data, determine the student's intention; Based on the student profile data, teaching strategies are determined; Using the aforementioned teaching strategies and student intentions, generate and execute corresponding teaching plans; Receive operation messages from students based on the teaching plan, and execute the transaction operation corresponding to the operation message.

[0005] In some embodiments, the student operation data includes the order price, and the market data includes the current stock selling price; the step of analyzing the student operation data and the market data to obtain behavioral analysis data includes: The order price is compared with the current stock selling price; if the order price is lower than the current stock selling price, the behavioral analysis data indicates that the transaction cannot be executed immediately.

[0006] In some embodiments, the student profile data includes student learning status, student personality traits, and historical win rate; the step of determining teaching strategies based on the student profile data includes: Determine whether the student has a basic understanding of the subject. If there is no prior knowledge, then the teaching strategy described is determined to be a guided teaching strategy; If there is a foundation, determine whether the student's personality traits are aggressive and whether the historical win rate is lower than the preset win rate; If the student's personality traits are aggressive and the historical win rate is lower than the preset win rate, then the teaching strategy is determined to be a challenging teaching strategy. If the student's personality traits are not aggressive or the historical win rate is not lower than the preset win rate, then the teaching strategy is determined to be a guided teaching strategy.

[0007] In some embodiments, the teaching strategy is a challenge-based teaching strategy; the step of generating and executing a corresponding teaching plan using the teaching strategy and student intentions includes: Using the student intent, a challenging teaching plan is generated and implemented based on a challenging teaching strategy; Based on the challenging teaching plan, an emotional tone is determined, and emotional feedback prompts with the emotional tone are generated and sent; the challenging teaching plan is a market operation that is the opposite of the student's intention.

[0008] In some embodiments, before receiving the operation message output by the student based on the teaching plan, the method further includes: When a student's question is received, a corresponding answer is generated based on the teaching context data.

[0009] In some embodiments, the method further includes updating the student profile data using the student intent.

[0010] In some embodiments, the teaching strategy is a prompting teaching strategy; the step of generating and executing a corresponding teaching plan using the teaching strategy and student intentions includes: generating and sending a reminder notification based on the prompting teaching strategy and student intentions; The teaching strategy is a guided teaching strategy; the step of generating and executing the corresponding teaching plan using the teaching strategy and student intentions includes: generating and sending guided thinking information based on the guided teaching strategy and student intentions.

[0011] This application also provides a financial teaching device based on digital human agents, including: The data acquisition unit is used to collect teaching context data when an interactive trigger event is detected; wherein, the interactive trigger event includes a student submitting a transaction operation; and the teaching context data includes student operation data, market data, and student profile data. The analysis unit is used to analyze the student operation data and market data to obtain behavioral analysis data; The first determining unit is used to determine the student's intention based on the behavioral analysis data, the market data, and the student profile data; The second determining unit is used to determine teaching strategies based on the student profile data; The first execution unit is used to generate and execute the corresponding teaching plan using the teaching strategy and student intentions; The second execution unit is used to receive the operation message output by the student based on the teaching plan and execute the transaction operation corresponding to the operation message.

[0012] This application also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the financial teaching method based on digital human agents as described above.

[0013] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the financial teaching method based on digital human agents.

[0014] The above embodiments provide a financial teaching method, apparatus, device, and medium based on a digital human agent. In this method, when an interaction trigger event is detected, the digital human begins to interact with the student. Specifically, the digital human collects teaching context data including student operation data, market data, and student profile data, and analyzes this data to obtain behavioral analysis data. Based on the behavioral analysis data, market data, and student profile data, the student's intention is determined. A suitable teaching strategy is determined based on the student's intention, and a corresponding teaching plan is generated. The corresponding teaching plan is executed, at which point the student can output corresponding operation messages based on the teaching plan. The digital human executes the corresponding trading operations based on these operation messages. By generating a corresponding teaching plan through a teaching strategy suitable for the student, the student gains a deep understanding of financial knowledge. The student outputs corresponding operation messages based on the teaching plan and continuously interacts with the digital human. Attached Figure Description

[0015] Figure 1 An exemplary flowchart is shown for a digital human agent-based financial education method provided according to some embodiments; Figure 2 An exemplary schematic diagram of a digital human agent-based financial education device is shown, according to some embodiments. Detailed Implementation

[0016] To make the objectives and implementation methods of this application clearer, the exemplary implementation methods of this application will be clearly and completely described below with reference to the accompanying drawings of the exemplary embodiments of this application. Obviously, the exemplary embodiments described are only some embodiments of this application, and not all embodiments.

[0017] It should be noted that the brief descriptions of terms in this application are only for the convenience of understanding the embodiments described below, and are not intended to limit the embodiments of this application. Unless otherwise stated, these terms should be understood in their ordinary and common meaning.

[0018] The terms "first," "second," "third," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar or related objects or entities, and do not necessarily imply a specific order or sequence, unless otherwise specified. It should be understood that such terms are interchangeable where appropriate.

[0019] The terms “comprising” and “having”, and any variations thereof, are intended to cover but not exclude inclusion, for example, a product or device that includes a range of components is not necessarily limited to all of the components that are clearly listed, but may include other components that are not clearly listed or that are inherent to such product or device.

[0020] To address the aforementioned technical problems, this application provides a financial teaching method, apparatus, device, and medium based on a digital human agent. In this method, upon detecting an interaction trigger event, the digital human begins interacting with the student. Specifically, the digital human collects teaching context data, including student operation data, market data, and student profile data, and analyzes this data to obtain behavioral analysis data. Based on the behavioral analysis data, market data, and student profile data, the student's intention is determined. A suitable teaching strategy is then determined based on the student's intention, and a corresponding teaching plan is generated. The corresponding teaching plan is executed, allowing the student to output corresponding operation messages based on the teaching plan. The digital human executes the corresponding transaction operations based on these operation messages. By generating a corresponding teaching plan through a suitable teaching strategy, the student gains a deeper understanding of financial knowledge. The student outputs corresponding operation messages based on the teaching plan and continuously interacts with the digital human.

[0021] This application provides a financial teaching system, which includes a digital human agent module (hereinafter referred to as digital human), a simulated trading environment module, a student learning profile module, and a teaching management backend module; The digital humans include teacher digital humans, market role digital humans, emotion engine digital humans, and market main force digital humans. The main tasks of teacher digital humans are to explain knowledge points, issue tasks, and answer questions. The main tasks of market role digital humans are to simulate fund managers, traders, analysts, etc. The main task of emotion engine digital humans is to determine the emotional tone. The main task of market main force digital humans is to provide the necessary market operations.

[0022] The simulated trading environment module is used for multi-market simulation (stocks, bonds, foreign exchange and derivatives, etc.), real-time data access (access to real market data or synthetic data streams, etc.), and event-driven mechanisms (generating simulated black swan events, policy changes, etc.).

[0023] The student learning profile module includes a student operation data collection module, a competency assessment model, and a personalized recommendation engine. The student operation data collection module records transaction behavior, dialogue interactions, decision-making time, etc. The competency assessment model evaluates student profile data from dimensions such as risk preference, decision-making logic, and emotional control. The personalized recommendation engine dynamically recommends learning content and practice tasks.

[0024] The teaching management backend module is used for course management (supporting teachers to customize course content and simulation scenarios, etc.), reporting and teaching effectiveness analysis (automatically generating student learning reports and teaching effectiveness analysis), and system management (user permissions, data backup, and system monitoring, etc.).

[0025] Figure 1 An exemplary flowchart of a digital human agent-based financial education method is shown, which includes steps S100-S600, according to some embodiments.

[0026] S100. When an interactive trigger event is detected, teaching context data is collected; wherein, the interactive trigger event includes a student submitting a transaction operation; the teaching context data includes student operation data, market data, and student profile data.

[0027] The method in this embodiment is implemented using the system described above. Before executing step S100, students need to register on the system and complete an initial ability assessment using the ability assessment model when using the system for the first time, thereby obtaining student profile data; a personalized learning path and initial task are generated through a personalized recommendation engine.

[0028] In one example, a student could submit a transaction in a simulated trading interface by entering "Buy 100 shares, limit price 10.5 yuan" for a specific stock (such as "xx Technology") and then clicking the "Submit" button.

[0029] In some embodiments, the interactive trigger event includes a student submitting a trading operation. The corresponding student operation data in the collected teaching context data may include the operation type (e.g., buy), stock code (e.g., 000XXX), order price (e.g., 10.5 yuan), order quantity (e.g., 100 shares), and order time (e.g., timestamp). Market data includes the current market conditions (e.g., real-time stock price of 10.48 yuan, and the rise and fall of the market index). Student profile data includes the student's learning stage (e.g., novice, weak foundation, some foundation), risk preference (e.g., aggressive), historical trading win rate, and common error types (e.g., tendency to chase highs and sell lows).

[0030] In this embodiment, the collection of student operation data in the teaching context can be accomplished by the teacher's digital human through the student operation data collection module. The collection of market data can be accomplished by the teacher's digital human through the simulated trading environment module. The collection of student profile data can be accomplished by the teacher's digital human through the competency assessment model.

[0031] In some embodiments, the teaching context data also includes student account information (e.g., available funds in a student's account and the status of stocks held by the student). The collection of student account information can be accomplished by the teacher's digital avatar through the teaching management backend module.

[0032] In some embodiments, the interactive triggering event also includes generating a simulated market event. Generating a simulated market event could be a black swan event simulating a "central bank suddenly announcing an interest rate cut." Generating a simulated market event can be accomplished through an event-driven mechanism.

[0033] In some embodiments, the interactive triggering event includes generating a simulated market event. The corresponding collected teaching context data includes event data, which includes event type (e.g., macroeconomic policy), event content (e.g., a 50 basis point interest rate cut), and affected asset classes (e.g., bonds, stocks, and exchange rates). The teaching context data also includes student behavior snapshots, which include the student's portfolio structure (e.g., stock-bond ratio), whether there are any unexecuted orders, and the consultation page currently being viewed when the simulated market event occurs.

[0034] In this embodiment of the application, when the digital human recognizes an interaction trigger event, the student enters the simulated trading environment and begins to interact with the digital human.

[0035] S200. Analyze the student operation data and market data to obtain behavioral analysis data. In this embodiment of the application, steps S200-S600 are all subsequent steps that are carried out in response to the interactive triggering event, including the collection of corresponding teaching context data when a student submits a transaction operation.

[0036] Step S200 can be completed by the teacher's digital human.

[0037] In some embodiments, the student operation data includes the order price, and the market data includes the current stock selling price; the step of analyzing the student operation data and the market data to obtain behavioral analysis data includes: The order price is compared with the current stock selling price; if the order price is lower than the current stock selling price, the behavioral analysis data indicates that the transaction cannot be executed immediately.

[0038] It should be noted that the real-time stock price mentioned above is the price of the last traded transaction. The order price is the price at which the student wants to buy the stock. The current selling price is the lowest price among all current sell orders for the stock. For example, the last traded price was 10.48. The student wants to buy the stock at 10.5. The lowest price among all current sell orders for the stock is 10.51. In this example, the order price of 10.5 is less than the current selling price of 10.51, so the behavioral analysis data indicates that the transaction cannot be executed immediately.

[0039] S300. Based on the behavioral analysis data, the market data, and the student profile data, determine the student's intention.

[0040] Step S300 can be completed by a digital teacher avatar. The digital teacher avatar can be driven by an AI model.

[0041] In one example, behavioral analysis data indicates that the transaction cannot be completed immediately, market data shows that the stock has recently experienced high volatility, and student profile data indicates that the student is aggressive. In this case, it is determined that the student's intention is to try to buy at the bottom and catch a rebound, but the offer price is too conservative.

[0042] S400. Based on the student profile data, determine the teaching strategy.

[0043] Step S400 can be completed by the teacher's digital human.

[0044] In this embodiment, the teaching strategy may include a challenging teaching strategy; it may also include a prompting teaching strategy and a guiding teaching strategy.

[0045] Challenging teaching strategies can create pressure or competitive situations, allowing students to experience the consequences in practice. This can strengthen memory and is suitable for students with a certain foundation who need a "lesson" to remember.

[0046] Hint-based teaching strategies can directly point out problems and give clear suggestions, which can quickly correct obvious mistakes and are suitable for students with no prior knowledge.

[0047] Guided learning strategies can help students discover their own mistakes by asking questions or providing hints. This can cultivate independent thinking and decision-making abilities and is suitable for students with a certain foundation.

[0048] In some embodiments, the student profile data includes student learning status, student personality traits, and historical win rate; the step of determining teaching strategies based on the student profile data includes: Determine whether the student has a basic understanding of the subject. If there is no prior knowledge, then the teaching strategy described is determined to be a guided teaching strategy; If there is a foundation, determine whether the student's personality traits are aggressive and whether the historical win rate is lower than the preset win rate; If the student's personality traits are aggressive and the historical win rate is lower than the preset win rate, then the teaching strategy is determined to be a challenging teaching strategy.

[0049] The students are students with a certain foundation, but they are aggressive and have a low historical win rate. This may be because they lack respect for the market and need to learn from certain "lessons" to remember the learning content. Therefore, the teaching strategy is determined to be a challenge-based teaching strategy.

[0050] If the student's personality traits are not aggressive or the historical win rate is not lower than the preset win rate, then the teaching strategy is determined to be a guided teaching strategy.

[0051] In this embodiment, student learning status includes those with and without prior knowledge. This can be analyzed using an ability assessment model. For example, a student could answer test questions; if the score exceeds a preset threshold, the student is considered to have a foundation; otherwise, they are considered to have no foundation. This embodiment does not limit the specific method used to determine student learning status. Student personality traits can be aggressive or conservative, etc. Historical win rate can be understood as the probability of a historical immediate trade. The preset win rate can be set according to actual circumstances and is not restricted here.

[0052] S500. Using the teaching strategy and student intentions, generate and execute the corresponding teaching plan.

[0053] In this embodiment of the application, when the teaching strategy is a prompting-based or guided teaching strategy, the generation and execution of the corresponding teaching plan is completed by the teacher digital human. The teacher digital human can be driven by an AI model.

[0054] For example, a student intends to buy at the bottom and profit from a rebound, but their offer is too conservative. If the teaching strategy is a prompting strategy, the teaching plan would be to remind the student to pay attention to the current price difference in the order book; if the teaching strategy is a guiding strategy, the teaching plan would be to guide the student to think about the applicable scenarios for limit orders and market orders.

[0055] In some embodiments, the teaching strategy is a challenge-based teaching strategy; the step of generating and executing a corresponding teaching plan using the teaching strategy and student intentions includes: Using the student intent, a challenging teaching plan is generated and implemented based on a challenging teaching strategy; For example, a student intends to buy at the bottom and profit from a rebound, but their offer is too conservative. Based on a challenging teaching strategy, the generated challenging teaching solution is to place a large buy order, quickly driving the stock price up from 10.51 yuan to 10.6 yuan.

[0056] When the teaching strategy is an adaptive teaching strategy, the generation and execution of the corresponding teaching plan are completed by the market's leading digital android. The market's leading digital android can be driven by an AI model.

[0057] Based on the aforementioned challenging teaching scheme, an emotional tone is determined, and emotional feedback prompts with the aforementioned emotional tone are generated and sent.

[0058] The challenging teaching plan involves market operations that contradict the students' intentions. This can be understood as, in order to enable students to learn the knowledge points more deeply, causing their operations to fail and allowing them to have a clearer understanding of their own mistakes.

[0059] Following the previous example, a challenging teaching approach involves placing a large buy order, rapidly driving the stock price from 10.51 yuan to 10.6 yuan. The student's order price is 10.5 yuan. At this point, the student will inevitably miss out on the stock, contradicting their attempt to buy at the bottom and profit from a rebound, but their price is too conservative. In this scenario, the emotional tone could be one of slight regret and instruction. The emotional tone can be determined using an emotion engine. This emotion engine can be driven by an AI model, which should be pre-trained using historical challenging teaching approaches and their corresponding emotional tones.

[0060] The emotion engine generates emotional feedback prompts with the aforementioned emotional tone. For example, the emotional feedback prompt could be: "Oh dear, it seems some 'big money' acted faster than you, driving up the stock price first. Your limit order at 10.5 yuan now looks a bit conservative. When the market is expected to move quickly, could you consider using a market order to ensure execution? Of course, this also needs to weigh the slippage risk. Should you cancel this order and chase the rise?"

[0061] S600: Receive the operation message output by the student based on the teaching plan, and execute the transaction operation corresponding to the operation message.

[0062] In this embodiment of the application, the operation message can be to cancel the order, modify the order to a market buy, or remain unchanged.

[0063] In some embodiments, before receiving the operation message output by the student based on the teaching plan, the method further includes: When a student's question is received, a corresponding response is generated based on the teaching context data. This response can be generated by a digital teacher avatar, which can be driven by an AI model.

[0064] For example, the question could be "Will I get trapped if I buy at a high price now?", and the corresponding answer generated based on the teaching context data could be "No, I won't get trapped."

[0065] In some embodiments, the method further includes updating the student profile data using the student's intent. This step can be accomplished using a competency assessment model. The competency assessment model is driven by an AI model.

[0066] In this embodiment of the application, the student's intention is generated based on the behavioral analysis data obtained from the student's operation data, etc., and then the student's intention is determined by using the behavioral analysis data, etc., so it can reflect the student's personality characteristics. Therefore, the student's intention is used to update the student profile data, making the student profile data more comprehensive.

[0067] In some embodiments, the system also includes dynamically adjusting task difficulty based on student performance; a digital teacher avatar providing real-time guidance and summative feedback; and automatic generation of learning reports to support student self-reflection.

[0068] In some embodiments, students' comprehensive abilities can be assessed by analyzing their simulated performance, student operation data, and operation messages, and advanced courses or reinforcement content can be recommended.

[0069] In this embodiment, the realism and interactivity of finance teaching can be enhanced, and personalized teaching and dynamic difficulty adjustment can be achieved. The system has low usage cost and low dimensional difficulty. In addition, it can enhance students' understanding of market sentiment and risk management. In this embodiment, by constructing an integrated teaching system of "a multi-role simulation environment driven by digital human agents (including digital teachers, digital market role agents, etc.) + real-time emotional feedback (such as the emotional tone mentioned above) + personalized learning paths (different students can use different teaching strategies)", a high degree of immersion and intelligent adaptation of finance simulation teaching can be achieved, and financial knowledge can be learned through interactive methods.

[0070] The above embodiments provide a financial teaching method, apparatus, device, and medium based on a digital human agent. In this method, when an interaction trigger event is detected, the digital human begins to interact with the student. Specifically, the digital human collects teaching context data including student operation data, market data, and student profile data, and analyzes this data to obtain behavioral analysis data. Based on the behavioral analysis data, market data, and student profile data, the student's intention is determined. A suitable teaching strategy is determined based on the student's intention, and a corresponding teaching plan is generated. The corresponding teaching plan is executed, at which point the student can output corresponding operation messages based on the teaching plan. The digital human executes the corresponding trading operations based on these operation messages. By generating a corresponding teaching plan through a teaching strategy suitable for the student, the student gains a deep understanding of financial knowledge. The student outputs corresponding operation messages based on the teaching plan and continuously interacts with the digital human.

[0071] Figure 2 An exemplary schematic diagram of a financial education device based on a digital human agent, according to some embodiments, is shown. The device includes: The data acquisition unit 201 is used to acquire teaching context data when an interactive trigger event is detected; wherein, the interactive trigger event includes a student submitting a transaction operation; and the teaching context data includes student operation data, market data, and student profile data. Analysis unit 202 is used to analyze the student operation data and market data to obtain behavioral analysis data; The first determining unit 203 is used to determine the student's intention based on the behavior analysis data, the market data, and the student profile data; The second determining unit 204 is used to determine teaching strategies based on the student profile data; The first execution unit 205 is used to generate and execute the corresponding teaching plan using the teaching strategy and student intentions; The second execution unit 206 is used to receive the operation message output by the student based on the teaching plan and execute the transaction operation corresponding to the operation message.

[0072] This application also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the financial teaching method based on digital human agents as described above.

[0073] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the financial teaching method based on digital human agents.

[0074] Through the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platform, or it can be implemented by hardware.

[0075] It should be noted that any AI models, software tools, or components not belonging to this company appearing in the embodiments of this application are merely illustrative examples and do not represent actual use. All user personal information involved in the embodiments of this application has been authorized (with the knowledge and consent) by the relevant parties or has been fully authorized by all parties, and the executing entity may obtain it through various legal and compliant means. The collection, storage, use, processing, transmission, provision, and disclosure of the information, data, and signals involved all comply with relevant laws and regulations and do not violate public order and good morals.

[0076] Those skilled in the art will understand that the accompanying drawings are merely schematic diagrams of a preferred embodiment, and the units or processes shown in the drawings are not necessarily essential for implementing this application. Those skilled in the art will understand that the units in the apparatus of the embodiment can be distributed within the apparatus of the embodiment as described, or can be located in one or more apparatuses different from this embodiment, with corresponding changes. The units of the above-described embodiment can be combined into one unit, or further divided into multiple sub-units.

[0077] The serial numbers in this application are for descriptive purposes only and do not represent the superiority or inferiority of any particular implementation scenario. The above disclosures are merely a few specific implementation scenarios of this application; however, this application is not limited thereto, and any variations conceived by those skilled in the art should fall within the protection scope of this application.

Claims

1. A financial teaching method based on digital human agents, characterized in that, include: When an interactive trigger event is detected, teaching context data is collected; wherein, the interactive trigger event includes a student submitting a transaction operation; the teaching context data includes student operation data, market data, and student profile data; The student operation data and market data are analyzed to obtain behavioral analysis data; Based on the behavioral analysis data, the market data, and the student profile data, determine the student's intention; Based on the student profile data, teaching strategies are determined; Using the aforementioned teaching strategies and student intentions, generate and execute corresponding teaching plans; Receive operation messages from students based on the teaching plan, and execute the transaction operation corresponding to the operation message.

2. The method according to claim 1, characterized in that, The student operation data includes the order price, and the market data includes the current stock selling price; The steps for analyzing the student operation data and market data to obtain behavioral analysis data include: Compare the order price with the current stock selling price; If the order price is lower than the current stock selling price, the behavioral analysis data indicates that the transaction cannot be executed immediately.

3. The method according to claim 1, characterized in that, The student profile data includes student learning status, student personality traits, and historical win rate; the steps for determining teaching strategies based on the student profile data include: Determine whether the student has a basic understanding of the subject. If there is no prior knowledge, then the teaching strategy described is determined to be a guided teaching strategy; If there is a foundation, determine whether the student's personality traits are aggressive and whether the historical win rate is lower than the preset win rate; If the student's personality traits are aggressive and the historical win rate is lower than the preset win rate, then the teaching strategy is determined to be a challenging teaching strategy. If the student's personality traits are not aggressive or the historical win rate is not lower than the preset win rate, then the teaching strategy is determined to be a guided teaching strategy.

4. The method according to claim 3, characterized in that, The teaching strategy is a challenge-based teaching strategy; the steps of generating and executing a corresponding teaching plan using the teaching strategy and student intentions include: Using the student intent, a challenging teaching plan is generated and implemented based on a challenging teaching strategy; Based on the challenging teaching plan, an emotional tone is determined, and emotional feedback prompts with the emotional tone are generated and sent; the challenging teaching plan is a market operation that is the opposite of the student's intention.

5. The method according to claim 1, characterized in that, Before receiving the operation messages output by the student based on the teaching plan, the process also includes: When a student's question is received, a corresponding answer is generated based on the teaching context data.

6. The method according to claim 1, characterized in that, Also includes: Update the student profile data based on the student's intent.

7. The method according to claim 2, characterized in that, The teaching strategy is a prompting-based teaching strategy; the step of generating and executing the corresponding teaching plan using the teaching strategy and student intentions includes: generating and sending a reminder notification based on the prompting-based teaching strategy and student intentions; The teaching strategy is a guided teaching strategy; the step of generating and executing the corresponding teaching plan using the teaching strategy and student intentions includes: generating and sending guided thinking information based on the guided teaching strategy and student intentions.

8. A financial teaching device based on digital human agents, characterized in that, include: The data acquisition unit is used to collect teaching context data when an interactive trigger event is detected; wherein, the interactive trigger event includes a student submitting a transaction operation; and the teaching context data includes student operation data, market data, and student profile data. The analysis unit is used to analyze the student operation data and market data to obtain behavioral analysis data; The first determining unit is used to determine the student's intention based on the behavioral analysis data, the market data, and the student profile data; The second determining unit is used to determine teaching strategies based on the student profile data; The first execution unit is used to generate and execute the corresponding teaching plan using the teaching strategy and student intentions; The second execution unit is used to receive the operation message output by the student based on the teaching plan and execute the transaction operation corresponding to the operation message.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the financial teaching method based on digital human agents as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the financial teaching method based on digital human agents as described in any one of claims 1 to 7.

Images