Artificial intelligence interaction method, device and computer equipment introducing a reward mechanism

Abstract

The present application relates to an artificial intelligence interaction method, device, and computer device introducing a reward mechanism. The method includes: in response to a question event of an object asking a question to an artificial intelligence, displaying, on an artificial intelligence interaction page, a response result output by the artificial intelligence in response to the question event; in response to a triggering operation on the response result, displaying, on the artificial intelligence interaction page, an answer task publishing entry; the answer task publishing entry is used for the object asking the question to publish an answer reward task for the question event; the answer reward task is associated with event processing resources to be transferred to the answer object for the question event; displaying an answer result input by the answer object for the answer reward task; in response to the object asking the question inputting satisfactory information for the answer result, outputting a first resource scheduling instruction; the first resource scheduling instruction is used to send at least a part of the event processing resources to the answer object. Using this method can improve the trustworthiness of answers based on large language models.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and particularly to an artificial intelligence interaction method, device, and computer device that introduce a reward mechanism. Background Art

[0002] With the development of multimodal dialogue technology, multimodal dialogue models have emerged. This model refers to a technology that uses multiple sensory inputs (such as voice, text, images, videos, etc.) for human-computer interaction. By integrating different input modes, this technology enhances the understanding and response capabilities of the dialogue system, enabling it to more naturally handle complex scenarios and user needs. For example, in a multimodal dialogue system, a user can describe an object through voice while uploading a picture, and the system can comprehensively analyze the voice and image information to provide a more accurate feedback. This technology is widely used in fields such as intelligent assistants, virtual customer service, and education.

[0003] In traditional technology, introducing web links or real-time online searches during a dialogue is a technology to enhance the answering ability of a question-and-answer system. This enables the system to obtain the latest and dynamically changing information to provide more accurate and timely answers. Such a question-and-answer system can, during a dialogue, obtain external web content or links through instant online searches. This not only enriches the system's knowledge base but also enables it to handle questions with strong timeliness or beyond the scope of the original training data. This function is particularly suitable for scenarios that require real-time information, such as news events, stock market quotes, weather forecasts, etc. However, although large language models perform well in generating natural language text, they still have the inherent defect of "hallucinations", that is, the model may generate seemingly reasonable but actually inaccurate or even false information when answering questions. This phenomenon is due to the model's reliance on its training data and generation mechanism rather than a true understanding of facts. Therefore, the trustworthiness of the answers based on large language models in the question-and-answer system is low. Summary of the Invention

[0004] Based on this, to address the above technical problems, it is necessary to provide an artificial intelligence interaction method, device, computer device, computer-readable storage medium, and computer program product that introduce a reward mechanism and can improve the trustworthiness of answers based on large language models.

[0005] In a first aspect, this application provides an artificial intelligence interaction method that introduces a reward mechanism. The method includes:

[0006] In response to a question event of an object asking an artificial intelligence, display, on an artificial intelligence interaction page, a response result output by the artificial intelligence in response to the question event;

[0007] In response to a trigger operation on the response result, a response task publishing entry is displayed on the artificial intelligence interaction page; the response task publishing entry is used for the questioner to publish a response reward task for the question event; the response reward task is associated with event processing resources to be transferred to the responder for the question event.

[0008] Display the response result input by the responder for the response reward task.

[0009] In response to the satisfaction information input by the questioner for the response result, output a first resource scheduling instruction; the first resource scheduling instruction is used to send at least a part of the event processing resources to the responder.

[0010] In a second aspect, the present application further provides an artificial intelligence interaction device introducing a reward mechanism. The device includes:

[0011] A processing result display module, configured to display, in an artificial intelligence interaction page, a response result output by the artificial intelligence in response to a question event of a questioner.

[0012] A task publishing display module, configured to display a response task publishing entry in the artificial intelligence interaction page in response to a trigger operation on the response result; the response task publishing entry is used for the questioner to publish a response reward task for the question event; the response reward task is associated with event processing resources to be transferred to the responder for the question event.

[0013] A task result display module, configured to display the response result input by the responder for the response reward task.

[0014] A resource scheduling indication module, configured to output a first resource scheduling instruction in response to the satisfaction information input by the questioner for the response result; the first resource scheduling instruction is used to send at least a part of the event processing resources to the responder.

[0015] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0016] In response to a question event of a questioner for an artificial intelligence, display, in an artificial intelligence interaction page, a response result output by the artificial intelligence in response to the question event.

[0017] In response to a trigger operation on the response result, a response task publishing entry is displayed on the artificial intelligence interaction page; the response task publishing entry is used for the questioner to publish a response reward task for the question event; the response reward task is associated with event processing resources to be transferred to the responder for the question event.

[0018] The response result input by the responder for the response reward task is displayed.

[0019] In response to the satisfaction information input by the questioner for the response result, a first resource scheduling instruction is output; the first resource scheduling instruction is used to send at least a part of the event processing resources to the responder.

[0020] Fourthly, the present application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0021] In response to a question event of a questioner to artificial intelligence, a response result output by the artificial intelligence in response to the question event is displayed on the artificial intelligence interaction page.

[0022] In response to a trigger operation on the response result, a response task publishing entry is displayed on the artificial intelligence interaction page; the response task publishing entry is used for the questioner to publish a response reward task for the question event; the response reward task is associated with event processing resources to be transferred to the responder for the question event.

[0023] The response result input by the responder for the response reward task is displayed.

[0024] In response to the satisfaction information input by the questioner for the response result, a first resource scheduling instruction is output; the first resource scheduling instruction is used to send at least a part of the event processing resources to the responder.

[0025] Fifthly, the present application also provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0026] In response to a question event of a questioner to artificial intelligence, a response result output by the artificial intelligence in response to the question event is displayed on the artificial intelligence interaction page.

[0027] In response to a trigger operation on the response result, a response task publishing entry is displayed on the artificial intelligence interaction page; the response task publishing entry is used for the question asker to publish a response reward task for the question event; the response reward task is associated with event processing resources to be transferred to the responder for the question event.

[0028] Display the response result input by the responder for the response reward task.

[0029] In response to the satisfaction information input by the question asker for the response result, a first resource scheduling instruction is output; the first resource scheduling instruction is used to send at least a part of the event processing resources to the responder.

[0030] The above artificial intelligence interaction method, device, computer device, storage medium, and computer program product introducing a reward mechanism display, on the artificial intelligence interaction page, the response result output by the artificial intelligence in response to the question event of the question asker; in response to a trigger operation on the response result, a response task publishing entry is displayed on the artificial intelligence interaction page; the response task publishing entry is used for the question asker to publish a response reward task for the question event; the response reward task is associated with event processing resources to be transferred to the responder for the question event; display the response result input by the responder for the response reward task; in response to the satisfaction information input by the question asker for the response result, a first resource scheduling instruction is output; the first resource scheduling instruction is used to send at least a part of the event processing resources to the responder.

[0031] By introducing a response task publishing entry on the artificial intelligence interaction page, closely combining the questions raised by users with an incentive mechanism, the question asker can publish a reward task to attract more responders with professional knowledge or skills to participate in problem-solving. By associating event processing resources, responders can obtain corresponding resource rewards when providing solutions, further stimulating their enthusiasm and sense of responsibility. This mechanism not only ensures high-quality and diverse responses, improves the efficiency of problem-solving, but also promotes the rational allocation of resources and avoids resource waste. In addition, the feedback of user satisfaction further optimizes the resource scheduling process, forming a closed-loop feedback system, which can significantly improve the trustworthiness of responses based on large language models, while enhancing the user experience of the artificial intelligence system and the overall efficiency of the platform. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 It is an application environment diagram of the artificial intelligence interaction method introducing a reward mechanism in an embodiment.

[0033] Figure 2Schematic flowchart of an artificial intelligence interaction method introducing a reward mechanism in an embodiment;

[0034] Figure 3 Schematic flowchart of a method for displaying an answer task release entry in an embodiment;

[0035] Figure 4 Schematic flowchart of a method for displaying an answer result input for a reward answer task in an embodiment;

[0036] Figure 5 Schematic flowchart of a method for displaying a pop-up window for an answer result in an embodiment;

[0037] Figure 6 Block diagram of an artificial intelligence interaction device introducing a reward mechanism in an embodiment;

[0038] Figure 7 Internal structure diagram of a computer device in an embodiment. Detailed implementation manners

[0039] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0040] An artificial intelligence interaction method introducing a reward mechanism provided by an embodiment of the present application can be applied to, for example Figure 1In the application environment shown. Among them, the first terminal 102, the server 104, and the second terminal 106 communicate with each other through the network respectively. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or can be placed on the cloud or other network servers. In response to the question event of the questioner for the artificial intelligence, the response result output by the artificial intelligence in response to the question event is displayed on the artificial intelligence interaction page; among them, the first terminal 102, in response to the trigger operation on the response result, displays an answer task release entry on the artificial intelligence interaction page; the answer task release entry is used for the questioner to release an answer reward task for the question event; the answer reward task is associated with the event processing resources to be transferred to the answerer of the question event; the answer result input by the answerer for the answer reward task is displayed; in response to the satisfaction information input by the questioner for the answer result, a first resource scheduling instruction is output; the first resource scheduling instruction is used to send at least a part of the event processing resources to the answerer. Among them, the first terminal 102 and the second terminal 106 can be, but are not limited to, various personal computers, laptop computers, smart phones, tablet computers, Internet of Things devices, and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. The portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0041] In one embodiment, as Figure 2 shown, an artificial intelligence interaction method introducing a reward mechanism is provided. Taking the first terminal in Figure 1 as an example for illustration, the method includes the following steps:

[0042] Step 202, in response to the question event of the questioner for the artificial intelligence, display the response result output by the artificial intelligence in response to the question event on the artificial intelligence interaction page.

[0043] Among them, the questioner can be a user or entity that asks questions or initiates a query in the artificial intelligence interaction system.

[0044] Among them, the question event can be an act or process of a specific question or query request initiated by the questioner in the artificial intelligence interaction system.

[0045] Among them, the artificial intelligence interaction page can be an interface for users to communicate and interact with the artificial intelligence system. On this page, users can input questions or instructions, view the response results generated by the system, and further operate.

[0046] Among them, the response result can be the answer or solution generated and returned by the artificial intelligence system based on the input question or instruction after receiving the question event of the questioner. This result is usually displayed to the user on the artificial intelligence interaction page.

[0047] Specifically, after the questioner registers or / and logs in on the artificial intelligence interaction page, the server 104 returns the user's authentication auth. This auth needs to be carried in the Header of subsequent requests from the first terminal 102, usually placed in Authorization. Then subsequent requests will be intercepted in the gateway layer to verify whether the Authorization is valid. If it is valid, it will be released; if it is invalid, a 401 will be directly returned. The security of subsequent resource interactions is effectively guaranteed through authentication.

[0048] After the questioner sees the login success display on the artificial intelligence interaction page, the questioner can directly enter the dialogue interaction page for the question on the artificial intelligence interaction page. The first terminal 102 will request the question event input by the questioner to the gateway layer. After successful authentication in the gateway layer, the request flows to the model inference module. After inference, the model inference module returns the corresponding response result to the first terminal 102.

[0049] Among them, the backend of this system (server 104) adopts a microservices architecture. The language used is golang, and the web framework is goFiber. The services are divided into a gateway module, a user module, a model inference module, and a reward content module. The gateway module is mainly responsible for api authentication. The functions of the user module include login, registration, logout, cancellation, resource retrieval, and resource import. The model inference module is mainly responsible for processing the query according to the existing open-source large language model Qwen2 and giving an answer. The reward module is responsible for storing the published reward questions. The front-end (first terminal 102) page of this system mainly includes a login page, an AI dialogue interaction page, a published reward pop-up window page, a published reward page, and a user management page. The language used is vue3, and the component library used is Element-plus.

[0050] Step 204, in response to the triggering operation on the response result, display an answer task publishing entry on the artificial intelligence interaction page.

[0051] Among them, the triggering operation can be the operation of the questioner clicking "Publish Reward" on the first terminal 102.

[0052] Among them, the answer task publishing entry can be the information input box corresponding to "Publish Reward", which is used for the questioner to publish an answer reward task for the question event.

[0053] Specifically, if the questioner doubts the response result, in response to the triggering operation on the response result, the cursor can be suspended over the question. The first terminal 102 triggers a Hover event, and the words "Offer a Reward" pop up for clicking. After the questioner clicks "Offer a Reward", an answer task release entry is displayed in the artificial intelligence interaction page, that is, a specific reward-offering form, which includes the question description and the model's answer content (this will be filled in automatically). The reward resource value is filled in by the questioner. Once the reward resource value exceeds the remaining resource value of the questioner on the system, the questioner will be prompted to increase the resource quantity on the system. The way to increase the resource quantity on the system is to add it voluntarily through the third-party resource addition entry. After filling in the reward resource value, the release can be clicked.

[0054] After the release, the reward resource value of the user will be immediately deducted. The deducted reward resource value will be held by the server 104 until an answerer successfully claims the reward and the questioner is satisfied. Then, the server 104 will transfer the reward resource value to the answerer's account. The answerer can perform a resource withdrawal operation at any time by entering the user management page.

[0055] After the questioner successfully offers a reward, if other answerers claim the reward, the backend will actively notify the first terminal 102 via websocket, and the first terminal 102 will give a message pop-up window to notify the questioner.

[0056] Step 206, display the answer result input by the answerer for the answer reward task.

[0057] Among them, the answerer can be the object that answers the question event of the questioner and is located at the second terminal 106.

[0058] Among them, the answer reward task can be a task published by the questioner in the artificial intelligence interaction page, aiming to encourage the answerer to provide high-quality answers. In the task, the questioner sets rewards in the form of a reward to attract answerers with relevant knowledge or skills to participate in problem-solving. Among them, the answer reward task is associated with the event processing resources to be transferred to the answerer of the question event, and the event processing resources are the rewards for the answerer to answer the question event.

[0059] Among them, the answer result can be the answer information of the answerer for the question event.

[0060] Specifically, after the questioner receives a notice regarding the answer result input by the answerer for the answer reward task, the questioner can enter the user management page, click on "My Published Rewards", and view the published reward records, which are displayed on the first terminal 102 in the form of cards. The length and width of the cards are dynamically adjusted according to the width of the browser, and it is best to ensure that there are 3 to 4 cards in a row. The card will display the content of the question and the number of answerers who have claimed the reward. If there are several answerers who have claimed a certain reward, the first terminal 102 page will mark it as N in the red circle at the upper right corner of the card. When the questioner clicks on this specific card record, a pop-up window will appear, and the answer results input for the answer reward task, that is, the answers of the answerers, will be displayed in the form of a "waterfall flow" in the pop-up window. In the

[0061] Step 208, in response to the satisfaction information input by the questioner for the answer result, output the first resource scheduling instruction.

[0062] Among them, the satisfaction information can be the degree of satisfaction of the questioner with the answer information of the answerer.

[0063] Among them, the resource scheduling instruction can be an instruction in the artificial intelligence system to control the server 104 to transfer the reward resource value to the account corresponding to the second terminal 106 after the questioner is satisfied with the answer information of the answerer.

[0064] Specifically, the questioner can directly preview 20% of the content of each answer result. If the questioner clicks on a specific answer result, the questioner can view all the answer content in a new pop-up window page, but at the same time, immediately 10% of the reward resource value will be transferred from the server 104 that temporarily stores the reward to the account of the answerer. Therefore, when clicking to view a certain claimed answer, the first terminal 102 needs to give a prompt button to confirm whether the questioner is sure.

[0065] If the questioner is not satisfied after viewing the answer content of the answer result, the questioner can click on the "Not Satisfied" button in the lower right corner of the page, and then return to the "My Published" page. The deducted 10% reward resource value will not be returned to the server 104, and the reward resource value of the question event seen by other answerers will also be updated to 90% of the original value in real time. If the questioner is satisfied after viewing the answer content of the answer result, the questioner can click on the "Satisfied" button in the lower right corner of the viewing page. That is, in response to the satisfaction information input by the questioner for the answer result, the first terminal 102 outputs the first resource scheduling instruction to control the server 104 to transfer all the remaining reward resource values to the account of the answerer of this answer.

[0066] In the above artificial intelligence interaction method introducing a reward mechanism, in response to a question event of a questioner to the artificial intelligence, a response result output by the artificial intelligence in response to the question event is displayed on the artificial intelligence interaction page; in response to a trigger operation on the response result, an answer task publishing entry is displayed on the artificial intelligence interaction page; the answer task publishing entry is used for the questioner to publish an answer reward task for the question event; the answer reward task is associated with event processing resources to be transferred to the answerer of the question event; an answer result input by the answerer for the answer reward task is displayed; in response to the satisfaction information input by the questioner for the answer result, a first resource scheduling instruction is output; the first resource scheduling instruction is used to send at least a part of the event processing resources to the answerer.

[0067] By introducing an answer task publishing entry on the artificial intelligence interaction page, the questions raised by users are closely combined with the incentive mechanism, enabling the questioner to publish a reward task and attracting more answerers with professional knowledge or skills to participate in problem-solving. By associating event processing resources, answerers can obtain corresponding resource rewards when providing solutions, further stimulating their enthusiasm and sense of responsibility. This mechanism not only ensures high-quality and diverse answers, improves the efficiency of problem-solving, but also promotes the rational allocation of resources and avoids resource waste. In addition, the feedback of user satisfaction further optimizes the resource scheduling process, forming a closed-loop feedback system, which can significantly improve the trustworthiness of answers based on large language models, while enhancing the user experience of the artificial intelligence system and the overall efficiency of the platform.

[0068] In one embodiment, as Figure 3 shown, in response to a trigger operation on the response result, displaying an answer task publishing entry on the artificial intelligence interaction page includes:

[0069] Step 302, in response to a trigger operation on the response result, display an answer task publishing page for the question event.

[0070] Among them, the answer task publishing page can be a dedicated page in the artificial intelligence interaction system for publishing reward tasks.

[0071] Specifically, when the questioner performs a triggering operation on the response result generated by the artificial intelligence system (such as clicking, hovering, or other interaction behaviors), the interface of the first terminal 102 will capture this operation through the event listening mechanism and send a request to the background to confirm the legality and validity of the questioner's operation. Subsequently, the first terminal 102 will dynamically generate an answer task publishing page, which includes a pre-filled form containing details of the question event, the preliminary answer generated by the server 104, an input box for the reward resource value, and other necessary task parameter setting items. The display process of the page depends on the component-based rendering of the front-end framework (such as Vue or React), combined with the real-time data processing and verification mechanism of the back-end service, to ensure that the page can respond quickly and accurately reflect the current task publishing requirements, ultimately enabling the questioner to conveniently publish a reward task and attracting other questioners to provide higher-quality answers.

[0072] Step 304, in response to the triggering operation on the task publishing button, publish an answer reward task.

[0073] Specifically, when the questioner fills in the relevant information on the answer task publishing page and clicks the task publishing button, the first terminal 102 will capture this triggering operation and package the data input by the questioner into a request through the event listening mechanism and send it to the back-end server 104. After receiving the request, the back-end server 104 first verifies the various parameters of the task, including the legality of the reward resource value, the sufficiency of the remaining resources in the questioner's account, the integrity of the task content, etc. After passing the verification, the server 104 will store the task information in the database, record the reward resource value, and at the same time lock the corresponding resources in the questioner's account as a guarantee for the reward resource value. Then, the server 104 will trigger the task management module in the background to push the newly published task to the public page of the reward tasks or the task notification bar of the relevant questioners, ensuring that other answerers can see and participate in the answer, thus completing the publication of the answer reward task. The entire publication process realizes the creation, verification, storage, and distribution of tasks through the collaborative work of the front and back ends, ensuring the efficient, safe, and accurate publication of the reward tasks.

[0074] In this embodiment, by introducing an answer task publishing page for the question event and integrating the description information of the question event, the response result output by the artificial intelligence, the input box for the task reward resource quantity, and the task publishing button in this page, the system greatly simplifies the operation process of the user to publish a reward task. This integrated design enables the user to quickly convert the question into a reward task, clarify the task content and reward mechanism, thereby more effectively attracting capable answerers to participate in the solution. At the same time, this process ensures the accuracy of task publishing and the rationality of resource allocation, improving the efficiency of problem-solving and user satisfaction.

[0075] In one embodiment, as Figure 4 shown, the answer result input by the answer object for the answer reward task is displayed, including:

[0076] Step 402, display a pop-up window for displaying the answer result.

[0077] Among them, the pop-up window for displaying the answer result can be a dynamic pop-up interface in the artificial intelligence interaction system, which is used to display the specific answer content selected by the question object.

[0078] Specifically, after the server 104 receives the answer result of the answer object, it packages it into a response and returns it to the first terminal 102. After receiving the data, the first terminal 102 uses the component-based rendering technology of a framework (such as Vue or React) to generate a pop-up window for displaying the answer result, and dynamically fills the answer content into the pop-up window. At the same time, additional information such as the name of the question object of the answerer and the answer time can be displayed. The pop-up window may also include options for the question object to evaluate the answer result or perform further operations (such as satisfaction confirmation) to ensure that the question object has a comprehensive interactive experience when viewing the answer.

[0079] Step 404, display the answer results input by multiple answer objects for the answer reward task in turn through the pop-up window for displaying the answer result.

[0080] Specifically, when the cursor of the question object moves above the pop-up window for displaying the answer result or clicks on a specific answer result, the first terminal 102 needs to display in turn one or more specified answer results submitted by the answer objects for the reward task. To implement this function, the first terminal 102 requests all answer data related to this task from the server 104 and caches this data locally. Then, the first terminal 102 uses a carousel or paging component to display the answer results of each answer object in the pop-up window in a timed switching or manual page-turning manner. Each time it is displayed, the first terminal 102 dynamically updates the content area of the pop-up window to display the detailed information of the current answer, while retaining the functions for the question object to perform operations, such as evaluation, switching to the next answer, or returning to the previous answer, etc. Through this way of displaying in turn, the question object can conveniently view all the submitted answer results and select the best answer by comparison.

[0081] In this embodiment, the system provides a convenient way for users to centrally view and compare the quality of different answers by displaying the answer results of multiple answer objects in a pop-up window in turn. Users can quickly view and compare all answers in the same interface without switching between multiple pages, which greatly improves the user experience and efficiency. At the same time, the mode of displaying in turn also avoids information overload, helps users filter out the best answers more orderly, and then makes a satisfactory choice faster and more accurately, improving the task completion efficiency and overall user satisfaction.

[0082] In one embodiment, as Figure 5 shown, a pop-up window for displaying answer results is shown, including:

[0083] Step 502, display the answer preview information of the answer result in the pop-up window for displaying answer results.

[0084] Among them, the answer preview information can be a part of the information displayed after simplifying or summarizing the complete answer content when displaying the answer result.

[0085] Specifically, when the cursor of the questioner moves above the pop-up window for displaying answer results, the first terminal 102 will first obtain the preview information of the corresponding answer result from the server 104. These preview information usually include the first few sentences of the answer or a short summary, as well as brief information such as the name of the questioner of the answer and the answer time. After receiving these data, the first terminal 102 will use the component rendering technology of a framework (such as Vue or React) to fill the preview information into the specified area of the pop-up window to ensure that each answer result is displayed in a compact and clear form. In this process, the interface of the first terminal 102 is designed so that the questioner can click on the preview information to expand and view the complete answer content or quickly browse between multiple answers. Through this preview display method, the questioner can quickly filter and find the answer results of interest, thereby improving the viewing efficiency and the experience of the questioner. The whole process depends on the efficient data transmission between the front and back ends and the flexible rendering of the first terminal 102 to ensure that the preview information is displayed accurately, timely and user-friendly.

[0086] Step 504, in response to the trigger operation on the answer preview information, display all the content of the answer result in the pop-up window for displaying answer results.

[0087] Specifically, when the questioner clicks or triggers an operation on a certain answer preview information in the answer result display pop-up window, the first terminal 102 will monitor this operation and capture the trigger event. At this time, the system will request the complete content of the answer from the server 104 according to the answer ID or other identifiers associated with the preview information, or extract the complete answer data from the local cache. After receiving the complete answer, the first terminal 102 replaces the preview information with the complete answer text by dynamically updating the content area of the pop-up window, and may also adjust the size or layout of the pop-up window to adapt to the display of longer text. During this process, the first terminal 102 will use asynchronous data loading and rendering technologies to ensure that the complete content can be loaded seamlessly, avoiding interface lag or delay. In addition, the first terminal 102 may provide an option to return to the preview mode, allowing the questioner to switch between the complete content and the preview information.

[0088] In this embodiment, by first displaying the answer preview information in the answer result display pop-up window and providing a trigger operation mechanism to view the complete content, the system effectively improves the efficiency of users browsing the answer results. The preview information concisely presents the core content of the answer, helping users quickly screen out the answers they are interested in, thus avoiding information overload and unnecessary time waste. Only when the user has a need to further understand a certain answer, its complete content is displayed, which not only optimizes the page loading speed but also provides a smoother user experience. In addition, this step-by-step display method also improves the user's decision-making efficiency and helps them find the most satisfactory answer more quickly.

[0089] In one embodiment, the method further includes: outputting a second resource scheduling instruction in response to a trigger operation on the answer preview information.

[0090] Specifically, when the questioner clicks or triggers an operation on the answer preview information in the answer result display pop-up window to view all content, the system front-end first captures this trigger operation and immediately sends a request to the back-end, indicating the intention of the questioner to view the complete answer content. After receiving the request, the back-end will generate and output a second resource scheduling instruction, which is used to instruct the server 104 to deduct a part of the reward resource value in the questioner's account (if viewing the complete content involves a fee), and send the deducted part of the event processing resources to the answer object corresponding to the answer preview information. At the same time, the system will execute resource allocation according to the scheduling instruction to ensure that relevant resources (such as content access rights, fund transfers, etc.) are correctly allocated and executed, and display the complete answer to the questioner and update the corresponding questioner interface.

[0091] In this embodiment, by immediately outputting a second resource scheduling instruction after the user triggers the answer preview information and sending a part of the event processing resources to the corresponding answer object, the system realizes the timely incentive and resource allocation for the answerer. This mechanism not only encourages the answerer to provide higher-quality preview content, but also effectively improves the enthusiasm of the answerer, ensuring that they receive immediate partial rewards. This resource scheduling method also helps to maintain the transparency and fairness of the task, enhances the user's trust in the system, and improves the quality and efficiency of the overall task completion.

[0092] In one embodiment, before the step of outputting the first resource scheduling instruction in response to the satisfaction information input by the questioner for the answer result, the method further includes: in response to the dissatisfaction information input by the questioner for all the content, returning to the step of displaying the answer result display pop-up window until it is detected that the questioner inputs satisfaction information for all the content, and outputting the third resource scheduling instruction.

[0093] Specifically, when the questioner views the complete answer content and inputs "dissatisfied" information to the first terminal 102, the first terminal 102 will capture this operation and trigger the fallback logic to return the user interface to the step of displaying the answer result display pop-up window, allowing the questioner to continue browsing other answers or return to the answer preview mode. At this time, the system will not deduct more reward amounts, but will record the user's "dissatisfied" feedback. The system continues to wait for the questioner's operation on other answers until the questioner inputs "satisfied" information for a certain answer result. At this time, the first terminal 102 will transmit this satisfaction operation to the server 104 and generate and output the third resource scheduling instruction to instruct the server 104 to perform relevant resource allocation, such as transferring the remaining part of the reward resource value to the account of the answer object, updating the task status to completed, and notifying the questioner that the task is over. The whole process ensures the flexible operation space for the questioner in the case of dissatisfaction, and at the same time triggers the final scheduling of resources through the confirmation of the satisfaction feedback.

[0094] In this embodiment, by returning to the answer result display pop-up window and allowing the user to continue browsing other answers when the user is dissatisfied with the answer content, the system provides multiple selection and comparison opportunities to ensure that the user can find the most satisfactory answer. This mechanism avoids the frustration of the user due to dissatisfaction with a single answer, enhances the flexibility and user experience of the system. In addition, when the user finally expresses satisfaction with a certain answer, the system outputs the third resource scheduling instruction to allocate the remaining resources to the answerer, ensuring the reasonable distribution of rewards. This closed-loop feedback process not only improves the quality of task completion, but also effectively motivates the answerer to provide better answers, promoting the efficient operation of the overall system.

[0095] In one embodiment, the respondent registers on the artificial intelligence interaction page of the second terminal 106. After logging in, the respondent clicks on the "Reward" LOGO in the upper left corner of the page to enter the reward page. The reward content on this page is still presented in the form of cards, and the scrolling method uses the "waterfall flow". Each card is a reward question, and the card content only displays the question and the reward amount. After clicking on a specific card, a window pops up, where the question, the reward resource value, the reply content of the model, and the date can be seen. There is a button to claim the reward in the lower right corner. Clicking on the button to claim the reward will enable the respondent to write an answer at the bottom of the pop-up window. After finishing writing, clicking on the "Submit" button means successfully claiming the reward. At the same time, a search box can be introduced at the top of this reward page, and users can filter by the reward amount or perform a fuzzy search for questions they are interested in.

[0096] In one embodiment, an artificial intelligence interaction system introducing a reward mechanism is provided. The system includes: an event processing initiating end, a first event processing end, and a second event processing end.

[0097] The event processing initiating end is configured to send a to-be-processed event to the first event processing end when the first event processing end passes the login verification.

[0098] The first event processing end is configured to process the to-be-processed event and return a first processing result to the event processing initiating end.

[0099] The event processing initiating end is further configured to, in response to a result dissatisfaction message corresponding to the first processing result, send the to-be-processed event to the second event processing end, and send the event processing resources corresponding to the to-be-processed event to the first event processing end.

[0100] The second event processing end is configured to process the to-be-processed event and return a second processing result to the event processing initiating end.

[0101] The first event processing end is further configured to, in response to a result satisfaction message corresponding to the second processing result from the event processing initiating end, send the event processing resources to the second event processing end.

[0102] In one embodiment, the first event processing end is further configured to, in response to a processing result operation message corresponding to the second processing result from the event processing initiating end, determine the resource allocation information corresponding to the result satisfaction message; the first event processing end is further configured to send the event processing resources to the second event processing end according to the resource allocation information.

[0103] In one embodiment, when the processing result operation information is unsatisfactory; the first event processing end is further configured to remove the resources corresponding to the resource allocation information from the event processing resources to obtain the remaining processing resources; the second event processing end is further configured to, when the remaining processing resources are positive, return to execute the processing of the event to be processed until the event processing initiation end confirms that the processing result operation information is satisfactory; the first event processing end is further configured to send the remaining processing resources to the second event processing end.

[0104] In one embodiment, the second event processing end is further configured to, in response to the selection operation of the event data card corresponding to each event processing initiation end, display the event to be processed and the event processing input box corresponding to the event data card; the second event processing end is further configured to, when it detects that there is processing data input in the event processing input box, in response to the confirmation operation of the event processing input box, send the processing data to the corresponding event processing initiation end.

[0105] In one embodiment, the event processing initiation end is further configured to generate an event data card according to the event to be processed and the description information corresponding to the event to be processed; the event processing initiation end is further configured to generate event resource data according to the event to be processed and the event processing resources corresponding to the event to be processed; the event processing initiation end is further configured to send the event data card to the second event processing end and send the event resource data to the first event processing end.

[0106] It should be understood that although the steps in the flowcharts involved in the above embodiments are shown in sequence according to the arrows, these steps do not necessarily have to be executed in the order indicated by the arrows. Unless otherwise clearly stated in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least some of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages. These steps or stages do not necessarily have to be executed at the same time, but can be executed at different times. The execution order of these steps or stages does not necessarily have to be sequential, but can be executed alternately or in turn with at least some of the steps or stages in other steps or other steps.

[0107] Based on the same inventive concept, the embodiments of the present application further provide an artificial intelligence interaction device with a reward mechanism introduced for implementing the artificial intelligence interaction method with a reward mechanism introduced as described above. The solution provided by this device for solving problems is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the artificial intelligence interaction device with a reward mechanism introduced below can refer to the limitations for an artificial intelligence interaction method with a reward mechanism introduced in the above text, and will not be repeated here.

[0108] In one embodiment, as Figure 6 shown, an artificial intelligence interaction device introducing a reward mechanism is provided, including: a processing result display module 602, a task publishing display module 604, a task result display module 606, and a resource scheduling indication module 608, where:

[0109] The processing result display module 602 is configured to, in response to a question event of a questioner to the artificial intelligence, display a response result output by the artificial intelligence in response to the question event on an artificial intelligence interaction page;

[0110] The task publishing display module 604 is configured to, in response to a trigger operation on the response result, display an answer task publishing entry on the artificial intelligence interaction page; the answer task publishing entry is used for the questioner to publish an answer reward task for the question event; the answer reward task is associated with event processing resources to be transferred to the answerer of the question event;

[0111] The task result display module 606 is configured to display an answer result input by the answerer for the answer reward task;

[0112] The resource scheduling indication module 608 is configured to, in response to satisfactory information input by the questioner for the answer result, output a first resource scheduling instruction; the first resource scheduling instruction is used to send at least a part of the event processing resources to the answerer.

[0113] In one embodiment, the task publishing display module 604 is further configured to, in response to a trigger operation on the response result, display an answer task publishing page for the question event; the answer task publishing page includes a description information of the question event and a response result output by the artificial intelligence, a task reward resource amount input box, and a task publishing button; the task reward resource amount input box is used to input a resource value of the event processing resources; in response to a trigger operation on the task publishing button, an answer reward task is published.

[0114] In one embodiment, the task result display module 606 is further configured to display an answer result display pop-up window; multiple answer results input by multiple answerers for the answer reward task are alternately displayed through the answer result display pop-up window.

[0115] In one embodiment, the task result display module 606 is further configured to display answer preview information of the answer result in the answer result display pop-up window; the answer preview information includes partial content of the answer result; in response to a trigger operation on the answer preview information, all content of the answer result is displayed in the answer result display pop-up window.

[0116] In one embodiment, the resource scheduling indication module 608 is further configured to output a second resource scheduling instruction in response to a trigger operation on the answer preview information; the second resource scheduling instruction is used to send a part of the event processing resources to the answer object corresponding to the answer preview information.

[0117] In one embodiment, the task result display module 606 is further configured to return the step of displaying the answer result display pop-up window in response to the dissatisfaction information input by the questioner for all the content, until it detects that the questioner inputs satisfactory information for all the content, and then output a third resource scheduling instruction; the third resource scheduling instruction is used to send the remaining part of the event processing resources to the answer object.

[0118] Each module in the above artificial intelligence interaction device introducing a reward mechanism can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor of the computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above modules.

[0119] In one embodiment, a computer device is provided. The computer device can be a terminal, and its internal structure diagram can be as Figure 7 shown. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements an artificial intelligence interaction method introducing a reward mechanism. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a button, a trackball, or a touchpad set on the shell of the computer device, or an external keyboard, a touchpad, or a mouse, etc.

[0120] Those skilled in the art can understand that Figure 7 the structure shown in

[0121] In one embodiment, a computer device is further provided, which includes a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0122] In one embodiment, a computer-readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0123] In one embodiment, a computer program product or a computer program is provided. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device implements the steps in the above method embodiments.

[0124] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data that have been authorized by the user or fully authorized by all parties.

[0125] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memories can include read-only memory (ROM), magnetic tapes, floppy disks, flash memories, optical memories, high-density embedded non-volatile memories, resistive random access memories (ReRAM), magnetoresistive random access memories (MRAM), ferroelectric random access memories (FRAM), phase change memories (PCM), graphene memories, etc. Volatile memories can include random access memory (RAM) or external cache memories, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logics, data processing logics based on quantum computing, etc., without limitation.

[0126] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0127] The above-described embodiments merely represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. An artificial intelligence interaction method introducing a reward mechanism, characterized in that, The method includes: In response to a question event of a questioner to the artificial intelligence, displaying a response result output by the artificial intelligence in response to the question event on an artificial intelligence interaction page; In response to a trigger operation on the response result, displaying an answer task publishing entry on the artificial intelligence interaction page; the answer task publishing entry is used for the questioner to publish an answer reward task for the question event; the answer reward task is associated with event processing resources to be transferred to an answer object of the question event; Displaying an answer result input by the answer object for the answer reward task; In response to satisfactory information input by the questioner for the answer result, outputting a first resource scheduling instruction; the first resource scheduling instruction is used to send at least a part of the event processing resources to the answer object.

2. The method according to claim 1, wherein The step of, in response to a trigger operation on the response result, displaying an answer task publishing entry on the artificial intelligence interaction page includes: In response to a trigger operation on the response result, displaying an answer task publishing page for the question event; the answer task publishing page includes description information of the question event and the response result output by the artificial intelligence, a task reward resource amount input box, and a task publishing button; the task reward resource amount input box is used to input a resource value of the event processing resources; In response to a trigger operation on the task publishing button, publishing the answer reward task.

3. The method according to claim 1, characterized in that, The step of displaying an answer result input by the answer object for the answer reward task includes: Displaying an answer result display pop-up window; displaying answer results input by multiple answer objects for the answer reward task in turn through the answer result display pop-up window.

4. The method according to claim 3, wherein The step of displaying the answer result display pop-up window includes: Displaying answer preview information of the answer result in the answer result display pop-up window; the answer preview information includes partial content of the answer result; In response to a trigger operation on the answer preview information, displaying all content of the answer result in the answer result display pop-up window.

5. The method according to claim 4, wherein The method further includes: In response to a trigger operation on the answer preview information, outputting a second resource scheduling instruction; the second resource scheduling instruction is used to send a part of the event processing resources to the answer object corresponding to the answer preview information.

6. The method according to claim 5, characterized in that, Before the step of, in response to satisfactory information input by the questioner for the answer result, outputting a first resource scheduling instruction, the method further includes: In response to unsatisfactory information input by the questioner for the all content, returning to the step of displaying the answer result display pop-up window until it is detected that the questioner inputs the satisfactory information for the all content, and outputting a third resource scheduling instruction; the third resource scheduling instruction is used to send the remaining part of the event processing resources to the answer object.

7. An artificial intelligence interaction device introducing a reward mechanism, characterized in that, The device includes: A processing result display module, configured to, in response to a question event of a questioner to the artificial intelligence, display a response result output by the artificial intelligence in response to the question event on an artificial intelligence interaction page; A task publishing display module, which is used to display an answer task publishing entry on the artificial intelligence interaction page in response to a triggering operation on the response result; the answer task publishing entry is used for the questioner to publish an answer reward task for the question event; the answer reward task is associated with event processing resources to be transferred to the answer object of the question event. A task result display module, which is used to display the answer result input by the answer object for the answer reward task. A resource scheduling instruction module, which is used to output a first resource scheduling instruction in response to the satisfactory information input by the questioner for the answer result; the first resource scheduling instruction is used to send at least a part of the event processing resources to the answer object.

8. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the method according to any one of claims 1 to 6.

Images