Artificial intelligence interaction method and device introducing reward mechanism and computer equipment
By introducing a reward mechanism into the artificial intelligence interactive page, the problem of low trust in large language models is solved, and the enthusiasm of the answerees is stimulated through the reward task, the quality and efficiency of the answers are improved, and the overall efficiency and user experience of the system are improved. .
Patent Information
- Application Number
- CN202411231216.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-04
- Publication Date
- 2024-11-29
- Estimated Expiration
- 2044-09-04
AI Technical Summary
The question-and-answer system based on large language models has the problem of low trust. The model may generate seemingly reasonable but inaccurate or false information when answering questions, making it difficult for users to rely on the system's answers.
Introduce a reward mechanism to provide an answer task release portal in the artificial intelligence interactive page, allowing users to post reward tasks, attract answering subjects with professional knowledge or skills to participate in problem solving, and stimulate their enthusiasm and responsibility through resource rewards to ensure high quality and diverse answers.
It improves the trustworthiness of answers based on large language models, improves the efficiency and user experience of problem solving, promotes the rational allocation of resources, avoids resource waste, and forms a closed-loop feedback system to optimize the resource scheduling process.
Smart Images

Figure CN119046436A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of artificial intelligence technology, and in particular to an artificial intelligence interaction method, device and computer equipment that introduces a bounty mechanism. Background Art
[0002] With the development of multimodal dialogue technology, a multimodal dialogue model has emerged. This model refers to the technology of using multiple sensory inputs (such as voice, text, images, videos, etc.) for human-computer interaction. This technology improves the understanding and response capabilities of the dialogue system by integrating different input modes, enabling it to handle complex scenarios and user needs more naturally. For example, in a multimodal dialogue system, users can describe objects through voice and upload pictures at the same time. The system can comprehensively analyze the voice and image information to make more accurate feedback. This technology is widely used in smart assistants, virtual customer service, education and other fields.
[0003] In traditional technology, introducing web links or real-time online search during the conversation is a technology that enhances the answering ability of the question-answering system, which allows the system to obtain the latest and dynamically changing information to provide more accurate and timely answers. Such a question-answering system can obtain external web content or links through instant online search during the conversation, which not only enriches the system's knowledge base, but also enables it to handle questions that are time-sensitive 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 quotes, weather forecasts, etc. However, although large language models perform well in generating natural language text, they still have the inherent defect of "hallucination", 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 the facts. Therefore, the trustworthiness of the answers of the question-answering system based on the large language model is low. Summary of the invention
[0004] Based on this, it is necessary to provide an artificial intelligence interaction method, device, computer equipment, computer-readable storage medium and computer program product that introduces a bounty mechanism and can improve the credibility of answers based on a large language model in order to address the above technical problems.
[0005] In a first aspect, the present application provides an artificial intelligence interaction method that introduces a bounty mechanism. The method comprises:
[0006] In response to a questioning event of the questioning subject to the artificial intelligence, a response result output by the artificial intelligence in response to the questioning event is displayed on the artificial intelligence interaction page;
[0007] In response to the triggering operation of the response result, an answer task publishing entrance is displayed in the artificial intelligence interaction page; the answer task publishing entrance is used for the question object to publish an answer bounty task for the question event; the answer bounty task is associated with an event processing resource to be transferred to the answer object of the question event;
[0008] Displaying the answer result input by the answer subject for the answer bounty task;
[0009] In response to the question object's satisfactory information inputted for the answer result, a first resource scheduling instruction is outputted; the first resource scheduling instruction is used to send at least a part of the event processing resources to the answer object.
[0010] In a second aspect, the present application also provides an artificial intelligence interaction device that introduces a reward mechanism. The device includes:
[0011] A processing result display module, used to respond to a questioning event of the questioning subject to the artificial intelligence, and display the response result output by the artificial intelligence in response to the questioning event in the artificial intelligence interaction page;
[0012] A task publishing and displaying module is used to display an answer task publishing entrance in the artificial intelligence interaction page in response to a triggering operation on the response result; the answer task publishing entrance is used for the question object to publish an answer bounty task for the question event; the answer bounty task is associated with an event processing resource to be transferred to the answer object of the question event;
[0013] A task result display module, used to display the answer result input by the answer object for the answer reward task;
[0014] The resource scheduling instruction module is used to output a first resource scheduling instruction in response to the satisfaction information input by the question object on 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.
[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 the processor implements the following steps when executing the computer program:
[0016] In response to a questioning event of the questioning subject to the artificial intelligence, a response result output by the artificial intelligence in response to the questioning event is displayed on the artificial intelligence interaction page;
[0017] In response to the triggering operation of the response result, an answer task publishing entrance is displayed in the artificial intelligence interaction page; the answer task publishing entrance is used for the question object to publish an answer bounty task for the question event; the answer bounty task is associated with an event processing resource to be transferred to the answer object of the question event;
[0018] Displaying the answer result input by the answer subject for the answer bounty task;
[0019] In response to the question object's satisfactory information inputted for the answer result, a first resource scheduling instruction is outputted; the first resource scheduling instruction is used to send at least a part of the event processing resources to the answer object.
[0020] In a fourth aspect, the present application further 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 questioning event of the questioning subject to the artificial intelligence, a response result output by the artificial intelligence in response to the questioning event is displayed on the artificial intelligence interaction page;
[0022] In response to the triggering operation of the response result, an answer task publishing entrance is displayed in the artificial intelligence interaction page; the answer task publishing entrance is used for the question object to publish an answer bounty task for the question event; the answer bounty task is associated with an event processing resource to be transferred to the answer object of the question event;
[0023] Displaying the answer result input by the answer subject for the answer bounty task;
[0024] In response to the question object's satisfactory information inputted for the answer result, a first resource scheduling instruction is outputted; the first resource scheduling instruction is used to send at least a part of the event processing resources to the answer object.
[0025] In a fifth aspect, the present application further 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 questioning event of the questioning subject to the artificial intelligence, a response result output by the artificial intelligence in response to the questioning event is displayed on the artificial intelligence interaction page;
[0027] In response to the triggering operation of the response result, an answer task publishing entrance is displayed in the artificial intelligence interaction page; the answer task publishing entrance is used for the question object to publish an answer bounty task for the question event; the answer bounty task is associated with an event processing resource to be transferred to the answer object of the question event;
[0028] Displaying the answer result input by the answer subject for the answer bounty task;
[0029] In response to the question object's satisfactory information inputted for the answer result, a first resource scheduling instruction is outputted; the first resource scheduling instruction is used to send at least a part of the event processing resources to the answer object.
[0030] The above-mentioned artificial intelligence interaction method, device, computer equipment, storage medium and computer program product that introduces a bounty mechanism, by responding to the question event of the question subject to the artificial intelligence, displaying the response result output by the artificial intelligence in response to the question event in the artificial intelligence interaction page; in response to the triggering operation of the response result, displaying the answer task publishing entrance in the artificial intelligence interaction page; the answer task publishing entrance is used for the question subject to publish the answer bounty task for the question event; the answer bounty task is associated with the event processing resources of the answer subject to be transferred to the question event; the answer result input by the answer subject for the answer bounty task is displayed; in response to the satisfactory information input by the question subject 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 answer subject.
[0031] By introducing the answer task publishing portal in the AI interactive page, the questions raised by users are closely combined with the incentive mechanism, so that the questioner can publish reward tasks and attract 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, which further stimulates their enthusiasm and sense of responsibility. This mechanism not only ensures high-quality and diverse answers and improves the efficiency of problem solving, but also promotes the rational allocation of resources and avoids resource waste. In addition, user satisfaction feedback further optimizes the resource scheduling process and forms a closed-loop feedback system, which can significantly improve the trustworthiness of answers based on large language models, while improving the user experience of the AI system and the overall effectiveness of the platform. BRIEF DESCRIPTION OF THE DRAWINGS
[0032] Figure 1 An application environment diagram of an artificial intelligence interaction method that introduces a bounty mechanism in one embodiment;
[0033] Figure 2A flowchart of an artificial intelligence interaction method that introduces a bounty mechanism in one embodiment;
[0034] Figure 3 A flowchart of a method for displaying a task publishing portal in one embodiment;
[0035] Figure 4 A flowchart of a method for displaying answer results of an answering reward task input in one embodiment;
[0036] Figure 5 A flowchart of a method for displaying a pop-up window showing an answer result in one embodiment;
[0037] Figure 6 A structural block diagram of an artificial intelligence interaction device that introduces a reward mechanism in one embodiment;
[0038] Figure 7 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION
[0039] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with 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] The artificial intelligence interaction method introducing a reward mechanism provided in the embodiment of the present application can be applied to Figure 1In the application environment shown. Among them, the first terminal 102, the server 104 and the second terminal 106 communicate 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 it can be placed on the cloud or other network servers. In response to the question event of the question object to the artificial intelligence, the response result output by the artificial intelligence in response to the question event is displayed in the artificial intelligence interaction page; wherein the first terminal 102 responds to the trigger operation of the response result, and displays the answer task release entrance in the artificial intelligence interaction page; the answer task release entrance is used for the question object to publish the answer reward task for the question event; the answer reward task is associated with the event processing resource to be transferred to the answer object of the question event; the answer result input by the answer object for the answer reward task is displayed; in response to the satisfactory information input by the question object for the answer result, the first resource scheduling instruction is output; the first resource scheduling instruction is used to send at least a part of the event processing resource to the answer object. The first terminal 102 and the second terminal 106 may be, but are not limited to, various personal computers, laptops, smart phones, tablet computers, IoT devices, and portable wearable devices. IoT devices may be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. Portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers.
[0041] In one embodiment, Figure 2 As shown, an artificial intelligence interaction method introducing a reward mechanism is provided, and the method is applied to Figure 1 Taking the first terminal in the example as an example, the method includes the following steps:
[0042] Step 202, in response to the questioning event of the questioning subject to the artificial intelligence, the response result output by the artificial intelligence in response to the questioning event is displayed in the artificial intelligence interaction page.
[0043] The question object may be a user or entity that asks questions or initiates questions in the artificial intelligence interactive system.
[0044] Among them, the question event can be the behavior or process of a specific question or query request initiated by the questioning object 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 enter questions or instructions, view the response results generated by the system, and take further actions.
[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 from the questioner. This result is usually displayed to the user on the artificial intelligence interaction page.
[0047] Specifically, after the user registers or / and logs in the question object's artificial intelligence interaction page, the server 104 returns the user's identity authentication auth, and the subsequent header of the first terminal 102 request needs to carry this auth, usually in Authorization. Then the subsequent requests will be intercepted in the gateway layer to verify whether the Authorization is valid. If it is valid, it will be released, and if it is invalid, 401 will be directly returned. The security of subsequent resource interaction is effectively guaranteed through identity authentication.
[0048] After the questioner displays successful login on the artificial intelligence interaction page, the questioner can directly enter the dialogue interaction page for the question asked on the artificial intelligence interaction page. The first terminal 102 will request the question event input by the questioner to the gateway layer. After the gateway layer authenticates successfully, the request flows to the model reasoning module. After reasoning, the model reasoning module returns the corresponding response result to the first terminal 102.
[0049] Among them, the backend of this system (server 104) adopts a microservice architecture, the language used is golang, and the web framework is goFiber. The services are divided into gateway module, user module, model reasoning module, and bounty content module. The gateway module is mainly responsible for API authentication. The functions of the user module include login, registration, logout, deregistration, resource transfer out, and resource transfer in. The model reasoning module is mainly responsible for processing the query according to the existing open source large language model Qwen2 and giving answers. The bounty module is responsible for storing published bounty questions. The front-end page of this system (first terminal 102) mainly includes a login page, an AI dialogue interaction page, a bounty pop-up page, a published bounty 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 of the response result, the answer task publishing entrance is displayed in the artificial intelligence interaction page.
[0051] The triggering operation may be an operation in which the question subject clicks “Publish Reward” in the first terminal 102 .
[0052] Among them, the answer task publishing entrance can be an information input box corresponding to "publish reward", wherein the answer task publishing entrance is used for the questioner to publish the answer reward task for the question event.
[0053] Specifically, if the questioner has doubts about the response result, in response to the trigger operation of the response result, the cursor can be suspended to the question. The first terminal 102 triggers the Hover event, and the words "Publish Reward" pop up for clicking. After the questioner clicks "Publish Reward", the artificial intelligence interaction page pops up to display the answer task publishing entrance, that is, the specific form for publishing the reward, including the question description and the model's answer content (this will be automatically filled in), and the reward resource value is filled in by the questioner. Once the reward resource value exceeds the current remaining value of the questioner's resources on the system, the questioner will be prompted to increase the number of resources on the system. The way to increase the number of resources on the system is to add a third-party resource entry for voluntary addition. After filling in the reward resource value, you can click to publish.
[0054] After the release, the user's reward resource value will be deducted immediately. The deducted reward resource value will be kept by server 104 until an answerer successfully answers the question and the questioner is satisfied. Server 104 will then transfer the reward resource value to the answerer's account. The answerer can access the user management page at any time to call out resources.
[0055] After the questioner successfully publishes the 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 pop-up message to notify the questioner.
[0056] Step 206, displaying the answer result input by the answer subject for the answer bounty task.
[0057] The answering object may be an object that answers the question event of the questioning object, and is located at the second terminal 106 .
[0058] Among them, the answer bounty task can be a task posted by the questioner on the artificial intelligence interaction page, which is designed to encourage the answerer to provide high-quality answers. In the task, the questioner sets rewards in the form of rewards to attract answerers with relevant knowledge or skills to participate in problem solving. The answer bounty task is associated with the event processing resources of the answerer to be transferred to the question event. The event processing resources are the rewards for the answerer to answer the question event.
[0059] The answer result may be the answer information of the answer object to the question event.
[0060] Specifically, after the questioner receives a notification about the answer result input by the answering object for the answering bounty task, the questioner can enter the user management page and click "My Published Bounty" to view the published bounty record, which is displayed in the form of a card on the first terminal 102. The length and width of the card 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 show the content of the question and the number of answering objects that have been revealed. If a certain bounty has several answering objects revealed, the first terminal 102 page will mark N in the red circle ○ in the upper right corner of the card. The questioner clicks on the specific card record, and a pop-up window will be obtained, which displays the answer result input for the answering bounty task, that is, the answer of the answering object, in the form of a "waterfall flow".
[0061] Step 208: In response to the question subject's satisfactory information inputted regarding the answer result, output a first resource scheduling instruction.
[0062] The satisfaction information may be the satisfaction degree of the questioner with respect to the answer information of the answerer.
[0063] The resource scheduling instruction may be an instruction in the artificial intelligence system, in which the control server 104 schedules 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 a specific answer result is clicked, the entire answer content can be viewed in a new pop-up page, but at the same time, 10% of the reward resource value will be immediately transferred from the temporary reward server 104 to the account of the answerer. Therefore, when clicking to view a certain answer, the first terminal 102 needs to give a prompt button to confirm.
[0065] If the questioning object is not satisfied with the answer content after reading the answer result, the "unsatisfied" button in the lower right corner of the page can be clicked, and the page will be returned 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 answering objects will also be updated to the original 90% in real time. If the questioning object is satisfied with the answer content after reading the answer result, the "satisfied" button in the lower right corner of the viewing page can be clicked, that is, in response to the satisfactory information input by the questioning object 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 answering object of the answer.
[0066] In the above-mentioned artificial intelligence interaction method that introduces a bounty mechanism, in response to a question event of the question subject to the artificial intelligence, a response result output by the artificial intelligence in response to the question event is displayed in the artificial intelligence interaction page; in response to a trigger operation on the response result, an answer task publishing entrance is displayed in the artificial intelligence interaction page; the answer task publishing entrance is used for the question subject to publish an answer bounty task for the question event; the answer bounty task is associated with event processing resources to be transferred to the answer subject of the question event; the answer result input by the answer subject for the answer bounty task is displayed; in response to the satisfactory information input by the question subject 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 answer subject.
[0067] By introducing the answer task publishing portal in the AI interactive page, the questions raised by users are closely combined with the incentive mechanism, so that the questioner can publish reward tasks and attract 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, which further stimulates their enthusiasm and sense of responsibility. This mechanism not only ensures high-quality and diverse answers and improves the efficiency of problem solving, but also promotes the rational allocation of resources and avoids resource waste. In addition, user satisfaction feedback further optimizes the resource scheduling process and forms a closed-loop feedback system, which can significantly improve the trustworthiness of answers based on large language models, while improving the user experience of the AI system and the overall effectiveness of the platform.
[0068] In one embodiment, Figure 3 As shown, in response to the triggering operation of the response result, the answer task publishing entrance is displayed in the artificial intelligence interaction page, including:
[0069] Step 302: In response to the triggering operation on the response result, a page for publishing the answer task for the question event is displayed.
[0070] Among them, the answer task publishing page can be a special page in the artificial intelligence interaction system for publishing bounty 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 interactive behaviors), the interface of the first terminal 102 will capture the operation through the event monitoring 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, the content of which covers a detailed description of the question event, the preliminary answer generated by the server 104, the input box for the reward resource value, and other necessary task parameter setting items. The display process of the page relies on the componentized 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 needs, ultimately enabling the questioner to conveniently publish reward tasks and attract other questioners to provide higher-quality answers.
[0072] Step 304, in response to the triggering operation of the task release button, the answer bounty task is released.
[0073] Specifically, when the questioning object fills in the relevant information in the answering 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 questioning object into a request and send it to the back-end server 104 through the event monitoring mechanism. After receiving the request, the back-end server 104 first verifies the various parameters of the task, including the legitimacy of the reward resource value, the adequacy of the remaining resources in the account of the questioning object, the integrity of the task content, etc. After the verification is passed, the server 104 will store the task information in the database, record the reward resource value, and lock the corresponding resources in the questioning object account as a guarantee of the reward resource value. Then, the server 104 will trigger the task management module of the background, push the newly released task to the public page of the reward task or the task notification column of the relevant questioning object, ensure that other answering objects can see and participate in the answer, and complete the release of the answer reward task. The entire release process realizes the creation, verification, storage and distribution of tasks through the collaborative work of the front and back ends, ensuring that the release of the reward task is efficient, safe and accurate.
[0074] In this embodiment, by introducing a task publishing page for answering questions, and integrating the description information of the questioning event, the response result output by artificial intelligence, the input box for the amount of task reward resources, and the task publishing button, the system greatly simplifies the operation process of users publishing reward tasks. This integrated design enables users to quickly convert questions into reward tasks, clarify the task content and reward mechanism, and thus more effectively attract capable answerers to participate in answering. At the same time, this process ensures the accuracy of task publishing and the rationality of resource allocation, and improves the efficiency of problem solving and user satisfaction.
[0075] In one embodiment, Figure 4 As shown, the answer result entered by the answering object for the answering bounty task is displayed, including:
[0076] Step 402, display the answer result in a pop-up window.
[0077] Among them, the answer result display pop-up window 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 questioner.
[0078] Specifically, after receiving the answer result of the answer object, the server 104 packages it into a response and returns it to the first terminal 102. After receiving the data, the first terminal 102 uses the component rendering technology of the 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, and can also display additional information such as the name of the question object of the answerer, the answer time, etc. The pop-up window may also include the option 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: The answer results input by multiple answer subjects for the answer bounty task are displayed in turn through an answer result display pop-up window.
[0080] Specifically, when the cursor of the questioning object moves to the top of the answer result display pop-up window or clicks on the specific answer result, the first terminal 102 needs to display the answer results submitted by the specified one or more answering objects for the reward task in turn. To achieve this function, the first terminal 102 will request all answer data related to the task from the server 104, and cache these data locally. Then, the first terminal 102 uses a carousel or paging component to display the answer results of each answering object in the pop-up window in a timed switching or manual page turning manner. Each time it is displayed, the first terminal 102 will dynamically update the content area of the pop-up window, display the detailed information of the current answer, and retain the function of the questioning object to operate, such as evaluation, switching to the next answer, or returning to the previous answer, etc. Through this method of displaying in turn, the questioning object can easily view all submitted answer results and select the best answer in comparison.
[0081] In this embodiment, the answer results of multiple answer objects are displayed in turn through the answer result display pop-up window, and the system provides users with a convenient way to centrally browse and compare the quality of different answers. Users can quickly view and compare all answers in the same interface without switching between multiple pages. This design greatly improves the user experience and efficiency. At the same time, the rotating display mode also avoids information overload, helps users to filter out the best answers in a more organized manner, and then make satisfactory choices faster and more accurately, improving the efficiency of task completion and overall user satisfaction.
[0082] In one embodiment, Figure 5 As shown, a pop-up window showing the answer result is displayed, including:
[0083] Step 502: display the answer preview information of the answer result in the answer result display pop-up window.
[0084] The answer preview information may be a portion of information displayed after simplifying or summarizing the complete answer content when displaying the answer result.
[0085] Specifically, when the cursor of the questioner moves to the top of the answer result display pop-up window, 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 brief summary, as well as the name of the questioner, answer time and other brief information of the respondent. After receiving these data, the first terminal 102 will use the component rendering technology of the 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 will be designed so that the questioner can expand and view the complete answer content by clicking on the preview information, 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 viewing efficiency and the questioner experience. The whole process relies on efficient data transmission between the front and back ends and flexible rendering of the first terminal 102 to ensure that the preview information display is accurate, timely and friendly to the questioner.
[0086] Step 504, in response to the triggering operation on the answer preview information, the entire content of the answer result is displayed in the answer result display pop-up window.
[0087] Specifically, when the questioner clicks or triggers an answer preview information in the answer result display pop-up window, the first terminal 102 will monitor the operation and capture the triggering event. At this time, the system will request the complete content of the answer from the server 104 or extract the complete answer data from the local cache based on the answer ID or other identifier associated with the preview information. 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 adjust the size or layout of the pop-up window to accommodate longer text display. During this process, the first terminal 102 will use asynchronous data loading and rendering technology to ensure that the complete content can be loaded seamlessly and avoid interface freezes or delays. In addition, the first terminal 102 may provide an option to return to preview mode, allowing the questioner to switch between complete content and preview information.
[0088] In this embodiment, by first displaying the answer preview information in the answer result display pop-up window and providing a mechanism for triggering an operation to view the full 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 filter out answers of interest, thereby avoiding information overload and unnecessary waste of time. Only when the user needs to further understand an answer, its full 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, helping 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 triggering operation on the answer preview information.
[0090] Specifically, when the questioner clicks or triggers the answer preview information in the answer result display pop-up window to view the entire content, the system front end first captures this trigger operation and immediately sends a request to the back end to indicate the questioner's intention 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 part of the reward resource value in the questioner's account (if viewing the complete content involves fees), and send the deducted part of the event processing resources to the answerer 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 the complete answer will be displayed to the questioner, and the corresponding questioner interface will be updated.
[0091] In this embodiment, by outputting the second resource scheduling instruction immediately after the user triggers the answer preview information, and sending part of the event processing resources to the corresponding answer object, the system realizes timely incentives 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 and ensures that they get immediate partial rewards. This resource scheduling method also helps to maintain the transparency and fairness of the task, enhance the user's trust in the system, and improve the overall task completion quality and efficiency.
[0092] In one embodiment, before the step of outputting a first resource scheduling instruction in response to the questioner expressing satisfaction with the answer result, the method also includes: in response to the questioner expressing dissatisfaction with the entire content, returning to the step of displaying a pop-up window showing the answer result, until it is detected that the questioner expresses satisfaction with the entire content, and outputting a third resource scheduling instruction.
[0093] Specifically, after the questioner has viewed the complete answer content, if the "unsatisfied" message is input to the first terminal 102, the first terminal 102 will capture this operation and trigger the fallback logic, returning the user interface to the step of displaying the answer result pop-up window, allowing the questioner to continue to browse 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 "unsatisfied" feedback. The system continues to wait for the questioner to operate on other answers until the questioner inputs "satisfied" information on a certain answer result. At this time, the first terminal 102 will pass this satisfactory operation to the server 104, and generate and output a third resource scheduling instruction for instructing the server 104 to perform related resource allocation, such as transferring the remaining part of the reward resource value to the account of the answerer, updating the task status to completed, and notifying the questioner of the task end. The whole process ensures the flexible operating space of the questioner in the case of dissatisfaction, and at the same time triggers the final scheduling of resources through the confirmation of satisfactory feedback.
[0094] In this embodiment, by returning to the pop-up window showing the answer result when the user is dissatisfied with the answer content and allowing the user to continue browsing other answers, the system provides multiple opportunities for selection and comparison to ensure that the user can find the most satisfactory answer. This mechanism avoids the frustration of users due to dissatisfaction with a single answer, and enhances the flexibility of the system and user experience. In addition, when the user finally expresses satisfaction with an answer, the system outputs a third resource scheduling instruction to allocate the remaining resources to the respondent to ensure the reasonable distribution of rewards. This closed-loop feedback process not only improves the quality of task completion, but also effectively motivates respondents to provide better answers, promoting the efficient operation of the system as a whole.
[0095] In one embodiment, the answer object registers on the artificial intelligence interaction page of the second terminal 106. After logging in, click the "Reward" LOGO in the upper left corner of the page to enter the reward page. The reward content display method of this page is still in the form of cards, and the scrolling method adopts "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, in which you can see the question, reward resource value, model's reply content, and date. There is a button to reveal the list in the lower right corner. Click on the list, and you will write the answer at the bottom of the pop-up window. After writing, click the "Submit" button to successfully reveal the list. At the same time, a search box can be introduced at the top of this reward page, and users can filter according to the reward amount, or fuzzy search for questions of interest.
[0096] In one embodiment, an artificial intelligence interaction system introducing a bounty mechanism is provided, the system comprising: an event processing initiator, a first event processing terminal, and a second event processing terminal.
[0097] The event processing initiator is used to send the event to be processed to the first event processing terminal when the first event processing terminal passes the login verification;
[0098] A first event processing end is used to process the event to be processed and return a first processing result to the event processing initiating end;
[0099] The event processing initiator is further used to send the event to be processed to the second event processing terminal in response to the result dissatisfaction information corresponding to the first processing result, and send the event processing resources corresponding to the event to be processed to the first event processing terminal;
[0100] The second event processing end is used to process the event to be processed and return the second processing result to the event processing initiating end;
[0101] The first event processing end is further used to send the event processing resource to the second event processing end in response to the result satisfaction information corresponding to the second processing result of the event processing initiator.
[0102] In one embodiment, the first event processing end is also used to determine resource allocation information corresponding to result satisfaction information in response to processing result operation information corresponding to the second processing result from the event processing initiating end; the first event processing end is also used to send 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 also used 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 also used to return to execute the processing of the event to be processed when the remaining processing resources are positive, until the event processing initiator confirms that the processing result operation information is satisfactory; the first event processing end is also used to send the remaining processing resources to the second event processing end.
[0104] In one embodiment, the second event processing end is also used to respond to the selection operation of the event data card corresponding to each event processing initiating end, and display the pending events and the event processing input box corresponding to the event data card; the second event processing end is also used to send the processed data to the corresponding event processing initiating end in response to the confirmation operation of the event processing input box when the event processing input box detects that the processing data has been input.
[0105] In one embodiment, the event processing initiator is also used to generate an event data card based on the event to be processed and the description information corresponding to the event to be processed; the event processing initiator is also used to generate event resource data based on the event to be processed and the event processing resources corresponding to the event to be processed; the event processing initiator is also used 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 displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.
[0107] Based on the same inventive concept, the embodiment of the present application also provides an artificial intelligence interaction device that introduces a bounty mechanism for implementing the artificial intelligence interaction method that introduces a bounty mechanism. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more embodiments of the artificial intelligence interaction device that introduces a bounty mechanism provided below can refer to the limitations of an artificial intelligence interaction method that introduces a bounty mechanism above, and will not be repeated here.
[0108] In one embodiment, Figure 6 As shown, an artificial intelligence interactive device introducing a reward mechanism is provided, including: a processing result display module 602, a task release display module 604, a task result display module 606 and a resource scheduling indication module 608, wherein:
[0109] The processing result display module 602 is used to respond to the questioning event of the questioning object to the artificial intelligence, and display the response result output by the artificial intelligence in response to the questioning event in the artificial intelligence interaction page;
[0110] The task publishing and displaying module 604 is used to display the answer task publishing entrance in the artificial intelligence interaction page in response to the triggering operation of the response result; the answer task publishing entrance is used for the question object to publish the answer reward task for the question event; the answer reward task is associated with the event processing resources to be transferred to the answer object of the question event;
[0111] The task result display module 606 is used to display the answer result input by the answer object for the answer reward task;
[0112] The resource scheduling instruction module 608 is used to output a first resource scheduling instruction in response to the question object's satisfactory information input on 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.
[0113] In one embodiment, the task release display module 604 is also used to respond to the trigger operation of the response result and display the answer task release page for the question event; the answer task release page includes the description information of the question event and the response result output by the artificial intelligence, the task reward resource amount input box and the task release button; the task reward resource amount input box is used to input the resource value of the event processing resources; in response to the trigger operation of the task release button, the answer bounty task is released.
[0114] In one embodiment, the task result display module 606 is also used to display an answer result display pop-up window; the answer results input by multiple answer objects for the answer bounty task are displayed in turn through the answer result display pop-up window.
[0115] In one embodiment, the task result display module 606 is also used to display the answer preview information of the answer result in the answer result display pop-up window; the answer preview information includes part of the answer result content; in response to the triggering operation of the answer preview information, the entire content of the answer result is displayed in the answer result display pop-up window.
[0116] In one embodiment, the resource scheduling instruction module 608 is further used 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 portion 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 also used to respond to the questioner's dissatisfaction information input for all the content, return to the step of displaying the answer result pop-up window, until it is detected that the questioner has input satisfactory information for all the content, and 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 answerer.
[0118] Each module in the above-mentioned artificial intelligence interactive device introducing a bounty mechanism can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.
[0119] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 7 As 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 achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, an artificial intelligence interaction method that introduces a bounty mechanism is implemented. 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 key, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.
[0120] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0121] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.
[0122] In one embodiment, a computer-readable storage medium is provided, storing a computer program, which implements the steps in the above method embodiments when executed by a processor.
[0123] In one embodiment, a computer program product or computer program is provided, the computer program product or computer program includes computer instructions, the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps in the above-mentioned 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 used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.
[0125] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and 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-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.
[0126] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, 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, they should be considered to be within the scope of this specification.
[0127] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the present application. It should be noted that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.
Claims
1. An artificial intelligence interaction method introducing a reward mechanism, characterized in that: The method comprises: In response to a questioning event of the questioning subject to the artificial intelligence, a response result output by the artificial intelligence in response to the questioning event is displayed on the artificial intelligence interaction page; In response to the triggering operation of the response result, an answer task publishing entrance is displayed in the artificial intelligence interaction page; the answer task publishing entrance is used for the question object to publish an answer bounty task for the question event; the answer bounty task is associated with an event processing resource to be transferred to the answer object of the question event; Displaying the answer result input by the answer subject for the answer bounty task; In response to the question object's satisfactory information inputted for the answer result, a first resource scheduling instruction is outputted; 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, characterized in that In response to the triggering operation on the response result, displaying the answer task publishing entrance in the artificial intelligence interaction page includes: In response to the triggering operation of the response result, a page for publishing an answer task for the question event is displayed; the page for publishing an answer task 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 release button; the task reward resource amount input box is used to input the resource value of the event processing resource; In response to a triggering operation on the task publishing button, the answer bounty task is published.
3. The method according to claim 1, characterized in that The display of the answer result input by the answer object for the answer bounty task includes: Display the answer result display pop-up window; display the answer results input by multiple answer objects for the answer bounty task in turn through the answer result display pop-up window.
4. The method according to claim 3, characterized in that The pop-up window showing the answer result includes: Displaying answer preview information of the answer result in the answer result display pop-up window; the answer preview information includes part of the content of the answer result; In response to a triggering operation on the answer preview information, the entire content of the answer result is displayed in the answer result display pop-up window.
5. The method according to claim 4, characterized in that The method further comprises: In response to a triggering operation on the answer preview information, a second resource scheduling instruction is output; the second resource scheduling instruction is used to send a portion 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 outputting the first resource scheduling instruction in response to the satisfaction information input by the question object regarding the answer result, the method further includes: In response to the question object's input of dissatisfaction information regarding the entire content, return to the step of displaying the answer result pop-up window until it is detected that the question object inputs the satisfaction information regarding the entire content, and 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.
7. An artificial intelligence interactive device that introduces a reward mechanism, characterized in that: The device comprises: A processing result display module, used to respond to a question event of the question subject to the artificial intelligence, and display the response result output by the artificial intelligence in response to the question event in the artificial intelligence interaction page; A task publishing and displaying module is used to display an answer task publishing entrance in the artificial intelligence interaction page in response to a triggering operation on the response result; the answer task publishing entrance is used for the question object to publish an answer bounty task for the question event; the answer bounty task is associated with an event processing resource to be transferred to the answer object of the question event; A task result display module, used to display the answer result input by the answer object for the answer reward task; The resource scheduling instruction module is used to output a first resource scheduling instruction in response to the satisfaction information input by the question object on 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, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.
10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.
Citation Information
Patent Citations
Mobile search method and device based on artificial intelligence
CN105786978A
Information search method and device, computer equipment and storage medium
CN116226500A
Automatic reward function design system and method based on large language model
CN118036675A
Multi-task cooperative processing method based on artificial intelligence agent and event chain
CN118331199A
Artificial intelligence engine having multiple independent processes on a cloud based platform configured to scale
US20170213156A1
