An information display method and device, computer equipment and a storage medium

Abstract

The present disclosure provides an information display method and device, computer equipment and a storage medium, wherein the method comprises: in response to receiving a question information on a dialogue page, displaying generated result content in an answer result matched with the question information according to the generation progress of the answer result; in the process of displaying the generated result content, stopping the generation of the answer result in response to receiving a stop generation instruction; and in response to obtaining an answer result modification instruction, displaying an updated answer result, which is obtained by modifying the answer result according to a target content question under a question dimension indicated by the answer result modification instruction.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and more specifically, to an information display method, apparatus, computer equipment, and storage medium. Background Technology

[0002] With the rapid development of artificial intelligence technology, users can obtain responses from various models by engaging in dialogue within intelligent dialogue application interfaces. In some cases, the responses provided by the models may be of poor quality. In such cases, users often need to reorganize and re-enter the question to try and obtain a response that meets their expectations.

[0003] However, the new answers obtained using this method often suffer from poor quality, resulting in unsatisfactory responses to the same question multiple times. Therefore, improving the reasonableness of secondary responses has become an urgent problem to be solved. Summary of the Invention

[0004] This disclosure provides at least one information display method, apparatus, computer device, and storage medium.

[0005] In a first aspect, embodiments of this disclosure provide an information display method, including:

[0006] In response to receiving a question on the dialogue page, the generated results in the answer results are displayed according to the generation progress of the answer results that match the question.

[0007] During the display of the generated results, in response to receiving a stop generation command, the generation of the answer results is stopped;

[0008] In response to receiving an instruction to modify the answer result, an updated answer result is displayed. The updated answer result is obtained by modifying the answer result according to the target content question under the question dimension indicated by the instruction to modify the answer result.

[0009] In one possible implementation, the instruction to modify the answer result is obtained according to the following steps:

[0010] In response to receiving a stop generation command, content processing identifiers under different problem dimensions are displayed; each content processing identifier under a problem dimension is used to guide and indicate the content problem of the currently displayed generated result content under that problem dimension;

[0011] In response to triggering any of the content processing identifiers, the target content question under the question dimension corresponding to the content processing identifier is obtained, and the answer result modification instruction is generated based on the target content question.

[0012] In one possible implementation, the instruction to modify the answer result is obtained according to the following steps:

[0013] Obtain the input content modification information, and determine the problem dimension and target content problem based on the content modification information;

[0014] Based on the question dimension and the target content question, generate an instruction to modify the answer result.

[0015] In one possible implementation, the problem dimension includes a problem understanding dimension, and the content processing identifier includes a first processing identifier under the problem understanding dimension;

[0016] Retrieve the target content issue under the issue dimension corresponding to the content processing identifier, including:

[0017] The question information is displayed in the dialog box on the dialog page;

[0018] In response to an editing operation on the question information in the dialog box, obtain the edited updated question information;

[0019] The updated question information is used as the target content question under the question understanding dimension.

[0020] In one possible implementation, the question dimension includes a content error dimension for the answer content, and the content processing identifier includes a second processing identifier under the content error dimension;

[0021] Retrieve the target content issue under the issue dimension corresponding to the content processing identifier, including:

[0022] Obtain the first error input prompt information and the input error content information from the dialog box on the dialog page, and determine the target content problem based on the error content information and the content error dimension.

[0023] In one possible implementation, the question dimension includes a content redundancy dimension for the answer content, and the content processing identifier includes a third processing identifier under the content redundancy dimension.

[0024] Retrieve the target content issue under the issue dimension corresponding to the content processing identifier, including:

[0025] Obtain the content redundancy problem under the content redundancy dimension, and use the content redundancy problem as the target content problem under the content redundancy dimension;

[0026] Show updated answer results, including:

[0027] Display the default answer result; the default answer result is pre-generated to address the issue of content redundancy.

[0028] According to the generation progress of the updated answer results, the generated result content in the updated answer results is displayed; the generated result content in the updated answer results is obtained by simplifying the answer results based on the content redundancy issues.

[0029] In one possible implementation, before displaying the updated response result, the method further includes:

[0030] Below the generated results, a preset response message matching the triggered content processing identifier is displayed.

[0031] Secondly, embodiments of this disclosure also provide an information display device, including:

[0032] The first display module is configured to, in response to receiving a question on the dialogue page, display the generated results from the answer results according to the generation progress of the answer results matching the question; and, during the display of the generated results, to stop generating the answer results in response to receiving a stop generation command.

[0033] The second display module is used to respond to the received answer result modification instruction and display the updated answer result. The updated answer result is obtained by modifying the answer result according to the target content question under the question dimension indicated by the answer result modification instruction.

[0034] Thirdly, an optional implementation of this disclosure also provides a computer device, a processor, and a memory, wherein the memory stores machine-readable instructions executable by the processor, and the processor is configured to execute the machine-readable instructions stored in the memory. When the machine-readable instructions are executed by the processor, the steps of the first aspect above, or any possible implementation of the first aspect, are performed.

[0035] Fourthly, an optional implementation of this disclosure also provides a computer-readable storage medium storing a computer program that, when run, performs the steps of the first aspect or any possible implementation of the first aspect.

[0036] For a description of the effects of the aforementioned information display device, computer equipment, and computer-readable storage medium, please refer to the description of the aforementioned information display method; it will not be repeated here.

[0037] The information display method, apparatus, computer equipment, and storage medium provided in this disclosure display the generated results according to the generation progress, enabling real-time display of the answer results. This avoids the problem of excessively long waiting times caused by waiting for all answer results to be generated before displaying them. By responding to a stop generation command during the generation of the generated results, the generation of answer results can be stopped at any time, improving control flexibility. Since the answer result modification command indicates a target content problem under the question dimension, modifying the answer result using the acquired answer result modification command allows for targeted modifications to the target content problem existing in the current generation process, resulting in a more reasonable and expected updated answer result, improving the effectiveness of secondary responses. Furthermore, modifying the answer result using the answer result modification command allows for reasonable modification of the answer result without re-entering the question information, improving both the flexibility of modification and the reasonableness of the answer result obtained from a secondary response.

[0038] To make the above-mentioned objects, features and advantages of this disclosure more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0039] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings used in the embodiments will be briefly described below. These drawings are incorporated in and constitute a part of this specification. They illustrate embodiments conforming to this disclosure and, together with the specification, serve to explain the technical solutions of this disclosure. It should be understood that the following drawings only show some embodiments of this disclosure and should not be considered as limiting the scope. Those skilled in the art can obtain other related drawings based on these drawings without creative effort.

[0040] Figure 1 A flowchart of an information display method provided by an embodiment of this disclosure is shown;

[0041] Figure 2 This illustration shows a schematic diagram of a generated result content provided by an embodiment of the present disclosure;

[0042] Figure 3 This illustration shows a schematic diagram of stopping the generation of answer results according to an embodiment of the present disclosure;

[0043] Figure 4 This illustration shows a page diagram after triggering a first processing identifier, as provided in an embodiment of this disclosure.

[0044] Figure 5This illustration shows a page diagram after triggering a second processing identifier, as provided in an embodiment of this disclosure.

[0045] Figure 6 This illustration shows a page diagram after triggering a third processing identifier, as provided in an embodiment of this disclosure.

[0046] Figure 7 A schematic diagram of an information display device provided in an embodiment of this disclosure is shown;

[0047] Figure 8 A schematic diagram of the structure of a computer device provided in an embodiment of this disclosure is shown. Detailed Implementation

[0048] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of them. The components of the embodiments of this disclosure described and shown herein can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this disclosure is not intended to limit the scope of the claimed disclosure, but merely represents selected embodiments of this disclosure. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without inventive effort are within the scope of protection of this disclosure.

[0049] Furthermore, the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein.

[0050] In this article, "multiple or several" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0051] Research has revealed that with the rapid development of artificial intelligence models, various intelligent dialogue models have emerged. These models can understand user input and provide corresponding responses. However, because user input is complex and variable, the model's responses often do not meet the user's expectations. In such cases, users frequently need to adjust and re-enter their input to obtain a new answer. However, this method still often results in poor response quality, affecting the overall dialogue experience.

[0052] Based on the above research, this disclosure provides an information display method, apparatus, computer device, and storage medium. It displays the generated results according to the generation progress, enabling real-time display of the answer results and avoiding the problem of excessively long waiting times caused by waiting for all answer results to be generated before displaying them. By responding to a stop generation command during the generation of the generated results, the generation of answer results can be stopped at any time, improving control flexibility. Since the answer result modification command indicates the target content question under the question dimension, modifying the answer result using the acquired answer result modification command allows for targeted modifications to the target content question existing in the current generation process, resulting in a more reasonable and expected updated answer result, improving the effectiveness of secondary responses. Furthermore, modifying the answer result using the answer result modification command allows for reasonable modification of the answer result without re-entering the question information, improving both the flexibility of modification and the reasonableness of the answer result obtained from secondary responses.

[0053] The shortcomings of the above solutions are the result of the inventor's practical experience and careful research. Therefore, the discovery process of the above problems and the solutions proposed in this disclosure below should be considered as the inventor's contribution to this disclosure.

[0054] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0055] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0056] To facilitate understanding of this embodiment, a detailed description of the information display method disclosed in this disclosure is provided first. The execution subject of the information display method provided in this disclosure is generally a terminal device or other processing device with certain computing capabilities. The terminal device can be a user equipment (UE), mobile device, user terminal, terminal, personal digital assistant device (PDA), handheld device, computer device, etc. In some possible implementations, the information display method can be implemented by the processor calling computer-readable instructions stored in the memory.

[0057] The following describes the information display method provided in this embodiment of the disclosure, taking the terminal as the executing entity as an example.

[0058] like Figure 1 The flowchart shown is a method for displaying information provided in an embodiment of this disclosure, which may include the following steps:

[0059] S101: In response to receiving a question on the dialogue page, display the generated results in the answer results according to the generation progress of the answer results that match the question.

[0060] Here, the dialogue page corresponds to any intelligent dialogue application, allowing users to converse with artificial intelligence models. Questions can be input by the user based on their desired outcome, aiming to obtain answers that meet their specific needs. For example, questions could include "Generate an article about XX" or "How to solve problem XX." Questions can be in any format, such as text, images, a combination of text and images, video, or tables / documents.

[0061] The answer results that match the question information can be the results output by the artificial intelligence model to answer the question information. The answer results provided by the artificial intelligence model can also be in any format, such as text format, image format, graphic and text format, document format, video format, etc.

[0062] When generating answers, AI models can do so step-by-step, thus showing a generation progress. For example, if the answer is an article, it can be generated word by word; if the answer is a video, it can be generated frame by frame.

[0063] The generated results represent the partial answers produced at the current generation progress stage. When the generation progress reaches 100%, all generated results constitute the complete answer. For example, when the answer is an article, each time the AI ​​model generates a character or word, that character or word can be displayed as a generated result at the current generation progress stage. After generating the last character of the article, the last character can be displayed sequentially after the generated results to obtain the complete article.

[0064] In practice, users can enter questions in the dialog box on the dialogue page. Upon receiving the question, the terminal sends it to the server. The server uses an artificial intelligence model to identify and process the question, and then sends feedback on the generated results to the terminal according to the progress of the response generation. The terminal can then retrieve the generated results from the server and display them sequentially on the dialogue page.

[0065] like Figure 2 The diagram shown illustrates a display of generated results content according to an embodiment of this disclosure. The user inputs the question, "Write an article in the style of XX, with the title 'August Beach Outfit Guide'." The generated results displayed sequentially on the dialog page are "One night, XXXXXXXXX prepared _", where "_" indicates the position of the next generated result content. Below the displayed generated results content, a stop-generation indicator is shown; triggering this indicator stops the generation of the answer result.

[0066] S102: During the process of displaying the generated results, in response to receiving a stop generation command, stop generating the answer results.

[0067] Here, since the content of the generated results displayed is determined by the content of the generated results, the process of displaying the content of the generated results can also be regarded as the process of generating the content of the generated results.

[0068] The stop generation command can be obtained after the user triggers the stop generation indicator on the dialog page, or after the user enters it in the dialog box, or after the user performs a preset operation. The stop generation command is used to indicate that the generation of answer results for the question information will stop, and also to stop displaying new generated result content.

[0069] In practice, if a stop-generation command is received during the display of generated results, the terminal can respond to the command by ceasing the display of new generated results. Simultaneously, the stop-generation command can be sent back to the server, causing the server to stop generating further results. Since the server stops generating results, the terminal also stops displaying any new generated results; therefore, from the user's perspective, the terminal has stopped generating results.

[0070] Simultaneously, after stopping the generation of response results, the terminal can display a stop-generation prompt message at a preset location on the already displayed generated results content. The stop-generation prompt message could be, for example, "Generation has stopped."

[0071] like Figure 3 The diagram shown illustrates a method for stopping the generation of answer results according to an embodiment of this disclosure, wherein, in response to a user click... Figure 2 After the "Stop Generation" flag is displayed, a stop generation command can be received. Then, the system can respond to this command and display... Figure 3 The page shown. In Figure 3 In the middle, after stopping the generation of answer results, a prompt message indicating that generation has stopped can be displayed (i.e., Figure 3 The "Stop generating" flag can be updated to a "Regenerate" flag. Once triggered, the "Regenerate" flag can regenerate an answer that matches the question information. Furthermore, in... Figure 3 The document also displays several content processing identifiers, each used to guide and indicate the content issue of the currently displayed generated results within that specific issue dimension. These identifiers will be discussed in detail later.

[0072] S103: In response to receiving the answer result modification instruction, display the updated answer result. The updated answer result is the result obtained after modifying the answer result according to the target content question under the question dimension indicated by the answer result modification instruction.

[0073] Here, the answer modification instruction is used to indicate the question dimension corresponding to the currently generated result content and the target content question under that question dimension. It also instructs the regeneration of the answer result based on the question information according to the answer modification instruction. The target content question is the current problem existing in the generated result content. For example, the question dimension indicated by the answer modification instruction could be the information comprehension dimension, and the target content question under that dimension could be "The generated answer result needs to conform to XX style and XX theme." The answer modification instruction can be entered directly in the dialog box or obtained after triggering the content processing indicator on the dialog page.

[0074] Updating the answer result means regenerating the answer result based on the question information and the content of the already generated results, according to the answer result modification instruction. This regenerated answer result is still used to answer the question information. Specifically, the answer result modification instruction can modify the content of the already generated results while also affecting the ungenerated answer results. Updating the answer result means obtaining a new answer result after simultaneously affecting both the content of the already generated results and the ungenerated answer results according to the answer result modification instruction.

[0075] In practice, the terminal can respond to a modified answer instruction by sending the instruction to the server. Upon receiving the modified answer instruction, the server can re-input the instruction, the generated result content, and the question information into the AI ​​model to obtain an updated answer result output by the AI ​​model, which is then sent to the terminal. The terminal can then display the updated answer result below the previously displayed generated result content.

[0076] Understandably, updated response results can also be generated step-by-step by an AI model. Therefore, the server can sequentially feed back the generated results from the updated response results to the client according to the AI ​​model's generation progress. Subsequently, the client can sequentially display the generated results from the updated response results on the chat page according to the generation progress, until the AI ​​model generates all the updated response results. At this point, the client can display the complete updated response results on the chat page.

[0077] In one embodiment, the instruction to modify the answer result can be obtained in the following two ways:

[0078] Method 1: Obtain the input content modification information, determine the question dimension and target content question based on the content modification information, and generate the answer modification instruction based on the question dimension and target content question.

[0079] Here, the content modification information can be the modification instructions entered by the user in the dialog box for the generated result content. Problem dimensions can include, but are not limited to, problem comprehension, content error, content redundancy, and other dimensions. Specific problem dimensions can be set based on experience, and this embodiment does not impose specific limitations. The target content problem is the problem existing under the problem dimension.

[0080] In practice, the system can acquire the modification instructions entered by the user in the dialog box, parse the content modification information, and determine the question dimension indicated by the content modification information and the target content question under the question dimension. Understandably, the parsed question dimension can include one or more; if there are multiple question dimensions, the target content question under each question dimension can be parsed. Then, a modification instruction for the answer result, including the question dimension and the target content question, can be generated.

[0081] Optionally, the format for the modified information can be displayed during the user's input process. For example, the format could be "Question Dimension + Content Question". This allows users to input their modified information according to the format. Afterward, the terminal, upon receiving the modified information, can directly generate an answer instruction that includes the modified information.

[0082] Method 2, Step 1: Upon receiving the stop generation command, display the content processing identifiers under different issue dimensions; the content processing identifiers under each issue dimension are used to guide and indicate the content issues of the currently displayed generated results under that issue dimension.

[0083] Step 2: In response to triggering any content processing identifier, obtain the target content question under the question dimension corresponding to the content processing identifier, and generate an answer modification instruction based on the target content question.

[0084] Here, the specific question dimensions and their number can be set based on experience, and this embodiment does not impose specific limitations. For example, question dimensions may include question comprehension dimensions, content error dimensions, content redundancy dimensions, and other dimensions, where "other dimensions" refers to dimensions other than the three dimensions of question comprehension, content error, and content redundancy. Each question dimension corresponds to a content processing identifier. The content processing identifier under each question dimension is used to guide the user to point out content problems in the currently displayed generated results within that question dimension. For example, the content processing identifier under the question comprehension dimension is used to guide the user to point out problems reflected in the generated results when understanding the question information. The operation that triggers the content processing identifier can specifically be clicking the content processing identifier.

[0085] In practical implementation, the terminal can respond to a stop generation command, ceasing the generation and display of answer results while simultaneously displaying content processing identifiers corresponding to multiple question dimensions. For example, in Figure 3 The document displays the content processing identifiers corresponding to the problematic understanding dimension (i.e., the first processing identifier), the content processing identifiers corresponding to the content error dimension (i.e., the second processing identifier), the content processing identifiers corresponding to the content redundancy dimension (i.e., the third processing identifier), and the content processing identifiers corresponding to other dimensions (i.e., the fourth processing identifier).

[0086] Subsequently, in response to a user's trigger action on any content processing identifier, the system can retrieve the target content question under the corresponding question dimension and generate an answer modification instruction based on the target content question. For example, a default target content question can be pre-set for each content processing identifier. Upon triggering a content processing identifier, the system can retrieve this default target content question and generate an answer modification instruction that includes both the target content question and the question dimension corresponding to the content processing identifier. Alternatively, for each content processing identifier, an answer modification instruction corresponding to that identifier can be pre-set. Upon triggering that identifier, the system can directly retrieve the answer modification instruction set for that content processing identifier.

[0087] In one embodiment, when the question dimension includes a question understanding dimension, the content processing identifier may include a first processing identifier under the question understanding dimension. For example, the first processing identifier may be a "question not understood" identifier. The first processing identifier is used to guide and indicate the content problems that exist in the currently displayed generated result content when understanding the question information. In this case, the step of "obtaining the target content problem under the question dimension corresponding to the content processing identifier" in step two above can be implemented according to the following steps:

[0088] S1: Display the question information in the dialog box on the dialog page.

[0089] In practice, in response to the triggering of the first processing flag, the user's input question information can be displayed in the dialog box of the dialog page.

[0090] S2: In response to an edit operation on the question information in the dialog box, retrieve the updated question information after editing.

[0091] Here, "editing" refers to actions performed on the question information in the dialog box, such as deleting or adding content. "Update question information" refers to the information obtained after editing the question information.

[0092] For example, a user can edit the question information in the dialog box, and the terminal can respond to the editing operation by obtaining the updated question information after the user has finished editing.

[0093] S3: Update the question information as the target content question under the question understanding dimension.

[0094] For example, after receiving updated question information, the terminal can use this updated question information as the target content question indicated by the user in terms of question understanding. Then, based on the target content question and the question understanding dimension, it can generate an instruction to modify the answer result, thereby obtaining an updated answer.

[0095] like Figure 4 The image shown is a schematic diagram of a page after triggering a first processing identifier, according to an embodiment of this disclosure. Figure 4 The 'a' in the text is... Figure 3 The page shown Figure 4 The page shown in b is in response to a trigger. Figure 3 The page displayed after the first processing flag shows the question information in the dialog box in section b. After the user edits the question information, the terminal obtains the updated question information. For example, the updated question information could be "Write an article in the XX style, using 'August Beach Outfit Guide' as the title. The generated answer should fit the XX style and XX theme, and should not contain XX information." Then, the updated question information can be used as the target content question under the question understanding dimension, and an answer modification instruction can be generated based on the updated question information and the question understanding dimension. In response to the send flag in the trigger dialog box, the answer modification instruction is sent to the server, so that the server uses an artificial intelligence model to output the updated answer according to the answer modification instruction. Simultaneously, after responding to the send flag, the updated question information can be displayed on the dialog page.

[0096] In one embodiment, when the question dimension includes a content error dimension for the answer content, the content processing identifier may include a second processing identifier under the content error dimension. The answer content is the displayed generated result content. For example, the second processing identifier could be a "serious error occurred" identifier. The second processing identifier is used to guide and indicate content problems in the currently displayed generated result content, such as typos, grammatical errors, or the inclusion of sensitive information. In this case, the step of "obtaining the target content problem under the question dimension corresponding to the content processing identifier" in step two above can be implemented according to the following steps:

[0097] Retrieve the first error input prompt information from the dialog box on the dialog page, the input error content information, and determine the target content problem based on the error content information and the error dimension.

[0098] Here, the first error input prompt is used to indicate errors in the generated results. For example, the first error input prompt could be "The error in the above answer is:".

[0099] Error content information refers to the error information identified from the generated results by the user.

[0100] In practice, in response to triggering the second processing flag, a first error input prompt message can be displayed in the dialog box. Then, in response to the user's input in the dialog box, the error content information entered by the user based on the first error input prompt message can be obtained. Afterwards, the error content information can be organized according to the error dimension to obtain the target content problem. For example, the information format corresponding to the error dimension can be pre-set; after obtaining the error content information, the format can be adjusted according to this information format to obtain the target content problem.

[0101] like Figure 5 The image shown is a schematic diagram of a page after triggering a second processing identifier, according to an embodiment of this disclosure. Figure 5 c in the text is Figure 3 The page shown Figure 5 The page indicated by 'd' in the image is in response to a trigger. Figure 3 The page displayed after the second processing flag shows a dialog box in section d displaying the first error input prompt (i.e., "The error in the above answer is:"). Then, the error content information entered by the user in the dialog box can be obtained, and the target content question can be determined based on the error content information. Afterwards, an answer modification instruction can be generated based on the target content question. In response to the send flag in the trigger dialog box, the answer modification instruction is sent to the server, so that the server uses an artificial intelligence model to update the answer result according to the answer modification instruction. Simultaneously, after responding to the send flag, the error content information can be displayed on the dialog page.

[0102] In one embodiment, when the question dimension includes a content redundancy dimension for the answer content, the content processing identifier may include a third processing identifier under the content redundancy dimension. The answer content is the displayed generated result content. For example, the third processing identifier may be a "question resolved" identifier or a "result can be simplified" identifier. In this case, the step of "obtaining the target content question under the question dimension corresponding to the content processing identifier" in step two above can be implemented according to the following steps:

[0103] Identify content redundancy issues under the content redundancy dimension and use these issues as target content problems within that dimension.

[0104] Here, the content redundancy question can be a question pre-set for the content redundancy dimension, for example, the content redundancy question can be "The current answer is redundant, please simplify"; or, the content redundancy question can also be a redundancy question specifically entered by the user in the dialog box, for example, the content redundancy question can be "The Xth sentence of the current answer is redundant".

[0105] For example, in response to a user triggering a third processing identifier, a default content redundancy issue can be obtained and used as the target content issue under the content redundancy dimension. Then, an answer modification instruction can be generated based on the target content issue, and this instruction can be fed back to the server to obtain an updated answer result output by the server using an artificial intelligence model, according to the answer modification instruction.

[0106] Furthermore, the step of displaying updated answer results can be implemented as follows:

[0107] Display the default answer, which is pre-generated for questions with redundant content.

[0108] Here, the default answer can be pre-generated for the content redundancy problem. That is, it can be a default answer that is pre-set to match the third processing identifier. After the user triggers the third processing identifier, the default answer can be obtained first and displayed on the chat page.

[0109] According to the generation progress of the updated answer results, the generated results in the updated answer results are displayed; the generated results in the updated answer results are obtained by simplifying the answer results based on the content redundancy issues.

[0110] In practice, after sending the instruction to modify the answer result to the server, the system can retrieve the generated result content from the updated answer result, based on the server's progress in generating the updated answer result. This generated result content in the updated answer result is obtained by simplifying the answer result using an artificial intelligence model to address content redundancy issues. This generated result content in the updated answer result can be displayed below the default answer result.

[0111] like Figure 6 The image shown is a schematic diagram of a page after triggering a third processing identifier, according to an embodiment of this disclosure. Figure 6 The 'e' in the text is... Figure 3 The page shown Figure 6 The page indicated by 'f' in the image is in response to a trigger. Figure 3 The page displayed after the third processing flag is triggered. Simultaneously, a default answer ("Okay, I'll pay attention to concise answers next time") is displayed in f, which can be displayed in response to triggering the third processing flag. Afterwards, after sending the instruction to modify the answer result generated based on the content redundancy issue to the server, the generated result content can be obtained from the server according to the progress of updating the answer result generation, and the generated result content can be displayed on the chat page.

[0112] Optionally, after a user triggers a third processing flag, the default answer can be directly displayed as the updated answer on the chat page.

[0113] In one embodiment, where the issue dimension includes other dimensions, the content processing identifier may include a fourth processing identifier under the other dimensions (e.g., Figure 3 (The "Other" flag in the code). In this case, in response to the user triggering the fourth processing flag, the system can retrieve the question information entered by the user in the dialog box regarding the already answered results, use this question information as the target answer question, and generate an answer result modification instruction that includes the target answer question. Then, the answer result modification instruction can be sent to the server, allowing the server to use an artificial intelligence model to modify the answer result according to the question information in the answer result modification instruction and output an updated answer result.

[0114] In one embodiment, the following steps may also be performed before displaying the updated answer results:

[0115] Below the generated results, preset response information matching the triggered content processing identifier is displayed.

[0116] Here, for each content processing identifier, preset response information can be pre-set for that memory processing identifier. The preset response information for each content processing identifier is based on the question dimension corresponding to that content processing identifier. For example, the preset response information for the first processing identifier could be "Sorry, I couldn't understand your question. Could you please provide more details about your question?"; the preset response information for the second processing identifier could be "Sorry, there was an error. Could you please point out the error?"; the preset response information for the third processing identifier could be "Sorry, I will pay attention to conciseness in the future"; and the preset response information for the fourth processing identifier could be "Sorry, I didn't provide the answer you wanted. Could you please point out the problem?"

[0117] Specifically, upon responding to a content processing trigger, the system can retrieve the preset answer information corresponding to the content processing trigger and display it below the generated results. For example, in Figure 4 In section b, the preset answer information corresponding to the first processing identifier is displayed (i.e., "Sorry, we couldn't understand your question. You can provide more details about your question"). Figure 5 In 'd', the preset response information corresponding to the second processing identifier is displayed (i.e., "Sorry, there was an error. Could you please point out the error?"); Figure 6 In f, the preset response information corresponding to the third processing identifier is displayed (i.e., "Sorry, we will pay attention to simplification in the future").

[0118] In one embodiment, to improve the answering performance of the AI ​​model, the model can be trained using question information and updated answer results. Specifically, multiple question messages, updated answer results for each question message, and evaluation information for the updated answer results can be obtained. Evaluation information can include, for example, ratings, likes, or block information. The question information is input into the AI ​​model, and the predicted answer result output by the AI ​​model is obtained. Here, the predicted answer result can be consistent with the answer result output by the AI ​​model for the question information when no stop generation instruction is received.

[0119] Then, based on the evaluation information of the updated answer result corresponding to the question information, the updated answer result, and the predicted answer result, the prediction loss of the artificial intelligence model can be determined. The prediction loss is then used to iteratively train the artificial intelligence model until a preset training cutoff condition is met, resulting in an updated artificial intelligence model. Afterwards, the updated artificial intelligence model can be used to output answer results for newly input question information from the user. The preset training cutoff condition can be reaching a preset number of iterations and / or the prediction accuracy of the trained artificial intelligence model reaching a preset accuracy.

[0120] Based on the above embodiments, displaying the generated results according to the generation progress enables real-time display of the answer results, avoiding the problem of excessively long waiting times caused by waiting for all answer results to be generated before displaying them. By responding to a stop generation command during the generation of the generated results, the generation of answer results can be stopped at any time, improving control flexibility. Since the answer result modification command indicates a target content issue under the question dimension, modifying the answer result using the acquired answer result modification command allows for targeted modifications to the target content issue existing in the current generation process, resulting in a more reasonable and expected updated answer result, improving the effectiveness of secondary responses. In other words, it allows for rapid correction of answer results based on user feedback on the generated results, thereby shortening the time and path for users to obtain better answers. Furthermore, modifying the answer result using the answer result modification command allows for reasonable modification of the answer result without re-entering the question information, improving both the flexibility of modification and the reasonableness of the answer result obtained from secondary responses.

[0121] Those skilled in the art will understand that, in the above-described method of the specific implementation, the order in which each step is written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0122] Based on the same inventive concept, this disclosure also provides an information display device corresponding to the information display method. Since the principle of the device in this disclosure for solving the problem is similar to the information display method described above in this disclosure, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be described again.

[0123] like Figure 7 The diagram shown is a schematic representation of an information display device provided in an embodiment of this disclosure, comprising:

[0124] The first display module 701 is configured to, in response to receiving a question on the dialogue page, display the generated result content in the answer results according to the generation progress of the answer results matching the question; and, during the display of the generated result content, stop the generation of the answer results in response to receiving a stop generation command.

[0125] The second display module 702 is used to display an updated answer result in response to a received answer result modification instruction. The updated answer result is obtained by modifying the answer result according to the target content question under the question dimension indicated by the answer result modification instruction.

[0126] In one possible implementation, the device further includes:

[0127] The first acquisition module 703 is used to acquire the answer result modification instruction according to the following steps:

[0128] In response to receiving a stop generation command, content processing identifiers under different problem dimensions are displayed; each content processing identifier under a problem dimension is used to guide and indicate the content problem of the currently displayed generated result content under that problem dimension;

[0129] In response to triggering any of the content processing identifiers, the target content question under the question dimension corresponding to the content processing identifier is obtained, and the answer result modification instruction is generated based on the target content question.

[0130] In one possible implementation, the device further includes:

[0131] The second acquisition module 704 is used to acquire the answer result modification instruction according to the following steps:

[0132] Obtain the input content modification information, and determine the problem dimension and target content problem based on the content modification information;

[0133] Based on the question dimension and the target content question, generate an instruction to modify the answer result.

[0134] In one possible implementation, the problem dimension includes a problem understanding dimension, and the content processing identifier includes a first processing identifier under the problem understanding dimension;

[0135] The first acquisition module 703, when acquiring the target content issue under the issue dimension corresponding to the content processing identifier, is used to:

[0136] The question information is displayed in the dialog box on the dialog page;

[0137] In response to an editing operation on the question information in the dialog box, obtain the edited updated question information;

[0138] The updated question information is used as the target content question under the question understanding dimension.

[0139] In one possible implementation, the question dimension includes a content error dimension for the answer content, and the content processing identifier includes a second processing identifier under the content error dimension;

[0140] The first acquisition module 703, when acquiring the target content issue under the issue dimension corresponding to the content processing identifier, is used to:

[0141] Retrieve the target content issue under the issue dimension corresponding to the content processing identifier, including:

[0142] Obtain the first error input prompt information and the input error content information from the dialog box on the dialog page, and determine the target content problem based on the error content information and the content error dimension.

[0143] In one possible implementation, the question dimension includes a content redundancy dimension for the answer content, and the content processing identifier includes a third processing identifier under the content redundancy dimension.

[0144] The first acquisition module 703, when acquiring the target content issue under the issue dimension corresponding to the content processing identifier, is used to:

[0145] Obtain the content redundancy problem under the content redundancy dimension, and use the content redundancy problem as the target content problem under the content redundancy dimension;

[0146] The second display module 702, when displaying updated answer results, is used for:

[0147] Display the default answer result; the default answer result is pre-generated to address the issue of content redundancy.

[0148] According to the generation progress of the updated answer results, the generated result content in the updated answer results is displayed; the generated result content in the updated answer results is obtained by simplifying the answer results based on the content redundancy issues.

[0149] In one possible implementation, the second display module 702, before displaying the updated answer result, is further configured to:

[0150] Below the generated results, a preset response message matching the triggered content processing identifier is displayed.

[0151] The processing flow of each module in the device and the interaction flow between each module can be referred to the relevant descriptions in the above method embodiments, and will not be detailed here.

[0152] Based on the same technical concept, embodiments of this application also provide a computer device. (Refer to...) Figure 8 The diagram shown is a structural schematic of a computer device provided in an embodiment of this application, comprising:

[0153] The system includes a processor 801, a memory 802, and a bus 803. The memory 802 stores machine-readable instructions executable by the processor 801. The processor 801 executes these machine-readable instructions, performing the following steps: S101: In response to receiving a question on the dialog page, the processor displays the generated results in the answer results according to the progress of generating the answer results matching the question; S102: During the display of the generated results, in response to receiving a stop-generation command, the processor stops generating the answer results; and S103: In response to receiving an answer result modification command, the processor displays an updated answer result, which is obtained by modifying the answer result to reflect the target content question under the question dimension indicated by the answer result modification command.

[0154] The aforementioned memory 802 includes a main memory 8021 and an external memory 8022. The main memory 8021, also known as internal memory, is used to temporarily store the computational data in the processor 801, as well as the data exchanged with external memory such as a hard disk 8022. The processor 801 exchanges data with the external memory 8022 through the main memory 8021. When the computer device is running, the processor 801 and the memory 802 communicate through the bus 803, so that the processor 801 executes the execution instructions mentioned in the above method embodiments.

[0155] This disclosure also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the information display method described in the above-described method embodiments. The storage medium can be a volatile or non-volatile computer-readable storage medium.

[0156] The computer program product of the information display method provided in this disclosure includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the steps of the information display method described in the above method embodiments. For details, please refer to the above method embodiments, which will not be repeated here.

[0157] The computer program product can be implemented specifically through hardware, software, or a combination thereof. In one alternative embodiment, the computer program product is specifically embodied in a computer storage medium; in another alternative embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.

[0158] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems and devices described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. In the several embodiments provided in this disclosure, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division; in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection may be through some communication interfaces; the indirect coupling or communication connection of devices or units may be electrical, mechanical, or other forms.

[0159] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0160] In addition, the functional units in the various embodiments of this disclosure can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0161] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this disclosure. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0162] If the technical solution of this application involves personal information, the product using this technical solution has clearly informed the user of the personal information processing rules and obtained the user's voluntary consent before processing the personal information. If the technical solution of this application involves sensitive personal information, the product using this technical solution has obtained the user's separate consent before processing the sensitive personal information, and also meets the requirement of "express consent". For example, at personal information collection devices such as cameras, clear and prominent signs are set up to inform users that they have entered the scope of personal information collection and that personal information will be collected. If an individual voluntarily enters the collection scope, it is deemed that they have agreed to the collection of their personal information; or on the personal information processing device, with clear signs / information informing users of the personal information processing rules, authorization is obtained from the user through pop-up information or by asking the user to upload their personal information; wherein, the personal information processing rules may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the types of personal information processed.

[0163] Finally, it should be noted that the above-described embodiments are merely specific implementations of this disclosure, used to illustrate the technical solutions of this disclosure, and not to limit it. The protection scope of this disclosure is not limited thereto. Although this disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this disclosure. Such modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this disclosure, and should all be covered within the protection scope of this disclosure. Therefore, the protection scope of this disclosure should be determined by the protection scope of the claims.

Claims

1. An information presentation method, characterized by, include: In response to receiving a question on the dialogue page, the generated results in the answer results are displayed according to the generation progress of the answer results that match the question. During the display of the generated results, in response to receiving a stop generation command, the generation of the answer results is stopped; In response to receiving an instruction to modify the answer result, an updated answer result is displayed. The updated answer result is obtained by modifying the answer result according to the target content question under the question dimension indicated by the answer result modification instruction. The answer result modification instruction is used to indicate the question dimension corresponding to the current generated result content and the target content question under the question dimension. It is also used to instruct to regenerate the answer result for the question information according to the answer result modification instruction. The target content question is the question that currently exists in the generated result content. The answer result modification instruction is obtained after triggering the content processing identifier in the dialog page. The content processing identifier is used to guide and point out the content question of the current generated result content under the question dimension corresponding to the content processing identifier.

2. The method according to claim 1, characterized in that, To obtain the modification instructions for the answer result, follow these steps: In response to receiving a stop generation command, content processing identifiers under different problem dimensions are displayed; each content processing identifier under a problem dimension is used to guide and indicate the content problem of the currently displayed generated result content under that problem dimension; In response to triggering any of the content processing identifiers, the target content question under the question dimension corresponding to the content processing identifier is obtained, and the answer result modification instruction is generated based on the target content question.

3. The method according to claim 2, characterized in that, The problem dimension includes the problem understanding dimension, and the content processing identifier includes the first processing identifier under the problem understanding dimension; Retrieve the target content issue under the issue dimension corresponding to the content processing identifier, including: The question information is displayed in the dialog box on the dialog page; In response to an editing operation on the question information in the dialog box, obtain the edited updated question information; The updated question information is used as the target content question under the question understanding dimension.

4. The method according to claim 2, characterized in that, The question dimension includes a content error dimension for the answer content, and the content processing identifier includes a second processing identifier under the content error dimension; Retrieve the target content issue under the issue dimension corresponding to the content processing identifier, including: Obtain the first error input prompt information and the input error content information from the dialog box on the dialog page, and determine the target content problem based on the error content information and the content error dimension.

5. The method according to claim 2, characterized in that, The question dimension includes a content redundancy dimension for the answer content, and the content processing identifier includes a third processing identifier under the content redundancy dimension. Retrieve the target content issue under the issue dimension corresponding to the content processing identifier, including: Obtain the content redundancy problem under the content redundancy dimension, and use the content redundancy problem as the target content problem under the content redundancy dimension; Show updated answer results, including: Display the default answer result; the default answer result is pre-generated to address the issue of content redundancy. According to the generation progress of the updated answer results, the generated result content in the updated answer results is displayed; the generated result content in the updated answer results is obtained by simplifying the answer results based on the content redundancy issues.

6. The method according to claim 2, characterized in that, Before displaying the updated answer results, the following is also included: Below the generated results, a preset response message matching the triggered content processing identifier is displayed.

7. An information display device, characterized in that, include: The first display module is used to respond to receiving a question on the dialogue page and display the generated result content in the answer results according to the generation progress of the answer results that match the question; And during the process of displaying the generated results, in response to receiving a stop generation command, the generation of the answer results is stopped; The second display module is used to display an updated answer result in response to a received answer result modification instruction. The updated answer result is obtained by modifying the answer result according to the target content question under the question dimension indicated by the answer result modification instruction. The answer result modification instruction is used to indicate the question dimension corresponding to the current generated result content and the target content question under the question dimension. It is also used to instruct the regeneration of the answer result for the question information according to the answer result modification instruction. The target content question is the question that currently exists in the generated result content. The answer result modification instruction is obtained after triggering the content processing identifier in the dialogue page. The content processing identifier is used to guide and point out the content question of the current generated result content under the question dimension corresponding to the content processing identifier.

8. A computer device, characterized in that, include: A processor and a memory, wherein the memory stores machine-readable instructions executable by the processor, the processor is configured to execute the machine-readable instructions stored in the memory, and when the machine-readable instructions are executed by the processor, the processor performs the steps of the information display method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and when the computer program is run by a computer device, the computer device performs the steps of the information display method as described in any one of claims 1 to 6.

Images