Interaction method and apparatus, computer device, and storage medium

Abstract

The present disclosure provides an interaction method and apparatus, a computer device, and a storage medium. The method comprises: displaying an artificial intelligence question and answer page; receiving input first question information on the question and answer page; and in response to receiving input second question information in the process of generating a first answer result corresponding to the first question information, displaying a second answer result determined on the basis of the first question information and the second question information. According to the embodiments of the present disclosure, the second question information can be continued to receive without the need to wait for the generation of all the first answer results or without the need to interrupt the generation process of the first answer result by a first user, so that the user can input new question information at any time and is timely given an answer result, thereby saving the waiting time of the user, and improving the interaction efficiency in the man-machine question and answer process.

Description

Interaction method, device, computer equipment and storage medium

[0001] This application claims priority to Chinese patent application No. 202310988652.X filed on August 7, 2023, the entire text of which is incorporated herein by reference as a part of this application. Technical Field

[0002] The present disclosure relates to an interaction method, apparatus, computer equipment and storage medium. Background Art

[0003] With the development of computer technology, the application of human-computer dialogue in areas such as intelligent customer service and intelligent assistants has gradually matured. In the process of human-computer question and answer, the user enters a question and the intelligent robot can generate the corresponding answer.

[0004] However, in the scenario of continuous question and answer, after the user enters a question, he or she usually needs to wait for the intelligent robot to give a complete answer or pause the current answer generation process before entering a new question, making the human-computer dialogue inefficient.

[0005] Summary of the Invention

[0006] The embodiments of the present disclosure at least provide an interaction method, apparatus, computer equipment, and storage medium.

[0007] In a first aspect, an embodiment of the present disclosure provides an interaction method, including:

[0008] Display the AI ​​Q&A page;

[0009] On the question-and-answer page, receiving a first question input;

[0010] In response to receiving input of second question information during the process of generating a first answer result corresponding to the first question information, a second answer result determined based on the first question information and the second question information is displayed.

[0011] In combination with the first aspect, the embodiment of the present disclosure further provides a first optional implementation of the first aspect, wherein, before receiving the input second question information, the method further includes:

[0012] Displaying a partial answer result of the first answer result generated in real time;

[0013] In response to generating a first answer result corresponding to the first question information, receiving a second question information, and displaying a second answer result determined based on the first question information and the second question information, including:

[0014] In response to receiving a second question message input before generating the complete answer result of the first answer result, an interruption prompt mark is displayed after the partial answer result displayed, and the second answer result is displayed after the second question message; the interruption prompt mark is used to indicate that the generation process of the first answer result has been interrupted.

[0015] In combination with the first aspect, the embodiment of the present disclosure further provides a second optional implementation of the first aspect, wherein, in response to receiving input of second question information during the process of generating a first answer result corresponding to the first question information, displaying a second answer result determined based on the first question information and the second question information includes:

[0016] In response to receiving the second question information input before starting to generate the first answer result, the second answer result is displayed after the first question information and the second question information are displayed.

[0017] In combination with the first aspect, the embodiment of the present disclosure further provides a third optional implementation of the first aspect, wherein, before receiving the input second question information, the method further includes:

[0018] Displaying a partial answer result of the first answer result generated in real time;

[0019] In response to receiving input of second question information during a process of generating a first answer result corresponding to the first question information, displaying a second answer result determined based on the first question information and the second question information includes:

[0020] In response to receiving input of second question information before generating all answer results of the first answer result, after displaying the first answer result in full, the second answer result is displayed after the second question information.

[0021] In combination with the first aspect, the embodiment of the present disclosure further provides a fourth optional implementation of the first aspect, wherein the displaying of the second answer result determined based on the first question information and the second question information includes:

[0022] In response to a semantic contextual relationship between the first question information and the second question information, a second answer result corresponding to the integrated question information corresponding to the first question information and the second question information is displayed; the second answer result is used to answer the first question information and the second question information.

[0023] In combination with the fourth optional implementation of the first aspect, the embodiment of the present disclosure further provides a fifth optional implementation of the first aspect, wherein the second answer result includes an overall answer result that can answer the first question information and the second question information; or,

[0024] The second answer result includes a first sub-answer result corresponding to the first question information and a second sub-answer result corresponding to the second question information.

[0025] In combination with the first aspect, the embodiment of the present disclosure further provides a sixth optional implementation of the first aspect, wherein the displaying of the second answer result determined based on the first question information and the second question information includes:

[0026] In response to the absence of a semantic contextual relationship between the first question information and the second question information, a second answer result corresponding to the second question information is displayed.

[0027] In combination with any of the fourth to sixth optional implementations of the first aspect, the embodiment of the present disclosure further provides a seventh optional implementation of the first aspect, wherein determining whether a semantic context relationship exists between the first question information and the second question information is performed according to the following steps:

[0028] determining a semantic relevance between the first question information and the second question information based on a first semantic feature vector corresponding to the first question information and a second semantic feature vector corresponding to the second question information;

[0029] When the semantic relevance is greater than a set threshold, it is determined that a semantic contextual relationship exists between the first question information and the second question information.

[0030] In combination with the first optional implementation of the first aspect, the embodiment of the present disclosure further provides an eighth optional implementation of the first aspect, wherein the method further includes:

[0031] In response to the triggering operation for the interruption prompt indicator, the remaining answer results of the first answer result continue to be displayed.

[0032] In a second aspect, an embodiment of the present disclosure further provides an interactive device, including:

[0033] The first display module is used to display the artificial intelligence question and answer page;

[0034] A receiving module, configured to receive a first question input on the question-and-answer page;

[0035] The second display module is configured to display a second answer result determined based on the first question information and the second question information in response to receiving second question information input during the process of generating the first answer result corresponding to the first question information.

[0036] In a third aspect, an embodiment of the present disclosure further provides a computer device comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps in the above-mentioned first aspect or any optional implementation of the first aspect are performed.

[0037] In a fourth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned first aspect or any optional implementation of the first aspect are executed. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following briefly introduces the drawings required for use in the embodiments. The drawings herein are incorporated into and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and, together with the specification, are used to illustrate the technical solutions of the present disclosure. It should be understood that the following drawings only illustrate certain embodiments of the present disclosure and should not be regarded as limiting the scope. For those of ordinary skill in the art, other relevant drawings can be obtained based on these drawings without inventive effort.

[0039] FIG1 shows a schematic diagram of the effect of a question-and-answer page in the related technology provided by an embodiment of the present disclosure;

[0040] FIG2 shows a schematic diagram of another effect of a question-and-answer page in the related technology provided by an embodiment of the present disclosure;

[0041] FIG3 shows a flow chart of an interaction method provided by an embodiment of the present disclosure;

[0042] FIG4 shows a schematic diagram showing the effect of an artificial intelligence question-and-answer page provided by an embodiment of the present disclosure;

[0043] FIG5 shows a schematic diagram showing the effect of another artificial intelligence question-and-answer page provided by an embodiment of the present disclosure;

[0044] FIG6 shows a schematic diagram showing the effect of another artificial intelligence question-and-answer page provided by an embodiment of the present disclosure;

[0045] FIG7 shows a schematic diagram showing the effect of another artificial intelligence question-and-answer page provided by an embodiment of the present disclosure;

[0046] FIG8 shows a schematic diagram showing the effect of another artificial intelligence question-and-answer page provided by an embodiment of the present disclosure;

[0047] FIG9 shows a schematic diagram showing the effect of another artificial intelligence question-and-answer page provided by an embodiment of the present disclosure;

[0048] FIG10 shows a schematic diagram showing the effect of another artificial intelligence question-and-answer page provided by an embodiment of the present disclosure;

[0049] FIG11 shows a schematic structural diagram of an interactive device provided by an embodiment of the present disclosure;

[0050] FIG12 shows a schematic diagram of a computer device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. The components of the embodiments of the present disclosure generally described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present disclosure provided in the drawings is not intended to limit the scope of the disclosure for which protection is sought, but merely represents selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present disclosure.

[0052] Research has found that in related technologies, in a human-computer dialogue scenario, after a user enters question A on a question-and-answer page, it is impossible to enter question B while generating answer result A corresponding to question A.

[0053] As shown in Figure 1, after the user enters question A on the Q&A page, during the process of generating the answer result A corresponding to question A, the input box on the Q&A page is in a disabled state (as an illustration, the disabled state is represented by a grayscale state here). Only after all the answer results A are generated can the input box be changed from a disabled state to an enabled state (as an illustration, the enabled state is represented by a white state here). Alternatively, as shown in Figure 2, during the process of generating the answer result A corresponding to question A, a pause button can be displayed on the Q&A page. When the user triggers the pause button, the generation process of the answer result A can be paused, and the user can then enter question B.

[0054] Based on this, the present disclosure provides an interactive method, including: displaying an artificial intelligence question and answer page; receiving a first question information input on the question and answer page; in response to generating a first answer result corresponding to the first question information, receiving a second question information input, and displaying a second answer result determined based on the first question information and the second question information.

[0055] The interactive method provided by the embodiment of the present disclosure can receive the input second question information and display the second answer result determined based on the first question information and the second question information during the process of generating the first answer result corresponding to the first question information. The above process can continue to receive the second question information without waiting for the first answer result to be fully generated or the first user interrupting the generation process of the first answer result, so that the user can input new question information at any time and give the answer result in time, saving the user's waiting time and improving the interaction efficiency in the human-computer question and answer process.

[0056] The defects of the above solutions and the proposed solutions are the results obtained by the inventor after practice and careful research. Therefore, the discovery process of the above problems and the solutions proposed in the present disclosure for the above problems below should be the contributions made by the inventor to the present disclosure during the disclosure process.

[0057] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings.

[0058] It is understandable that before using the technical solutions disclosed in the various embodiments of this disclosure, the type, scope of use, usage scenarios, etc. of the personal information involved in this disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0059] To facilitate understanding of this embodiment, an interactive method disclosed in an embodiment of the present disclosure is first introduced in detail. The execution subject of the interactive method provided in the embodiment of the present disclosure is generally a computer device with certain computing capabilities.

[0060] The interactive method provided by the embodiment of the present disclosure is suitable for scenarios where question information is input on an artificial intelligence question-and-answer page and answer results are obtained.

[0061] The interactive method provided in the embodiment of the present disclosure is described below by taking the execution subject as a terminal device as an example.

[0062] FIG3 is a flow chart of an interactive method provided by an embodiment of the present disclosure. The method includes S301 to S303, wherein:

[0063] S301: Display the artificial intelligence question and answer page.

[0064] S302: On the question-and-answer page, receiving first question information input.

[0065] S303: In response to receiving input of second question information during the process of generating a first answer result corresponding to the first question information, display a second answer result determined based on the first question information and the second question information.

[0066] In an embodiment of the present disclosure, an artificial intelligence question and answer page can be used to display the answer results generated based on artificial intelligence (AI) technology after the question information is input. The artificial intelligence question and answer page can be displayed after executing a target trigger operation, and specifically, it can be a target trigger operation executed at any possible entrance. The embodiment of the present disclosure is not limited. For example, the artificial intelligence question and answer page can be displayed starting from the multimedia content display page, or it can be triggered to display the artificial intelligence question and answer page at a special artificial intelligence function entrance. For example, in the process of browsing the multimedia content details on the target page, or browsing the search results after initiating a search, or browsing the recommended information flow, if the user has the need to use artificial intelligence to answer related questions, the artificial intelligence logo displayed on the target page is triggered to display the artificial intelligence question and answer page; for another example, the artificial intelligence function can be found and triggered in the function options of the application to enter the artificial intelligence question and answer page.

[0067] The AI ​​Q&A page may display a question input area that can receive customized text questions, voice questions, etc. The AI ​​Q&A page may also display preset questions, and in response to a selected preset question, an answer determined based on the preset question may be displayed.

[0068] In the effect diagram of an artificial intelligence question-and-answer page shown in Figure 4, a voice input box can be displayed at the bottom of the artificial intelligence question-and-answer page. Users can use the voice input box to input customized voice question information. The input box also displays a switch mark for switching between a text input box and a voice input box. After triggering the switch mark, the voice input box can be switched to a text input box, so that text question information can be entered in the text input box. When the text input box is displayed, after triggering the switch mark, the text input box can be switched to a voice input box.

[0069] The AI ​​Q&A page shown in FIG4 also displays preset question information. When any preset question information is triggered, the triggered preset question information can be used as the first question information, and the first question information and the first answer result corresponding to the first question information are displayed on the AI ​​Q&A page. It should be understood that the AI ​​Q&A page shown in FIG4 is only illustrative and does not limit the present disclosure.

[0070] The first question information received above may be text question information or voice question information inputted by user, or may be preset question information inputted, which is not specifically limited here.

[0071] In an embodiment of the present disclosure, in the process of generating a first answer result corresponding to the first question information, the process of receiving the second question information can occur at the following stages: (1) the stage before starting to generate the first answer result; (2) the stage after a partial answer result of the first answer result has been generated.

[0072] The above stages will be described below respectively.

[0073] (1) The stage before generating the first answer result.

[0074] Receiving a second question at this stage can mean that the second question was entered after the first question was entered but before the first answer was displayed. As shown in Figure 5, after the user entered the question "How's the weather today?", before the answer to "How's the weather today?" was displayed, they immediately entered the question "What about tomorrow?"

[0075] In one embodiment, in response to receiving the second question information input before starting to generate the first answer result, the second answer result may be displayed after the first question information and the second question information are displayed.

[0076] In this case, the second answer result may be a comprehensive answer or a selective answer to the first question information and the second question information. The display process of the second answer result will be described later.

[0077] The above implementation method receives the input of the second question information before starting to generate the first answer result corresponding to the first question information. This allows the user to continuously input multiple question information before giving any answer result. There is no need to wait for the process of generating the answer results separately, and the answer results of multiple question information are given in a timely manner, thereby improving the efficiency of human-computer question and answer.

[0078] (2) The stage where a partial answer result of the first answer result has been generated.

[0079] Receiving the second question information at this stage may mean that the user has generated a partial answer result of the first answer result before inputting the second question information, but has not yet generated a complete answer result of the first answer result.

[0080] Before receiving the input second question information, a partial answer result of the first answer result generated in real time may be displayed.

[0081] There are many reasons why the user may enter the second question information at this stage. For example, in some cases, the user has already obtained the expected answer through the partial answer result of the generated first answer result. In this case, the user enters the second question information before the full answer result of the first answer result is generated. In this case, after receiving the second question information, the generation process of the first answer result can be interrupted, and only the partial answer result of the generated first answer result can be displayed, and the second answer result can be displayed. Specifically, in response to receiving the input of the second question information before the full answer result of the first answer result is generated, the partial answer result of the generated first answer result can be displayed, and the second answer result can be displayed after the second question information.

[0082] If the user does not enter the third question information during the process of generating the second answer result, all the second answer results can be generated and displayed. If the user enters the third question information during the process of generating the second answer result, the third answer result determined based on the target question information entered by the user can be displayed according to the process of step S103. The target question information can include at least one of the first question information, the second question information, and the third question information.

[0083] In order to make the user clearly aware that what is currently displayed is a partial answer result of the first answer result, in one embodiment, in response to receiving a second question information input before generating the full answer result of the first answer result, an interrupt prompt icon can be displayed after the displayed partial answer result, and the second answer result can be displayed after the second question information; the interrupt prompt icon is used to indicate that the generation process of the first answer result has been interrupted.

[0084] In the above embodiment, the generation process of the first answer result can be automatically interrupted without the user having to interrupt the generation process of the first answer result. Furthermore, by displaying an interruption prompt indicator, the user can be informed that the generation process of the first answer result has been interrupted and that the currently displayed answer result is not the full answer result. Furthermore, the above embodiment can automatically interrupt the generation process of the first answer result without the user triggering a stop button and receive the second question information input by the user, allowing the user to enter new question information at any time and receive the answer result in a timely manner, thus saving the user's waiting time and improving the interaction efficiency during the human-computer question-and-answer process.

[0085] As shown in Figure 6, after a user enters the question "What's the weather like today?" on the AI ​​answer page, a partial answer generated based on the question is displayed. While displaying the partial answer, the user enters the question "What about tomorrow?" and an ellipsis is displayed after the generated partial answer. This ellipsis is an interruption indicator, indicating that the generation of the answer to "What's the weather like today?" has been interrupted. The answer "It will be sunny tomorrow" is then displayed after the question "What about tomorrow?"

[0086] In one embodiment, if the user still wants to view all the answers to the first answer result after the first answer result is interrupted, the user can trigger an interruption prompt indicator. In response to the triggering operation of the interruption prompt indicator, the remaining answers to the first answer result can continue to be displayed. If the user does not need to view all the answers, the user can do nothing, and the interruption prompt indicator will continue to be displayed after the partial answer result.

[0087] In the above embodiment, by displaying the interruption prompt mark, and when the interruption prompt mark is triggered, the remaining answer results of the first answer result can be continued to be viewed, so that the user can determine whether to continue to view the complete answer result according to the viewing needs, which not only meets the user's personalized viewing needs, but also improves the intelligence level of generating answer results.

[0088] The reason a user enters the second question at this stage can also be, for example, in some cases, not because the user wants to view all the answers to the first answer, but simply because they are eager to enter the second question. In this case, in one embodiment, after receiving the second question, the first answer generation process can continue, and after the first answer is fully displayed, the second answer can be displayed. In other words, in response to receiving the second question before generating all the answers to the first answer, the second answer can be displayed after the first answer is fully displayed.

[0089] Figure 7 shows another schematic diagram of the effect of artificial intelligence answer results. After entering the question information "How is the weather today?" on the artificial intelligence answer page, partial answer results generated based on the question information can be displayed. In the process of displaying partial answer results, the user enters the question information "What about tomorrow?" After displaying all the answer results of "How is the weather today?", the answer result of "What about tomorrow?" "It will be sunny tomorrow" can be displayed.

[0090] The above implementation method, by displaying the second answer result after the second question information after the first answer result is fully displayed, can avoid the situation where the user fails to view the complete answer result in time due to being in a hurry to enter the second question information, and meets the user's need to view the answer results corresponding to each question information.

[0091] Considering that the first question information and the second question information input may be related or unrelated, whether the first question information and the second question information are related can be represented by a semantic context relationship. If a semantic context relationship exists between the first question information and the second question information, it can be represented that the first question information and the second question information are related; if no semantic context relationship exists between the first question information and the second question information, it can be represented that the first question information and the second question information are unrelated.

[0092] The semantic context relationship here can be determined by analyzing whether there is an association relationship between the semantics of the first question information and the semantics of the second question information. The association relationship here may include a relationship with a large semantic similarity, and may also include a logical relationship between the preceding and following contexts.

[0093] In one embodiment, whether there is a semantic context relationship between the first question information and the second question information can be determined by the following steps: determining the semantic relevance between the first question information and the second question information based on the first semantic feature vector corresponding to the first question information and the second semantic feature vector corresponding to the second question information; when the semantic relevance is greater than a set threshold, determining that there is a semantic context relationship between the first question information and the second question information.

[0094] In the above embodiment, the first semantic feature vector and the second semantic feature vector may be obtained in any feasible manner, and are not specifically limited here.

[0095] After determining the first semantic feature vector and the second semantic feature vector, for example, the cosine similarity between the first semantic feature vector and the second semantic feature vector can be calculated. The cosine similarity between the first semantic feature vector and the second semantic feature vector can represent the semantic relevance between the first semantic feature vector and the second semantic feature vector.

[0096] If the semantic relevance between the first question and the second question is greater than a set threshold, it can be said that the first question and the second question are highly semantically related, that is, a semantic contextual relationship exists. Conversely, if the semantic relevance between the first question and the second question is less than or equal to the set threshold, it can be said that the first question and the second question are less semantically related, that is, no semantic contextual relationship exists.

[0097] In the process of displaying the second answer result, different results may be displayed depending on whether there is a semantic contextual relationship between the first question information and the second question information.

[0098] In one embodiment, in response to the semantic context relationship between the first question information and the second question information, a second answer result corresponding to the integrated question information corresponding to the first question information and the second question information can be displayed; the second answer result is used to answer the first question information and the second question information.

[0099] When a semantic contextual relationship exists between the first and second questions, the first and second questions can be integrated based on their semantics to yield a complete question. As shown in Figure 8, the first question is "What's the weather like today?" and the second question is "What about tomorrow?" Based on the second question, it can be seen that the second question only provides a time phrase, "tomorrow," but lacks other grammatical components such as a subject and predicate. The user's intent cannot be determined based solely on the second question. Although the second question does not fully express the user's intent, it is clear that the first and second questions have a semantic contextual relationship, and the second question inherits some of the content expressed in the first question. Therefore, based on the first and second questions, it can be determined that the user intended to inquire about the weather conditions both today and tomorrow. In this case, the first and second questions can be integrated into "What's the weather like today and tomorrow?" and the corresponding second answer to the integrated question can be displayed. The second answer can answer both the first and second questions.

[0100] In an embodiment of the present disclosure, when displaying the second answer result corresponding to the integrated question information, the second answer result may include an overall answer result that can answer the first question information and the second question information, or the second answer result may include a first sub-answer result corresponding to the first question information and a second sub-answer result corresponding to the second question information.

[0101] Here, the first sub-answer result can be used to answer the first question information; the second sub-answer result can be used to answer the second question information. The overall answer result can refer to the overall answer result that is the result of integrating the first sub-answer result corresponding to the first question information and the second sub-answer result corresponding to the second question information.

[0102] For example, when the second sub-answer result can inherit part of the expression content of the first sub-answer result, the second sub-answer result can be abbreviated. In this case, the first sub-answer result corresponding to the first question information and the second sub-answer result corresponding to the second question information can be integrated.

[0103] For example, in the example above, the first question is "What's the weather like today?" and the second question is "What about tomorrow?" The first sub-answer corresponding to the first question may be "It's sunny today." The second sub-answer corresponding to the second question may be "It's sunny tomorrow." The displayed second answer may include the first and second sub-answers, i.e., "It's sunny today, and it's sunny tomorrow." The first sub-answer answers the first question, and the second sub-answer answers the second question.

[0104] For another example, the second answer result displayed may also be the overall answer result after integrating the above two sub-answer results, that is, "The weather is sunny today and tomorrow" or "The weather is sunny today and tomorrow as well."

[0105] As shown in Figure 9 , the first question is "Do foxes hibernate?" and the second question is "What about brown bears?" The first answer to the first question may be "Foxes don't hibernate." The second sub-answer to the second question may be "Brown bears do hibernate." The displayed second answer may include the first and second sub-answers, i.e., "Foxes don't hibernate, but brown bears do." The displayed second answer may also be a combined answer of the two sub-answers, i.e., "Foxes don't hibernate, but brown bears do."

[0106] In the above implementation manner, after receiving the second question information before starting to generate the first answer result, the overall answer result of the first question information and the second question information can be given based on the semantic context relationship between the first question information and the second question information. This can not only provide the answer result more timely, but also provide a more concise and accurate answer result.

[0107] The previous section described how, when a semantic contextual relationship exists between the first and second questions, a second answer corresponding to the integrated question can be displayed. However, when a semantic contextual relationship does not exist between the first and second questions, a second answer corresponding to the second question can be displayed in response to the lack of a semantic contextual relationship between the first and second questions.

[0108] Since there's no semantic contextual relationship between the first question and the second question, this indicates the user may be seeking an answer to the second question. Therefore, the second answer corresponding to the second question can be displayed. The first answer corresponding to the first question can be displayed according to the process of receiving the second question after a partial answer to the first answer has been generated. The specific process is not further described.

[0109] Figure 10 shows a schematic diagram of the effect of another artificial intelligence question-and-answer page. In the figure, there is no semantic context relationship between the first question information entered by the user, "What are the latest research results in quantum entanglement?" and the second question information, "Does quantum entanglement have any applications?" These two question information can be regarded as two independent questions. At this time, after the user asks the second question information, the answer result corresponding to the second question information can be displayed after the second question information.

[0110] In addition, in Figure 10, the second question information may be received at the stage where a partial answer result of the first answer result has been generated. Here, an interrupt prompt mark (i.e., ellipsis) may be displayed after the partial answer result of the first answer result, and the second answer result corresponding to the second question information may be displayed after the second question information.

[0111] The interactive method provided by the embodiment of the present disclosure can receive the input second question information and display the second answer result determined based on the first question information and the second question information during the process of generating the first answer result corresponding to the first question information. The above process can continue to receive the second question information without waiting for the first answer result to be fully generated or the first user interrupting the generation process of the first answer result, so that the user can input new question information at any time and give the answer result in time, saving the user's waiting time and improving the interaction efficiency in the human-computer question and answer process.

[0112] Those skilled in the art will understand that in the above-mentioned method of the specific implementation method, the writing order of each step does not mean 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.

[0113] Based on the same inventive concept, an interactive device corresponding to the interactive method is also provided in the embodiment of the present disclosure. Since the principle of solving the problem by the device in the embodiment of the present disclosure is similar to the above-mentioned interactive method in the embodiment of the present disclosure, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0114] 11 is a schematic diagram of the structure of an interactive device provided in an embodiment of the present disclosure, wherein the device includes:

[0115] The first display module 1101 is used to display an artificial intelligence question-answering page;

[0116] A receiving module 1102 is configured to receive a first question input on the question-and-answer page;

[0117] The second display module 1103 is configured to display a second answer result determined based on the first question information and the second question information in response to receiving a second question information input during the process of generating the first answer result corresponding to the first question information.

[0118] In an optional implementation, before the receiving module executes the step of receiving the input second question information, the device further includes:

[0119] A third display module is used to display a partial answer result of the first answer result generated in real time;

[0120] The second display module 1103 is specifically used to:

[0121] In response to receiving a second question message input before generating the complete answer result of the first answer result, an interruption prompt mark is displayed after the partial answer result displayed, and the second answer result is displayed after the second question message; the interruption prompt mark is used to indicate that the generation process of the first answer result has been interrupted.

[0122] In an optional implementation, the second display module 1103 is specifically configured to:

[0123] In response to receiving the second question information input before starting to generate the first answer result, the second answer result is displayed after the first question information and the second question information are displayed.

[0124] In an optional implementation, before the receiving module executes the step of receiving the input second question information, the device further includes:

[0125] A fourth display module, configured to display a partial answer result of the first answer result generated in real time;

[0126] The second display module 1103 is specifically used to:

[0127] In response to receiving input of second question information before generating all answer results of the first answer result, after displaying the first answer result in full, the second answer result is displayed after the second question information.

[0128] In an optional implementation, the second display module 1103 is specifically configured to:

[0129] In response to a semantic contextual relationship between the first question information and the second question information, a second answer result corresponding to the integrated question information corresponding to the first question information and the second question information is displayed; the second answer result is used to answer the first question information and the second question information.

[0130] In an optional implementation manner, the second answer result includes an overall answer result that can answer the first question information and the second question information; or,

[0131] The second answer result includes a first sub-answer result corresponding to the first question information and a second sub-answer result corresponding to the second question information.

[0132] In an optional implementation, the second display module 1103 is specifically configured to:

[0133] In response to the absence of a semantic contextual relationship between the first question information and the second question information, a second answer result corresponding to the second question information is displayed.

[0134] In an optional implementation, the apparatus further includes: a first determining module configured to determine whether a semantic contextual relationship exists between the first question information and the second question information:

[0135] The first determination module is specifically configured to:

[0136] determining a semantic relevance between the first question information and the second question information based on a first semantic feature vector corresponding to the first question information and a second semantic feature vector corresponding to the second question information;

[0137] When the semantic relevance is greater than a set threshold, it is determined that a semantic contextual relationship exists between the first question information and the second question information.

[0138] In an optional embodiment, the device further includes:

[0139] The third display module is used to continue displaying the remaining answer results of the first answer result in response to the trigger operation of the interrupt prompt indicator.

[0140] For descriptions of the processing flow of each module in the device and the interaction flow between each module, reference can be made to the relevant descriptions in the above method embodiment, which will not be described in detail here.

[0141] Based on the same technical concept, the embodiment of the present disclosure also provides a computer device. Referring to Figure 12, it is a structural diagram of the computer device 1200 provided in the embodiment of the present disclosure, including a processor 1201, a memory 1202, and a bus 1203. Among them, the memory 1202 is used to store execution instructions, including a memory 12021 and an external memory 12022; the memory 12021 here is also called an internal memory, which is used to temporarily store the calculation data in the processor 1201, as well as the data exchanged with the external memory 12022 such as the hard disk. The processor 1201 exchanges data with the external memory 12022 through the memory 12021. When the computer device 1200 is running, the processor 1201 communicates with the memory 1202 through the bus 1203, so that the processor 1201 executes the following instructions:

[0142] Display the AI ​​Q&A page;

[0143] On the question-and-answer page, receiving a first question input;

[0144] In response to receiving input of second question information during the process of generating a first answer result corresponding to the first question information, a second answer result determined based on the first question information and the second question information is displayed.

[0145] The present disclosure also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, executes the steps of the interactive method described in the above method embodiment. The storage medium may be a volatile or non-volatile computer-readable storage medium.

[0146] The embodiments of the present disclosure also provide a computer program product, which carries program code. The instructions included in the program code can be used to execute the steps of the interactive method described in the above method embodiment. For details, please refer to the above method embodiment and will not be repeated here.

[0147] The computer program product may be implemented in hardware, software, or a combination thereof. In one embodiment, the computer program product is implemented as a computer storage medium. In another embodiment, the computer program product is implemented as a software product, such as a software development kit (SDK).

[0148] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. In the several embodiments provided in the present disclosure, it should be understood that the disclosed device and method can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of the device or unit can be electrical, mechanical or other forms.

[0149] The units described as separate components may or may not be physically separate, and 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 these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0150] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0151] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present disclosure, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0152] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present disclosure, which are used to illustrate the technical solutions of the present disclosure, rather than to limit them. The scope of protection of the present disclosure is not limited thereto. Although the present disclosure has been described in detail with reference to the above-described embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily conceive of changes to the technical solutions described in the above-described embodiments within the technical scope disclosed in the present disclosure, or replace some of the technical features therein with equivalents. Such modifications, changes, or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be included in the scope of protection of the present disclosure. Therefore, the scope of protection of the present disclosure should be based on the scope of protection of the claims.

Claims

1. An interactive method, comprising: Display the AI ​​Q&A page; On the question-and-answer page, receiving first question information input; In response to receiving input of second question information during the process of generating a first answer result corresponding to the first question information, a second answer result determined based on the first question information and the second question information is displayed.

2. The method according to claim 1, wherein: Before receiving the second question information input, the method further includes: Displaying a partial answer result of the first answer result generated in real time; In response to generating a first answer result corresponding to the first question information, receiving a second question information, and displaying a second answer result determined based on the first question information and the second question information, comprising: In response to receiving a second question message input before generating a complete answer result of the first answer result, an interruption prompt mark is displayed after the partial answer result displayed, and the second answer result is displayed after the second question message; the interruption prompt mark is used to indicate that the generation process of the first answer result has been interrupted.

3. The method according to claim 1 or 2, wherein: In response to receiving input of second question information during the process of generating a first answer result corresponding to the first question information, displaying a second answer result determined based on the first question information and the second question information includes: In response to receiving input of second question information before starting to generate the first answer result, the second answer result is displayed after the first question information and the second question information are displayed.

4. The method according to claim 1, wherein: Before receiving the second question information input, the method further includes: Displaying a partial answer result of the first answer result generated in real time; In response to receiving input of second question information during the process of generating a first answer result corresponding to the first question information, displaying a second answer result determined based on the first question information and the second question information includes: In response to receiving a first answer result input before generating all answer results for the first answer result, Second question information: after the first answer result is fully displayed, the second answer result is displayed after the second question information.

5. The method according to any one of claims 1 to 4, wherein: The presenting a second answer result determined based on the first question information and the second question information includes: In response to a semantic contextual relationship between the first question information and the second question information, a second answer result corresponding to the integrated question information corresponding to the first question information and the second question information is displayed; the second answer result is used to answer the first question information and the second question information.

6. The method according to claim 5, wherein: The second answer result includes an overall answer result that can answer the first question information and the second question information; or The second answer result includes a first sub-answer result corresponding to the first question information and a second sub-answer result corresponding to the second question information.

7. The method according to any one of claims 1 to 4, wherein: The presenting a second answer result determined based on the first question information and the second question information includes: In response to the absence of a semantic contextual relationship between the first question information and the second question information, a second answer result corresponding to the second question information is displayed.

8. The method according to any one of claims 5 to 7, wherein: Determine whether there is a semantic contextual relationship between the first question information and the second question information according to the following steps: determining a semantic relevance between the first question information and the second question information according to a first semantic feature vector corresponding to the first question information and a second semantic feature vector corresponding to the second question information; When the semantic relevance is greater than a set threshold, it is determined that a semantic context relationship exists between the first question information and the second question information.

9. The method according to claim 2, wherein: The method further comprises: In response to the triggering operation for the interruption prompt mark, continue to display the remaining answer results of the first answer result.

10. An interactive device, comprising: The first display module is used to display the artificial intelligence question and answer page; A receiving module, configured to receive a first question information input on the question-and-answer page; The second display module is used to generate a first answer result corresponding to the first question information in response to the first answer result. In the process of determining the result, a second question information is received as input, and a second answer result determined based on the first question information and the second question information is displayed.

11. A computer device comprising: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the interaction method as described in any one of claims 1 to 9 are performed.

12. A computer-readable storage medium storing a computer program, wherein: When the computer program is executed by a processor, the steps of the interaction method according to any one of claims 1 to 9 are executed.

Images