Interaction method and device, electronic equipment, storage medium and program product

Abstract

The invention relates to an interaction method and device, electronic equipment, a storage medium and a program product, and relates to the technical field of computers. The interaction method comprises the steps that in response to information input by a user, a search result and a generative result are determined according to the input information, the search result is associated with the generative result, and the style type of the search result is determined according to intention information represented by the input information; generating reply information according to the search result and the generative result; and displaying the reply information.

Description

Interaction methods, devices, electronic devices, storage media, and program products Technical Field

[0001] This disclosure relates to the field of computer technology, and in particular to an interactive method, apparatus, electronic device, storage medium, and program product. Background Technology

[0002] With the development of AI (Artificial Intelligence) and ML (Machine Learning) technologies, interactive AI applications have emerged that can engage in more fluent dialogues with users.

[0003] Interactive AI applications can use LLM (Large Language Model) to generate response information based on user input, providing users with a more realistic chat experience.

[0004] Summary of the Invention

[0005] This summary section is provided to briefly introduce the concepts, which will be described in detail in the detailed description section below. This summary section is not intended to identify key or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0006] According to some embodiments of this disclosure, an interaction method is provided, comprising: responding to user input information, determining search results and generative results based on the input information, wherein the search results and generative results are associated, and the genre type of the search results is determined based on the intent information represented by the input information; generating response information based on the search results and generative results; and displaying the response information.

[0007] According to some other embodiments of this disclosure, an interactive device is provided, comprising: a determining module configured to, in response to user input information, determine search results and generative results based on the input information, wherein the search results and generative results are associated, and the genre type in the search results is determined based on intent information represented by the input information; a generating module configured to generate response information based on the search results and generative results; and a display module configured to display the response information.

[0008] According to further embodiments of the present disclosure, an electronic device is provided, including: a processor; and a memory coupled to the processor for storing instructions that, when executed by the processor, cause the processor to perform an interactive method of any embodiment of the present disclosure.

[0009] According to further embodiments of the present disclosure, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, performs the interactive method of any embodiment of the present disclosure.

[0010] According to further embodiments of the present disclosure, a computer program product is provided, comprising: instructions that, when executed by a processor, implement the interaction method of any embodiment of the present disclosure.

[0011] According to further embodiments of the present disclosure, a computer program is provided, comprising: instructions that, when executed by a processor, implement the interactive method of any embodiment of the present disclosure.

[0012] Other features, aspects, and advantages of this disclosure will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0013] Preferred embodiments of the present disclosure are described below with reference to the accompanying drawings. The accompanying drawings, which are included to provide a further understanding of the present disclosure, and which, together with the following detailed description, are incorporated in and form a part of this specification and are used to explain the present disclosure. It should be understood that the drawings described below only relate to some embodiments of the present disclosure and are not intended to limit the present disclosure. In the drawings:

[0014] Figure 1 shows a flowchart illustrating the interaction methods of some embodiments of this disclosure;

[0015] Figures 2 to 5 show schematic diagrams of interactive interfaces of some embodiments of this disclosure;

[0016] Figure 6 shows a schematic diagram of the structure of an interactive device according to some embodiments of the present disclosure;

[0017] Figure 7 shows a schematic diagram of the structure of an electronic device according to some embodiments of the present disclosure;

[0018] Figure 8 shows a schematic diagram of the structure of a computer system according to some embodiments of the present disclosure.

[0019] It should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not necessarily drawn to actual scale. The same or similar reference numerals are used in the various drawings to denote the same or similar parts. Therefore, once an item is defined in one drawing, it may not be discussed further in subsequent drawings. Detailed Implementation

[0020] The technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. However, it is obvious that the described embodiments are only some embodiments of this disclosure, and not all embodiments. The following description of the embodiments is merely illustrative and is in no way intended to limit this disclosure or its application or use. It should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein.

[0021] It should be understood that the various steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect. Unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of components and steps set forth in these embodiments should be interpreted as merely exemplary and do not limit the scope of this disclosure.

[0022] As used in this disclosure, the term "comprising" and its variations are open-ended terms that include at least the following elements / features but do not exclude other elements / features, i.e., "including but not limited to". Furthermore, as used in this disclosure, the term "including" and its variations are open-ended terms that include at least the following elements / features but do not exclude other elements / features, i.e., "including but not limited to". Therefore, "comprising" and "including" are synonymous. The term "based on" means "at least partially based on".

[0023] Throughout this specification, the terms "one embodiment," "some embodiments," or "embodiment" mean that a specific feature, structure, or characteristic described in connection with an embodiment is included in at least one embodiment of the invention. For example, the term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; and the term "some embodiments" means "at least some embodiments." Furthermore, the appearance of the phrases "in one embodiment," "in some embodiments," or "in an embodiment" in various places throughout the specification does not necessarily refer to the same embodiment, but may refer to the same embodiment.

[0024] It should be noted that the concepts of "first," "second," etc., used in this disclosure are used only to distinguish different devices, modules, or units, and are not intended to define the order of functions performed by these devices, modules, or units or their interdependencies. Unless otherwise specified, the concepts of "first," "second," etc., are not intended to imply that the objects described herein must be in a given temporal, spatial, rank, or any other given order.

[0025] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0026] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0027] The embodiments of this disclosure are described in detail below with reference to the accompanying drawings; however, this disclosure is not limited to these specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. Furthermore, in one or more embodiments, specific features, structures, or characteristics can be combined in any suitable manner that will be apparent to those skilled in the art from this disclosure.

[0028] Interactive AI applications, such as agents and bots, typically generate responses directly from user input, such as text. However, these responses often lack information density in certain scenarios. For example, a user might input, "What was the most exciting basketball game recently?" If the response is merely a text description of the game, it's difficult to clearly explain how exciting it was, and the lengthy text might be unappealing to the user, resulting in a unsatisfactory response. Therefore, interactive AI applications that simply generate results based on user input often fail to meet the needs and intentions of users in certain scenarios, and struggle to provide accurate and appropriate responses.

[0029] This disclosure proposes an interaction method that can generate more accurate and appropriate response information based on user input, improving the matching degree between the response information and the user's intent, and enhancing the interaction effect. Some embodiments of the interaction method of this disclosure are described below with reference to Figures 1-5.

[0030] Figure 1 is a flowchart of some embodiments of the interaction method of this disclosure. As shown in Figure 1, the interaction method of this embodiment includes steps S102 to S106. The method of this embodiment can be implemented by a client. The client can be implemented in software, hardware, or a combination of software and hardware. For example, the client is an interactive AI application (e.g., Agent, Bot), or the client is a terminal, not limited to the examples given.

[0031] In step S102, in response to user input information, search results and generative results are determined based on the input information.

[0032] In some embodiments, search results are associated with generative results, where the genre type (or media type) in the search results is determined based on the intent information represented by the input information.

[0033] Users can input information via text, voice, or other means in the interactive interface displayed on the client side; there are no restrictions on the form of the input. Based on the user's input, search results and generated results can be obtained. Search results are stored content retrieved from the database based on the input information, and the genre of the search results matches the intent expressed by the input information. The input information can explicitly or implicitly express the user's intent to request one or more target genres. Determining the genre of the search results based on the intent expressed by the input information improves the accuracy of the search results, thereby improving the accuracy of the final response. For example, if the input information expresses the user's intent to request video, then the search results will include video as a genre.

[0034] The generated results can be obtained using generative models, such as LLM models, and are not limited to the examples given. Search results and generative results are interconnected and not entirely independently determined. For example, generative results may be generated based on search results, and / or search results may be selected based on generative results. The interconnectedness and mutual influence between search results and generative results ensure that the final generated response is a cohesive whole, rather than two completely separate parts. This enhances the interactive experience and provides users with more accurate, natural, and fluent responses.

[0035] In step S104, response information is generated based on the search results and the generative results.

[0036] Search results and generated results can be combined according to a preset layout to serve as response information. Search results can include one or more. For example, if there are multiple search results, they can be sorted based on the relevance of each search result to the input information and / or the relevance of each search result to the generated results; or, they can be sorted based on at least one of the following: the relevance of each search result to the input information, the relevance of each search result to the generated results, and access data for each search result. Access data for search results may include at least one of the following: number of views, number of likes, number of shares, and number of comments. The layout of search results and generated results can be set according to the actual scenario and is not limited here.

[0037] The response information includes not only generated results but also search results. For example, if a user enters "What was the most exciting basketball game recently?", the response information can include not only generated results describing the basketball game but also videos of the basketball game found through the search. This makes the response information richer and more accurate, providing a more appropriate answer to the user's question and improving the interaction.

[0038] In step S106, the response information is displayed.

[0039] For example, the response information is displayed in the client's interactive interface. For instance, during an interaction between the agent and the user, the user inputs information, the agent generates a response based on the above method, and displays the response sent by the agent in the interaction interface between the agent and the user.

[0040] In the method of the above embodiments, after the user inputs information, search results and generative results are determined based on the input information. Response information is then generated based on the search results and generative results and displayed. Since the response information includes not only generative results but also search results, combining the two results results in higher information density and richer content. This makes it applicable to different scenarios, providing users with more targeted, accurate, and appropriate responses, thus improving the interaction effect. Furthermore, the search results and generative results in the response information are interconnected, rather than completely independent, making the content of the response information a cohesive whole, rather than two separate parts, further enhancing the interaction effect. Furthermore, the genre type of the search results is determined based on the intent expressed by the input information. The search results better match the user's intent, providing the user with the genre type of content they want to see, further improving the accuracy of the response information and enhancing the interaction effect.

[0041] The following examples illustrate how to determine search results and generative results based on input information.

[0042] In some embodiments, query information is generated based on the input information; a search is performed based on the query information to obtain search results; and the generative result is generated based on the input information and the search results.

[0043] User input is described in natural language and may contain repetitive words or modifiers. Machine learning models (e.g., LLM) can simplify the input based on its semantics, generating a query. A search is then performed based on this query, and the search results can be obtained through a search chain. Transforming input information into query information improves search accuracy and efficiency. After obtaining the search results, generative results are determined based on both the input and the search results. Generative results are generated not only from the input information but also from the search results, creating a correlation between them. Generative results can be obtained through a generative chain.

[0044] In some embodiments, based on the semantic information of the input information, it is determined whether the input information includes intent information about the user's demand for one or more target genres; in response to the input information including intent information about the user's demand for one or more target genres, one or more target genres and search keywords are determined, and query information is generated.

[0045] A user's intent regarding their need for one or more target genres can be explicitly or implicitly represented in the input information, depending on the semantics of the input. For example, machine learning models can be used to understand the input information, determine its semantics, and then identify whether the input information includes the user's intent regarding their need for one or more target genres. For instance, if a user inputs, "I want some introductory videos about the Great Wall, and also generate a text describing the Great Wall," the input explicitly indicates that the user needs search results for the video genre. Conversely, if a user inputs, "What was the most exciting basketball game recently?", the input implicitly indicates that the user needs search results for the video genre.

[0046] In some embodiments, based on the semantic information of the input information, the domain related to the input information is determined, and based on the domain related to the input information, the user's intent information regarding their need for one or more target genres is determined. For example, if the input information is related to fields such as travel, film and television, game tutorials, and fitness tutorials, it can be determined that the user needs video and / or images as target genres. For example, if the input information is related to fields such as news and encyclopedias, it can be determined that the user needs text and / or images as target genres. The correspondence between domains and target genres is not limited to the examples given above.

[0047] In response to the input information not including the user's intent to request one or more target genres, one or more preset genres are used as target genres. For example, images and / or videos are used as target genres. In some embodiments, in response to the input information not including the user's intent to request one or more target genres, search keywords are extracted; query information is generated based on the search keywords and preset genres. Even if the user does not express a need for one or more target genres, search results for one or more target genres can still be provided to the user, improving the richness of the content in the response information.

[0048] After determining the target genre, the target genre and search keywords are used to generate query information. If different genre-specific databases are set up, searches can be performed within the corresponding databases based on the target genre, resulting in fast and accurate search results. If different domain-specific databases are set up, searches can also be performed within relevant domain-specific databases based on the input information, target genre, and search keywords, improving search efficiency and accuracy.

[0049] After obtaining the search results, a generative result is determined based on the input information and the search results. For example, the input information and search results are fed into a machine learning model to obtain the output generative result. In some embodiments, the content of the search results is summarized to obtain summary information; the generative result is then generated based on the input information and the summary information.

[0050] For example, in response to search results including images, the image is recognized, and summary information is generated based on the recognition results. For instance, images related to fitness tutorials may include a person's movements and descriptive text about those movements. The actions and descriptive text can be recognized to generate summary information.

[0051] For example, in response to search results including videos, the video is identified, and summary information is generated based on the identification results. Video identification can include identifying subtitles, images, sounds, etc., in the video, and then generating summary information based on the identification results.

[0052] For example, in response to search results including audio, the audio is recognized, and summary information is generated based on the recognition results. Speech recognition methods can be used to recognize the audio, and then summary information is generated based on the recognition results.

[0053] For example, generative results can be in various formats such as text and audio. The format of generative results differs at least partially from that of search results, providing users with a wider range of content. Generative results not only summarize and relate to search results, but also provide accurate responses based on the input information.

[0054] The information users input in different situations can express different needs and intentions regarding search results. If users have a strong need for search results, then the search results need to account for a larger proportion in the response information. Search results can have a greater impact on the generated results, thereby enabling the response information to better meet the user's needs.

[0055] In some embodiments, the degree of user demand for the search results is determined based on the semantic information of the input information; the generative result is generated based on the degree of user demand for the search results, the summary information, and the input information, wherein the higher the degree of user demand for the search results, the greater the influence of the summary information on the generative result.

[0056] Machine learning models can be used to perform semantic recognition on the input information to determine the user's level of demand for search results. For example, if the user clearly expresses their desired search results in their input, it can be determined that the user has a high level of demand for the search results. For instance, if the user inputs, "I want some introductory videos about the Great Wall, and also generate a text description of the Great Wall," it clearly expresses a need for search results containing introductory videos about the Great Wall.

[0057] For example, machine learning models can be used to determine generative results based on the demand level of search results, summary information, input information, and prompts. Constraints can be set in the prompts to indicate that the higher the demand level of the search results, the greater the influence of the summary information on the generative results. This allows machine learning to generate different generative results tailored to different user needs, improving the interactive experience.

[0058] Furthermore, in some embodiments, the domain related to the input information is determined based on the semantic information of the input information; and the degree of user demand for the search results is determined based on the domain related to the input information.

[0059] For example, multiple domain categories can be defined, each containing one or more subcategories, with different categories corresponding to different levels of demand. For instance, fashion, travel, film and television, game tutorials, and fitness tutorials belong to one domain category, corresponding to a high level of demand. Conversely, news and encyclopedias belong to another domain category, corresponding to a low level of demand. The division of domain categories and levels of demand can be determined based on the specific circumstances and is not limited to the examples given.

[0060] The role of search results as part of the response varies across different domains. In some domains, providing search results such as images and videos can effectively reduce the cognitive load of the response and enhance visual appeal; therefore, users have a higher demand for search results in these domains. Conversely, in other domains, search results play a limited auxiliary role, and users have a lower demand for them. Therefore, determining the user's demand for search results based on the domain of the input information, and then determining the generative results accordingly, can improve the matching degree between the response and the user's intent, increase the accuracy of the response, and enhance the interaction effect.

[0061] In some embodiments, the user's level of demand for search results is determined based on the semantic information of the input information; the target number of search results is then determined based on this level of demand. The higher the user's level of demand for search results, the larger the target number. After obtaining the target number of search results, the target number of search results is summarized to obtain summary information. Based on the user's level of demand for search results, the summary information, and the input information, the generative result is generated.

[0062] The higher the user's demand for search results, the more search results they will obtain, the richer the content contained in the search results will be, and the greater the impact on the generated results will be. As a result, the content in the response information will be richer, and the interaction effect will be improved.

[0063] In the above embodiments, search results are first obtained based on the input information, and then generative results are determined based on the input information and the search results. The following describes some other embodiments on how to determine search results and generative results based on the input information.

[0064] In some embodiments, multiple candidate search results are obtained based on the input information; the generative result is generated based on the input information; and one or more candidate search results are selected from the multiple candidate search results as search results based on the relevance between the multiple candidate search results and the generative result.

[0065] For example, based on the input information, query information is generated; based on the query information, a search is performed to obtain multiple candidate search results. The method for obtaining multiple candidate search results can be referred to the aforementioned embodiment for obtaining search results, and will not be repeated here.

[0066] Multiple search results and generative results can be generated simultaneously using both search and generative links. The relevance of each search result to the generative result is then determined. Based on the relevance of each candidate search result to the generative result, one or more candidate search results with a relevance greater than a threshold are selected as the search results. If no candidate search results with a relevance greater than the threshold exist, or if the selected candidate search results do not meet the preset number, the generative result is redefined, or multiple candidate search results are reacquired, and then a new candidate search result is selected.

[0067] By selecting candidate search results as search results based on the generative results, we can obtain related generative results and search results, making the content in the response information interconnected as a whole, rather than two separate parts, thus improving the interaction effect.

[0068] In some embodiments, the degree of user demand for search results is determined based on the semantic information of the input information; multiple candidate search results are obtained based on the degree of user demand for search results and the input information, wherein the higher the degree of user demand for search results, the more candidate search results are obtained.

[0069] The more candidate search results obtained, the richer the content, and the more content the selected search results will contain, thus improving the interactive experience.

[0070] In some embodiments, in response to input information including user intent information regarding a need for one or more target genres, the genres of the multiple candidate search results include one or more target genres, and one or more candidate search results that match one or more target genres are selected from the multiple candidate search results based on the relevance of the multiple candidate search results to the generative results.

[0071] If a user's need for one or more target genres is determined, then the selected one or more candidate search results need to match one or more target genres in order to provide the user with accurate response information.

[0072] There can be multiple candidate search results, that is, there can be multiple search results. In some embodiments, the display order of multiple search results is determined according to the relevance of multiple search results to the generative result; according to the display order of multiple search results, the multiple search results in the response information are laid out and displayed.

[0073] The display order of multiple search results can be determined based on their relevance to the generated results. The search results most relevant to the generated results can be placed in the positions most easily seen by users, improving the display and interaction effects.

[0074] Regarding how to determine search results and generated results based on input information, the aforementioned embodiments provide two methods: one is to obtain search results and determine generated results based on the input information and search results; the other is to obtain multiple candidate search results and generated results, and select one or more candidate search results as the search results based on the relevance between the multiple candidate search results and the generated results. These two methods can be used in combination.

[0075] In some embodiments, multiple candidate search results are obtained based on the input information; the generative result is generated based on the input information; one or more candidate search results are selected from the multiple candidate search results as search results based on the relevance between the multiple candidate search results and the generative result; and the generative result is rewritten based on the search results.

[0076] The content of the search results can be summarized to obtain summary information, which can then be used to rewrite the generative results. The rewritten generative results can incorporate more information from the search results, making the correlation between the two better.

[0077] In some embodiments, multiple candidate search results are obtained based on the input information; the generative result is generated based on the input information; one or more candidate search results are selected from the multiple candidate search results based on the relevance between the multiple candidate search results and the generative result; if the number of candidate search results with a relevance greater than a threshold cannot meet the preset number, a preset number of candidate search results are selected from the multiple candidate search results as search results; and the generative result is redefined based on the search results and the input information.

[0078] The method for redetermining the generative result can refer to the foregoing embodiments and will not be repeated here. A preset number of candidate search results are selected from multiple candidate search results, which can be based on the relevance of the multiple candidate search results to the generative result and / or the access data of the multiple candidate results. Access data includes, for example, at least one of the following: number of views, number of likes, number of shares, and number of comments.

[0079] In the above embodiments, the response information includes search results and generated results. In some cases, users may not need search results or generated results, and the response information may only include generated results or search results, thereby improving the efficiency of response information generation.

[0080] In some embodiments, determining the user's demand type based on the input information; determining the search results and generated results based on the input information includes: in response to the demand type being a first type, determining the search results and generated results based on the input information, wherein the first type indicates that the user has a demand for both search results and generated results.

[0081] In some embodiments, in response to a second type of demand, search results are determined and displayed based on the input information, wherein the second type indicates that the user only has a demand for search results; and / or in response to a third type of demand, generative results are determined and displayed based on the input information, wherein the third type indicates that the user only has a demand for generative results.

[0082] The user's need type can be determined based on the semantic information of the input. For example, if the user inputs "I want some cherry blossom wallpapers," it indicates that the user only needs search results, so the need type can be determined as type two. Conversely, if the user inputs "Help me write a story," it indicates that the user only needs generative results, so the need type can be determined as type three.

[0083] Based on the input information, determine the user's needs for search results and generated results, and provide different types of response information to the user according to different needs, thereby improving the efficiency of response information generation while meeting user needs.

[0084] The following are some application examples of the interactive method disclosed herein, as shown in Figures 2-5.

[0085] Figure 2 shows the interaction interface between the user and the intelligent agent A. The user input information 201 is "pictures of car X". The response information 202 includes multiple images of car X. The number and layout of the images can be set according to the actual situation. For example, if Figure 2 displays 4 images, and there are a total of 5 images, a "+1" prompt symbol can be displayed to indicate that one image has not yet been displayed. In response to the user triggering control 203, the remaining image can be displayed. The display of the remaining images can also be triggered by swiping or other methods, and is not limited to the example given. The response information 202 can also include "These are the pictures I found for you" as guiding information to guide the user to view the images.

[0086] In some embodiments, where the response information includes an image, the image is enlarged in response to a user's triggering action on the image. The user can trigger the enlarged image display through actions such as clicking.

[0087] As shown in Figure 3, the user input information 301 is "New appearance of Y car". The response information 302 includes multiple images of the new appearance of Y car, as well as descriptive text describing the appearance features of Y car. This descriptive text can be generated based on the images. In response to the user triggering control 303, the remaining text and images can be displayed, or in response to the user triggering the "+7" prompt symbol, the remaining images can be displayed, not limited to the examples given.

[0088] As shown in Figure 4, the user input information 401 is "Beijing attractions videos". The response information 402 includes videos of multiple Beijing attractions, and may also include "These are the videos I found for you" as guiding information to encourage the user to view the videos. Multiple videos can be included; if any videos are not displayed, the remaining videos can be displayed in response to the user triggering control 403.

[0089] In some embodiments, where the response information includes a video, the video is played in response to a user's triggering action on the video. For example, a user can trigger video playback by clicking the video, clicking the play control, or other actions. The video can be played in a new page, overlay, window, etc., and is not limited to the examples given.

[0090] As shown in Figure 5, the user input 501 is "Recommend a recent movie," and the response 502 includes a descriptive text of the recommended movie and an introductory video. In response to the user's trigger action on the video, the video can be played.

[0091] In some embodiments, where the response information includes audio, the audio is played in response to a user's triggering action on the audio. For example, the user triggers audio playback by clicking the audio file, clicking the play control, or other similar actions.

[0092] This disclosure also provides an interactive device, which will be described below with reference to FIG6.

[0093] Figure 6 is a structural diagram of some embodiments of the interactive device of this disclosure. As shown in Figure 6, the interactive device 60 of this embodiment includes: a determining module 610, a generating module 620, and a display module 630.

[0094] The determination module 610 is configured to respond to user input information and determine search results and generative results based on the input information, wherein the search results and generative results are associated, and the genre type in the search results is determined based on the intent information represented by the input information.

[0095] The generation module 620 is configured to generate response information based on the search results and the generative results.

[0096] Display module 630 is configured to display response information.

[0097] In some embodiments, the determining module 610 is configured to generate query information based on the input information; perform a search based on the query information to obtain search results; and generate the generative result based on the input information and the search results.

[0098] In some embodiments, the determining module 610 is configured to determine, based on the semantic information of the input information, whether the input information includes intent information about the user's demand for one or more target genres; and in response to the input information including intent information about the user's demand for one or more target genres, to determine one or more target genres and search keywords, and to generate query information.

[0099] In some embodiments, the determining module 610 is configured to summarize the content of the search results to obtain summary information; and generate the generative result based on the input information and the summary information.

[0100] In some embodiments, the determining module 610 is configured to determine the degree of user demand for the search results based on the semantic information of the input information; and to generate the generative result based on the degree of user demand for the search results, summary information, and input information, wherein the higher the degree of user demand for the search results, the greater the influence of the summary information on the generative result.

[0101] In some embodiments, the determining module 610 is configured to determine the domain related to the input information based on the semantic information of the input information; and to determine the degree of user demand for the search results based on the domain related to the input information.

[0102] In some embodiments, the determining module 610 is configured to extract search keywords in response to the input information not including intent information of the user’s need for one or more target genres; and generate query information based on the search keywords and preset genres.

[0103] In some embodiments, the determining module 610 is configured to obtain multiple candidate search results based on input information; generate the generative result based on the input information; and select one or more candidate search results from the multiple candidate search results as search results based on the relevance between the multiple candidate search results and the generative result.

[0104] In some embodiments, in response to input information including user intent information regarding a need for one or more target genres, and the genres of the multiple candidate search results including one or more target genres, the determining module 610 is configured to select one or more candidate search results that conform to one or more target genres from the multiple candidate search results based on the relevance of the multiple candidate search results to the generative results.

[0105] In some embodiments, the determining module 610 is configured to determine the degree of user demand for search results based on the semantic information of the input information; and to obtain multiple candidate search results based on the degree of user demand for search results and the input information, wherein the higher the degree of user demand for search results, the more candidate search results are obtained.

[0106] In some embodiments, the search results include multiple results, and the display module 630 is configured to determine the display order of the multiple search results based on the relevance of the multiple search results to the generative results; and to lay out and display the multiple search results in the response information according to the display order of the multiple search results.

[0107] In some embodiments, the determining module 610 is further configured to determine the user's demand type based on the input information; and in response to the demand type being a first type, to determine the search results and generative results based on the input information, wherein the first type indicates that the user has a demand for both the search results and the generative results.

[0108] In some embodiments, the determining module 610 is further configured to, in response to a second type of demand, determine search results based on the input information and display the search results, wherein the second type indicates that the user only has a demand for search results; and / or, in response to a third type of demand, determine generative results based on the input information and display the generative results, wherein the third type indicates that the user only has a demand for generative results.

[0109] In some embodiments, the display module 630 is further configured to perform at least one of the following: if the response information includes an image, to enlarge and display the image in response to a user's triggering operation on the image; if the response information includes a video, to play the video in response to a user's triggering operation on the video; and if the response information includes audio, to play the audio in response to a user's triggering operation on the audio.

[0110] It should be noted that the above-described units (modules) are logical modules divided according to their specific functions, and are not intended to limit the specific implementation method. For example, they can be implemented in software, hardware, or a combination of both. In actual implementation, the above-described units can be implemented as independent physical entities, or they can be implemented by a single entity (e.g., a processor (CPU or DSP, etc.), integrated circuit, etc.). Furthermore, the units shown in the accompanying drawings with dashed lines indicate that these units may not actually exist, and the operations / functions they perform can be implemented by the processing circuitry itself.

[0111] In addition, although not shown, the device may also include a memory that can store various information generated by the device and its constituent units during operation, programs and data used for operation, data to be transmitted by the communication unit, etc. The memory can be volatile memory and / or non-volatile memory. For example, the memory may include, but is not limited to, random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), read-only memory (ROM), and flash memory. Of course, the memory may also be located outside the device. Optionally, although not shown, the device may also include a communication unit that can be used to communicate with other devices. In one example, the communication unit can be implemented in a manner known in the art, such as including communication components such as antenna arrays and / or radio frequency links, various types of interfaces, communication units, etc. These will not be described in detail here. Furthermore, the device may also include other components not shown, such as radio frequency links, baseband processing units, network interfaces, processors, controllers, etc. These will not be described in detail here.

[0112] Some embodiments of this disclosure also provide an electronic device. Figure 7 shows a block diagram of some embodiments of the electronic device of this disclosure. For example, in some embodiments, the electronic device 70 can be various types of devices, such as mobile terminals including, but not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs, desktop computers, etc. For example, the electronic device 70 may include a display panel for displaying data and / or execution results utilized in the scheme according to this disclosure. For example, the display panel can be of various shapes, such as a rectangular panel, an elliptical panel, or a polygonal panel. In addition, the display panel can be not only a planar panel, but also a curved panel, or even a spherical panel.

[0113] As shown in FIG. 7, the electronic device 70 of this embodiment includes a memory 71 and a processor 72 coupled to the memory 71. It should be noted that the components of the electronic device 70 shown in FIG. 7 are merely exemplary and not limiting; the electronic device 70 may also have other components depending on the actual application requirements. The processor 72 can control other components in the electronic device 70 to perform desired functions.

[0114] In some embodiments, memory 71 is used to store one or more computer-readable instructions. When processor 72 executes the computer-readable instructions, the computer-readable instructions are executed by processor 72 to implement the method according to any of the above embodiments. For specific implementations and related explanations of the various steps of the method, please refer to the above embodiments; repeated details will not be elaborated here.

[0115] For example, processor 72 and memory 71 can communicate with each other directly or indirectly. For example, processor 72 and memory 71 can communicate via a network. The network can include wireless networks, wired networks, and / or any combination of wireless and wired networks. Processor 72 and memory 71 can also communicate with each other via a system bus, which is not limited in this disclosure.

[0116] For example, processor 72 can be embodied in various suitable processors, processing devices, such as central processing unit (CPU), graphics processing unit (GPU), network processor (NP), etc.; it can also be digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The central processing unit (CPU) can be an x86 or ARM architecture, etc. For example, memory 71 can include any combination of various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. Memory 71 can include, for example, system memory, which stores, for example, the operating system, application programs, boot loader, database, and other programs. Various application programs and various data can also be stored in the storage medium.

[0117] Furthermore, according to some embodiments of this disclosure, various operations / processes according to this disclosure, implemented via software and / or firmware, can install programs constituting the software from a storage medium or network onto a computer system with a dedicated hardware architecture, such as the computer system (or electronic device) 80 shown in FIG. 8. When various programs are installed, the computer system is capable of performing various functions, including those described above. FIG. 8 is a block diagram illustrating an example structure of a computer system that may be employed in an embodiment of this disclosure.

[0118] In Figure 8, the Central Processing Unit (CPU) 801 performs various processes based on a program stored in the Read-Only Memory (ROM) 802 or a program loaded from the Storage Section 808 into the Random Access Memory (RAM) 803. The RAM 803 also stores data required as needed when the CPU 801 performs various processes. The CPU is merely exemplary and can be other types of processors, such as the various processors described above. The ROM 802, RAM 803, and Storage Section 808 can be various forms of computer-readable storage media, as described below. It should be noted that although the ROM 802, RAM 803, and Storage Section 808 are shown separately in Figure 8, one or more of them can be combined or located in the same or different memories or storage modules.

[0119] CPU 801, ROM 802 and RAM 803 are interconnected via bus 804. Input / output interface 805 is also connected to bus 804.

[0120] The following components are connected to the input / output interface 805: input section 806, such as a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output section 807, including displays such as cathode ray tube (CRT), liquid crystal display (LCD), speakers, vibrators, etc.; storage section 808, including hard disks, magnetic tapes, etc.; and communication section 809, including network interface cards such as LAN cards, modems, etc. The communication section 809 allows communication processing to be performed via a network such as the Internet. It is readily understood that although the various devices or modules in the computer system 80 shown in Figure 8 communicate via bus 804, they can also communicate via a network or other means, wherein the network can include wireless networks, wired networks, and / or any combination of wireless and wired networks.

[0121] As needed, drive 810 is also connected to input / output interface 805. Removable media 811, such as disks, optical disks, magneto-optical disks, semiconductor memories, etc., are installed on drive 810 as needed, so that computer programs read from them can be installed into storage section 808 as needed.

[0122] When the above series of processes are implemented through software, the program constituting the software can be installed from a network such as the Internet or from a storage medium such as removable media 811.

[0123] According to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 809, or installed from a storage device 808, or installed from a ROM 802. When the computer program is executed by the CPU 801, it performs the functions defined in the methods of embodiments of this disclosure.

[0124] It should be noted that, in the context of this disclosure, a computer-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, capable of transmitting, propagating, or transmitting a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0125] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0126] In some embodiments, a computer program is also provided, comprising: instructions that, when executed by a processor, cause the processor to perform the interactive method of any of the above embodiments. For example, the instructions may be embodied in computer program code.

[0127] In embodiments of this disclosure, computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include, but are not limited to, object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network (including a local area network (LAN) or a wide area network (WAN)), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0128] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0129] The modules, components, or units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the modules, components, or units do not necessarily constitute a limitation on the module, component, or unit itself.

[0130] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary hardware logic components that can be used include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0131] According to some embodiments of this disclosure, an interaction method is provided, comprising: responding to user input information, determining search results and generative results based on the input information, wherein the search results and generative results are associated, and the genre type of the search results is determined based on the intent information represented by the input information; generating response information based on the search results and generative results; and displaying the response information.

[0132] In some embodiments, determining the search results and generative results based on the input information includes: generating query information based on the input information; performing a search based on the query information to obtain the search results; and generating the generative results based on the input information and the search results.

[0133] In some embodiments, generating query information based on input information includes: determining whether the input information includes intent information indicating a user's need for one or more target genres based on the semantic information of the input information; and, in response to the input information including intent information indicating a user's need for one or more target genres, determining one or more target genres and search keywords, and generating query information.

[0134] In some embodiments, generating the generative result based on the input information and the search results includes: summarizing the content of the search results to obtain summary information; and generating the generative result based on the input information and the summary information.

[0135] In some embodiments, generating the generative result based on input information and summary information includes: determining the degree of user demand for the search results based on the semantic information of the input information; and generating the generative result based on the degree of user demand for the search results, the summary information, and the input information, wherein the higher the degree of user demand for the search results, the greater the influence of the summary information on the generative result.

[0136] In some embodiments, determining the degree of user demand for search results based on the semantic information of the input information includes: determining the domain related to the input information based on the semantic information of the input information; and determining the degree of user demand for search results based on the domain related to the input information.

[0137] In some embodiments, generating query information based on the input information further includes: extracting search keywords in response to the input information not including intent information of the user's need for one or more target genres; and generating query information based on the search keywords and preset genres.

[0138] In some embodiments, determining the search results and the generative result based on the input information includes: obtaining multiple candidate search results based on the input information; generating the generative result based on the input information; and selecting one or more candidate search results from the multiple candidate search results as the search results based on the relevance between the multiple candidate search results and the generative result.

[0139] In some embodiments, in response to input information including user intent information regarding a need for one or more target genres, the genres of the multiple candidate search results include one or more target genres, and selecting one or more candidate search results from the multiple candidate search results based on the relevance of the multiple candidate search results to the generated results includes: selecting one or more candidate search results that conform to one or more target genres from the multiple candidate search results based on the relevance of the multiple candidate search results to the generated results.

[0140] In some embodiments, obtaining multiple candidate search results based on input information includes: determining the degree of user demand for search results based on the semantic information of the input information; and obtaining multiple candidate search results based on the degree of user demand for search results and the input information, wherein the higher the degree of user demand for search results, the more candidate search results are obtained.

[0141] In some embodiments, the search results include multiple results, and displaying the response information includes: determining the display order of the multiple search results based on their relevance to the generative results; and laying out and displaying the multiple search results in the response information according to their display order.

[0142] In some embodiments, the interaction method further includes: determining the user's demand type based on the input information; wherein determining the search results and generative results based on the input information includes: in response to the demand type being a first type, determining the search results and generative results based on the input information, wherein the first type indicates that the user has a demand for both the search results and the generative results.

[0143] In some embodiments, the interaction method further includes at least one of the following: in response to a second type of demand, determining and displaying search results based on input information, wherein the second type indicates that the user only has a demand for search results; and in response to a third type of demand, determining and displaying generative results based on input information, wherein the third type indicates that the user only has a demand for generative results.

[0144] In some embodiments, the interaction method further includes at least one of the following: when the response information includes an image, in response to a user's triggering operation on the image, enlarging and displaying the image; when the response information includes a video, in response to a user's triggering operation on the video, playing the video; when the response information includes audio, in response to a user's triggering operation on the audio, playing the audio.

[0145] According to some other embodiments of this disclosure, an interactive device is provided, comprising: a determining module configured to determine search results and generative results in response to user input information, wherein the search results and generative results are associated, and the genre type in the search results is determined based on intent information represented by the input information; a generating module configured to generate response information based on the search results and generative results; and a display module configured to display the response information.

[0146] According to further embodiments of the present disclosure, an electronic device is provided, including: a processor; and a memory coupled to the processor for storing instructions that, when executed by the processor, cause the processor to perform an interactive method of any embodiment of the present disclosure.

[0147] According to further embodiments of the present disclosure, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, performs the interactive method of any embodiment of the present disclosure.

[0148] According to further embodiments of the present disclosure, a computer program product is provided, comprising: instructions that, when executed by a processor, implement the interaction method of any embodiment of the present disclosure.

[0149] According to further embodiments of the present disclosure, a computer program is provided, comprising: instructions that, when executed by a processor, implement the interactive method of any embodiment of the present disclosure.

[0150] The above description is merely an embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0151] Many specific details are set forth in the description provided herein. However, it is understood that embodiments of the invention may be practiced without these specific details. In other instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of the description.

[0152] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0153] While specific embodiments of this disclosure have been described in detail by way of example, those skilled in the art should understand that the examples are for illustrative purposes only and not intended to limit the scope of this disclosure. Those skilled in the art should understand that modifications can be made to the above embodiments without departing from the scope and spirit of this disclosure. The scope of this disclosure is defined by the appended claims.

Claims

1. An interaction method, comprising: In response to user input, search results and generative results are determined based on the input information, wherein the search results and generative results are associated, and the genre type of the search results is determined based on the intent information represented by the input information; Based on the search results and the generative results, generate response information; The response information is displayed.

2. The interaction method according to claim 1, wherein, The process of determining the search results and generative results based on the input information includes: Generate query information based on the input information; The search results are obtained based on the query information. The generative result is generated based on the input information and the search results.

3. The interaction method according to claim 2, wherein, The process of generating query information based on the input information includes: Based on the semantic information of the input information, determine whether the input information includes the user's intent information regarding their needs for one or more target genres; In response to the input information, including the user's intent information regarding their need for one or more target genres, the one or more target genres and search keywords are determined, and the query information is generated.

4. The interaction method according to claim 2 or 3, wherein, The step of generating the generative result based on the input information and the search results includes: The content of the search results is summarized to obtain summary information; The generative result is generated based on the input information and the summary information.

5. The interaction method according to claim 4, wherein, The step of generating the generative result based on the input information and the summary information includes: Based on the semantic information of the input information, determine the degree of the user's need for the search results; The generative result is generated based on the user's demand for the search results, the summary information, and the input information, wherein the higher the user's demand for the search results, the greater the influence of the summary information on the generative result.

6. The interaction method according to claim 5, wherein, Determining the user's level of need for the search results based on the semantic information of the input information includes: Based on the semantic information of the input information, determine the domain related to the input information; Based on the relevant domain of the input information, determine the degree of user demand for the search results.

7. The interaction method according to any one of claims 2-6, wherein, The step of generating query information based on the input information further includes: In response to the fact that the input information does not include the user's intent information regarding their need for one or more target genres, search keywords are extracted; The query information is generated based on the search keywords and the preset genre.

8. The interaction method according to claim 1, wherein, The process of determining the search results and generative results based on the input information includes: Based on the input information, multiple candidate search results are obtained; The generative result is generated based on the input information; Based on the relevance between the multiple candidate search results and the generative result, one or more candidate search results are selected from the multiple candidate search results as the search results.

9. The interaction method according to claim 8, wherein, The information in response to the input includes intent information about the user's demand for one or more target genres, the genres of the plurality of candidate search results include the one or more target genres, and the step of selecting one or more candidate search results from the plurality of candidate search results based on the relevance of the plurality of candidate search results to the generative result includes: Based on the relevance between the multiple candidate search results and the generative result, one or more candidate search results that match the one or more target genres are selected from the multiple candidate search results.

10. The interaction method according to claim 8 or 9, wherein, The step of obtaining multiple candidate search results based on the input information includes: Based on the semantic information of the input information, determine the degree of the user's need for the search results; Based on the user's level of demand for the search results and the input information, multiple candidate search results are obtained, wherein the higher the user's level of demand for the search results, the more candidate search results are obtained.

11. The interaction method according to any one of claims 8-10, wherein, The search results include multiple results, and displaying the reply information includes: The display order of the multiple search results is determined based on their relevance to the generative results. The multiple search results in the response information are laid out and displayed according to their display order.

12. The interaction method according to any one of claims 1-11, further comprising: Based on the input information, determine the user's need type; The step of determining the search results and generative results based on the input information includes: In response to the requirement type being a first type, the search results and the generative results are determined based on the input information, wherein the first type indicates that the user has a requirement for both the search results and the generative results.

13. The interaction method according to claim 12, further comprising at least one of the following: In response to the requirement type being the second type, the search results are determined based on the input information and displayed, wherein... The second type indicates that the user only needs the search results; In response to the requirement type being the third type, the generative result is determined based on the input information and displayed, wherein the third type indicates that the user only requires the generative result.

14. The interaction method according to any one of claims 1-13, further comprising at least one of the following: If the response information includes an image, the image is enlarged and displayed in response to the user's triggering action on the image; If the response information includes a video, the video is played in response to the user's triggering action on the video; If the response information includes audio, the audio is played in response to the user's triggering action on the audio.

15. An interactive device, comprising: The determination module is configured to respond to user input information and determine search results and generative results based on the input information, wherein the search results and the generative results are associated, and the genre type in the search results is determined based on the intent information represented by the input information; The generation module is configured to generate response information based on the search results and the generative results; The display module is configured to display the response information.

16. An electronic device comprising: processor; as well as A memory coupled to the processor is used to store instructions, which, when executed by the processor, cause... The processor executes the interaction method as described in any one of claims 1-14.

17. A computer-readable storage medium having a computer program stored thereon, wherein, When the program is executed by the processor, it implements the interaction method as described in any one of claims 1-14.

18. A computer program product comprising: Instructions, wherein, when executed by a processor, the instructions implement the interaction method according to any one of claims 1-14.

19. A computer program comprising: Instructions, wherein, when executed by a processor, the instructions implement the interaction method according to any one of claims 1-14.

Images