Search method and apparatus, and computer-readable storage medium and computer program product

Abstract

Provided are a search method and apparatus, and a computer-readable storage medium and a computer program product, which relate to the technical field of terminals. The search method comprises: from an interface of a conversation list, acquiring first information input by a user, wherein the conversation list comprises conversations with virtual objects (S102); determining search approaches corresponding to the first information (S104); in response to the first information corresponding to a first search approach, displaying a search result interface (S106); and in response to the first information corresponding to a second search approach, displaying conversation interfaces of the virtual objects, and displaying responses of the virtual objects to the first information in the conversation interfaces (S108).

Description

Search method, device, computer-readable storage medium, and computer program product

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application is based on and claims priority to an application filed in China with application number 202410139586.3 and filing date January 31, 2024. The disclosed content of the Chinese application is hereby introduced as a whole into this application. Technical Field

[0003] The present disclosure relates to the field of terminal technology, and in particular to a search method, device, computer-readable storage medium, and computer program product. Background Art

[0004] In the related art, a user can enter search information in a search page to obtain results corresponding to the search information. After the user triggers the search process, a search engine is usually called to query web pages including the search information and return these web pages to the user.

[0005] Summary of the Invention

[0006] This summary is provided to briefly introduce concepts that will be described in detail in the detailed description below. This summary is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0007] According to some embodiments of the present disclosure, a search method is provided, including: obtaining first information input by a user in a conversation list interface, the conversation list including conversations with a virtual object; determining a search path corresponding to the first information; displaying a search result interface in response to the first information corresponding to the first search path; displaying a conversation interface of the virtual object in response to the first information corresponding to the second search path, and displaying the virtual object's response to the first information on the conversation interface.

[0008] According to other embodiments of the present disclosure, a search device is provided, including: an acquisition module, configured to acquire first information input by a user in a conversation list interface, the conversation list including an entry to a conversation interface of a virtual object; a determination module, configured to determine a search path corresponding to the first information; a first display module, configured to display a search result interface in response to the first information corresponding to the first search path; a second display module, configured to display a conversation interface of the virtual object in response to the first information corresponding to the second search path, and display the virtual object's response to the first information on the conversation interface.

[0009] According to some embodiments of the present disclosure, a search device is provided, including: a memory; and a processor coupled to the memory, wherein the processor is configured to execute the search method of any embodiment of the present disclosure based on instructions stored in the memory.

[0010] According to some embodiments of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the search method of any embodiment of the present disclosure is performed.

[0011] According to some embodiments of the present disclosure, a computer program product is provided. When the computer program product is run on a computer, the computer is enabled to implement the search method of any one of the embodiments of the present disclosure.

[0012] According to some embodiments of the present disclosure, a computer program is provided, comprising: instructions, which, when executed by a processor, cause the processor to perform the search method of any one of the embodiments of the present disclosure.

[0013] Other features, aspects and advantages of the present disclosure will become apparent from the following detailed description of exemplary embodiments of the present disclosure with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The preferred embodiments of the present disclosure are described below with reference to the accompanying drawings. The drawings described herein are used to provide a further understanding of the present disclosure. Each of the drawings, together with the following detailed description, is included in this specification and forms a part of the specification to explain the present disclosure. It should be understood that the drawings described below only relate to some embodiments of the present disclosure and do not constitute a limitation of the present disclosure. In the drawings:

[0015] FIG1 shows a schematic flow chart of a search method according to some embodiments of the present disclosure.

[0016] FIG2 shows a schematic flow chart of a method for automatically determining a search path according to some embodiments of the present disclosure.

[0017] FIG3 shows a schematic diagram of an interface of a conversation list according to some embodiments of the present disclosure.

[0018] 4A and 4B exemplarily show schematic diagrams of interfaces for a user to manually select a search path.

[0019] FIG5 shows a schematic diagram of a search result interface according to some embodiments of the present disclosure.

[0020] FIG6 shows a schematic diagram of a conversation interface of a virtual object according to some embodiments of the present disclosure.

[0021] FIG7 shows a schematic structural diagram of a search device according to some embodiments of the present disclosure.

[0022] FIG8 shows a schematic structural diagram of an electronic device according to some embodiments of the present disclosure.

[0023] FIG9 shows a schematic structural diagram of a computer system according to some embodiments of the present disclosure.

[0024] It should be understood that, for ease of description, the dimensions of the various parts shown in the drawings are not necessarily drawn to scale. The same or similar reference numerals are used throughout the drawings to indicate the same or similar parts. Therefore, once an item is defined in one drawing, it may not be discussed further in subsequent drawings. DETAILED DESCRIPTION

[0025] The following will be combined with the accompanying drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. However, it is obvious that the embodiments described are only some embodiments of the present disclosure, rather than all embodiments. The following description of the embodiments is actually only illustrative and is in no way intended to limit the present disclosure and its application or use. It should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein.

[0026] It should be understood that the various steps described in the method embodiments of the present disclosure can be performed in different orders and / or performed in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect. Unless otherwise specifically stated, the relative arrangement, numerical expressions and numerical values ​​of the parts and steps set forth in these embodiments should be interpreted as being merely exemplary and do not limit the scope of the present disclosure.

[0027] As used in this disclosure, the term "include" and its variations are intended to be 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, the term "comprise" and its variations are intended to be 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, "include" and "include" are synonymous. The term "based on" means "based, at least in part, on."

[0028] Reference throughout this specification to "one embodiment," "some embodiments," or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present 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 appearances of the phrases "in one embodiment," "in some embodiments," or "in an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment, but may.

[0029] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are only used to distinguish different devices, modules, or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules, or units. Unless otherwise specified, concepts such as "first" and "second" are not intended to imply that the objects described in such a manner must be in a given order in time, space, ranking, or any other manner.

[0030] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".

[0031] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0032] The following detailed description of the embodiments of the present disclosure is provided in conjunction with the accompanying drawings, but the present disclosure is not limited to these specific embodiments. The following specific embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments. In addition, in one or more embodiments, specific features, structures, or characteristics may be combined in any suitable manner that will be apparent to those skilled in the art from this disclosure.

[0033] Each record in the search results obtained by the search engine includes part or all of the information entered by the user. However, sometimes the user cannot accurately express the desired search results through the input information, resulting in the need for a secondary search.

[0034] With the development of artificial intelligence technology, users can now chat with intelligent virtual objects to answer questions. These objects are typically based on machine learning models, performing semantic analysis on user input and integrating it with content from a knowledge base to generate responses. However, intelligent virtual objects may sometimes fail to integrate content from the source information to provide responses, resulting in false or illogical responses. This can also result in inaccurate responses to users.

[0035] The present disclosure provides a search method, apparatus, and related devices to solve the problem of how to accurately send feedback information based on information input by a user.

[0036] The present disclosure displays a search result interface based on a first search path or invokes a virtual object based on a second search path for a first information input by a user. This enables more accurate feedback to be provided to the user. An embodiment of the present disclosure's search method is described below with reference to FIG1 .

[0037] Figure 1 shows a schematic flow chart of a search method according to some embodiments of the present disclosure. As shown in Figure 1 , the search method of this embodiment includes steps S102 to S108.

[0038] In step S102, first information input by the user is obtained in the interface of the conversation list, where the conversation list includes conversations with virtual objects.

[0039] "Conversation" refers to a conversation between a user and a virtual object or a real user. The content of the conversation can be in various forms such as text, images, voice, video, or a combination of at least two of the above. A virtual object refers to a response to the user's conversation based on the user's conversation and a machine learning model. In the scenario where a user is conversing with a virtual object, the virtual object can generate corresponding results based on the information entered by the user in the conversation page. Virtual objects can also be called "robots" or "digital humans". They can be intelligent customer service, intelligent assistants, or intelligent objects used in specific fields such as translation and problem solving. The machine learning model that the virtual object relies on can be a foundation model (Foundation Model) or a large language model (Large Language Model, abbreviated as: LLM), which can generally be collectively referred to as a "large model". As needed, the machine learning model can also be other types of models, which will not be detailed here.

[0040] The conversation list includes one or more entries to the conversation pages of virtual objects. These entries may display one or more of the virtual object's avatar, name, profile, and abridged content of historical conversations. Furthermore, the conversation list may also include entries to the conversation pages of real users. When a user wants to communicate with one of the objects (virtual objects or real users), they typically access the conversation page by triggering an entry in the conversation list or searching for the entry to the conversation page of the object.

[0041] In embodiments of the present disclosure, a user may enter first information through the conversation list interface. The first information is used to describe the information the user desires to obtain. If the first information is text, it may be in the form of one or more words, questions, commands, etc. In some embodiments, the first information may be understood as search information. In addition to text, the first information may also be an image, sound, video, or a combination of data in multiple formats.

[0042] In some embodiments, the first information input by the user can be obtained through an input control of the interface of the conversation list, such as a text input box, an upload entry for multimedia files, etc.

[0043] In step S104, a search path corresponding to the first information is determined, wherein the search path includes a first search path and a second search path.

[0044] The determination process may be automatically determined based on the first information or manually determined by the user. In the case of automatic determination, a search path that has a higher degree of matching with the first information may be determined based on the type or intent of the first information as the search path corresponding to the first information.

[0045] In step S106, in response to the first information corresponding to the first search path, a search result interface is displayed. That is, in the case where the first information corresponds to the first search path, responding to the first information through the search result interface will obtain more accurate results.

[0046] The search result interface includes one or more links, and the page corresponding to each link includes part or all of the first information. The search result interface is obtained and returned based on the search engine.

[0047] The content in the search result interface obtained through the first search approach includes content with a real and clear source. If the first information indicates a higher requirement for credibility, or its semantics are clear so that the user is unlikely to need to search again, the first search approach can provide more accurate response results.

[0048] In step S108, in response to the first information corresponding to the second search path, a dialogue interface for the virtual object is displayed, and the virtual object's response to the first information is displayed on the dialogue interface. In other words, if the first information corresponds to the second search path, having the virtual object respond to the first information will yield more accurate results.

[0049] In the second search approach, a virtual object can be automatically invoked, and the first message can be sent to the virtual object as a conversation between the user and the virtual object. The conversation returned by the virtual object based on the semantics of the first message is a response to the first message. The virtual object's response can include at least one of content and links generated by the virtual object.

[0050] The responses obtained through the second search path are the result of semantic analysis of the first message. Therefore, they can more accurately capture the implicit information in the first message and provide results that better match it. In other words, if the first message contains complex semantics, indicating that the user may need further communication, the second search path can provide more accurate results and allow the user to more conveniently engage in further communication within the dialogue interface, such as entering a second message to obtain more content.

[0051] The embodiments of the present disclosure provide two search paths for user-entered information, allowing the user to obtain a response result using the search path that best matches the characteristics of the first information. Therefore, the present disclosure can more accurately provide feedback to the user, avoiding repeated searches. This improves search accuracy and user search efficiency.

[0052] Some embodiments of the present disclosure can determine whether the user has a secondary search intention based on the first information to further determine the search path. An embodiment of the search path determination method of the present disclosure is described below with reference to FIG2 .

[0053] Figure 2 shows a flow chart of a method for automatically determining a search path according to some embodiments of the present disclosure. As shown in Figure 2 , the method for automatically determining a search path in this embodiment includes steps S202 to S206.

[0054] In step S202 , based on the first information, it is determined whether the user has an intention to perform a secondary search.

[0055] Secondary search refers to a user performing a further search based on the initial search results. For example, if the user is not satisfied with the results of the initial search, or needs more precise information, or needs to continue to obtain other information associated with the search results, the user will search again. In some embodiments, semantic analysis of the first information can be performed to directly or indirectly determine whether the user has the intention of a secondary search. For example, the result of whether the first information has the intention of a secondary search can be directly obtained through semantic analysis, or a preliminary analysis result can be obtained through semantic analysis, and then the result of whether the first information has the intention of a secondary search can be obtained based on the preliminary analysis result. This semantic analysis can be implemented through a semantic analysis model.

[0056] In some embodiments, a determination is made based on the type of the first information whether the user intends a secondary search. For example, the type of the first information is first determined; then, if the first information is factual, it is determined that the user does not intend a secondary search; and if the first information is non-factual, it is determined that the user intends a secondary search. Factual searches require accurate search results, so feedback is provided through the first search path to clarify the source of the search results, reducing the user's verification workload and improving search efficiency and accuracy. Non-factual searches, on the other hand, require less stringent information sources, so feedback can be provided through the second search path, allowing the user to efficiently interact with the virtual object again based on the initial feedback. Of course, the step of determining whether there is a secondary search intention can also be skipped, and the search path can be determined directly based on the type of the first information. That is, if the first information is factual, the first information is determined to correspond to the first search path; and if the first information is non-factual, the first information is determined to correspond to the second search path.

[0057] In some embodiments, fact types include at least one of historical events, scientific facts, scientific definitions, statistics, product information, and geographic information; non-fact types include at least one of conversations, evaluations, consultations, creativity, conceptual understanding, skills, suggestions, logical deductions, career development and planning, and recommendations. For example, if the first information is "the distance between the Earth and the Moon," it indicates that the first information is of fact type, and its corresponding result is unique, so there is no intention of a second search. If the first information is "what are the fun attractions in XX city," it indicates that the user is interested in traveling to XX city and may search again for information such as tourist attractions and XX city cuisine, so there is an intention of a second search.

[0058] In step S204, in response to the user not having the intention of a second search, it is determined that the first information corresponds to the first search path. That is, if the probability of the user performing a second search based on the first information is low, the search results can be fed back through the search results interface to improve the accuracy of the search.

[0059] In step S206, in response to the user's intention to conduct a secondary search, it is determined that the first information corresponds to a second search path. That is, if the user is likely to conduct a second search based on the first information, the search results can be fed back through the virtual object to improve search efficiency.

[0060] The above embodiment automatically determines the search path based on whether the user has the intention of a secondary search, thereby automatically selecting a path that can respond to the first information more accurately and efficiently according to the semantics of the first information, thereby improving the efficiency and accuracy of the search.

[0061] Figure 3 shows a schematic diagram of a conversation list interface according to some embodiments of the present disclosure. As shown in Figure 3, interface 3 of this embodiment includes an input control 31, exemplarily represented as an input box. Furthermore, interface 3 also includes entry controls 32 to 37 for conversation interfaces of multiple virtual objects. Each entry control may include, for example, an avatar, a name, a description, and the like. Those skilled in the art can customize their specific content as needed. As needed, interface 3 may also include an entry for a conversation interface of a real user, which will not be described in detail here. A user can enter first information through input control 31. If the first information corresponds to a first search path, the user is directed from interface 3 to the search results interface. If the first information corresponds to a second search path, the user is directed from interface 3 to the conversation interface corresponding to a virtual object within that interface. Since the conversation list may not be fully displayed on the screen, the virtual object may be currently displayed or not displayed in interface 3.

[0062] In some embodiments, the conversation list includes conversations with multiple virtual objects. In response to the first information corresponding to the second search path, displaying the conversation interface of the virtual object includes: determining the type of the first information; determining the target virtual object corresponding to the first information based on the type corresponding to each of the multiple virtual objects; and displaying the conversation interface of the target virtual object. That is, based on the type of the first information, the virtual object used to respond to the first information can be automatically determined from the multiple virtual objects, so as to more accurately feedback the response to the first information to the user. For example, if the first information involves emotional counseling, the virtual object "psychologist" can be used to respond; if the first information involves artistic creativity, the virtual object "AI artist" can be used to respond. Therefore, on the basis of selecting an appropriate search path based on the first information, the virtual object can be determined again in combination with the first information to feedback a more accurate response to the user, thereby improving the user's search efficiency and accuracy.

[0063] In some embodiments, the user can manually select a search path corresponding to the first information. For example, a first jump control corresponding to the first search path and a second jump control corresponding to the second search path are displayed; the search path is determined based on the user's selection result of the first jump control or the second jump control. Figures 4A and 4B exemplarily show interface diagrams of a user manually selecting a search path. When the user triggers the input of the first information, for example, when the input control 31 is clicked in the interface 3 shown in Figure 3, the search interface 4 shown in Figure 4A can be displayed. As shown in Figure 4A, the interface 4 includes an input control 41 (which can be the same as the input control 31), a first jump control 42 and a second jump control 43 to prompt the user that the search behavior can be triggered by two jump controls, and the two jump controls can display a description of the jump path by default. For example, the first jump control 42 displays "Get search results" and the second jump control displays "Ask a question to get an answer" to clearly indicate that the two jump controls correspond to different search paths. After the user begins inputting, for example, entering the first information "What are the fun attractions in XX city?", interface 4 may display as shown in FIG4B , with the text portion of both first jump control 42 and second jump control 43 updated to the content of the first information, while retaining different icons. This allows the user to further determine whether to obtain a search result interface for "What are the fun attractions in XX city?" or to ask the question "What are the fun attractions in XX city?" in a virtual object dialogue interface. The search path is determined based on the user's triggering of either first jump control 42 or second jump control 43.

[0064] The display interfaces corresponding to the two search paths are further described below.

[0065] First, the search results interface is described. The search results interface includes one or more results corresponding to the first information based on the search engine recall. Each result includes, for example, one or more of the title, link, text of the web page content, and pictures of the searched web page, wherein the text comes from the original content of the web page. In some embodiments, in addition to one or more results based on the search engine recall, the search results interface may also include a generative response of a virtual object to the first information, and an entry control of the dialogue interface of the virtual object, wherein the generative response is determined based on the processing result of the generative machine learning model on the first information.

[0066] In response to the entry control being triggered, a dialogue interface of the virtual object corresponding to the entry control is displayed. The virtual object can be any virtual object, a specified virtual object, or a virtual object determined based on the first information. Thus, after browsing the search results, the user can also easily jump to the dialogue interface of the virtual object to obtain the information generated by the virtual object. In the dialogue interface, the first information and the generated response can be automatically synchronized. For example, the first information is automatically used as the last message sent by the user (i.e., a dialogue), and the generated response is used as the last message sent by the virtual object (i.e., a dialogue). Of course, the first information can also be displayed in other forms in the dialogue interface, or the first information may not be included.

[0067] A generative machine model refers to a machine learning model that a virtual object relies on. It can be a model that generates text based on text, a model that generates multimedia content (such as images) based on text, a model that generates text based on multimedia content, a model that generates multimedia content based on multimedia content, and so on.

[0068] An embodiment of a search result interface is described below with reference to FIG5 .

[0069] Figure 5 shows a schematic diagram of a search result interface according to some embodiments of the present disclosure. As shown in Figure 5, the search result interface 5 of this embodiment includes an input control 51 and search result controls 53 and 54. By triggering the search result control, you can jump to the web page or application corresponding to the search result. In addition, the search result interface 5 also includes an entry control 52 of the dialogue interface of the virtual object, and the entry control 52 displays the content automatically generated by the virtual object "smart assistant" based on the first information "What are the fun attractions in XX city". If the automatically generated content is long, only a part of it can be displayed. After the "Continue Asking Questions" button in the entry control 52 is triggered, the dialogue interface with the "smart assistant" can be displayed.

[0070] Therefore, users can choose to view the content of the real source or communicate with the virtual object to obtain more in-depth information on the search results page as needed, thereby improving the user's search efficiency.

[0071] The following describes a conversation interface with a virtual object. After the conversation interface with the virtual object is displayed through the second search path, the first message can be automatically displayed as the last message sent by the user (i.e., the conversation). Of course, the first message can also be displayed in other forms in the conversation interface, or the first message can be omitted.

[0072] In some embodiments, the virtual object's response to the first information includes at least one of: generated content generated by a generative machine learning model based on the first information; and one or more links corresponding to the first information. The link corresponding to the first information can include part or all of the content of the first information, or can include the semantic meaning of the first information after semantic analysis of the first information. The link can be a webpage link or a link to a page within an application.

[0073] Figure 6 shows a schematic diagram of a dialogue interface of a virtual object according to some embodiments of the present disclosure. As shown in Figure 6, the dialogue interface 6 of this embodiment includes a chat record between a user and a virtual object "smart assistant", wherein the dialogue 61 sent by the user is biased towards the right side of the interface 6, and the dialogues 62 to 64 sent by the smart assistant are biased towards the left side of the interface. The first information "What are the fun attractions in XX city" is automatically displayed in the interface 6 as a dialogue sent by the user. In response to the first information, the "smart assistant" automatically generates content and sends it as a dialogue 62. The content in 62 may be a fusion and splicing of content from multiple information sources. The user can further ask questions through the input control 65 to obtain more information.

[0074] The dialogue interface with the virtual object may or may not display a link, which can be determined based on the type, semantics, content and other dimensions of the first information. The following is an exemplary description of a situation. In some embodiments, when the first information includes creative intent, the virtual object's response to the first information includes generative content and does not include a link; when the first information does not include creative intent, the virtual object's response to the first information includes generative content and a link. For example, if the first information is "draw a photo of Beethoven and Einstein", then the first information is actually a demand for an AI painting. In this case, the virtual object may only send the generated image without sending a link related to "draw a photo of Beethoven and Einstein". Through this embodiment, feedback can be sent to the user more accurately, reducing redundant information.

[0075] When the virtual object's feedback includes both generated content and links, the generated content may be sent to the user (i.e., displayed first), or the link may be sent to the user (i.e., displayed first). The order of sending the generated content and the link may be specified or automatically determined based on the first information, for example, based on the degree of match between the content in the link and the first information.

[0076] In some embodiments, when the degree of match between the content in the link and the first information is higher than a threshold, the link is displayed first, that is, the link is displayed first, and then the generated content is displayed; when the degree of match between the content in the link and the first information is not higher than a threshold, the generated content is displayed first, that is, the generated content is displayed first, and then the link, or the generated content is displayed and the link is not displayed. For example, if the content in the link can well describe or answer the first information, the link can be displayed first, so that the user can obtain the desired information from the content displayed first; if each link is not highly relevant to the first information, or only involves a very small part of the first information, then the generated content can be responded to first, so as to first feedback to the user the content that is integrated through the content of multiple information sources and can more accurately respond to the first information. Thereby, the efficiency of users in obtaining information can be further improved.

[0077] The above describes various embodiments of the search method of the present disclosure. Based on the method embodiment of the present disclosure, an embodiment of the search device of the present disclosure is further described with reference to Figures 7 to 9.

[0078] Figure 7 shows a schematic diagram of the structure of a search device according to some embodiments of the present disclosure. As shown in Figure 7, the search device 70 of this embodiment includes: an acquisition module 702, configured to acquire first information input by a user in a conversation list interface, where the conversation list includes an entry to a conversation interface of a virtual object; a determination module 704, configured to determine a search path corresponding to the first information; a first display module 706, configured to display a search result interface in response to the first information corresponding to the first search path; and a second display module 708, configured to display a conversation interface of a virtual object in response to the first information corresponding to a second search path, and to display the virtual object's response to the first information on the conversation interface.

[0079] In some embodiments, the determination module 704 is further configured to: determine whether the user has the intention of a secondary search based on the first information; determine that the first information corresponds to the first search path in response to the user having the intention of a secondary search; and determine that the first information corresponds to the second search path in response to the user having the intention of a secondary search.

[0080] In some embodiments, the determination module 704 is further configured to: determine the type of the first information; in response to the first information being of a factual type, determine that the user has no intention of a secondary search; in response to the first information being of a non-factual type, determine that the user has an intention of a secondary search.

[0081] In some embodiments, the determination module 704 is further configured to: display a first jump control corresponding to the first search path and a second jump control corresponding to the second search path; and determine the search path based on the user's selection result of the first jump control or the second jump control.

[0082] In some embodiments, the search results interface includes: one or more results corresponding to the first information based on search engine recall; or, one or more results based on search engine recall, a generative response of the virtual object to the first information, and an entry control of the dialogue interface of the virtual object, wherein the generative response is determined based on the processing result of the generative machine learning model on the first information.

[0083] In some embodiments, the second display module 708 is further configured to: determine the type of the first information; determine the target virtual object corresponding to the first information based on the type corresponding to each of the multiple virtual objects; and display a dialogue interface of the target virtual object.

[0084] In some embodiments, the virtual object's response to the first information includes: at least one of: generative content generated by the generative machine learning model based on the first information, and one or more links corresponding to the first information.

[0085] In some embodiments, when the first information includes creative intent, the virtual object's response to the first information includes generative content and does not include a link; when the first information does not include creative intent, the virtual object's response to the first information includes generative content and a link.

[0086] In some embodiments, the second display module 708 is further configured to: when the degree of match between the content in the link and the first information is higher than a threshold, display the link first and then display the generated content; when the degree of match between the content in the link and the first information is not higher than a threshold, display the generated content first and then display the link, or display the generated content and not display the link.

[0087] In some embodiments, fact types include: at least one of historical events, scientific facts, scientific definitions, statistical data, product information, and geographic information; non-fact types include: at least one of dialogue, evaluation, consultation, creativity, conceptual understanding, skills, suggestions, logical deduction, career development and planning, and recommendation.

[0088] It should be noted that the above-mentioned units are merely logical modules divided according to the specific functions they implement, and are not intended to limit specific implementation methods. For example, they can be implemented in software, hardware, or a combination of software and hardware. In actual implementation, the above-mentioned units can be implemented as independent physical entities, or can also be implemented by a single entity (for example, a processor (CPU or DSP, etc.), an integrated circuit, etc.). In addition, the above-mentioned units are shown with dotted lines in the accompanying drawings to indicate that these units may not actually exist, and the operations / functions they implement can be implemented by the processing circuit itself.

[0089] In addition, although not shown, the device may also include a memory that can store various information generated by the device and the various units contained in the device during operation, programs and data used for operation, data to be sent by the communication unit, etc. The memory can be volatile memory and / or non-volatile memory. For example, the memory can 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 can 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 an appropriate manner known in the art, for example, including communication components such as an antenna array and / or a radio frequency link, various types of interfaces, communication units, etc. This will not be described in detail here. In addition, the device may also include other components not shown, such as a radio frequency link, a baseband processing unit, a network interface, a processor, a controller, etc. This will not be described in detail here.

[0090] Some embodiments of the present disclosure also provide an electronic device. Figure 8 shows a schematic structural diagram of an electronic device according to some embodiments of the present disclosure. For example, in some embodiments, the electronic device 8 can be various types of devices, for example, 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), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. For example, the electronic device 8 may include a display panel for displaying data and / or execution results utilized in the scheme of the present 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 flat panel, but also a curved panel or even a spherical panel.

[0091] As shown in FIG8 , the electronic device 8 of this embodiment includes a memory 81 and a processor 82 coupled to the memory 81. It should be noted that the components of the electronic device 8 shown in FIG8 are merely exemplary and non-limiting. The electronic device 8 may also include other components as required by actual applications. The processor 82 may control the other components in the electronic device 8 to perform desired functions.

[0092] In some embodiments, the memory 81 is configured to store one or more computer-readable instructions. When the processor 82 is configured to execute the computer-readable instructions, the computer-readable instructions, when executed by the processor 82, implement the method according to any of the above-described embodiments. The specific implementation and related explanations of each step of the method can be found in the above-described embodiments, and any repetitive details are omitted here.

[0093] For example, the processor 82 and the memory 81 may communicate with each other directly or indirectly. For example, the processor 82 and the memory 81 may communicate with each other via a network. The network may include a wireless network, a wired network, and / or any combination of wireless networks and wired networks. The processor 82 and the memory 81 may also communicate with each other via a system bus, which is not limited in this disclosure.

[0094] For example, the processor 82 can be embodied as various appropriate processors, processing devices, etc., such as a central processing unit (CPU), a graphics processing unit (GPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The central processing unit (CPU) can be an X86 or ARM architecture, etc. For example, the memory 81 can include any combination of various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The memory 81 can include, for example, a system memory, which stores, for example, an operating system, an application, a boot loader (Boot Loader), a database, and other programs. Various applications and various data can also be stored in the storage medium.

[0095] In addition, according to some embodiments of the present disclosure, when various operations / processes according to the present disclosure are implemented through software and / or firmware, the programs constituting the software can be installed from a storage medium or a network to a computer system having a dedicated hardware structure, such as the computer system 90 shown in Figure 9. When the various programs are installed, the computer system can perform various functions, including the functions described above. Figure 9 shows a schematic structural diagram of a computer system according to some embodiments of the present disclosure.

[0096] In Figure 9, a central processing unit (CPU) 901 performs various processes according to a program stored in a read-only memory (ROM) 902 or a program loaded from a storage part 908 to a random access memory (RAM) 903. In the RAM 903, data required when the CPU 901 performs various processes, etc., is also stored as needed. The central processing unit is merely exemplary and may also be other types of processors, such as the various processors described above. The ROM 902, RAM 903, and storage part 908 may be various forms of computer-readable storage media, as described below. It should be noted that although ROM 902, RAM 903, and storage device 908 are shown separately in Figure 9, one or more of them may be combined or located in the same or different memory or storage modules.

[0097] The CPU 901, the ROM 902, and the RAM 903 are connected to one another via a bus 904. An input / output interface 905 is also connected to the bus 904.

[0098] The following components are connected to the input / output interface 905: an input portion 906, such as a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; an output portion 907, including a display, such as a cathode ray tube (CRT), liquid crystal display (LCD), speaker, vibrator, etc.; a storage portion 908, including a hard disk, magnetic tape, etc.; and a communication portion 909, including a network interface card, such as a LAN card, modem, etc. The communication portion 909 allows communication processing to be performed via a network, such as the Internet. It will be readily understood that although FIG9 shows that the various devices or modules in the computer system 90 communicate via the bus 904, they may also communicate via a network or other means, where the network may include a wireless network, a wired network, and / or any combination of wireless and wired networks.

[0099] A drive 910 is also connected to the input / output interface 905 as needed. A removable medium 911 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory or the like is mounted on the drive 910 as needed so that a computer program read therefrom is installed in the storage portion 908 as needed.

[0100] In the case of realizing the above-described series of processing by software, a program constituting the software can be installed from a network such as the Internet or a storage medium such as the removable medium 911 .

[0101] According to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network via the communication device 909, or installed from the storage device 908, or installed from the ROM 902. When the computer program is executed by the CPU 901, the above-mentioned functions defined in the method of the embodiment of the present disclosure are performed.

[0102] It should be noted that in the context of the present disclosure, a computer-readable medium may 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 may be a computer-readable signal medium or a computer-readable storage medium or any combination thereof. A computer-readable storage medium may 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 computer-readable storage media may include, but are not limited to, an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that may be used by or in conjunction with an instruction execution system, apparatus, or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction 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 cables, RF (radio frequency), etc., or any suitable combination thereof.

[0103] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0104] In some embodiments, a computer program is further provided, comprising: instructions, which, when executed by a processor, cause the processor to perform any of the methods of the above embodiments. For example, the instructions may be embodied as computer program codes.

[0105] In embodiments of the present disclosure, computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or combinations thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate 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 a remote computer, the remote computer may 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 may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0106] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0107] The modules, components, or units described in the embodiments of the present disclosure may be implemented in software or hardware. The names of the modules, components, or units do not, in some cases, limit the modules, components, or units themselves.

[0108] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, and without limitation, exemplary hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0109] The above descriptions are merely some embodiments of the present disclosure and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but also encompasses other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the above-mentioned disclosed concepts. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in the present disclosure.

[0110] In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the present invention may be practiced without these specific details. In other cases, well-known methods, structures, and techniques are not presented in detail in order not to obscure the understanding of the description.

[0111] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details have been included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0112] Although some specific embodiments of the present disclosure have been described in detail by way of examples, those skilled in the art will appreciate that the above examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Those skilled in the art will appreciate that modifications may be made to the above embodiments without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.

Claims

1. A search method, comprising: On a conversation list interface, obtaining first information input by a user, wherein the conversation list includes conversations with a virtual object; determining a search path corresponding to the first information; In response to the first information corresponding to the first search approach, displaying a search results page; In response to the first information corresponding to the second search path, a dialogue interface of the virtual object is displayed, and a response of the virtual object to the first information is displayed on the dialogue interface.

2. The search method according to claim 1, wherein: Determining the search path corresponding to the first information includes: Based on the first information, determining whether the user has an intention of a secondary search; In response to the user not having an intention of a secondary search, determining that the first information corresponds to the first search path; In response to the user having an intention of a secondary search, it is determined that the first information corresponds to the second search path.

3. The search method according to claim 2, wherein: The determining, based on the first information, whether the user has an intention for a secondary search includes: determining a type of the first information; In response to the first information being of a fact type, determining that the user does not have an intention of a secondary search; In response to the first information being of a non-factual type, it is determined that the user has an intention of a secondary search.

4. The search method according to any one of claims 1 to 3, wherein: Determining the search path corresponding to the first information includes: displaying a first jump control corresponding to the first search path and a second jump control corresponding to the second search path; The search path is determined according to the selection result of the user on the first jump control or the second jump control.

5. The search method according to any one of claims 1 to 4, wherein: The search result interface includes: One or more results corresponding to the first information retrieved by a search engine; or Based on the one or more results recalled by the search engine, the virtual object's response to the first information A generative response, and an entry control of the dialogue interface of the virtual object, wherein the generative response is determined based on the processing result of the generative machine learning model on the first information.

6. The search method according to any one of claims 1 to 5, wherein: The conversation list includes conversations with a plurality of virtual objects, and in response to the first information corresponding to the second search path, displaying a conversation interface of the virtual objects includes: determining a type of the first information; determining a target virtual object corresponding to the first information based on the type corresponding to each of the plurality of virtual objects; Display a dialogue interface of the target virtual object.

7. The search method according to any one of claims 1 to 6, wherein: The virtual object's response to the first information includes: at least one of: generative content generated by a generative machine learning model based on the first information, and one or more links corresponding to the first information.

8. The search method according to claim 7, wherein: In a case where the first information includes creative intent, the response of the virtual object to the first information includes the generated content but does not include the link; In a case where the first information does not include creative intent, the virtual object's response to the first information includes the generated content and the link.

9. The search method according to claim 7 or 8, wherein: Displaying the virtual object's response to the first information on the dialogue interface includes: If the matching degree between the content in the link and the first information is higher than a threshold, display the link first and then display the generated content; If the matching degree between the content in the link and the first information is not higher than the threshold, the generated content is displayed first and then the link is displayed, or the generated content is displayed and the link is not displayed.

10. The search method according to claim 3, wherein: The fact type includes at least one of: historical events, scientific facts, scientific definitions, statistical data, product information, and geographic information; The non-factual type includes at least one of: dialogue, evaluation, consultation, creativity, conceptual understanding, skills, suggestions, logical deduction, career development and planning, and recommendation.

11. A search device comprising: an acquisition module configured to acquire first information input by a user on a conversation list interface, wherein the conversation list includes an entry of a conversation interface of a virtual object; a determining module, configured to determine a search path corresponding to the first information; a first display module configured to display a search result interface in response to the first information corresponding to the first search path; The second display module is configured to display a dialogue interface of the virtual object in response to the first information corresponding to the second search path, and display the response of the virtual object to the first information on the dialogue interface.

12. A search device comprising: Memory; as well as A processor coupled to the memory, wherein the processor is configured to execute the search method according to any one of claims 1 to 10 based on instructions stored in the memory.

13. A computer-readable storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the search method according to any one of claims 1 to 10 is implemented. 14 . A computer program product, which, when executed on a computer, enables the computer to implement the search method according to claim 1 .

15. A computer program comprising: Instructions, which, when executed by a processor, cause the processor to perform the search method according to any one of claims 1 to 10.

Images