Information retrieval method, apparatus, device, and storage medium

Abstract

Embodiments of this disclosure relate to methods, apparatus, devices, and storage media for information retrieval. The proposed method includes receiving input information indicating an information retrieval request, presenting a results page containing a set of type tags corresponding to different types of search results, and presenting target content in a target window corresponding to a target tag among the set of tags, wherein the target content is generated based on a set of search results that match the input information, and the set of search results has a target type corresponding to a tag different from the target tag among the set of tags. By this method, embodiments of this disclosure can improve the efficiency of information retrieval for users by providing more aggregated search results.

Description

Technical Field

[0001] (Field of the Invention) Exemplary embodiments of the present disclosure generally relate to the field of computers, and in particular, to information search methods, devices, equipment, and computer-readable storage media.

[0002] (Cross-reference to Related Applications) This application claims priority to a Chinese patent application filed on December 7, 2023, with the title "Information Search Method, Device, Equipment, and Storage Medium" and application number 202311676005.1, the entire content of which is incorporated herein by reference.

Background Art

[0003] With the development of computer technology, the Internet has already become an important route for people to share and obtain information. As the information scale on the Internet becomes larger and larger, information search has already become a challenge. People expect to be able to obtain the information they expect more efficiently through information search.

Summary of the Invention

Means for Solving the Problems

[0004] According to a first aspect of the present disclosure, an information search method is provided. The method includes receiving input information indicating an information search request, presenting a result page including a set of type tags corresponding to different types of search results, and presenting target content in a target window corresponding to a target tag among the set of tags, where the target content is generated based on a set of search results that match the input information, and the set of search results has a target type corresponding to a tag different from the target tag among the set of tags.

[0005] A second aspect of this disclosure provides an information search method. This method includes: obtaining input information indicating an information search request; determining a set of search results that match the input information; generating first guidance information for a first model based on descriptive information relating to the set of search results; and providing target content generated by the first model based on the first guidance information as a response to the input information.

[0006] A third aspect of this disclosure provides an information search device. The device includes an information receiving module configured to receive input information indicating an information search request; a page presence module configured to present a results page containing a set of type tags corresponding to different types of search results; and a content presence module configured to present target content in a target window corresponding to a target tag among a set of tags, wherein the target content is generated based on a set of search results matching the input information, and the set of search results has a target type corresponding to a tag different from the target tag among a set of tags.

[0007] A fourth aspect of this disclosure provides an information search device. The device includes an information acquisition module configured to acquire input information indicating an information search request; a result determination module configured to determine a set of search results that match the input information; an information generation module configured to generate first guidance information of a first model based on descriptive information relating to the set of search results; and an information provision module configured to provide target content generated by the first model based on the first guidance information as a response to the input information.

[0008] A fifth aspect of this disclosure provides an electronic device. The device comprises at least one processing unit and at least one memory, the at least one memory being coupled to the at least one processing unit and storing instructions to be executed by the at least one processing unit. When instructions are executed by the at least one processing unit, the device is made to perform the method of the first or second aspect.

[0009] A sixth aspect of this disclosure provides a computer-readable storage medium in which a computer program is stored, and the computer program can be executed by a processor to carry out the method of the first or second aspect.

[0010] The information described in this section is not intended to limit any essential or important features of the embodiments of this disclosure, nor to limit the scope of this disclosure. It should be understood that other features of this disclosure are made clearer by the following description. [Brief explanation of the drawing]

[0011] The above and other features, advantages, and aspects of each embodiment of this disclosure will become more apparent by linking the drawings and referring to the following detailed description. In the drawings, identical or similar reference numerals represent identical or similar elements. Here, [Figure 1] A schematic diagram of an exemplary environment in which the embodiments described herein can be implemented is shown. [Figure 2] A flowchart illustrating an exemplary information search process according to some embodiments of this disclosure is shown. [Figure 3A] The following illustrates an exemplary interface in some embodiments of the present disclosure. [Figure 3B] The following illustrates an exemplary interface in some embodiments of the present disclosure. [Figure 3C] The following illustrates an exemplary interface in some embodiments of the present disclosure. [Figure 3D]The following illustrates an exemplary interface in some embodiments of the present disclosure. [Figure 4] A flowchart illustrating an exemplary information search process according to some embodiments of this disclosure is shown. [Figure 5A] A schematic structural block diagram of an information search device according to several embodiments of this disclosure is shown. [Figure 5B] A schematic structural block diagram of an information search device according to several embodiments of this disclosure is shown. [Figure 6] A block diagram of an electronic device capable of carrying out multiple embodiments of this disclosure is shown. [Modes for carrying out the invention]

[0012] The embodiments of this disclosure will be described in more detail below with reference to the drawings. While the drawings show several embodiments of this disclosure, it should be understood that this disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein. Rather, these embodiments are provided to provide a clearer and more complete understanding of this disclosure. It should be understood that the drawings and embodiments of this disclosure are illustrative and not intended to limit the scope of protection of this disclosure.

[0013] It should be noted that the titles of any section / subsection in this specification are not limiting. Various embodiments are described throughout this specification, and any type of embodiment may be included in any section / subsection. Furthermore, an embodiment described in any one section / subsection may be combined in any manner with any other embodiment described in the same section / subsection and / or in a different section / subsection.

[0014] In the description of the embodiments of this disclosure, the term “including,” and similar terms should be understood as unrestrictive “including,” i.e., “including, but not limited to.” The term “based on,” should be understood as “based at least in part.” The term “one embodiment” or “this embodiment” should be understood as “at least one embodiment.” The term “several embodiments” should be understood as “at least several embodiments.” The following may include other explicit and implicit definitions. Terms such as “first,” “second,” etc., may refer to different or the same subject. The following may include other explicit and implicit definitions.

[0015] The embodiments of this disclosure may involve user data, data acquisition and / or use, etc. All of these must comply with applicable laws, regulations and related provisions. In the embodiments of this disclosure, all data collection, acquisition, processing, modification, transfer, use, etc., is carried out on the premise of user awareness and confirmation. Accordingly, when implementing each embodiment of this disclosure, the user should be informed in an appropriate manner, in accordance with applicable laws and regulations, of the type of data or information involved, the scope of use, the usage scenario, etc., and permission should be obtained from the user. The specific method of notification and / or permission may vary depending on the actual situation and application scenario, and the scope of this disclosure is not limited in this respect.

[0016] The methods described herein and in the examples, when dealing with personal information, are all based on a legal foundation (e.g., obtaining the consent of the data subject, or being essential for contractual performance, etc.) and are processed only within the scope specified or agreed upon. A user's refusal to process personal information other than that necessary for basic functions will not affect the user's use of those basic functions.

[0017] As introduced by referring to the above, information search is a basic and important task on the Internet. General information search is generally performed by a method of matching keywords, and thus, in order for a user to efficiently obtain the expected information, it is necessary to use accurate keywords.

[0018] On the other hand, general information search generally distributes various results to users easily, which requires users to further digest and extract such information, bringing additional costs to users.

[0019] In view of this, embodiments of the present disclosure propose an information search solution. According to this solution, input information indicating an information search request can be received. Further, a result page including a set of type tags corresponding to different types of search results can be presented. Additionally, target content can be presented in a target window corresponding to a target tag among a set of tags, and the target content is generated based on a set of search results that match the input information, and the set of search results has a target type corresponding to a tag different from the target tag among the set of tags.

[0020] By this method, embodiments of the present disclosure can improve the efficiency of users' information search by providing more intensive search results.

[0021] Hereinafter, various exemplary implementations of this solution will be described in detail with reference to the drawings.

[0022] Exemplary environment FIG. 1 shows a schematic diagram of an exemplary environment 100 in which embodiments of the present disclosure can be realized. As shown in FIG. 1, the exemplary environment 100 may include a terminal device 110.

[0023] In this exemplary environment 100, terminal device 110 may be running an application 120 for providing and viewing media content. Application 120 may be any suitable type of application for information searching or any suitable application that can provide information search services. User 140 can interact with application 120 via terminal device 110 and / or its peripherals. In the environment 100 of Figure 1, when application 120 is active, terminal device 110 can have interface 150 present through application 120.

[0024] In some embodiments, the terminal device 110 communicates with the server 130 to provide services to the application 120. The terminal device 110 may be any type of mobile terminal, fixed terminal, or portable terminal, and includes mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, taglet PCs, media computers, multimedia taglets, palmtop computers, portable game terminals, VR / AR devices, Personal Communication System (PCS) devices, personal navigation devices, Personal Digital Assistants (PDAs), audio / video players, digital cameras / cameras, positioning devices, television receivers, radio broadcast receivers, e-book devices, game devices, or any combination of the foregoing, and includes components and peripherals of these devices or any combination thereof. In some embodiments, the terminal device 110 may also support any type of interface to the user (e.g., a "wearable" circuit).

[0025] Server 130 may be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks, and big data and smart platforms. Server 130 may also include, for example, computing systems / servers such as mainframes, edge computing nodes, and computing equipment in a cloud environment. Server 130 can provide backend services to applications 120 that support virtual scenarios on terminal devices 110.

[0026] A communication connection may be established between the server 130 and the terminal device 110. The communication connection may be established by a wired or wireless method. The communication connection may include, but is not limited to, Bluetooth® connection, mobile network connection, Universal Serial Bus (USB) connection, Wireless Fidelity (WiFi) connection, etc., and the embodiments of this disclosure are not limited in this respect. In the embodiments of this disclosure, the server 130 and the terminal device 110 can realize signaling interaction through the communication connection between them.

[0027] The structure and function of each element in Environment 100 are described for illustrative purposes only, and should be understood as not to imply any limitation on the scope of this disclosure.

[0028] In the following sections, several exemplary embodiments of this disclosure will be described with reference to the drawings.

[0029] Exemplary process Figure 2 shows a flowchart of an exemplary information search process 200 according to some embodiments of the present disclosure. Process 200 may be performed in the terminal device 110 shown in Figure 1. Process 200 will be described below with reference to Figure 1.

[0030] As shown in Figure 2, in block 210, terminal device 110 receives input information indicating an information search request.

[0031] The process 200 will be described below with reference to Figures 3A to 3D. Figure 3A shows an exemplary interface 300A according to some embodiments of the present disclosure. As shown in Figure 3A, the terminal device 110 may provide a search control 305 in the interface 300A and may obtain input information 310 indicating an information search request through the search control 305.

[0032] For example, the user may input text content as input information 310 using a search control. As another example, the user may input audio content or image content as input information 310 using a search control.

[0033] Continuing to refer to Figure 2, in block 220, terminal device 110 presents a results page containing a set of type tags corresponding to different types of search results.

[0034] For example, as shown in Figure 3A, the terminal device 110 may present a search results page corresponding to the input information 310. Such a search results page may include, for example, a set of type tags 315, and this set of type tags may correspond to different types of search results.

[0035] For example, the "video" tag may correspond to video-related search results, the "user" tag may correspond to user-related search results, the "music" tag may correspond to music-related search results, and the "product" tag may correspond to product-related search results.

[0036] As another example, the "General" tag may correspond to general search results, which may include aggregations of various search results such as videos, users, and music. The "Smart Search" tag may correspond to the provision of generative search results.

[0037] It should be understood that such a set of tags 315 depends on the types of content supported on the content platform the user is searching. For example, it may further include tags such as "live streaming" and "topic."

[0038] In block 230, terminal device 110 presents target content in a target window corresponding to a target tag among a set of tags. The target content is generated based on a set of search results that match the input information, and the set of search results has a target type that corresponds to a tag different from the target tag among the set of tags.

[0039] In some embodiments, before presenting the target content, the terminal device 110 may present search status information in the target window to indicate a change in the processing status of the information search request.

[0040] For example, as shown in Figure 3A, the terminal device 110 may display first search status information 320 to indicate that the information search request is in the analysis state. The analysis state may indicate that the input information is being analyzed and an information search is being performed.

[0041] As another example, as shown in Figure 3B, the terminal device 110 may dynamically present a second search state information 325 to indicate that the information search request is in a search state, in response to a change in the processing state. The search state may indicate that a set of search results matching the input information is being searched.

[0042] As another example, as shown in Figure 3C, the terminal device 110 may dynamically present a second search status information 330 to indicate that the information search request is in the generation state, in response to a change in the processing state. The generation state may indicate that target content is being generated based on a set of search results.

[0043] Based on this method, the embodiments of the present disclosure can make it easier for users to better perceive the processing process of an information search request by indicating the processing status of the information search request through dynamic changes in state information.

[0044] Furthermore, as shown in Figure 3D, the terminal device 110 may present the target content 335 in the target window. For example, the terminal device 110 may present the target content 335 on a word-by-word or line-by-line basis. The process for generating the target content 335 will be described below with reference to Figure 4, and will not be described in detail here.

[0045] In some embodiments, the terminal device 110 may present source information, for example, source information 340-1 and source information 340-2, in the target window. Such source information 340-1 and source information 340-2 may represent at least one of a set of search results for generating the target content 335.

[0046] For example, the target content 335 may be generated based on multiple search results. The terminal device 110 may, for example, provide source information corresponding to all of the multiple search results, or provide source information corresponding to some of the search results whose correlation is greater than a threshold.

[0047] For example, terminal device 110 may present a corresponding content viewing interface based on a pre-configured operation on the user's source information 340-1 or source information 340-2.

[0048] In some embodiments, the terminal device 110 may provide feedback controls in the target window, for example, feedback control 345-1 and feedback control 345-2. The user may, for example, provide feedback via feedback control 345-1 indicating whether they are satisfied with the target content 335. Alternatively, the user may, for example, input specific feedback content via feedback control 345-2.

[0049] In some other embodiments, as shown in Figure 3D, the terminal device 110 may present a set of search themes 350 associated with the input information 310 in the target window. In some embodiments, such a set of search themes 350 may be used to help the user retrieve other content related to the input information 310, thereby improving the user's information retrieval efficiency.

[0050] The process of generating target content will be described below, with reference to Figure 4. Figure 4 shows a flowchart of an exemplary information search process 400 according to some embodiments of this disclosure. Process 400 may be performed on the server 130 shown in Figure 1. Process 400 will be described below with reference to Figure 1.

[0051] As shown in Figure 4, in block 410, the server 130 obtains input information indicating an information search request. For example, the terminal device 110 may send the received input information to the server 130 in order to perform an information search.

[0052] In block 420, server 130 determines a set of search results that match the input information.

[0053] In some embodiments, the server 130 may determine (also called recall) one or more search results in various appropriate ways.

[0054] In some embodiments, the server 130 may determine one or more search results that match the input information by using a method such as matching keywords.

[0055] In some other embodiments, the server 130 may perform generalization processing on the input information using, for example, a model (also called a second model). Specifically, the server 130 may generate model guidance information (also called second guidance information) based on the input information. This guidance information is used, for example, to indicate that a search expression associated with this model input information should be generated. In some embodiments, this guidance information may further indicate, for example, the user's search context, such as history search items.

[0056] Such models may be implemented based on any appropriate machine learning technique, and examples may include, but are not limited to, language models.

[0057] Furthermore, the server 130 may obtain a set of search expressions generated by this model based on the guidance information. For example, the server 130 may obtain a set of generalized search expressions (e.g., search terms) generated by this model.

[0058] Furthermore, the server 130 may determine at least one search result from a set of search results that match the input information based on a set of search expressions. For example, the server 130 may determine one or more search results based on this received set of search expressions using methods such as keyword matching or vector matching.

[0059] Based on this method, the embodiments of the present disclosure can expand the input information, thereby improving the comprehensiveness of information retrieval and avoiding limitations imposed by the representation of user input information.

[0060] In some other embodiments, the server 130 may also improve the comprehensiveness of information retrieval by, for example, using a model (also called a third model) to generate answers to queries indicated by input information and performing information retrieval based on those answers.

[0061] Specifically, the server 130 may generate guidance information (also called third guidance information) for the model (also called third model) based on the input information. The guidance information may be used to indicate that the server will generate an answer to a query indicated by the model input information. In some embodiments, this guidance information may further indicate, for example, the user's search context, such as historical search items.

[0062] Please understand that the third model may be a different or the same machine learning model as the second model.

[0063] Furthermore, the server 130 may obtain answer content generated by the model based on the guidance information, and based on the answer content, may determine at least one of a set of search results that match the input information.

[0064] In some other embodiments, the server 130 may determine the search result by matching feature representations, for example. Specifically, the server 130 may determine a first feature representation of the input information. For example, the server 130 may determine the feature representation of the input information using an appropriate model (e.g., the second model, third model, or other appropriate model discussed above).

[0065] Furthermore, the server 130 may determine at least one of a pair of search results from the candidate search result set based on the first feature representation and the second feature representation of the candidate search result set.

[0066] For example, server 130 may use an appropriate model (e.g., the second model, the third model, or another appropriate model discussed above) to determine the feature representation of each candidate search result in the candidate search result set, and may determine one or more search results based on the similarity between the feature representations.

[0067] Based on the process described above, server 130 may determine, for example, multiple candidate search results (also called recalls). Furthermore, server 130 may determine a set of search results from the multiple candidate search results for generating target content, based on the correlation between the multiple candidate search results and the input information.

[0068] In some embodiments, the server 130 may determine the correlation between candidate search results and input information using, for example, an appropriate model (e.g., the second model, the third model, or other appropriate model discussed above). Furthermore, the server 130 may retain a predetermined number of candidate search results with the highest correlation in order to generate target content.

[0069] In block 430, server 130 generates first guidance information for the first model based on descriptive information about a set of search results.

[0070] Specifically, server 130 may obtain descriptive information for this set of search results. Such descriptive information may include, for example, summary information of the search results. For example, the search results may be processed by an appropriate model (e.g., the first model, second model, third model, or other appropriate model discussed above) to generate the corresponding summary information.

[0071] As another example, such descriptive information may further include search result titles, search result links, and so on.

[0072] Furthermore, the server 130 may construct first guidance information (also called guidance words or prompt words) for the first model based on the descriptive information of the search results. Such first guidance information may be used, for example, to instruct the first model to generate target content for input information based on the provided descriptive information of the search results.

[0073] In block 440, server 130 provides target content generated by the first model based on the first guidance information as a response to the input information.

[0074] Specifically, the server 130 may acquire the target content generated by the first model and, for example, send this target content to the terminal device 110 in order to establish presence with the user via the terminal device 110.

[0075] In some embodiments, such target content may include any suitable format of content. For example, the target content may include various forms of content such as text content, video content, audio content, and product content. In some embodiments, such target content may further include various types of card content that support user interaction, such as product cards, user cards, and video cards. This allows embodiments of the present disclosure to further enhance the efficiency of user interaction.

[0076] In some embodiments, the server 130 may generate a set of search themes 350 as discussed above, based on the input information and / or target content. Specifically, the server 130 can help users more efficiently obtain the information they expect by generating this set of search themes using, for example, an appropriate model (e.g., the first model, second model, third model, or other appropriate model discussed above).

[0077] Exemplary devices and equipment Embodiments of this disclosure further provide applicable apparatus for implementing the above method or process. Figure 5A shows a schematic structural block diagram of an information search apparatus 500A according to some embodiments of this disclosure. Apparatus 500A may be implemented as a terminal device 110 or included therein. Each module / component in apparatus 500A may be implemented by hardware, software, firmware, or a combination thereof.

[0078] As shown in Figure 5A, the device 500A comprises an information receiving module 510 configured to receive input information indicating an information search request, a page presence module 520 configured to present a results page containing a set of type tags corresponding to different types of search results, and a content presence module 530 configured to present target content in a target window corresponding to a target tag among a set of tags, wherein the target content is generated based on a set of search results that match the input information, and the set of search results has a target type corresponding to a tag different from the target tag among a set of tags.

[0079] In some embodiments, the device 500A further includes a state presence module configured to present search state information in the target window to indicate a change in the processing state of an information search request before presenting the target content.

[0080] In some embodiments, the processing state includes an analysis state indicating that input information is analyzed and an information search is performed; a search state indicating that a set of search results matching the input information is searched for; and a generation state indicating that target content is generated based on the set of search results.

[0081] In some embodiments, the device 500A further comprises a source presence module configured to present source information in the target window to indicate at least one of a set of search results.

[0082] In some embodiments, the device 500A further comprises a feedback acquisition module configured to acquire feedback information about target content via feedback controls in the target window.

[0083] In some embodiments, the device 500A further comprises a theme presence module configured to make a set of search themes associated with input information present in the target window.

[0084] In some embodiments, a set of tags corresponds to multiple types among video type, user type, product type, music type, and live streaming type.

[0085] Embodiments of this disclosure further provide applicable apparatus for carrying out the above method or process. Figure 5B shows a schematic structural block diagram of an information search apparatus 500B according to some embodiments of this disclosure. Apparatus 500B may be implemented as or included in server 130. Each module / component in apparatus 500B may be implemented as hardware, software, firmware, or a combination thereof.

[0086] As shown in Figure 5B, the device 500B includes an information acquisition module 540 configured to acquire input information indicating an information search request; a result determination module 550 configured to determine a set of search results that match the input information; an information generation module 560 configured to generate first guidance information for a first model based on descriptive information relating to the set of search results; and an information provision module 570 configured to provide target content generated by the first model based on the first guidance information as a response to the input information.

[0087] In some embodiments, the result determination module 550 is further configured to generate second guidance information for a second model to guide the second model to generate search expressions associated with the input information based on the input information, to obtain a set of search expressions generated by the second model based on the second guidance information, and to determine at least one search result from a set of search results that matches the input information based on the set of search expressions.

[0088] In some embodiments, the result determination module 550 is further configured to generate third guidance information for the third model to guide the third model to generate an answer to the query indicated by the input information, to retrieve answer content generated by the third model based on the third guidance information, and to determine at least one search result from a set of search results that match the input information based on the answer content.

[0089] In some embodiments, the result determination module 550 is further configured to determine a first feature representation of the input information and to determine at least one search result from a pair of search results from the candidate search result set based on the first feature representation and a second feature representation of the candidate search result set.

[0090] In some embodiments, the result determination module 550 is further configured to obtain a plurality of candidate search results based on the input information, and to determine a set of search results from the plurality of candidate search results based on the correlation between the plurality of candidate search results and the input information.

[0091] In some embodiments, the descriptive information relating to a set of search results includes at least one of the following: summary information of the search results, title information of the search results, and link information of the search results.

[0092] Figure 6 shows a block diagram of an electronic device 600 that can implement one or more embodiments of the present disclosure. It should be understood that the electronic device 600 shown in Figure 6 is illustrative and does not imply any limitation on the functionality and scope of the embodiments described herein. The electronic device 600 shown in Figure 6 may be used to implement the terminal device 110 or server 130 of Figure 1.

[0093] As shown in Figure 6, the electronic device 600 is a general-purpose electronic device. The components of the electronic device 600 may include, but are not limited to, one or more processors or processing units 610, memory 620, storage devices 630, one or more communication units 640, one or more input devices 650, and one or more output devices 660. The processing unit 610 may be an actual or virtual processor and can perform various processes based on a program stored in memory 620. In a multiprocessor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing capability of the electronic device 600.

[0094] The electronic device 600 generally includes multiple computer storage media. Such media may be any obtainable media accessible to the electronic device 600, and may include, but are not limited to, volatile and non-volatile media, and removable and non-removable media. Memory 620 may be volatile memory (e.g., registers, caches, random access memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or any combination thereof. Storage device 630 may be removable or non-removable media, and may include machine-readable media, such as flash memory drives, magnetic disks, or any other media, which can be used to store information and / or data and are accessible within the electronic device 600.

[0095] The electronic device 600 may further include other removable / non-removable, volatile / non-volatile storage media. Not shown in Figure 6, a magnetic disk drive for reading from or writing to removable, non-volatile magnetic disks (e.g., "floppy disks") and an optical disk drive for reading from or writing to removable, non-volatile optical disks can be provided. In these cases, each drive may be connected to a bus (not shown) by one or more data media interfaces. The memory 620 may also include a computer program product 625, which includes one or more program modules, configured to perform various methods or operations of various embodiments of the present disclosure.

[0096] The communication unit 640 communicates with other electronic devices via a communication medium. Additionally, the functions of the components of the electronic device 600 can be implemented by a single computing cluster or multiple computing machines, which can communicate via a communication connection. Therefore, the electronic device 600 can operate in a network environment using logical connections with one or more other servers, network personal computers (PCs), or other network nodes.

[0097] The input device 650 may be one or more input devices, such as a mouse, keyboard, trackball, etc. The output device 660 may be one or more output devices, such as a display, speaker, printer, etc. The electronic device 600 may further communicate with one or more external devices (not shown), such as a memory device, display device, etc., via the communication unit 640 as needed, with one or more devices for interaction between the user and the electronic device 600, or with any devices (e.g., a network card, modem, etc.) for communication between the electronic device 600 and one or more other electronic devices. Such communication may be carried out via an input / output (I / O) interface (not shown).

[0098] According to an exemplary embodiment of the present disclosure, a computer-readable storage medium is provided, in which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to carry out the methods described above. According to an exemplary embodiment of the present disclosure, a computer program product is further provided, which is tangibly stored in a non-temporary computer-readable medium and includes computer-executable instructions, wherein the computer-executable instructions are executed by a processor to carry out the methods described above.

[0099] Here, each aspect of the disclosure is described with reference to flowcharts and / or block diagrams of methods, apparatus, devices, and computer program products implemented based on the disclosure. It should be understood that each block in the flowcharts and / or block diagrams, and each combination of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0100] By providing these computer-readable program instructions to a processing unit of a general-purpose computer, a dedicated computer, or other programmable data processing device, a machine can be generated, thereby generating a device that performs the functions / operations defined in one or more blocks of a flowchart and / or block diagram when these instructions are executed by the processing unit of the computer or other programmable data processing device. These computer-readable program instructions may be stored in a computer-readable storage medium, and by using these instructions to operate a computer, a programmable data processing device, and / or other device in a particular manner, the computer-readable medium storing the instructions will contain a product containing instructions that perform various modes of the functions / operations defined in one or more blocks of a flowchart and / or block diagram.

[0101] Computer-readable program instructions may be loaded into a computer, another programmable data processing device, or other device, thereby generating a process performed by the computer by executing a series of operational steps on the computer, another programmable data processing device, or other device, and thereby the instructions executed on the computer, another programmable data processing device, or other device perform the functions / operations defined in one or more blocks in a flowchart and / or block diagram.

[0102] The flowcharts and block diagrams in the drawings illustrate the implementable system architectures, functions, and operations of systems, methods, and computer program products in multiple implementations of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, program segment, or part of an instruction, and a module, program segment, or part of an instruction may contain one or more executable instructions for implementing a defined logical function. In some implementations as replacements, the functions described in a block may occur in a different order than those shown in the drawings. For example, two consecutive blocks may actually be executed essentially in parallel, or in reverse order depending on the function. Note also that each block in a block diagram and / or flowchart, and combinations of blocks in a block diagram and / or flowchart, may be implemented by a dedicated hardware-based system that performs the defined function or operation, or by a combination of dedicated hardware and computer instructions.

[0103] The above descriptions of the various implementations of this disclosure are illustrative, not exhaustive, and not limited to the implementations disclosed. Many modifications and changes will be apparent to those skilled in the art without departing from the scope and spirit of the implementations described. The choice of terms used herein is intended to best interpret the principles, practical applications, or technological advancements in the market of each implementation, or to enable other those skilled in the art to understand each implementation disclosed herein.

Claims

1. It is an information search method, Receiving input information indicating an information search request, Present a results page containing a set of type tags corresponding to different types of search results, This involves making the target content present in the target window corresponding to the target tag among the aforementioned set of tags. The target content is generated based on a set of search results that match the input information. The set of search results has a target type that corresponds to a tag in the set of tags that is different from the target tag. Including, method.

2. The above method further, Before presenting the aforementioned target content, In the target window, search status information is displayed to indicate a change in the processing status of the information search request. The method according to claim 1, including the method described in claim 1.

3. The aforementioned processing state is An analysis state indicating that the aforementioned input information is analyzed and an information search is performed, A search state indicating that the search is performed to find the set of search results that match the input information, Based on the aforementioned set of search results, a generation state is given that indicates the generation of the target content, The method according to claim 2, including the method described in claim 2.

4. The above method further, In the target window, the source information for indicating at least one of the set of search results is present. The method according to claim 1, including the method described in claim 1.

5. The method further includes obtaining feedback information regarding the target content via the feedback control in the target window. The method according to claim 1, comprising:

6. The above method further, In the target window, present a set of search themes associated with the input information. The method according to claim 1, including the method described in claim 1.

7. The aforementioned pair of tags is It supports multiple types, including video type, user type, product type, music type, and live streaming type. The method according to claim 1.

8. It is an information search method, Obtaining input information indicating an information search request, Determine a set of search results that match the aforementioned input information, Based on the explanatory information relating to the aforementioned set of search results, the first guidance information of the first model is generated. The first model provides target content generated based on the first guidance information as a response to the input information, Methods that include...

9. Determining a set of search results that match the aforementioned input information is: Based on the input information, second guidance information for the second model is generated to indicate to the second model that it should generate a search expression associated with the input information. The second model obtains a set of search expressions generated based on the second guidance information, Based on the set of search expressions, determine at least one search result from the set of search results that matches the input information. The method according to claim 8, including the method described in claim 8.

10. Determining a set of search results that match the aforementioned input information is: Based on the input information, the third guidance information of the third model is generated to instruct the third model to generate an answer to the query indicated by the input information, The third model obtains the answer content generated based on the third guidance information, Based on the aforementioned answer content, determine at least one search result from the set of search results that matches the input information. The method according to claim 8, including the method described in claim 8.

11. Determining a set of search results that match the aforementioned input information is: Determining the first feature representation of the input information, Based on the first feature representation and the second feature representation of the candidate search result set, at least one search result from the candidate search result set is determined from the set of candidate search results. The method according to claim 8, including the method described in claim 8.

12. Determining a set of search results that match the aforementioned input information is: Based on the aforementioned input information, multiple candidate search results are obtained, Based on the correlation between the plurality of candidate search results and the input information, one set of search results is determined from the plurality of candidate search results. The method according to claim 8, including the method described in claim 8.

13. The explanatory information relating to the set of search results is, Summary information of the search results, The title information of the search results, Link information from the search results, The method according to claim 8, comprising at least one of the following.

14. An information search device, An information receiving module configured to receive input information indicating an information search request, A page presence module configured to have a results page that contains a set of type tags corresponding to different types of search results, A content presence module configured to make the target content present in the target window corresponding to the target tag among the aforementioned set of tags, The target content is generated based on a set of search results that match the input information. The set of search results has a target type that corresponds to a tag in the set of tags that is different from the target tag. Content presence module, A device equipped with the following features.

15. An information search device, An information acquisition module configured to acquire input information indicating an information search request, A result determination module configured to determine a set of search results that match the input information, An information generation module configured to generate first guidance information for a first model based on the explanatory information relating to the set of search results, An information providing module configured to provide target content generated by the first model based on the first guidance information as a response to the input information, A device equipped with the following features.

16. It is an electronic device, It comprises at least one processing unit and at least one memory, The at least one memory is coupled to the at least one processing unit and stores instructions to be executed by the at least one processing unit. When the instruction is executed by the at least one processing unit, the electronic device is made to perform the method according to any one of claims 1 to 7 or 8 to 13. electronic equipment.

17. A computer-readable storage medium, A computer program is stored there. When the computer program is executed by the processor, the method described in any one of claims 1 to 7 or 8 to 13 is performed. Computer-readable storage medium.

Images