Information search method and information search apparatus

Abstract

The application discloses an information search method and an information search device, and belongs to the technical field of electronic equipment. The method comprises the following steps: in the case that a search result interface is displayed, receiving a first voice input of a user; wherein the search result interface comprises search information corresponding to at least one application program; and in response to the first voice input, updating the display content or the display parameter of the search result interface.

Description

Technical Field

[0001] This application belongs to the field of electronic equipment technology, and specifically relates to an information search method and an information search device. Background Technology

[0002] As the mobile application ecosystem continues to expand, when browsing social content, news images, or information shared by others, users can search for relevant information within various applications or through system-level search portals to further understand the price, origin, evaluation, or background of the objects displayed in the images or text.

[0003] In actual use, users often have further refined adjustment needs when viewing search results. For example, users may want to change the search source, add specific filters to exclude irrelevant results, or change the sorting of search results to prioritize the newest or most popular content. These adjustment needs are characterized by real-time, multi-dimensional, and personalized features.

[0004] To address these adjustment needs, the relevant technologies typically require users to exit the current search results interface, return to the search input interface, modify search keywords or filter conditions, and then re-initiate the search. This method involves a lengthy process, and users cannot preview the changes in results in real time during the adjustment process, resulting in low interaction efficiency.

[0005] Therefore, how to provide an adjustment mechanism that does not interrupt the current interaction flow while users are viewing search results, so that users can efficiently and flexibly optimize the generated search results, has become a technical problem that urgently needs to be solved in this field. Summary of the Invention

[0006] The purpose of this application is to provide an information search method, apparatus, electronic device, storage medium, and program product that can improve information acquisition efficiency and decision-making efficiency.

[0007] In a first aspect, embodiments of this application provide an information search method, the method comprising: When displaying the search results interface, the system receives the user's first voice input; wherein the search results interface includes search information corresponding to at least one application. In response to the first voice input, update the displayed content or display parameters of the search results interface.

[0008] Secondly, embodiments of this application provide an information search device, the device comprising: A receiving module is used to receive the user's first voice input when the search results interface is displayed; wherein the search results interface includes search information corresponding to at least one application; The processing module is used to update the displayed content or display parameters of the search results interface in response to the first voice input.

[0009] Thirdly, embodiments of this application provide an electronic device including a processor and a memory, wherein the memory stores programs or instructions executable on the processor, and the programs or instructions, when executed by the processor, implement the steps of the method described in the first aspect.

[0010] Fourthly, embodiments of this application provide a readable storage medium on which a program or instructions are stored, which, when executed by a processor, implement the steps of the method described in the first aspect.

[0011] Fifthly, embodiments of this application provide a chip, the chip including a processor and a communication interface, the communication interface being coupled to the processor, the processor being used to run programs or instructions to implement the method as described in the first aspect.

[0012] In a sixth aspect, embodiments of this application provide a computer program product stored in a storage medium, which is executed by at least one processor to implement the method described in the first aspect.

[0013] In this embodiment, when viewing search results, if a user needs to make adjustments, there is no need to exit the current search results interface, return to the search input page, or restart the search. The user can simply input voice commands directly in the search results interface to adjust the displayed content or display parameters in real time. This shortens the user's operation path, improves interaction efficiency, and does not interrupt the viewing process, thus maintaining the continuity and immersion of the interaction. Attached Figure Description

[0014] Figure 1 This is a flowchart illustrating an information search method provided in some embodiments of this application; Figure 2 These are schematic diagrams of application interfaces provided in some embodiments of this application; Figure 3 These are schematic diagrams of application interfaces provided in other embodiments of this application; Figure 4 This is a schematic diagram of a search results interface provided in some embodiments of this application; Figure 5 These are schematic diagrams of search result interfaces provided in other embodiments of this application; Figure 6 These are schematic diagrams of search result interfaces provided in other embodiments of this application; Figure 7 These are schematic diagrams of search result interfaces provided in other embodiments of this application; Figure 8 These are schematic diagrams of information search devices provided in some embodiments of this application; Figure 9 These are schematic diagrams of the structure of electronic devices provided in some embodiments of this application; Figure 10 These are schematic diagrams of the hardware structure of electronic devices provided in some embodiments of this application. Detailed Implementation

[0015] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0016] The terms "first," "second," etc., used in this application's specification are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class, without limiting the number of objects; for example, a first object can be one or more. Furthermore, in the specification, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects have an "or" relationship.

[0017] The information search method, apparatus, device, storage medium, and program product provided in this application will be described in detail below with reference to the accompanying drawings and through specific embodiments and application scenarios.

[0018] The information search method provided in this application can be applied to information search scenarios across multiple platforms, such as product search, attraction search, travel guide search, food search, academic or news search, etc. The information search method provided in the embodiments of this application will be described in detail below with reference to the accompanying drawings. It should be noted that the information search method provided in the embodiments of this application can be executed by an electronic device. This application uses an electronic device executing the information search method as an example to illustrate the information search method provided in the embodiments of this application.

[0019] See Figure 1 A flowchart illustrating the information search method provided for some embodiments of this application, such as... Figure 1 As shown, the method includes the following steps 110-120, which will be described in detail below.

[0020] Step 110. When the search results interface is displayed, receive the user's first voice input; wherein the search results interface includes search information corresponding to at least one application.

[0021] In some embodiments of this application, a search can be performed before step 110 above, and a search results interface can be generated and displayed based on the search results. The search can be a cross-platform search, which refers to unified information retrieval in at least two applications. This overcomes the limitations of a single search platform and enables the integration and efficient acquisition of multi-source data. Therefore, the search results interface generated based on the search results can include search information corresponding to at least one application.

[0022] In some embodiments of this application, the search can be performed via the following steps 210-240 before step 110 described above.

[0023] Step 210. Receive the user's first input on any application interface.

[0024] In some embodiments of this application, the first input is an input used to initiate a search on the application interface. Exemplarily, the first input includes, but is not limited to: a user clicking on the content to be searched on the application interface using a touch device such as a finger or stylus; a voice command input by the user; a specific gesture input by the user; or other feasible inputs. The specific input can be determined according to actual usage needs, and this embodiment of the invention does not limit it. The specific gesture in this embodiment can be any one of a single-click gesture, a swipe gesture, a drag gesture, a pressure-recognition gesture, a long-press gesture, an area-change gesture, a double-press gesture, or a double-tap gesture; the click input in this embodiment can be a single-click input, a double-tap input, or any number of clicks, and can also be a long-press input or a short-press input. For example, the first input described above can be: a user long-pressing any application interface currently displayed on the electronic device using their finger.

[0025] In practical applications, users can make initial input on any application interface displayed on the electronic device based on their actual needs. These applications include, but are not limited to, shopping apps, games, social networking apps, and news apps. For example... Figure 2 As shown, if a user is browsing a product page 200 in a shopping application on an electronic device, the user can make the first input on the product interface 200.

[0026] In some embodiments of this application, to achieve more accurate searching, the first input can be the user's input of the display area of ​​the target content to be searched in the application interface. The target content includes, but is not limited to, images, video frames, text, or mixed areas containing text and images displayed in the application interface. The target content may differ in different application scenarios. Several examples of target content are given below.

[0027] For example, in such Figure 2 In the product search scenario shown, when a user is browsing the shopping application interface 200, if they are interested in a product A (such as clothing, an electronic product, or any product) displayed on interface 200, the user can long-press the image area of ​​product A. At this time, the target content is the product image 210 corresponding to the location where the user long-presses.

[0028] For example, in a tourist attraction search scenario, when a user sees an image containing landmarks (such as the Forbidden City or the Eiffel Tower) or natural scenery (such as Huangshan Mountain or the Maldives) in a travel information app or on social media, they can long-press the image to learn more about the attraction. In this case, the target content is the main area of ​​interest to the user within the image.

[0029] For example, in a travel guide search scenario, when browsing a long travelogue or travel videos, if a user becomes interested in an image that includes a route map, a transportation hub map, or the exterior of a unique accommodation, they can long-press to select that image. In this case, the target content is that image containing travel planning information.

[0030] For example, in a food search scenario, when a user comes across a video / image of a dish or a restaurant's facade on a short video platform or review app, they can simply long-press the video or image to learn how the dish is made, the restaurant's rating, or other users' reviews. In this case, the target content is the food image or restaurant image in the current video frame.

[0031] For example, in academic or news search scenarios, when users browse content in academic forums, document readers, or news applications, if they want to learn more about the information in a paper's cover, a conference logo, or a news screenshot (such as an image containing a scene of a major event), they can long-press on that image area. In this case, the target content will be the image containing the paper's cover, conference logo, or news event.

[0032] Step 220. In response to the first input, obtain the first information.

[0033] In some embodiments of this application, the first information is information used to indicate the object to be searched. The object to be searched refers to the core object in the application interface that the user most wants to know about. Simply put, the object to be searched is the focus of the user's attention in the application interface. The object to be searched can be a specific product in an image, a specific landmark, or a name, place name, or keyword in a text. All subsequent cross-platform searches will revolve around this core object. By determining the object to be searched, search results that accurately meet the user's needs can be obtained.

[0034] In some embodiments of this application, an application interface may often contain multiple objects, such as pedestrians, buildings, and goods in a street photo. If the entire content of the application interface is used as the search target, the search results will be mixed and have low relevance. Therefore, in this embodiment, a local subject search strategy is used by default, that is, objects at the touch point coordinates of the first input are prioritized for searching. Based on this, after receiving the first input, the electronic device can obtain first information according to the mapping relationship between the touch point coordinates of the first input and the screen content. Specifically, in response to the first input, the electronic device determines the touch point coordinates of the first input on the application interface; based on the touch point coordinates, it extracts a local area image containing the touch point coordinates from the application interface; and it performs subject recognition on the local area image to obtain the first information.

[0035] In some embodiments of this application, when cropping a local area image based on touch point coordinates, the touch point coordinates can be used as the center point coordinates, and a local image of a preset area can be cropped from the application interface as the local area image. The preset area can be set according to actual needs.

[0036] In some embodiments of this application, considering that local content may not cover all user search needs, or that touch-based content recognition may not be accurate enough, in order to further improve search accuracy, after determining the local area image, the local area image can be highlighted in the application interface to indicate to the user the location of the currently determined search object in the application interface. Highlighting the local area image may include, but is not limited to, highlighting the local area image, or displaying a range indicator box around the local area image. After highlighting the local area image, a third input for adjusting the range of the local area image can be received; in response to the third input, the image range of the local area image is adjusted. The third input may include, but is not limited to, click, drag, etc.

[0037] For example, after determining the local area image based on the touch point, the local area image is highlighted in the application interface, and a range indicator box of the local area image is displayed. The user can determine whether the objects to be searched are all within the range indicator box. If the range indicator box does not completely cover the objects to be searched, or if the range indicator box is too large and covers the objects that do not need to be searched, the user can adjust the size of the range indicator box by dragging it. Then, the electronic device can use the image within the adjusted range indicator box as a new local area image for subsequent subject recognition.

[0038] Using the methods described above, users can manually adjust local areas of the image based on their actual needs, thereby improving search accuracy and ensuring that search results meet their requirements.

[0039] In some embodiments of this application, subject recognition of a local area image refers to the technical process of analyzing and understanding a local area image to determine the core object that best represents the user's search intent.

[0040] In some embodiments of this application, subject recognition of local area images can be performed using one or a combination of techniques such as visual subject detection, text entity extraction, or semantic tag generation.

[0041] The visual subject detection process can include: when a local area image contains image information, such as image information of entities like goods, people, scenic spots, animals, or food, object detection algorithms can be used to identify the entities in the local area image and determine their boundary positions. Simultaneously, semantic segmentation techniques are used to separate the entities from the background, extracting clean entity images or visual feature vectors suitable for searching as the primary information.

[0042] Text entity extraction can include: when a local area image contains text information, the text in the local area image can be extracted using Optical Character Recognition (OCR) technology, and then key information with clear semantic reference can be extracted using Named Entity Recognition (NER) technology. Key information may include, but is not limited to: person names, place names, academic terms, product models, website links, etc. The extracted key information is used as the first information.

[0043] Semantic label generation can include: when a local area image cannot be accurately matched to a specific entity, such as when the local area image is an abstract art image or a creative design, image classification or multimodal large model understanding technology can be used to output semantic concept labels that can describe the core features of the local area image, such as "Nordic style coffee table", "retro film tone", "molecular gastronomy plating", and use the semantic concept labels as the first information.

[0044] Step 230. Determine at least one application based on the first information.

[0045] In some embodiments of this application, after obtaining the first information, a search strategy for guiding the search can be generated based on the first information. The search strategy includes at least information indicating at least one application applicable to the object to be searched. The application indicated in the search strategy is the search platform used to perform the search operation.

[0046] In some embodiments of this application, users' search intents differ in different scenarios, and different search intents can be realized through different applications. Therefore, to ensure that the final search results better match the user's true search intent, when determining the search platform to be used, the user's search intent can be comprehensively determined by combining the first information and its contextual information, and then a search strategy can be generated based on the search intent. The contextual information of the first information may include information that indicates the application scenario in which the application interface belongs (hereinafter referred to as the target application) and the content information of the application interface. The application category may be social, news, shopping, tools, audio-visual, or lifestyle services, etc.

[0047] In some embodiments of the application, when determining the application category of a target application, the application name of the target application currently in the foreground can be obtained by calling the application programming interface provided by the operating system of the electronic device. After obtaining the application name, the application category corresponding to the application name of the target application can be determined based on a preset correspondence between application names and application categories, and this category is then used as the application category of the target application. The application category of the target application can be used to help determine the tone of the user's current usage scenario. For example, when browsing e-commerce applications, a user's search intent is more likely to be biased towards comparing prices; when browsing news applications, the user is more likely to be biased towards further information reading.

[0048] In some embodiments of this application, the content information of the application interface can be obtained by analyzing screenshots of the application interface. Specifically, the electronic device can obtain screenshot data of the current complete application interface through the operating system-level screenshot function. The content information of the application interface is obtained by performing the following analysis on the screenshot data: 1. Image content recognition: Using a lightweight image classification model, identify the general type of the current interface, such as a single image browsing interface, an image and text list interface, or a video playback interface; 2. Text region extraction: Using optical character recognition (OCR) technology, extract text information displayed on the interface from screenshots, including titles, descriptions, comments, button text, etc. 3. Layout structure analysis: Identify the distribution of elements in the interface, such as whether there are product cards, price tags, or user comment areas.

[0049] In some embodiments of this application, after obtaining the first information and context information, the first information and context information can be fused into multimodal data and input into the intent prediction model. The intent prediction model then identifies the search intent, thereby obtaining the user search intent output by the intent prediction model. The user search intent can be, for example, shopping intent, location intent, travel guide intent, academic intent, or general intent.

[0050] In some embodiments of this application, after obtaining the user's search intent, a corresponding search strategy is generated based on the user's search intent to ensure that the search strategy meets the user's expectations.

[0051] In some embodiments of this application, the search strategy includes a set of search platforms, which includes at least one application for performing search operations.

[0052] In some embodiments of this application, the search strategy may include priority information in addition to a set of search platforms. This priority information indicates the priority relationship between applications within the set of search platforms, i.e., the display priority of each application. Search results from applications with higher priority are displayed first in the search results interface.

[0053] In some embodiments of this application, multiple policy templates can be pre-configured, thereby enabling the generation of search strategies based on these templates. Each policy template can correspond to a typical user intent type and may include a default set of search platforms and initial priority information.

[0054] For example, the strategy template may include a shopping comparison strategy template corresponding to the shopping intent, wherein the set of search platforms includes the following applications: e-commerce platform A, e-commerce platform B, price comparison platform C, and community platform D, wherein the priority information is: price comparison platform C has the highest priority.

[0055] For example, the strategy template may include an information query strategy template corresponding to the strategy intent, wherein the set of search platforms includes the following applications: general search engine E, encyclopedia platform F, community platform G, and video platform H, wherein the priority information is: general search engine E has the highest priority.

[0056] For example, the strategy template may include a local service strategy template corresponding to the location intent, wherein the search platform set includes the following applications: map platform I, review platform J, and guide platform K, and the priority information is: map platform I has the highest priority.

[0057] For example, the strategy template may include a knowledge exploration strategy template corresponding to academic intent, wherein the set of search platforms includes: academic database L, news media M, and encyclopedia platform N, and the priority information includes: academic database L has the highest priority.

[0058] For example, the strategy template may include a comprehensive search strategy template corresponding to a general intent, wherein the set of search platforms includes: general search engine E, encyclopedia platform F, and video platform H, and the priority information includes: general search engine E has the highest priority.

[0059] Therefore, after determining the user's search intent, the corresponding strategy template that matches the user's search intent can be used as the default search strategy for this search. In this way, search strategies can be generated quickly and efficiently.

[0060] In some embodiments of this application, steps 220 and 230 described above can be performed independently by an electronic device.

[0061] In other embodiments of this application, considering the limited computing power of electronic devices, in order to save computing power and improve efficiency, steps 220 and 230 can also be completed collaboratively by the electronic device and the cloud server. Specifically, the electronic device can send the information required to determine the first information and search strategy, such as the local area image and context information, to the cloud server, so that the cloud server can perform subject recognition on the local area image, obtain the first information, and determine the search strategy based on the first information and context information, and finally send the recognized first information and the generated search strategy to the electronic device for subsequent processing.

[0062] Step 240. Based on the first information, perform a search in at least one application, generate and display the search results interface.

[0063] In some embodiments of this application, after obtaining the first information and the search strategy, a search request can be initiated in each application used for searching based on the first information in the search strategy, so that all applications indicated by the search strategy can perform searches in parallel based on the first information, thereby obtaining the search results of each application, i.e., search information, and then generating and displaying the search results interface based on the search information of all applications. Thus, the search results interface may include the search information of at least one application.

[0064] In some embodiments of this application, a challenge lies in how to perform parallel searches across multiple applications when the search strategy includes at least two. To achieve cross-platform parallel search, embodiments of this application introduce a virtual screen interface. Cross-platform parallel search is implemented based on the virtual screen interface.

[0065] In some embodiments of this application, a virtual screen interface refers to a logical display container created at the underlying level by an electronic device, independent of the physical display screen, used to carry and run search tasks and their result pages from different applications.

[0066] It's important to note that a virtual screen is not a real physical screen, but rather a lightweight rendering buffer allocated in memory by the electronic device through a window management mechanism. Each virtual screen interface corresponds to an application, possessing an independent runtime environment and interactive capabilities, but its displayed content is ultimately captured, reassembled, and drawn onto the display area of ​​the physical screen by the system.

[0067] Specifically, the virtual screen interface has the following technical characteristics: Logical independence: Each virtual screen interface has its own independent view hierarchy, event handling thread, and application state, enabling the complete execution of an application's native search page. For example, application A's search results page loads and renders normally in virtual screen interface A, while application B's search page loads in parallel in virtual screen interface B, without interfering with each other.

[0068] Physical sharing means that although the virtual screen interfaces are logically independent, they share the display resources of the same physical screen (the display screen of the electronic device). The electronic device can use composite layer technology to combine the rendering outputs of multiple virtual screen interfaces according to a preset layout (such as matrix, card, main and secondary windows), and finally present them as an aggregated search results interface on the physical screen.

[0069] Based on this, when the search strategy includes at least two applications, step 240 above may include steps 2401-2403 as follows.

[0070] Step 2401. Create at least two virtual screen interfaces that correspond one-to-one with at least two applications.

[0071] Step 2402. Perform a search operation based on the first information in parallel on at least two virtual screen interfaces to obtain search information from at least two applications.

[0072] In some embodiments of this application, the electronic device can inject first information in parallel into the search interface or search page of each first application. The electronic device automatically triggers search requests in each virtual screen interface and obtains the search results data returned by each platform in real time, thereby obtaining search information from at least two applications.

[0073] Step 2403. Based on the search information from at least two applications, generate and display the search results interface.

[0074] In some embodiments of this application, a display area for each application can be divided in the search results interface, and the search information of each application can be displayed in the corresponding display area.

[0075] In some embodiments of this application, as described above, the search strategy may further include priority information. Based on this, when the search strategy includes at least two applications, a search result interface can be generated based on the priority of the at least two applications. For example, if the at least one application includes a first application and a second application, a search result interface can be generated based on the priority of the first application and the second application.

[0076] In some embodiments of this application, when generating a search results interface based on the priority of at least two applications, the layout information of the search information of the applications in the search results interface can be determined based on the priority information in the search strategy; the search results interface is then generated based on the layout information. The layout information of the search information indicates the layout format of the search information in the search results interface. The layout format may include, but is not limited to, a matrix or card format. Thus, multiple search results from multiple applications can be displayed in parallel in the search results interface based on the layout information.

[0077] In some embodiments of this application, when determining the layout information of the search information of an application in the search results interface based on the application's priority information, the target application with the highest priority among the applications can be identified. The search information corresponding to the target application is used as the window content displayed in the target area of ​​the search results interface. The search information corresponding to the other first applications besides the target application is used as the window content displayed in other areas of the search results interface, which are located around or to the side of the target area. The target area is the main display area of ​​the search results interface.

[0078] For example, see Figure 4The search strategy used included five applications: Application 1, Application 2, Application 3, Application 4, and Application 5. Application 2 had the highest priority. Based on this, in... Figure 4 In the search results interface 400 shown, the search information 410 of application 2 can be displayed in the central display area of ​​the search results interface 400, while the search information of other applications can be displayed in other display areas surrounding the central display area. In this way, users can prioritize viewing the search results of the applications with the highest priority.

[0079] The above describes a search solution directly based on the generated search strategy. Considering that users have specific search needs in practical applications, to achieve personalized searches based on actual user requirements, electronic devices are pre-set with several preset search strategies. Users can select the desired preset search strategy based on their needs. Thus, after obtaining the search strategy generated based on the initial information, the generated search strategy is adjusted based on the user-selected preset search strategy, and the search is performed based on the adjusted search strategy. Specifically, before generating and displaying the search results interface, steps 310-330 can be executed.

[0080] Step 310: Display at least one policy identifier, each policy identifier corresponding to an application category.

[0081] In some embodiments of this application, a strategy identifier corresponds to a preset search strategy, and a preset search strategy corresponds to a type of search subject. The preset search strategy includes a category of applications that matches the type of its corresponding search subject. Specifically, the preset search strategy can be set according to the type of its corresponding search subject, for example: Shopping search: Prioritize e-commerce and price comparison platforms; General search: Prioritize search engine results and encyclopedia results; Content community search: Prioritize communities and short video platforms; Maps / Local Services: Prioritizes maps, reviews, and trip information.

[0082] For example, see Figure 3Before generating and displaying the search results interface, a strategy selection panel can be displayed on the application interface 300. The strategy selection panel contains multiple interactive strategy icons, such as a voice input icon 310, a shopping strategy icon 320, a general strategy icon 330, and a more icon 340. The shopping strategy icon 320 and the general strategy icon 330 each correspond to a preset search strategy. In addition to the preset search strategies corresponding to the shopping strategy icon 320 and the general strategy icon 330, other preset search strategies can be set. These other preset search strategies can be viewed and selected by triggering the more icon 340.

[0083] Step 320: Receive a second input from the user for a first policy identifier among at least one policy identifier.

[0084] In some embodiments of this application, the second input is an input for selecting a strategy identifier corresponding to a preset search strategy to be used. Exemplarily, the second input may include, but is not limited to, click input, long-press input, drag input, etc. The first strategy identifier is the search identifier of the preset search strategy to be used by the user.

[0085] For example, when the first input is a long press, the user can slide their finger or touch device to the desired policy identifier while maintaining the long press state, thereby selecting the policy identifier. This allows for real-time intervention in the search strategy without interrupting the user's trigger gesture.

[0086] Step 330: In response to the second input, identify at least one application corresponding to the first strategy identifier as at least one search application.

[0087] In some embodiments of this application, the electronic device may adjust the generated search strategy based on the preset search strategy corresponding to the first strategy identifier, and determine the application included in the adjusted search strategy as the search application used during the search.

[0088] In some embodiments of this application, the produced search strategy can be used as the base strategy, and the search platform set and priority information in the preset search strategy selected by the user can be used to cover the search platform set and priority information in the strategy to obtain the adjusted search strategy.

[0089] The following combination Figure 3 The shopping-related strategy identifier 320 and the general strategy identifier 330 in the document explain the strategy adjustment method based on the predictive search strategy.

[0090] For example, when a user moves their finger to the shopping strategy identifier 320, the electronic device can switch the generated search strategy to a preset shopping search strategy. The applications in the shopping search strategy include e-commerce platforms, price comparison platforms, and product communities, with platform priority being: price comparison platforms have the highest priority. Therefore, e-commerce platforms, price comparison platforms, and product communities are used as search applications, with the highest priority for price comparison platforms being used as the priority information for the search application.

[0091] For example, if a user long-presses on a picture of a popular hair dryer on a short video platform, the default search strategy might be a comprehensive search strategy under a general intent, including applications such as a general search engine (E), an encyclopedia platform (F), and a video platform (H). However, if the user actually wants to compare prices for the product, they can swipe their finger to the shopping-specific strategy indicator (position 320). At this point, the electronic device can update the applications in the generated search strategy to those more suitable for the shopping scenario, such as e-commerce platform A, e-commerce platform B, and price comparison platform C, and update the priority information so that price comparison platform C has a higher priority as set in the shopping-specific strategy. The updated search strategy will then be used for subsequent searches.

[0092] For example, when a user moves their finger to the general search strategy identifier 330, the electronic device can switch the generated search strategy combination to a preset general search strategy. In the general search strategy, applications include general search engines, encyclopedia platforms, and Q&A communities, suitable for scenarios where users want to obtain background knowledge, concept explanations, news information, etc. The priority information and settings for these applications prioritize the general search engine.

[0093] For example, when a user long-presses on a news image about a "quantum computing prototype" in a news app, the electronic device's default search strategy is an academic intent search strategy. The applications included are academic databases (L), news media (M), and encyclopedia platforms (N), with academic database L having the highest priority. In this scenario, if the user swipes their finger to the general search strategy identifier 330, the electronic device can update the applications in the generated search strategy to those more suited to the general scenario, such as a general search engine (E), encyclopedia platform (F), or community platform (G). It will also update the priority information in the first search strategy combination strategy to prioritize the general search engine (E) as the highest priority.

[0094] The above methods allow for quick switching of search strategies.

[0095] Accordingly, after adjusting the search strategy based on the preset search strategy, step 240 above, which involves searching in at least one application based on the first information, can be specifically implemented as follows: searching in at least one search application based on the first information. Then, a search results interface is generated and displayed based on the search information from at least one search application.

[0096] The method of searching in at least one search application based on the first information is the same as the method of searching in at least one application indicated in the generated search strategy based on the first information, and the method of generating and displaying the search results interface is also the same. For specific implementation details, please refer to the relevant descriptions in the above embodiments; to avoid repetition, they will not be elaborated further here.

[0097] In some embodiments of this application, the electronic device supports voice input, based on which users can also use natural language input to adjust the generated search strategy. Specifically, before generating and displaying the search results interface, a second voice input from the user can also be received; wherein, the voice information corresponding to the second voice input includes second search control parameters.

[0098] Accordingly, in step 240 above, a search can be performed in at least one application based on the first information and the second search control parameters, and a search results interface can be generated and displayed based on the search information obtained from the search.

[0099] In some embodiments of this application, the voice information corresponding to the second voice input is voice information used to adjust the generated search strategy, including second search control parameters. The second search control parameters include, but are not limited to, search platform control parameters, filtering control parameters, and priority control parameters. Specifically, the search platform control parameters are used to adjust the applications in the generated search strategy, including adding or removing applications; the filtering control parameters are used to add or adjust search conditions; and the priority control parameters are used to adjust the priority information in the search strategy.

[0100] In practical applications, users can input second search control parameters into electronic devices via second voice input. The electronic devices can then perform semantic parsing on the voice information corresponding to the second voice input to obtain structured second search control parameters. Based on these parameters, the search strategy can be updated, and a search result interface can be generated.

[0101] For example, when a user selects to adjust the search strategy using natural language input, they can move their finger to, for instance,... Figure 3When the voice input indicator is at position 310, the electronic device automatically activates the voice recording function and begins receiving the user's natural language voice input. The user can state their personalized requirements for the search; for example, in a shopping scenario, the input voice information could be "Only e-commerce platform A and e-commerce platform B, with e-commerce platform A preferred, and the product price below 2,000." After the voice input is completed, the electronic device performs semantic analysis on the recorded voice information, extracts structured second search control parameters, and uses these parameters to update the search strategy, thus obtaining the updated search strategy.

[0102] For example, when a user long-presses an image of a brand of sneakers in a social media app, the default search strategy includes e-commerce platform A, e-commerce platform B, price comparison platform C, and community platform D, with price comparison platform C having the highest priority. The user then voice-inputs: "Only view e-commerce platforms A and B, with e-commerce platform A prioritized, and the latest releases." Semantic parsing of this voice information yields the following second search control parameter: Search platform control parameters: Only retain e-commerce platform A and e-commerce platform B, remove price comparison platform C and community platform D; Filtering control parameters: Add "newly released styles" as a search criterion; Priority control parameter: Update the priority information to: E-commerce platform A has the highest priority.

[0103] Based on the second search control parameters mentioned above, and using the generated search strategy as the baseline strategy, the price comparison platform C and community platform D are removed from the baseline strategy. The search condition "newly released styles" is added to the baseline strategy, and the priority information is updated to: e-commerce platform A has the highest priority. Thus, an updated search strategy is obtained that includes e-commerce platform A and e-commerce platform B, with e-commerce platform A having the highest priority and including the search condition "newly released styles."

[0104] In this way, users can adjust the search strategy via voice, which is simple and convenient.

[0105] Accordingly, after updating the search strategy based on voice input, in step 240 above, the search is no longer performed based on the generated search strategy, nor is the search result interface generated and displayed. Instead, the search is performed based on the updated search strategy, and the search result interface is generated and displayed. The method of performing the search based on the updated search strategy and generating and displaying the search result interface is essentially the same as that of performing the search based on the generated search strategy. It simply involves obtaining search information based on the updated search strategy, filtering the search information based on search criteria, and then generating and displaying the search result interface based on the filtered search information. For specific implementation details, please refer to the relevant descriptions in the above embodiments; to avoid repetition, they will not be repeated here.

[0106] The above methods enable a strategy decision-making mechanism that allows for intent-based default strategy generation, user-selectable preset strategies, and fine-tuning of voice input. This allows application combinations and result display formats to better align with users' actual needs.

[0107] In some embodiments of this application, after the search results interface is displayed, the user can perform normal application-level swiping and clicking within the search results interface to view the search information.

[0108] For example, users can access such... Figure 4 The search information 410 for application 2 displayed in the middle display area is shown. Sliding it to the left switches the content displayed in the middle display area to the following: Figure 5 The search information for application 3 shown is 510.

[0109] Using the above method, users can view search results from different platforms on the same interface without having to switch pages or repeatedly initiate a search.

[0110] In some embodiments of this application, after displaying the search results interface, the electronic device can activate the voice reception function. If the user needs further adjustments to the search information in the search results interface, these adjustments can also be made through natural language input. Based on this, after displaying the search results interface, the electronic device can receive the user's initial voice input.

[0111] In some embodiments of this application, such as Figure 6 As shown, the search results interface 600 may include a voice input identifier 610, which users can use to input voice by long-pressing the voice input identifier 610.

[0112] Step 120. In response to the first voice input, update the display content or display parameters of the search results interface.

[0113] In some embodiments of this application, the voice information corresponding to the first voice input is natural voice information input by the user for adjusting the search information in the search results interface. After receiving the user's first voice input, the electronic device performs semantic analysis on the voice information corresponding to the first voice input to obtain the first search control parameters; and then updates the display content or display parameters of the search results interface based on the first search control parameters.

[0114] In some embodiments of this application, similar to the second voice input, the first search control parameters obtained from the first voice input include, but are not limited to, search platform control parameters, filtering control parameters, and priority control parameters. The search platform control parameters are used to adjust the application used for searching; the priority control parameters are used to adjust the priority of the application; and the filtering control parameters are used to adjust the search criteria.

[0115] In some embodiments of this application, when the first search control parameter includes search platform control parameters, step 120 above may include: Update the displayed content or parameters of the search results interface based on the adjusted application.

[0116] In some embodiments of this application, when the first search control parameter includes a priority control parameter, step 120 above may include: Based on priority control parameters, adjust the display parameters of the search results interface; among which, the display parameters include layout information.

[0117] In some embodiments of this application, when the first search control parameter includes a filtering control parameter, step 120 above may include: The content displayed in the search results interface is updated based on the filtering control parameters.

[0118] For example: When a user long-presses an image of product A in a social application interface, the generated search strategy is a combination of strategies based on the user's intent. The applications included are App 1, App 2, App 3, App 4, and App 5—a total of five applications. After the search, the user presses... Figure 6 The layout shown displays the search results. After browsing the search results, the user finds they want to know more about product A in applications 6, 7, 8, 9, and 10. They then long-press the voice input icon 610 and say, "Change the applications to applications 6, 7, 8, 9, and 10, with application 6 having the highest priority." Semantic parsing of the above voice information yields the following first search control parameters: Search platform control parameters: Update the search platform set to "Application 6, Application 7, Application 8, Application 9 and Application 10"; Priority control parameter: Update the priority information to application 6, which has the highest priority.

[0119] Based on this, the search strategy and search results are updated to obtain, as follows: Figure 7 The search results page shown is 700.

[0120] In this embodiment, when displaying the search results interface, a first voice input from the user is received; wherein the search results interface includes search information corresponding to at least one application; in response to the first voice input, the display content or display parameters of the search results interface are updated. According to this embodiment, when viewing search results, if the user needs to adjust them, there is no need to exit the current search results interface, return to the search input page, or restart the search. The user can simply input a voice command directly in the search results interface to adjust the display content or display parameters in real time, shortening the user's operation path, improving interaction efficiency, and maintaining the continuity and immersion of the interaction without interrupting the viewing process.

[0121] The information search method provided in this application can be executed by an information search device. This application uses an information search device executing the information search method as an example to illustrate the information search device provided in this application.

[0122] See Figure 8 The above is a schematic diagram of an information search device provided in some embodiments of this application, such as... Figure 8 The information search device 800 provided in this embodiment of the application includes the following modules: The audio module 801 is used to receive the user's first voice input when the search results interface is displayed; wherein the search results interface includes search information corresponding to at least one application. The processing module 802 is used to update the display content or display parameters of the search results interface in response to the first voice input.

[0123] In some embodiments of this application, the processing module 802 is specifically used for: Perform semantic parsing on the voice information corresponding to the first voice input to obtain the first search control parameters; Based on the first search control parameters, update the displayed content or display parameters of the search results interface.

[0124] In some embodiments of this application, the first search control parameter includes search platform control parameters, which are used to adjust the application used for searching; the processing module 802 is specifically used for: Update the displayed content or parameters of the search results interface based on the adjusted application.

[0125] In some embodiments of this application, the first search control parameter includes a priority control parameter, which is used to adjust the priority of the application; the processing module 802 is specifically used for: Adjust the display parameters of the search results interface based on priority control parameters; The display parameters include layout information.

[0126] In some embodiments of this application, the first search control parameter includes a filtering control parameter, which is used to adjust the search conditions; the processing module 802 is specifically used for: The content displayed in the search results interface is updated based on the filtering control parameters.

[0127] In some embodiments of this application, the device 800 further includes: a receiving module and a display module; The receiving module is used to receive the user's first input to any application interface before receiving the user's first voice input; The processing module 802 is further configured to: in response to the first input, acquire first information; determine at least one application based on the first information; and perform a search in the at least one application based on the first information to generate a search results interface; The display module is used to display the search results interface.

[0128] In some embodiments of this application, at least one application includes a first application and a second application; the processing module 802 is specifically used for: The search results interface is generated based on the priority of the first and second applications.

[0129] In some embodiments of this application, the display module is further configured to display at least one strategy identifier before generating and displaying the search results interface, each strategy identifier corresponding to an application of a category; The receiving module is also configured to receive a second input from the user for a first policy identifier in at least one policy identifier; Processing module 802 is further configured to, in response to the second input, identify at least one application corresponding to the first strategy identifier as at least one search application; The processing module 802 is also configured to: perform a search in at least one search application based on the first information.

[0130] In some embodiments of this application, the audio receiving module 801 is further configured to receive a second voice input from the user before generating and displaying the search results interface; wherein the voice information corresponding to the second voice input includes a second search control parameter; Processing module 802 is used to perform a search in at least one application based on first information and second search control parameters.

[0131] The information search device in this application embodiment can be an electronic device or a component within an electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal or other devices besides a terminal. For example, the electronic device can be a mobile phone, tablet computer, laptop computer, PDA, in-vehicle electronic device, mobile internet device (MID), augmented reality (AR) / virtual reality (VR) device, robot, wearable device, ultra-mobile personal computer (UMPC), netbook, or personal digital assistant (PDA), etc. It can also be a server, network attached storage (NAS), personal computer (PC), television (TV), ATM, or self-service machine, etc. This application embodiment does not specifically limit the device.

[0132] The information search device in this application embodiment can be a device with an operating system. This operating system can be Android, iOS, or other possible operating systems; this application embodiment does not specifically limit the specific operating system used.

[0133] The information search device provided in this application embodiment can achieve... Figures 1 to 7 The various processes implemented in the method embodiments achieve the same technical effect, and will not be described again here to avoid repetition.

[0134] Optionally, such as Figure 9 As shown, this application embodiment also provides an electronic device 900, including a processor 901 and a memory 902. The memory 902 stores a program or instructions that can run on the processor 901. When the program or instructions are executed by the processor 901, they implement the various steps of the above-described information search method embodiment and can achieve the same technical effect. To avoid repetition, they will not be described again here.

[0135] It should be noted that the electronic devices in the embodiments of this application include the mobile electronic devices and non-mobile electronic devices described above.

[0136] Figure 10 A schematic diagram of the hardware structure of an electronic device to implement an embodiment of this application.

[0137] The electronic device 1000 includes, but is not limited to, the following components: radio frequency unit 1001, network module 1002, audio output unit 1003, input unit 1004, sensor 1005, display unit 1006, user input unit 1007, interface unit 1008, memory 1009, and processor 1010.

[0138] Those skilled in the art will understand that the electronic device 1000 may also include a power supply (such as a battery) for supplying power to various components. The power supply may be logically connected to the processor 1010 through a power management system, thereby enabling functions such as managing charging, discharging, and power consumption through the power management system. Figure 10 The electronic device structure shown does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown, or combine certain components, or have different component arrangements, which will not be elaborated here.

[0139] The microphone 10042 is used to receive the user's first voice input when the search results interface is displayed; wherein the search results interface includes search information corresponding to at least one application. Processor 1010 is used to update the displayed content or display parameters of the search results interface in response to the first voice input.

[0140] In some embodiments of this application, the processor 1010 is specifically used for: Perform semantic parsing on the voice information corresponding to the first voice input to obtain the first search control parameters; Based on the first search control parameters, update the displayed content or display parameters of the search results interface.

[0141] In some embodiments of this application, the first search control parameters include search platform control parameters, which are used to adjust the application used for searching; the processor 1010 is specifically used for: Update the displayed content or parameters of the search results interface based on the adjusted application.

[0142] In some embodiments of this application, the first search control parameter includes a priority control parameter, which is used to adjust the priority of the application; the processor 1010 is specifically used for: Adjust the display parameters of the search results interface based on priority control parameters; The display parameters include layout information.

[0143] In some embodiments of this application, the first search control parameter includes a filtering control parameter, which is used to adjust the search conditions; the processor 1010 is specifically used for: The content displayed in the search results interface is updated based on the filtering control parameters.

[0144] In some embodiments of this application, the device 800 further includes: a user input unit 1007 and a display unit 1006; User input unit 1007 is used to receive the user's first input on any application interface before receiving the user's first voice input; The processor 1010 is also used for: In response to the first input, obtain the first information; At least one application is identified based on the first information; Based on the first information, a search is performed in at least one application to generate a search results interface; Display unit 1006 is used to display the search results interface.

[0145] In some embodiments of this application, at least one application includes a first application and a second application; the processor 1010 is specifically used for: The search results interface is generated based on the priority of the first and second applications.

[0146] In some embodiments of this application, the display unit 1006 is further configured to display at least one strategy identifier before generating and displaying the search results interface, each strategy identifier corresponding to an application of a category; User input unit 1007 is also configured to receive a second input from a user for a first policy identifier among at least one policy identifier; The processor 1010 is also configured to, in response to the second input, identify at least one application corresponding to the first policy identifier as at least one search application; The processor 1010 is also used for: Based on the first information, a search is performed in at least one search application.

[0147] In some embodiments of this application, the microphone 10042 is further configured to receive a second voice input from the user before generating and displaying the search results interface; wherein the voice information corresponding to the second voice input includes second search control parameters; Processor 1010 is used to perform a search in at least one application based on first information and second search control parameters.

[0148] It should be understood that, in this embodiment, the input unit 1004 may include a graphics processing unit (GPU) 10041 and a microphone 10042. The GPU 10041 processes image data of still images or videos obtained by an image capture device (such as a camera) in video capture mode or image capture mode. The display unit 1006 may include a display panel 10061, which may be configured in the form of a liquid crystal display, an organic light-emitting diode, etc. The user input unit 1007 includes at least one of a touch panel 10071 and other input devices 10072. The touch panel 10071 is also called a touch screen. The touch panel 10071 may include a touch detection device and a touch controller. Other input devices 10072 may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, power buttons, etc.), trackballs, mice, joysticks, etc., which will not be described in detail here.

[0149] The memory 1009 can be used to store software programs and various data. The memory 1009 may primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area may store the operating system, application programs or instructions required for at least one function (such as sound playback, image playback, etc.). Furthermore, the memory 1009 may include volatile memory or non-volatile memory, or both. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus RAM (DRRAM). The memory 1009 in this embodiment includes, but is not limited to, these and any other suitable types of memory.

[0150] The processor 1010 may include one or more processing units; optionally, the processor 1010 integrates an application processor and a modem processor, wherein the application processor mainly handles operations involving the operating system, user interface, and applications, and the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into the processor 1010.

[0151] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described information search method embodiments and achieve the same technical effects. To avoid repetition, they will not be described again here.

[0152] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0153] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above-described information search method embodiments and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0154] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0155] This application provides a computer program product, which is stored in a storage medium and executed by at least one processor to implement the various processes of the information search method embodiments described above, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0156] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0157] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0158] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. An information search method, characterized in that, The method includes: When displaying the search results interface, the system receives the user's first voice input; wherein the search results interface includes search information corresponding to at least one application. In response to the first voice input, update the displayed content or display parameters of the search results interface.

2. The method according to claim 1, characterized in that, The step of updating the display content or display parameters of the search results interface in response to the first voice input includes: Perform semantic parsing on the voice information corresponding to the first voice input to obtain the first search control parameters; Based on the first search control parameters, update the display content or display parameters of the search results interface.

3. The method according to claim 2, characterized in that, The first search control parameters include search platform control parameters, which are used to adjust the application used for searching; The step of updating the display content or display parameters of the search results interface based on the first search control parameters includes: The displayed content or parameters of the search results interface are updated based on the adjusted application.

4. The method according to claim 2, characterized in that, The first search control parameter includes a priority control parameter, which is used to adjust the priority of the application. The step of updating the display content or display parameters of the search results interface based on the first search control parameters includes: Based on the priority control parameters, adjust the display parameters of the search results interface; The display parameters include layout information.

5. The method according to claim 2, characterized in that, The first search control parameter includes a filtering control parameter, which is used to adjust the search conditions; The step of updating the display content or display parameters of the search results interface based on the first search control parameters includes: Based on the filtering control parameters, the content displayed in the search results interface is updated.

6. The method according to any one of claims 1-5, characterized in that, Before receiving the user's first voice input, the method further includes: Receive the user's first input to any application interface; In response to the first input, obtain the first information; At least one application is identified based on the first information; Based on the first information, a search is performed in the at least one application to generate and display a search results interface.

7. The method according to claim 6, characterized in that, The at least one application includes a first application and a second application; The process of generating and displaying search results includes: A search results interface is generated based on the priority of the first application and the second application.

8. The method according to claim 6, characterized in that, Before generating and displaying the search results interface, the method further includes: Display at least one policy identifier, each policy identifier corresponding to an application category; Receive a second input from the user for a first policy identifier among the at least one policy identifier; In response to the second input, at least one application corresponding to the first policy identifier is identified as at least one search application; The search based on the first information in the at least one application includes: Based on the first information, a search is performed in the at least one search application.

9. The method according to claim 6, characterized in that, Before generating and displaying the search results interface, the method further includes: Receive a second voice input from the user; wherein the voice information corresponding to the second voice input includes a second search control parameter; The search based on the first information in the at least one application includes: A search is performed in the at least one application based on the first information and the second search control parameters.

10. An information search device, characterized in that, include: A voice module is used to receive the user's first voice input when the search results interface is displayed; wherein the search results interface includes search information corresponding to at least one application; The processing module is used to update the display content or display parameters of the search results interface in response to the first voice input.

Images