Content search method and apparatus, device, and storage medium
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2026-02-06
- Publication Date
- 2026-08-13
Smart Images
Figure CN2026077626_13082026_PF_FP_ABST
Abstract
Description
Methods, apparatus, devices and storage media for content search
[0001] This application claims priority to Chinese Patent Application No. 202510134402.9, filed on February 6, 2025, entitled "Method, Apparatus, Device and Storage Medium for Content Search", the entire contents of which are incorporated herein by reference. Technical Field
[0002] The exemplary embodiments disclosed herein relate generally to the field of computers, and more particularly to methods, apparatus, devices, and computer-readable storage media for content search. Background Technology
[0003] With the rapid development of the internet, more and more applications are able to provide users with a wide variety of content. This diverse content offers information on various aspects of life, including consultation, education, lifestyle, and entertainment. Users often have search needs for certain content while using these applications, and they can use the applications themselves to search for that specific content. Summary of the Invention
[0004] In a first aspect of this disclosure, a method for content search is provided. The method includes: in response to receiving a search term, providing response content for the search term, the response content including an information viewing component constructed by a model based on search results corresponding to the search term; and presenting first information matching the first filter term in the information viewing component based on a first filter term associated with the information viewing component.
[0005] In a second aspect of this disclosure, an apparatus for content search is provided. The apparatus includes: a providing module configured to provide response content for the search term in response to receiving a search term, the response content including an information viewing component constructed by a model based on search results corresponding to the search term; and a presenting module configured to present first information matching the first filter item in the information viewing component based on a first filter item associated with the information viewing component.
[0006] In a third aspect of this disclosure, an electronic device is provided. The device includes at least one processor; and at least one memory coupled to the at least one processor and storing instructions for execution by the at least one processor. When executed by the at least one processor, the instructions cause the device to perform the method of the first aspect.
[0007] In a fourth aspect of this disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores computer-executable instructions that can be executed by a processor to implement the method of the first aspect.
[0008] In a fifth aspect of this disclosure, a computer program product is provided. The computer program product is tangibly stored in a computer storage medium and includes computer-executable instructions that, when executed by a device, cause the device to perform the method of the first aspect.
[0009] It should be understood that the content described in this content section is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description
[0010] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:
[0011] Figure 1 shows a schematic diagram of an example environment in which embodiments of the present disclosure may be implemented;
[0012] Figures 2A and 2B illustrate example interfaces according to some embodiments of the present disclosure;
[0013] Figure 3 illustrates a flowchart of an example process for viewing build information components according to some embodiments of the present disclosure;
[0014] Figure 4 illustrates a flowchart of an example process for content search according to some embodiments of the present disclosure;
[0015] Figure 5 shows a schematic structural block diagram of an example device for content search according to some embodiments of the present disclosure; and
[0016] Figure 6 shows a block diagram of an electronic device capable of implementing several embodiments of the present disclosure. Detailed Implementation
[0017] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.
[0018] It should be noted that the headings of any section / subsection provided herein are not limiting. Various embodiments are described throughout this document, and embodiments of any type may be included under any section / subsection. Furthermore, embodiments described in any section / subsection may be combined in any way with any other embodiments described in the same section / subsection and / or different sections / subsections.
[0019] In the description of embodiments of this disclosure, the term "comprising" and similar terms should be understood as open-ended inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may also be included below. The terms "first", "second", etc., may refer to different or the same objects. Other explicit and implicit definitions may also be included below.
[0020] The embodiments of this disclosure may involve user data, data acquisition, and / or use. All of these aspects comply with applicable laws, regulations, and relevant provisions. In the embodiments of this disclosure, all data collection, acquisition, processing, manipulation, forwarding, and use are conducted with the user's knowledge and confirmation. Accordingly, in implementing the embodiments of this disclosure, the type, scope of use, and usage scenarios of any data or information that may be involved should be communicated to the user and their authorization obtained in accordance with relevant laws and regulations through appropriate means. The specific methods of notification and / or authorization may vary depending on the actual situation and application scenario, and the scope of this disclosure is not limited in this respect.
[0021] In this specification and the embodiments, any processing of personal information will be carried out only under the premise of legality (such as obtaining the consent of the personal information subject, or being necessary for the performance of a contract), and will only be carried out within the scope stipulated 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 basic functions.
[0022] As mentioned above, with the rapid development of the internet, more and more applications are able to provide users with a wide variety of content. This diverse content offers information on various aspects of life, including consultation, education, lifestyle, and entertainment. Users often have search needs for certain content while using these applications, and in such cases, they can use the applications to search for that specific content.
[0023] Embodiments of this disclosure propose a content search scheme. The scheme includes: in response to receiving a search term, providing response content for the search term, the response content including an information viewing component constructed by a model based on search results corresponding to the search term; and presenting first information matching the first filter term in the information viewing component based on a first filter term associated with the information viewing component.
[0024] In this way, embodiments of the present disclosure can construct information viewing components through models, thereby making the first information in the information viewing components more accurate.
[0025] The following section provides a detailed description of various example implementations of this scheme, with reference to the accompanying drawings.
[0026] Example Environment
[0027] Figure 1 illustrates a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. As shown in Figure 1, the example environment 100 may include an electronic device 110.
[0028] In this example environment 100, electronic device 110 may run an application 120 that supports content search. Application 120 may be any suitable type of application for content search, examples of which may include, but are not limited to, content sharing applications, social applications, online video applications, or other suitable applications. User 140 may interact with application 120 via electronic device 110 and / or its attached devices.
[0029] In environment 100 of Figure 1, if application 120 is active, electronic device 110 can present interface 150 for supporting content search through application 120.
[0030] In some embodiments, electronic device 110 communicates with server 130 to provide services to application 120. Electronic device 110 can be any type of mobile terminal, fixed terminal, or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, handheld computers, portable gaming terminals, VR / AR devices, personal communication system (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio receivers, e-book devices, gaming devices, or any combination thereof, including accessories and peripherals of these devices or any combination thereof. In some embodiments, electronic device 110 can also support any type of user-facing interface (such as "wearable" circuitry).
[0031] Server 130 can be a standalone 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 communication, middleware services, domain name services, security services, content delivery networks, and big data and artificial intelligence platforms. Server 130 may include, for example, computing systems / servers such as mainframes, edge computing nodes, computing devices in a cloud environment, etc. Server 130 can provide backend services for applications 120 that support content search in electronic devices 110.
[0032] A communication connection can be established between server 130 and electronic device 110. This communication connection can be established via wired or wireless means. The communication connection may include, but is not limited to, Bluetooth, mobile network, Universal Serial Bus (USB), and Wireless Fidelity (WiFi) connections; the embodiments of this disclosure are not limited in this respect. In the embodiments of this disclosure, server 130 and electronic device 110 can achieve signaling interaction through the communication connection between them.
[0033] It should be understood that the structure and function of the various elements in environment 100 are described for illustrative purposes only and do not imply any limitation on the scope of this disclosure.
[0034] The following description will continue with reference to the accompanying drawings, which will provide some exemplary embodiments of this disclosure.
[0035] Example Interaction
[0036] Figures 2A and 2B illustrate example interfaces 200A to 200B according to some embodiments of the present disclosure. Interfaces 200A to 200B may be provided, for example, by the electronic device 110 shown in Figure 1.
[0037] In some embodiments, in response to receiving a search term, the electronic device 110 provides response content for the search term, the response content including an information viewing component constructed by a model based on the search results corresponding to the search term.
[0038] As an example, as shown in FIG2A, FIG2A illustrates an example interface 200A according to some embodiments of the present disclosure. After receiving a search term input by user 140, electronic device 110 can present the interface 200A as shown in FIG2A. Interface 200A can, for example, be used to present a search results page. Interface 200A includes multiple response contents associated with the search term; such response contents may include, for example, multiple text contents or media contents associated with the search term. For example, if the search term is "which university is good," then the response contents associated with that search term may include introductions to multiple universities.
[0039] In some scenarios, the search results associated with the search term also include an information viewing component 205 (also known as a search card). The information viewing component 205 is associated with the search term; that is, the content in the information viewing component 205 is related to the search term. The information viewing component 205 may, for example, be constructed by the server 130 based on the search results of the search term and a preset component template.
[0040] In some embodiments, the response content also includes reply text generated by the model based on the search term. As an example, as shown in Figure 2A, the information viewing component 205 includes a content summary component 210, which includes reply text associated with multiple search results. For example, if the search term is "Which university is good in City A", then the summary information in the content summary component 210 could be "City A has University A, University B, and University C. In terms of comprehensive academic disciplines, University B is the better university in City A."
[0041] In some embodiments, electronic device 110 presents first information matching the first filter item in the information viewing component based on a first filter item associated with the information viewing component. The first filter item is determined based on a search term. As an example, as shown in FIG2A, when the information viewing component 205 is presented, electronic device 110 can present the first information matching the first filter item in the content display component of the information viewing component 205. The first filter item may be determined by server 130 based on a search term, such as "Which university is good in City A", then the first filter item may include the region indicated in the search term, i.e., "City A".
[0042] In some scenarios, the information viewing component 205 also includes a content display component 215, which can be used to present the first information matching the first filter item. For example, if the search term is "Which university is good in City A", the first information could include the rankings and types of universities in City A, such as comprehensive, science and engineering, and arts and law. The content display component 215 can present the information in a table format, thus better listing the information.
[0043] In other scenarios, as shown in Figure 2B, after presenting the information viewing component 205, the electronic device 110 can also present the content display component 215 in a card format. The presentation style of the content display component 215 can be associated with the search terms received by the electronic device 110. When the content of the search term indicates a comparison of multiple objects, the electronic device 110 can present the content display component 215 in a table format; when the content of the search term indicates a specific type of object, the electronic device 110 can present the content display component 215 in a card format. For example, when the content of the search term is "Which university in City A is good?", the electronic device 110 can present the content display component 215 in a list format. When the content of the search term is "Recommended reading materials for primary and secondary schools", the electronic device 110 can present the content display component 215 in a card format, where each card in the content display component 215 represents a recommended book.
[0044] In this way, embodiments of the present disclosure can present the information viewing component 205 in different presentation styles, thereby enabling the information viewing component 205 to present information associated with the search terms more clearly and concisely, so as to make it more efficient for users to obtain information.
[0045] In some embodiments, the information viewing component includes a filter control, and the electronic device 110 can determine a second filter item based on a user action associated with the filter control. Further, the electronic device 110 can update the information viewing component to present second information that matches the second filter item.
[0046] As an example, when the content display component 215 is presented, the electronic device 110 can also present a filter control 220 within the content display component. The filter control 220 includes multiple attribute selection bars, each indicating a content filter attribute. For example, when the search term is "How many students does University A recruit in City A?", the content filter attributes could include location attributes (e.g., "City A", "City B", etc.), year attributes (e.g., "2023", "2022", etc.), and other content filter attributes associated with the search term. The electronic device 110 can acquire user interaction with the filter control 220, such interaction could be, for example, selecting a content filter attribute in any conditional attribute selection bar. Furthermore, the electronic device 110 can determine a second filter based on the acquired interaction, thereby presenting second information matching the second filter in the content display component 215 of the information viewing component 205. In this way, the content in the information viewing component 205 can be modified by changing the content filter attributes in the filter control, thus simplifying the information retrieval process and improving the efficiency of information retrieval.
[0047] In this way, embodiments of the present disclosure can construct information viewing components through models, thereby making the first information in the information viewing components more accurate.
[0048] Example component building process
[0049] Figure 3 illustrates a flowchart of an example process 300 for viewing a build information component according to some embodiments of the present disclosure. Process 300 may be implemented at electronic device 110 or server 130. Process 300 will now be described with reference to Figure 1.
[0050] In some embodiments, after receiving a search term, the electronic device 110 can send the search term to the server 130, enabling the server 130 to construct an example component based on the received search term. Specifically, the server 130 can retrieve historical search results corresponding to the historical search terms in response to a similarity between the search term and historical search terms exceeding a first threshold. After retrieving the historical search results, the server 130 can determine historical structured data for the search term based on the historical search results. Further, the server 130 can construct an information viewing component based on the historical structured data.
[0051] As an example, Figure 3 illustrates the construction process of an example information viewing component according to some embodiments of this disclosure. After receiving a search term 310, the electronic device 110 can send the search term to the server 130 to obtain the information viewing component 205 constructed by the server 130 and multiple search results associated with the search term. After receiving the search term, the server 130 can perform standardization processing on the search term using the search term standardization module 320 to determine whether the similarity between the search term 310 and historical search terms in the cache is greater than a first threshold. Such similarity could be, for example, cosine similarity.
[0052] When the server 130 determines that the similarity between the search item 310 and the historical search item in the cache is greater than the first threshold, the server 130 can use the cache reading module 330 to retrieve the historical search results associated with the historical search item from the cache, and construct the information viewing component 205 based on the historical structured data corresponding to the historical search results.
[0053] In some embodiments, when server 130 determines that the similarity between search term 310 and historical search terms in the cache is no greater than a first threshold, server 130 can generate information viewing component 205 through a model. Specifically, server 130 can provide search term and tool description information to the model to determine multiple subtasks associated with the search term. These multiple subtasks include several of the following: comparison tasks, judgment tasks, query tasks, and transformation tasks. Typically, content search tasks involve multiple pieces of basic information or multiple summaries and calculations, making it difficult to process content search tasks using only a single task. By breaking down content search tasks and processing different subtasks separately, the complexity of task processing can be effectively reduced, thereby improving the efficiency of content search and the accuracy of the search results.
[0054] As an example, when server 130 determines that the similarity between search term 310 and historical search terms in the cache is no greater than a first threshold, server 130 can use the intelligent agent module 340 to decompose the task using a model. After the model decomposes the task, server 130 can determine multiple sub-tasks associated with the search term. Specifically, server 130 can pre-store multiple candidate tools, each corresponding to a tool description. When constructing the information viewing component 205, server 130 can provide the search term and multiple tool descriptions to the model through the intelligent agent module 340 to decompose the task. For example, if server 130 pre-stores query tools and comparison tools, server 130 can provide the model with the search term, the tool descriptions corresponding to the query tools, and the tool descriptions corresponding to the comparison tools, thereby obtaining query tasks and comparison tasks through the model.
[0055] In some embodiments, after determining multiple subtasks, the server 130 can use a model to determine multiple tools and at least one invocation parameter corresponding to the multiple tools from a set of candidate tools indicated by the tool description information.
[0056] As an example, as shown in Figure 3, after the server 130 provides the model with search terms and tool descriptions, the model can not only split the task, but also determine multiple tools used to execute multiple sub-tasks and at least one calling parameter corresponding to each tool. Such calling parameters can be the main information in the search terms. For example, if the search term is "Is University B in City A good?", then the calling parameters can include "City A" and "University B".
[0057] In some embodiments, server 130 can determine structured data for a search term by invoking multiple tools corresponding to multiple subtasks. As an example, as shown in Figure 3, after multiple subtasks are determined by server 130, server 130 can utilize tool invocation module 350 to invoke multiple tools corresponding to the multiple subtasks to determine the structured data for the search term. For example, if the multiple subtasks include query tasks and comparison tasks, then server 130 can use tool invocation module 350 to invoke the corresponding tools (e.g., query tools and comparison tools) to process the above tasks, thereby obtaining the execution results of the query tasks and comparison tasks. Furthermore, server 130 can determine the structured data based on the execution results of the query tasks and comparison tasks.
[0058] In some embodiments, server 130 may determine multiple query statements corresponding to multiple tools based on search terms. After determining the multiple query statements, server 130 may determine query results corresponding to multiple tools based on the multiple query statements. Further, server 130 may determine structured data based on the multiple query results.
[0059] As an example, as shown in Figure 3, server 130 can obtain multiple query statements generated by the model through tool invocation module 350. These multiple query statements correspond to multiple tools. After obtaining the query statements, server 130 can retrieve multiple query results from the database based on the query statements. The multiple query results are used to support the corresponding tools in processing subtasks. Furthermore, server 130 can determine structured data based on the multiple tools and the multiple query results corresponding to the multiple tools.
[0060] In some scenarios, after obtaining multiple query structures, server 130 can summarize and deduplicate the query results, thereby removing redundant data and data whose match with the search terms is below the second threshold. This ensures the accuracy of the structured data used to generate the information viewing component 205.
[0061] In some embodiments, server 130 can split multiple query results into multiple dimensions to enable the constructed information viewing component 205 to present the user's searched information in a more organized manner. Specifically, server 130 can determine at least one data summary dimension based on the search terms. Further, server 130 can process multiple query results based on at least one data summary dimension to determine structured data.
[0062] As an example, after obtaining multiple query results, server 130 can invoke the model through the retrieval enhancement generation module 360 to determine multiple data summary dimensions associated with the search term. For instance, if the search term is "admissions information for universities in Province A," the model can generate multiple data summary dimensions based on this search term. These multiple data summary dimensions could include, for example, a regional dimension (e.g., "City A" and "City B" within "Province A"), a school dimension (e.g., different schools within "Province A," such as "University A" and "University B"), and a school type dimension (e.g., "comprehensive," "science and engineering," and "humanities"). After determining these multiple data summary dimensions, server 130 can determine the structured data based on these dimensions and the multiple query results.
[0063] In some embodiments, the structured data corresponds to a preset output format, which is associated with the type of the information viewing component. For example, the type of the information viewing component 205 could be its presentation style, such as a card style or a table style. The server 130 can determine the presentation style of the information viewing component 205 based on the content of the search term. Once the presentation style of the information viewing component 205 is determined, the server 130 can obtain the output format corresponding to the structured data based on the determined presentation style.
[0064] In some scenarios, before the structured data is output, the server 130 can filter the structured data through the data validation and filtering module 370 to ensure that the structured data meets preset conditions. Such preset conditions could be, for example, the relevance between the structured data and the search terms. These preset conditions can be set by those skilled in the art, and this disclosure does not impose any limitations on them.
[0065] In some embodiments, after obtaining structured data, the server 130 can construct the information viewing component 205 based on the obtained structured data. As an example, after determining the presentation style of the information viewing component 205, the server 130 can determine a template for constructing the component based on the presentation style of the information viewing component 205. Further, the server 130 can populate the template with structured data in a determined output format to construct the information viewing component 205.
[0066] In this way, embodiments of the present disclosure can utilize language models to generate the information needed by the user (i.e., the information viewing component and the content within the information viewing component), thereby enabling the information provided to the user to be more accurate and helping the user to better obtain the information they need.
[0067] Example process
[0068] Figure 4 illustrates a flowchart of an example process 400 for content searching according to some embodiments of the present disclosure. Process 400 may be implemented at electronic device 110. Process 400 will now be described with reference to Figure 1.
[0069] As shown in Figure 4, in box 410, electronic device 110 responds to receiving a search term by providing response content for the search term. The response content includes an information viewing component, which is constructed by the model based on the search results corresponding to the search term.
[0070] In box 420, electronic device 110 presents first information matching the first filter in the information viewing component based on the first filter associated with the information viewing component.
[0071] In some embodiments, process 400 further includes: the first filter is determined based on the search term.
[0072] In some embodiments, the information viewing component includes a filter control, and the process 400 further includes: determining a second filter item based on a user action associated with the filter control; and updating the information viewing component to present second information that matches the second filter item.
[0073] In some embodiments, the response content may also include reply text generated by the model based on the search terms.
[0074] In some embodiments, the information viewing component is constructed based on the following process: providing the model with search terms and tool description information to identify multiple subtasks associated with the search terms; determining structured data for the search terms by invoking multiple tools corresponding to the multiple subtasks; and constructing the information viewing component based on the structured data.
[0075] In some embodiments, the model is further configured to: determine a plurality of tools and at least one invocation parameter corresponding to the plurality of tools from a set of candidate tools indicated by the tool description information.
[0076] In some embodiments, determining structured data for a search term by invoking multiple tools corresponding to multiple subtasks includes: determining multiple query statements corresponding to multiple tools based on the search term; determining multiple query results corresponding to multiple tools based on the multiple query statements; and determining structured data based on the multiple query results.
[0077] In some embodiments, determining structured data based on multiple query results includes: determining at least one data summary dimension based on search terms; and processing multiple query results based on at least one data summary dimension to determine structured data.
[0078] In some embodiments, the structured data corresponds to a preset output format, which is associated with the type of information viewing component.
[0079] In some embodiments, the multiple subtasks include multiple of the following: comparison tasks; judgment tasks; query tasks; and transformation tasks.
[0080] In some embodiments, the information viewing component is also constructed based on the following process: in response to a similarity between a search term and a historical search term being greater than a threshold, obtaining historical search results corresponding to the historical search terms; determining historical structured data for the search terms based on the historical search results; and constructing the information viewing component based on the historical structured data.
[0081] Example devices and equipment
[0082] Embodiments of this disclosure also provide corresponding apparatus for implementing the methods or processes described above. Figure 5 shows a schematic structural block diagram of an example apparatus 500 for content search according to certain embodiments of this disclosure. Apparatus 500 may be implemented as or included in electronic device 110. The various modules / components in apparatus 500 may be implemented by hardware, software, firmware, or any combination thereof.
[0083] As shown in Figure 5, the device 500 includes: a providing module 510 configured to provide response content for the search term in response to receiving a search term, the response content including an information viewing component constructed by a model based on search results corresponding to the search term; and a presentation module 520 configured to present first information matching the first filter item in the information viewing component based on a first filter item associated with the information viewing component.
[0084] In some embodiments, the first filter is determined based on the search term.
[0085] In some embodiments, the device 500 further includes an update module configured to determine a second filter item based on a user action associated with the filter control; and to update the information viewing component to present second information that matches the second filter item.
[0086] In some embodiments, the response content may also include reply text generated by the model based on the search terms.
[0087] In some embodiments, the information viewing component is constructed based on the following process: providing the model with search terms and tool description information to identify multiple subtasks associated with the search terms; determining structured data for the search terms by invoking multiple tools corresponding to the multiple subtasks; and constructing the information viewing component based on the structured data.
[0088] In some embodiments, the model is further configured to: determine a plurality of tools and at least one invocation parameter corresponding to the plurality of tools from a set of candidate tools indicated by the tool description information.
[0089] In some embodiments, determining structured data for a search term by invoking multiple tools corresponding to multiple subtasks includes: determining multiple query statements corresponding to multiple tools based on the search term; determining multiple query results corresponding to multiple tools based on the multiple query statements; and determining structured data based on the multiple query results.
[0090] In some embodiments, determining structured data based on multiple query results includes: determining at least one data summary dimension based on search terms; and processing multiple query results based on at least one data summary dimension to determine structured data.
[0091] In some embodiments, the structured data corresponds to a preset output format, which is associated with the type of information viewing component.
[0092] In some embodiments, the multiple subtasks include multiple of the following: comparison tasks; judgment tasks; query tasks; and transformation tasks.
[0093] In some embodiments, the information viewing component is also constructed based on the following process: in response to a similarity between a search term and a historical search term being greater than a threshold, obtaining historical search results corresponding to the historical search term; determining historical structured data for the search term based on the historical search results; and constructing the information viewing component based on the historical structured data.
[0094] The modules included in device 500 can be implemented in various ways, including software, hardware, firmware, or any combination thereof. In some embodiments, one or more modules may be implemented using software and / or firmware, such as machine-executable instructions stored on a storage medium. In addition to or as an alternative to machine-executable instructions, some or all of the units in device 500 may be implemented at least partially by one or more hardware logic components. By way of example, and not limitation, exemplary types of hardware logic components that may be used include field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.
[0095] Figure 6 illustrates a block diagram of an electronic device 600 in which one or more embodiments of the present disclosure may be implemented. It should be understood that the electronic device 600 shown in Figure 6 is merely exemplary and should not be construed as limiting the functionality and scope of the embodiments described herein. The electronic device 600 shown in Figure 6 can be used to implement the electronic device 110 discussed above.
[0096] As shown in Figure 6, electronic device 600 is in the form of a general-purpose electronic device. Components of electronic device 600 may include, but are not limited to, one or more processors or processor 610, memory 620, storage device 630, one or more communication units 640, one or more input devices 650, and one or more output devices 660. Processor 610 may be a physical or virtual processor and is capable of performing various processes according to programs stored in memory 620. In a multiprocessor system, multiple processors execute computer-executable instructions in parallel to improve the parallel processing capability of electronic device 600.
[0097] Electronic device 600 typically includes multiple computer storage media. Such media can be any accessible media that is accessible to electronic device 600, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 620 can be volatile memory (e.g., registers, cache, random access memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. Storage device 630 can be removable or non-removable media and can include machine-readable media, such as flash drives, disks, or any other media that can be used to store information and / or data and can be accessed within electronic device 600.
[0098] Electronic device 600 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not shown in FIG. 6, disk drives for reading from or writing to removable, non-volatile disks (e.g., "floppy disks") and optical disk drives for reading from or writing to removable, non-volatile optical disks may be provided. In these cases, each drive may be connected to a bus (not shown) via one or more data media interfaces. Memory 620 may include computer program product 625 having one or more program modules configured to perform various methods or actions of various embodiments of the present disclosure.
[0099] The communication unit 640 enables communication with other electronic devices via a communication medium. Additionally, the functionality of the components of the electronic device 600 can be implemented using a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, the electronic device 600 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network node.
[0100] Input device 650 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 660 can be one or more output devices, such as a monitor, speaker, printer, etc. Electronic device 600 can also communicate with one or more external devices (not shown) via communication unit 640 as needed. These external devices include storage devices, display devices, etc., and can communicate with one or more devices that enable user interaction with electronic device 600, or with any device that enables electronic device 600 to communicate with one or more other electronic devices (e.g., network card, modem, etc.). Such communication can be performed via input / output (I / O) interface (not shown).
[0101] According to an exemplary implementation of this disclosure, a computer-readable storage medium is provided that stores computer-executable instructions thereon, wherein the computer-executable instructions are executed by a processor to implement the methods described above. According to an exemplary implementation of this disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, which are executed by a processor to implement the methods described above.
[0102] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.
[0103] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.
[0104] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.
[0105] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.
[0106] Various implementations of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is chosen to best explain the principles, practical applications, or improvements to technology in the market, or to enable others skilled in the art to understand the various implementations disclosed herein.
Claims
1. A content search method, comprising: In response to receiving a search term, response content is provided for the search term, the response content including an information viewing component constructed by a model based on search results corresponding to the search term; and Based on a first filter associated with the information viewing component, first information matching the first filter is presented in the information viewing component.
2. The method of claim 1, wherein the first filter item is determined based on the search item.
3. The method according to claim 1 or 2, wherein the information viewing component includes a filtering control, and the method further includes: The second filter item is determined based on the user action associated with the filter control; as well as The information viewing component is updated to present second information that matches the second filter item.
4. The method according to any one of claims 1 to 3, wherein the response content further includes the reply text generated by the model based on the search term.
5. The method according to any one of claims 1 to 4, wherein the information viewing component is constructed based on the following process: The model is provided with the search terms and tool description information to identify multiple subtasks associated with the search terms; By invoking multiple tools corresponding to the multiple subtasks, structured data for the search item is determined; as well as The information viewing component is constructed based on the structured data.
6. The method of claim 5, wherein the model is further configured to: From a set of candidate tools indicated by the tool description information, determine the plurality of tools and at least one invocation parameter corresponding to the plurality of tools.
7. The method of claim 5, wherein determining the structured data for the search item by invoking multiple tools corresponding to the plurality of subtasks includes: Based on the search terms, determine multiple query statements corresponding to the multiple tools; Based on the multiple query statements, determine multiple query results corresponding to the multiple tools; as well as Based on the multiple query results, the structured data is determined.
8. The method according to claim 7, wherein determining the structured data based on the plurality of query results includes: Based on the search terms, at least one data summary dimension is determined; as well as The multiple query results are processed based on the at least one data summary dimension to determine the structured data.
9. The method of claim 5, wherein the structured data corresponds to a preset output format, the output format being associated with the type of the information viewing component.
10. The method of claim 5, wherein the plurality of subtasks includes a plurality of the following: Comparison tasks; Judgment-based tasks; Query tasks; Transformation tasks.
11. The method according to any one of claims 1 to 10, wherein the information viewing component is further constructed based on the following process: In response to a similarity greater than a threshold between the search term and historical search terms, historical search results corresponding to the historical search terms are obtained. Based on the historical search results, determine the historical structured data for the search item; as well as The information viewing component is constructed based on the aforementioned historical structured data.
12. An apparatus for content search, comprising: A module is configured to provide response content for a search term in response to receiving a search term, the response content including an information viewing component constructed by a model based on search results corresponding to the search term; as well as The presentation module is configured to present first information in the information viewing component that matches the first filter item based on a first filter item associated with the information viewing component.
13. An electronic device, comprising: At least one processor; as well as At least one memory coupled to the at least one processor and storing instructions for execution by the at least one processor, the instructions causing the electronic device to perform the method according to any one of claims 1 to 11 when executed by the at least one processor.
14. A computer-readable storage medium having stored thereon computer-executable instructions that can be executed by a processor to implement the method according to any one of claims 1 to 11.
15. A computer program product tangibly stored in a computer storage medium and comprising computer-executable instructions that, when executed by a device, cause the device to perform the method according to any one of claims 1 to 11.