WO2025245698A1 - 用于查询的方法、装置、设备和存储介质 - Google Patents

用于查询的方法、装置、设备和存储介质

Info

Publication number
WO2025245698A1
WO2025245698A1 PCT/CN2024/095797 CN2024095797W WO2025245698A1 WO 2025245698 A1 WO2025245698 A1 WO 2025245698A1 CN 2024095797 W CN2024095797 W CN 2024095797W WO 2025245698 A1 WO2025245698 A1 WO 2025245698A1
Authority
WO
WIPO (PCT)
Prior art keywords
response
page
digital assistant
request
query
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
PCT/CN2024/095797
Other languages
English (en)
French (fr)
Inventor
张凡
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Zitiao Network Technology Co Ltd
Original Assignee
Beijing Zitiao Network Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Zitiao Network Technology Co Ltd filed Critical Beijing Zitiao Network Technology Co Ltd
Priority to PCT/CN2024/095797 priority Critical patent/WO2025245698A1/zh
Priority to CN202480002188.5A priority patent/CN119173867A/zh
Publication of WO2025245698A1 publication Critical patent/WO2025245698A1/zh
Pending legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/338—Presentation of query results
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/903—Querying
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/904—Browsing; Visualisation therefor
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
    • G06F3/0481—Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance

Definitions

  • the exemplary embodiments disclosed herein generally relate to the field of data querying, and particularly to methods, apparatus, devices, and computer-readable storage media for querying.
  • Digital assistants can be used to respond to user queries.
  • digital assistants are provided to assist users with various task processing needs in different applications and scenarios.
  • Digital assistants typically possess intelligent dialogue and task processing capabilities.
  • Digital assistants can be invoked in response to user input. For example, during an interaction with a digital assistant, the user inputs interactive messages, and the digital assistant responds to the user's input by providing a response message.
  • a method for querying includes: presenting a first response in a first page of a first digital assistant using a first format, the first response being generated based on a first query request; presenting a first portion of the first response using a second format; and, in response to receiving a first interaction request for the first portion, presenting a first interactive control for invoking a processing application different from the first digital assistant to process a second query request associated with the first portion.
  • an apparatus for querying includes: a first response presentation module configured to present a first response in a first page of a first digital assistant using a first format, the first response being generated based on a first query request; a second response presentation module configured to present a first portion of the first response using a second format; and a first control presentation module configured to present a first interactive control in response to receiving a first interaction request for the first portion, the first interactive control being used to invoke a function different from the first digital assistant.
  • the word assistant's processing application is used to handle the second query request associated with the first part.
  • an electronic device in a third aspect of this disclosure, includes at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit. When executed by the at least one processing unit, the instructions cause the device to perform the method of the first aspect of this disclosure.
  • a computer-readable storage medium stores a computer program that can be executed by a processor to implement the method of the first aspect of this disclosure.
  • a computer program product comprising a computer program wherein the computer program, when executed by a processor, implements the method of the first aspect of this disclosure.
  • Figure 1 shows a schematic diagram of an example environment in which embodiments of the present disclosure can be implemented
  • Figure 2 shows a flowchart of a query process according to some embodiments of the present disclosure
  • FIGS. 3A and 3B illustrate schematic diagrams of example pages according to some embodiments of the present disclosure
  • Figure 4 shows a block diagram of a query apparatus according to some embodiments of the present disclosure.
  • Figure 5 shows a block diagram of an electronic device in which one or more embodiments of the present disclosure may be implemented.
  • performing a step in response to A does not mean that the step is performed immediately after A, but may include one or more intermediate steps.
  • a prompt message is sent to the user to clearly inform the user that the requested operation will require the acquisition and use of the user's personal information, thereby enabling the user to choose whether to provide personal information to the software or hardware such as electronic devices, applications, servers or storage media that perform the operation of the technical solution disclosed herein, based on the prompt message.
  • a prompt message in response to a user's active request, can be sent to the user, such as a pop-up window, where the prompt message can be presented in text format.
  • the pop-up window can also include a selection control allowing the user to choose "agree” or “disagree” to provide personal information to the electronic device.
  • model refers to a model that learns the relationship between inputs and outputs from training data, enabling it to generate corresponding outputs for a given input after training. Model generation can be based on machine learning techniques. Deep learning is a machine learning algorithm that processes inputs and provides corresponding outputs using multiple layers of processing units. A neural network model is an example of a deep learning-based model. In this paper, “model” may also be referred to as a “machine learning model,” “learning model,” “machine learning network,” or “learning network,” and these terms are used interchangeably.
  • a neural network is a machine learning network based on deep learning.
  • a neural network processes input and provides a corresponding output, typically consisting of an input layer, an output layer, and one or more hidden layers between the input and output layers.
  • Neural networks used in deep learning applications often include many hidden layers, thus increasing the network's depth.
  • the layers of a neural network are connected sequentially, so that the output of the previous layer is provided as the input to the next layer.
  • the input layer receives the input to the neural network, while the output layer's output serves as the final output.
  • Each layer of a neural network includes one or more nodes (also called processing nodes or neurons), each node processing the input from the layer above.
  • Machine learning typically comprises three phases: training, testing, and application (also known as inference).
  • training phase a given model is trained using a large amount of training data, iteratively updating parameter values until the model can consistently generate inferences that meet the expected goals from the training data.
  • the model can be considered to have learned the relationship between inputs and outputs (also known as an input-output mapping) from the training data.
  • the parameter values of the trained model are determined.
  • test inputs are applied to the trained model to test whether it can provide the correct output, thus determining the model's performance.
  • the testing phase can sometimes be integrated into the training phase.
  • the trained model can be used to process actual model inputs based on the trained parameter values to determine the corresponding model output.
  • Figure 1 illustrates a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented.
  • Environment 100 relates to a query platform 110.
  • the query platform 110 may integrate a processing application 112 and a digital assistant 114 (understandably, although the figure). Only one processing application 112 and one digital assistant 114 are shown, but in reality there can be multiple processing applications 112 and multiple digital assistants 114.
  • Processing application 112 can be any suitable application that provides query services.
  • Processing application 112 may also include a digital assistant.
  • Digital assistant 114 may be created by user 130 and provided by default by query platform 110, or it may be created by other users and shared with user 130. User 130 can interact with processing application 112 and/or digital assistant 114 via query platform 110 and/or attached devices of query platform 110.
  • Digital assistant 114 can be configured to have intelligent dialogue and task processing capabilities. Digital assistant 114 is provided to assist users with various task processing needs in different applications and scenarios. During interaction with digital assistant 114, the user inputs interactive messages, and digital assistant 114 responds to the user's input by providing response messages. Interactive messages may include multimodal messages, such as text messages (e.g., natural language text), voice messages, image messages, video messages, etc. Typically, digital assistant 120 can support users inputting questions in natural language and perform tasks and provide responses based on its understanding of natural language input and logical reasoning capabilities. In some embodiments, query platform 110 may present a corresponding page 140 to user 130 based on user 130's actions, to output and/or receive information from user 130.
  • text messages e.g., natural language text
  • voice messages e.g., voice messages
  • image messages e.g., video messages
  • digital assistant 120 can support users inputting questions in natural language and perform tasks and provide responses based on its understanding of natural language input and logical reasoning capabilities.
  • the implementation of at least some functions of the processing application 112 and/or at least some functions of the digital assistant 114 may be based on a target model.
  • the target model may be a machine learning model, a deep learning model, a learning model, a neural network, etc.
  • the model may be based on a language model (LM).
  • LM language model
  • the target model may also be based on other suitable models.
  • query platform 110 communicates with server 120 to provide services to processing application 112 and/or digital assistant 114.
  • Query platform 110 may operate on suitable electronic devices. These electronic devices may 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, personal communication system (PCS) devices, personal navigation devices, and 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, query platform 110 may also support any type of user-facing interface (such as "wearable" circuitry).
  • Server 120 may be various types of computing systems/servers capable of providing computing power, including but not limited to mainframes, edge computing nodes, computing devices in cloud environments, etc.
  • an improved method for querying is provided.
  • a first response is presented using a first format, which is generated based on a first query request.
  • a first part of the first response is presented using a second format.
  • a first interactive control is presented. This first interactive control is used to invoke a processing application different from the first digital assistant to process a second query request associated with the first part. This improves the efficiency of user queries and ensures the continuity of information retrieval.
  • Figure 2 shows a flowchart of a query process 200 according to some embodiments of the present disclosure.
  • Process 200 may be implemented at a query platform 110.
  • Process 200 is described below with reference to Figure 1. It should be noted that some operations described herein with reference to the query platform 110 may require the assistance of the server 120. Furthermore, the operations performed by the query platform 110 may specifically be performed by an electronic device running the query platform 110.
  • the query platform 110 presents a first response using a first format, which is generated by the first digital assistant based on a first query request.
  • the first format can be, for example, any suitable format such as text or card format.
  • the first page can be, for example, a conversation page between the user and the first digital assistant.
  • the first query request can be, for example, a query request entered by the user.
  • the query platform 110 can determine user input received via an input box in the conversation page as a user-entered query request.
  • the query platform 110 can also provide at least one predetermined query request in the conversation page between the user and the first digital assistant, and in response to receiving a user selection for a predetermined query request, determine that predetermined query request as the first query request.
  • query platform 110 presents the first part of the first response using a second format.
  • the first part can be automatically identified by the digital assistant or determined in response to a selection request.
  • the first part could be keywords automatically identified by the digital assistant in the first response, which can be automatically highlighted in a second format (e.g., highlighted, italicized, bolded, underlined, etc.).
  • the first part could also be a portion of the content selected by the user from the first response.
  • Query platform 110 can, in response to receiving a user's selection request for a portion of the content, determine the portion corresponding to the selection request as the first part and highlight it in the second format. Part One.
  • FIG3A illustrates a schematic diagram of an example page 300A (also referred to simply as Example 300A) according to some embodiments of the present disclosure.
  • operation controls 311 for creating a digital assistant and operation controls 312 for finding a digital assistant are presented in area 310, and the information stream of an instant messaging application is presented in area 320.
  • the query platform 110 may present a corresponding session window in area 330.
  • the query platform 110 may present a session window in area 330 showing the user's interaction with digital assistant A.
  • the user can enter a first query request 331 in the conversation window, and the query platform 110 can present the first query request 331 and the first response 332 in the conversation window where the user interacts with the digital assistant A.
  • the first query request 331 can be, for example, user input received by the query platform 110 via the input box 301.
  • the query platform 110 can identify text 333 as the first part and highlight the first part in a second format (e.g., highlight text 333).
  • query platform 110 in response to receiving a first interaction request for the first part, query platform 110 presents a first interactive control (e.g., one or more interactive controls 340).
  • the first interactive control is used to invoke a processing application to process a second query request associated with the first part.
  • the first interaction request may include, for example, a triggering operation for the first part, such as a long press, hover, click, double-click, etc.
  • the first interactive control may be used to invoke at least one processing application.
  • Query platform 110 may directly identify the first part as the second query request.
  • Query platform 110 may also fill the first part into a predetermined query template and determine the second query request based on the filled result.
  • the processing application can be selected by the query platform 110 from multiple processing applications integrated within the query platform 110 based on the first response and the first part. That is, the query platform 110 can select a processing application that can be invoked by the first interactive control from multiple processing applications integrated within the query platform 110 based on the first response and the first part.
  • the processing application may include... Various types are possible, such as search engines, other digital assistants, and chat groups, etc. For example, if the first response is related to physics knowledge, the processing application could be the one determined by the query platform 110 from among multiple processing applications for answering information related to physics knowledge.
  • the query platform 110 may present a first interactive control in response to determining that the duration of a first interaction request meets a first time period.
  • the first interactive control may, for example, be presented floating on top of a first page.
  • the query platform 110 may hide the first interactive control in response to determining that no second interaction request for the first interactive control has been received within a second time period. Both the first and second time periods can be any suitable time period, such as 1 second, 3 seconds, 5 seconds, etc.
  • the second interaction request may include, for example, a triggering operation on the first interactive control, such as a long press, hover operation, click operation, double-click operation, etc.
  • the query platform 110 may present the first interactive control in response to a hover operation on the first part lasting 3 seconds.
  • the query platform 110 may hide the first interactive control in response to no click operation on the first interactive control received within 5 seconds. In this way, interactive controls can be automatically popped up and hidden, thereby facilitating user operation.
  • the query platform 110 may also, in response to receiving a second interaction request for the first interactive control, present a second page of the processing application, and on the second page present a second response of the processing application to the first part (specifically, to the second query request associated with the first part).
  • the second interaction request for the first interactive control may, for example, be a triggering operation on a target option among multiple options presented by the first interactive control.
  • the second page may, for example, be a new session page corresponding to the user and the processing application.
  • the query platform 110 can respond to receiving a first interaction request for text 333 (i.e., the first part) by presenting an interactive control 340 (i.e., the first interactive control).
  • the interactive control 340 can display multiple options, each corresponding to a different processing application.
  • the query platform 110 can respond to a triggered operation on a target option by invoking the processing application corresponding to that target option to process the second query request associated with the text 333.
  • the query platform 110 can respond to a triggered operation on the option "Detailed Expansion” by...
  • the "Open" selection operation calls the corresponding processing application to handle the second query request associated with the text 333.
  • the query platform 110 may also present a page as shown in Figure 300B.
  • a second page corresponding to the processing application for the target option may be presented in area 330 of Figure 300B.
  • the second page may include, for example, a second query request 351 (associated with text 333) and a second response to the second query request 351 (including multiple media items and text 353 presented in area 352).
  • the processing application may include a second digital assistant that is different from the first digital assistant (e.g., the option "Digital Assistant 123" shown in the interactive control 340 in FIG. 3A may correspond to the second digital assistant).
  • the query platform 110 may forward contextual data from the first page to the second digital assistant so that the second digital assistant can provide a response based on the contextual data.
  • the contextual data in the first page may include, for example, at least the first query request and the first response.
  • the contextual data may also include a predetermined number of historical query requests and historical responses from users and the first digital assistant.
  • the second digital assistant can understand the contextual data of the second query request and provide a more accurate response based on the contextual data.
  • the query platform 110 may also, in response to receiving a third interaction request on a second page, present a response from the second digital assistant to the third interaction request on the second page. For example, the query platform 110 may determine that a third interaction request has been received in response to receiving user input on the second page. The query platform 110 may also, for example, present options (also referred to as shortcuts) associated with the second query request and/or the second response on the second page. The query platform 110 may determine that a third interaction request has been received in response to receiving a selection action for an option. In this way, the desired processing application can be invoked in a more convenient and efficient manner.
  • the processing application may include a search engine (e.g., the processing applications corresponding to the three options "Case Description", “Detailed Expansion”, and “Similar Conversations” shown in the interactive control 340 in Figure 3A).
  • the query platform 110 can create search keywords using the first part and present search results matching the search keywords on the second page.
  • the query platform 110 can perform operations based on predetermined keyword types, keyword templates, etc.
  • the search keywords are created based on the first part. It's understandable that if the first part itself includes at least one keyword, the query platform 110 can directly present search results matching that keyword on the second page. In this way, the search engine's capabilities can be directly invoked to provide real-time search results.
  • a search engine may be deployed within a data providing system, and the search results may point to data within that system.
  • multiple types of data providing systems may exist, and each system may provide corresponding data based on a search.
  • a data providing system may provide data of various types, such as text, images, audio, video, short videos, applications, rich media, etc., that match keywords.
  • a data providing system may be broadly understood to include data from one or more websites, applications, tools, databases, etc., within the internet environment.
  • the provided second response may include data with multiple contents and represented in multiple media types.
  • the processing application may also include a chat application (e.g., the option "Chat with him" shown in the interactive control 340 in Figure 3A may correspond to a chat group in the chat application).
  • the query platform 110 may forward the context data from the first page to the chat group and present messages from users in the chat group on a second page.
  • This chat group may be pre-created or created in real time. For example, if the first query request indicates a query for physics knowledge, the chat group may be a pre-existing group of physics enthusiasts or a group of physics enthusiasts created in real time. In this way, answers to the desired query questions can be obtained from other users.
  • the content of the second response may be determined based on the context associated with the first response and the first part.
  • the context associated with the first response may be obtained, that is, one or more rounds of previous interactions between the user and the first digital assistant may be obtained, as well as the first part selected by the user, to determine the user's specific question, thereby generating a second response that is more in line with the user's needs.
  • the media type of the second response can be determined based on the interaction history in the first digital assistant. Specifically, the media type for presenting the second response can be determined based on the user's interaction history with the first digital assistant. For example, assuming the interaction history indicates that the user prefers to view text data, the second response can be presented in text format. If the interaction history indicates that the user prefers to view video data, then the second response can be presented in video format. In this case, responses in video format can be searched first, and alternatively and/or additionally, a second response in video format can be generated based on various generation techniques (e.g., text-based video, image-based video, etc.). In this way, the second response can be presented according to a media type that is more conducive to user understanding.
  • various generation techniques e.g., text-based video, image-based video, etc.
  • the query platform 110 may also return to the first page in response to receiving a fourth request to exit the processing application on the second page.
  • the query platform 110 may determine that a fourth request to exit the processing application has been received in response to receiving a trigger operation on the return control 360 in example 300B. The query platform 110 may then return to the first page shown in example 300A. In this way, it is convenient for the user to quickly exit the processing application when desired and return to the previous digital assistant.
  • suitable processing applications can be recommended to the user based on the first part of the first response. This can improve the efficiency of user queries, provide more accurate results, and ensure the continuity of information retrieval.
  • FIG4 shows a block diagram of an apparatus 400 for querying according to some embodiments of this disclosure.
  • the apparatus 400 may be implemented as or included in a query platform 110.
  • the various modules/components in the apparatus 400 may be implemented by hardware, software, firmware, or any combination thereof.
  • the device 400 includes a first response presentation module 410, configured to present a first response in a first format on the first page of the first digital assistant. The first response is generated based on a first query request.
  • the device 400 also includes a second response presentation module 420, configured to present a first portion of the first response in a second format.
  • the device 400 further includes a first control presentation module 430, configured to present a first interactive control in response to receiving a first interaction request for the first portion.
  • the first interactive control is used to invoke a different control than the one requested for the first portion.
  • the first digital assistant's processing application handles the second query request associated with the first part.
  • the apparatus 400 further includes: a second page presentation module configured to present a second page of the processing application in response to receiving a second interaction request for a first interaction control; and a third response presentation module configured to present a second response of the processing application to the first part on the second page.
  • the processing application includes a second digital assistant that is different from the first digital assistant, and a third response presentation module is further configured to forward context data from the first page to the second digital assistant so that the second digital assistant provides a response based on the context data.
  • the device 400 further includes: a fourth response presentation module configured to present a response from the second digital assistant to the third interaction request on the second page in response to receiving the third interaction request on the second page.
  • the processing application includes a search engine, and a third response presentation module is further configured to: create search keywords using a first portion; and present search results matching the search keywords on a second page, wherein the search engine is deployed in a data provision system and the search results point to data in the data provision system.
  • the processing application includes a chat application
  • the third response presentation module is further configured to: forward context data from the first page to a chat group in the chat application; and present messages from users in the chat group on a second page.
  • the apparatus 400 further includes a second page return module configured to return to the first page in response to receiving a fourth request for exiting the processing application on the second page.
  • the first part is: automatically identified by the digital assistant, or determined in response to a selection request.
  • a first digital assistant and a processing application are integrated into a query platform, and the processing application is selected by the query platform from a plurality of processing applications integrated into the query platform based on a first response and a first portion.
  • the first interactive control is presented in response to determining that the duration of the first interaction request satisfies a first time period, and the first interactive control is presented in a floating manner. On the top layer of the first page.
  • the apparatus 400 further includes a control hiding module configured to hide the first interactive control in response to determining that no second interaction request for the first interactive control has been received during a second time period.
  • the content of the second response is determined based on the context associated with the first response and the first portion.
  • the media type of the second response is determined based on the interaction history in the first digital assistant.
  • the units and/or modules included in device 400 can be implemented in various ways, including software, hardware, firmware, or any combination thereof.
  • one or more units and/or modules can be implemented using software and/or firmware, such as machine-executable instructions stored on a storage medium.
  • some or all of the units and/or modules in device 400 can be implemented at least partially by one or more hardware logic components.
  • exemplary types of hardware logic components include field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-chips (SoCs), complex programmable logic devices (CPLDs), and so on.
  • Such electronic devices or combinations of electronic devices may, for example, include the query platform 110 in Figure 1.
  • Figure 5 shows a block diagram of an electronic device 500 in which one or more embodiments of the present disclosure may be implemented. It should be understood that the electronic device 500 shown in Figure 5 is merely exemplary and should not constitute any limitation on the functionality and scope of the embodiments described herein. The electronic device 500 shown in Figure 5 can be used to implement the query platform 110 of Figure 1, and/or the apparatus 400 of Figure 4.
  • the electronic device 500 is in the form of a general-purpose computing device.
  • the components of the electronic device 500 may include, but are not limited to, one or more processors or processing units 510, memory 520, storage devices 530, one or more communication units 540, one or more input devices 550, and one or more output devices 560.
  • the processing unit 510 may be physical or virtual.
  • the processor is also capable of performing various processes based on the programs stored in memory 520. In a multiprocessor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing capability of electronic device 500.
  • Electronic device 500 typically includes multiple computer storage media. Such media can be any available media accessible to electronic device 500, including but not limited to volatile and non-volatile media, removable and non-removable media.
  • Memory 520 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 530 can be removable or non-removable media and can include machine-readable media, such as flash drives, disks, or any other media capable of storing information and/or data and accessible within electronic device 500.
  • Electronic device 500 may further include additional removable/non-removable, volatile/non-volatile storage media.
  • disk drives for reading or writing from removable, non-volatile disks (e.g., "floppy disks") and optical disk drives for reading or writing from removable, non-volatile optical disks may be provided.
  • each drive may be connected to a bus (not shown) via one or more data media interfaces.
  • Memory 520 may include computer program product 525 having one or more program modules configured to perform various methods or actions of various implementations of this disclosure.
  • the communication unit 540 enables communication with other computing devices via a communication medium. Additionally, the functionality of the components of the electronic device 500 can be implemented as a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, the electronic device 500 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network node.
  • PCs network personal computers
  • Input device 550 can be one or more input devices, such as a mouse, keyboard, trackball, etc.
  • Output device 560 can be one or more output devices, such as a monitor, speaker, printer, etc.
  • Electronic device 500 can also communicate with one or more external devices (not shown) via communication unit 540 as needed. External devices include storage devices, etc. The device may communicate with a display device or other device that enables a user to interact with the electronic device 500, or with any device (e.g., a network card, modem, etc.) that enables the electronic device 500 to communicate with one or more other computing devices. Such communication may be performed via an input/output (I/O) interface (not shown).
  • I/O input/output
  • a computer-readable storage medium that stores computer-executable instructions thereon, wherein the computer-executable instructions are executed by a processor to implement the methods described above.
  • 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.
  • These computer-readable program instructions can be provided to a processing unit 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 processing unit 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.
  • 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.
  • 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.
  • each block in a flowchart or block diagram may represent a module, segment, or part of an instruction, which contains one or more executable instructions for implementing the specified logical function.
  • the functions marked in the blocks may occur in a different order than those shown in the figures. 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.
  • each block in a block diagram and/or flowchart, and combinations of blocks in 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.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Human Computer Interaction (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

提供了用于查询的方法、装置、设备和存储介质。方法中，在第一数字助手的第一页面中，利用第一格式呈现第一应答，第一应答是基于第一查询请求来生成的(210)。利用第二格式呈现第一应答中的第一部分(220)。响应于接收到针对第一部分的第一交互请求，呈现第一交互控件，第一交互控件用于调用不同于第一数字助手的处理应用来处理与第一部分相关联的第二查询请求(230)。

Description

用于查询的方法、装置、设备和存储介质 技术领域
本公开的示例实施例总体涉及数据查询领域，特别地涉及用于查询的方法、装置、设备和计算机可读存储介质。
背景技术
机器学习技术已经被广泛地用于多种技术领域，并且可以利用数字助手来回复用户的查询请求。在现有技术中，数字助手被提供用于协助用户在不同应用、场景下的各类任务处理需求。数字助手通常具有智能对话和任务处理能力。数字助手可以响应于用户输入而被调用。例如，在与数字助手的交互过程中，用户输入交互消息，并且数字助手响应于用户输入来提供应答消息。
发明内容
在本公开的第一方面，提供了一种用于查询的方法。该方法包括：在第一数字助手的第一页面中，利用第一格式呈现第一应答，第一应答是基于第一查询请求来生成的；利用第二格式呈现第一应答中的第一部分；以及响应于接收到针对第一部分的第一交互请求，呈现第一交互控件，第一交互控件用于调用不同于第一数字助手的处理应用来处理与第一部分相关联的第二查询请求。
在本公开的第二方面，提供了一种用于查询的装置。该装置包括：第一应答呈现模块，被配置为在第一数字助手的第一页面中，利用第一格式呈现第一应答，第一应答是基于第一查询请求来生成的；第二应答呈现模块，被配置为利用第二格式呈现第一应答中的第一部分；以及第一控件呈现模块，被配置为响应于接收到针对第一部分的第一交互请求，呈现第一交互控件，第一交互控件用于调用不同于第一数 字助手的处理应用来处理与第一部分相关联的第二查询请求。
在本公开的第三方面，提供了一种电子设备。该设备包括至少一个处理单元；以及至少一个存储器，至少一个存储器被耦合到至少一个处理单元并且存储用于由至少一个处理单元执行的指令。指令在由至少一个处理单元执行时使设备执行本公开的第一方面的方法。
在本公开的第四方面，提供了一种计算机可读存储介质。该计算机可读存储介质上存储有计算机程序，计算机程序可由处理器执行以实现本公开的第一方面的方法。
在本公开的第五方面，提供了一种计算机程序产品，包括计算机程序，其中计算机程序在被处理器执行时实现本公开的第一方面的方法。
应当理解，本内容部分中所描述的内容并非旨在限定本公开的实施例的关键特征或重要特征，也不用于限制本公开的范围。本公开的其它特征将通过以下的描述而变得容易理解。
附图说明
结合附图并参考以下详细说明，本公开各实施例的上述和其他特征、优点及方面将变得更加明显。在附图中，相同或相似的附图标记表示相同或相似的元素，其中：
图1示出了本公开的实施例能够在其中实现的示例环境的示意图；
图2示出了根据本公开的一些实施例的用于查询的过程的流程图；
图3A和图3B示出了根据本公开的一些实施例的示例页面的示意图；
图4示出了根据本公开的一些实施例的用于查询的装置的框图；以及
图5示出了其中可以实施本公开的一个或多个实施例的电子设备的框图。
具体实施方式
下面将参照附图更详细地描述本公开的实施例。虽然附图中示出了本公开的某些实施例，然而应当理解的是，本公开可以通过各种形式来实现，而且不应该被解释为限于这里阐述的实施例，相反，提供这些实施例是为了更加透彻和完整地理解本公开。应当理解的是，本公开的附图及实施例仅用于示例性作用，并非用于限制本公开的保护范围。
在本公开的实施例的描述中，术语“包括”及其类似用语应当理解为开放性包含，即“包括但不限于”。术语“基于”应当理解为“至少部分地基于”。术语“一个实施例”或“该实施例”应当理解为“至少一个实施例”。术语“一些实施例”应当理解为“至少一些实施例”。下文还可能包括其他明确的和隐含的定义。
在本文中，除非明确说明，“响应于A”执行一个步骤并不意味着在“A”之后立即执行该步骤，而是可以包括一个或多个中间步骤。
可以理解的是，本技术方案所涉及的数据(包括但不限于数据本身、数据的获得或使用)应当遵循相应法律法规及相关规定的要求。
可以理解的是，在使用本公开各实施例公开的技术方案之前，均应当根据相关法律法规通过适当的方式对本公开所涉及个人信息的类型、使用范围、使用场景等告知用户并获得用户的授权。
例如，在响应于接收到用户的主动请求时，向用户发送提示信息，以明确地提示用户，其请求执行的操作将需要获得和使用到用户的个人信息，从而使得用户可以根据提示信息来自主地选择是否向执行本公开技术方案的操作的电子设备、应用程序、服务器或存储介质等软件或硬件提供个人信息。
作为一种可选的但非限制性的实现方式，响应于接收到用户的主动请求，向用户发送提示信息的方式，例如可以是弹窗的方式，弹窗中可以以文字的方式呈现提示信息。此外，弹窗中还可以承载供用户选择“同意”或“不同意”向电子设备提供个人信息的选择控件。
可以理解的是，上述通知和获得用户授权过程仅是示意性的，不对本公开的实现方式构成限定，其他满足相关法律法规的方式也可应 用于本公开的实现方式中。
如本文中所使用的，术语“模型”可以从训练数据中学习到相应的输入与输出之间的关联关系，从而在训练完成后可以针对给定的输入，生成对应的输出。模型的生成可以基于机器学习技术。深度学习是一种机器学习算法，通过使用多层处理单元来处理输入和提供相应输出。神经网络模型是基于深度学习的模型的一个示例。在本文中，“模型”也可以被称为“机器学习模型”、“学习模型”、“机器学习网络”或“学习网络”，这些术语在本文中可互换地使用。
“神经网络”是一种基于深度学习的机器学习网络。神经网络能够处理输入并且提供相应输出，其通常包括输入层和输出层以及在输入层与输出层之间的一个或多个隐藏层。在深度学习应用中使用的神经网络通常包括许多隐藏层，从而增加网络的深度。神经网络的各个层按顺序相连，从而前一层的输出被提供作为后一层的输入，其中输入层接收神经网络的输入，而输出层的输出作为神经网络的最终输出。神经网络的每个层包括一个或多个节点(也称为处理节点或神经元)，每个节点处理来自上一层的输入。
通常，机器学习大致可以包括三个阶段，即训练阶段、测试阶段和应用阶段(也称为推理阶段)。在训练阶段，给定的模型可以使用大量的训练数据进行训练，不断迭代更新参数值，直到模型能够从训练数据中获得一致的满足预期目标的推理。通过训练，模型可以被认为能够从训练数据中学习从输入到输出之间的关联(也称为输入到输出的映射)。训练后的模型的参数值被确定。在测试阶段，将测试输入应用到训练后的模型，以测试模型是否能够提供正确的输出，从而确定模型的性能。测试阶段有时候可以被融合在训练阶段。在应用或推理阶段，已训练的模型可以被用于基于训练得到的参数值，对实际的模型输入进行处理，确定对应的模型输出。
图1示出了本公开的实施例能够在其中实现的示例环境100的示意图。环境100涉及查询平台110。在该示例环境100中，查询平台110中可以集成有处理应用112和数字助手114(可以理解，虽然图 中仅示出了一个处理应用112和一个数字助手114，但实际可以有多个处理应用112和多个数字助手114)。处理应用112可以为任意适当的可以提供查询服务的应用。处理应用112也可以包括数字助手。数字助手114可以是用户130自行创建的、查询平台110默认提供的，也可以是其他用户创建后分享给用户130的。用户130可以经由查询平台110和/或查询平台110的附接设备来与处理应用112和/或数字助手114进行交互。
数字助手114可以被配置为具有智能对话和任务处理能力。数字助手114被提供用于协助用户在不同应用、场景下的各类任务处理需求。在与数字助手114的交互过程中，用户输入交互消息，并且数字助手114响应于用户输入来提供应答消息。交互消息可以包括多模态形式的消息，诸如文本消息(例如，自然语言文本)、语音消息、图像消息、视频消息，等等。通常，数字助手120能够支持用户以自然语言方式输入提问，并基于对自然语言输入的理解和逻辑推理能力来执行任务和提供应答。在一些实施例中，查询平台110可以基于用户130的操作而向用户130呈现相应的页面140，以向用户130输出和/或从用户130接收信息。
在一些实施例中，处理应用112的至少部分功能的实现，和/或数字助手114的至少部分功能的实现可以基于目标模型来实现。在一些实施例中，目标模型可以是机器学习模型、深度学习模型、学习模型、神经网络等。在一些实施例中，模型可以基于语言模型(LM)。语言模型通过从大量语料中学习，能够具备问答能力。目标模型也可以基于其他适当的模型。
在一些实施例中，查询平台110与服务器120通信，以实现对处理应用112和/或数字助手114的服务的供应。查询平台110可以运行在适当的电子设备。这里的电子设备可以是任意类型的移动终端、固定终端或便携式终端，包括移动手机、台式计算机、膝上型计算机、笔记本计算机、上网本计算机、平板计算机、媒体计算机、多媒体平板、个人通信系统(PCS)设备、个人导航设备、个人数字助理(PDA)、 音频/视频播放器、数码相机/摄像机、定位设备、电视接收器、无线电广播接收器、电子书设备、游戏设备或者前述各项的任意组合，包括这些设备的配件和外设或者其任意组合。在一些实施例中，查询平台110也能够支持任意类型的针对用户的接口(诸如“可佩戴”电路等)。服务器120可以是能够提供计算能力的各种类型的计算系统/服务器，包括但不限于大型机、边缘计算节点、云环境中的计算设备，等等。
应当理解，仅出于示例性的目的描述环境100中各个元素的结构和功能，而不暗示对于本公开的范围的任何限制。
在现代的网络通信技术中，用户间的交流已经从传统的电子邮件、社交平台转移到了即时通信应用上。随着人工智能技术的发展，即时通信应用不仅仅承载了人与人之间的沟通，也逐步集成了人与机器人(Bot)的互动。目前，即时通信应用大多提供了基础的文字交流、文件传输等功能，但在提高信息处理效率方面还存在不少的改进空间。特别是在信息检索、内容高亮、快捷操作等方面，还没有形成一套完善的、智能化的交互体系。
现有的即时通信应用存在如下问题：
1、聊天场景中的信息处理效率较低：即时通信应用在处理里聊天内容时，缺乏一种快捷且直观的方式来处理特定文字或信息，这导致用户在聊天过程中需要多步骤操作来查找或执行特定命令，降低了交流效率。
2、关键信息的访问和操作不连贯：用户在聊天中经常遇到需要查询额外信息的情况，如人名、地点、专有名词等，现有的聊天应用未能提供一个快捷的方式直接进行高亮显示或执行相关操作，使用户需要离开聊天界面，影响了沟通连贯性。
3、智能互推机制的缺失：尽管一些通信应用集成了简单的机器人功能，但在实际交互中，缺少一种能够结合人工智能推荐算法的机制来增强人与Bot之间的互动，为用户提供更为精准的信息或建议。
有鉴于此，根据本公开的实施例，提供了一种用于查询的改进方 案。根据该方案，在第一数字助手的第一页面中，利用第一格式呈现第一应答，第一应答是基于第一查询请求来生成的。利用第二格式呈现第一应答中的第一部分。响应于接收到针对第一部分的第一交互请求，呈现第一交互控件，第一交互控件用于调用不同于第一数字助手的处理应用来处理与第一部分相关联的第二查询请求。由此，可以提升用户查询的效率，保证信息查询的连贯性。
以下将参考附图的示例来详细描述本公开的一些示例实施例。图2示出了根据本公开的一些实施例的用于查询的过程200的流程图。过程200可以被实现在查询平台110处。下面参考图1描述过程200。需要注意的是，在本文中，参考查询平台110所描述的一些操作可能需要服务器120的协助完成。此外，查询平台110所执行的操作，具体可以是运行有查询平台110的电子设备执行的。
在框210，在第一数字助手的第一页面中，查询平台110利用第一格式呈现第一应答，第一应答是第一数字助手基于第一查询请求来生成的。这里的第一格式例如可以为文本格式、卡片格式等任意适当的格式。第一页面例如可以为用户与第一数字助手的会话页面。第一查询请求例如可以为用户输入的查询请求。在一些实施例中，查询平台110可以将经由会话页面中的输入框所接收到的用户输入确定为用户输入的查询请求。在一些实施例中，查询平台110还可以在用户和第一数字助手的会话页面中提供至少一个预定查询请求，并响应于接收到用户针对某个预定查询请求的选择，将该预定查询请求确定为第一查询请求。
在框220，查询平台110利用第二格式呈现第一应答中的第一部分。第一部分可以是由数字助手自动识别的，也可以是响应于选择请求来确定的。例如，第一部分可以是第一应答中数字助手自动识别出的关键词，其可以自动以第二格式(例如高亮、倾斜、加粗、加下划线等)被突出呈现。第一部分也可以是用户从第一应答中选择的部分内容。查询平台110可以响应于接收到用户针对部分内容的选择请求，将选择请求对应的部分内容确定为第一部分，并以第二格式突出呈现 第一部分。
示例性地，参考图3A，图3A示出了根据本公开的一些实施例的示例页面300A(也可以简称为示例300A)的示意图。在示例300A中，用于创建数字助手的操作控件311和用于查找数字助手的操作控件312被呈现在区域310中，并且即时通信应用的信息流被呈现在区域320中。响应于用户在即时通信应用的信息流中选择了任意联系人或者任意群组，查询平台110可以在区域330中呈现相应的会话窗口。例如，响应于用户通过预设操作(例如从联系人列表中选择数字助手A)唤起数字助手A，查询平台110可以在区域330中呈现用户与数字助手A交互的会话窗口。
用户可以在会话窗口中输入第一查询请求331，查询平台110可以在用户与数字助手A交互的会话窗口中呈现第一查询请求331和第一应答332。第一查询请求331例如可以为查询平台110经由输入框301接收到的用户输入。查询平台110可以响应于接收到对文本333(也即图中所示的文本“根据文案描述生成相应的图片”)的选择请求，将文本333确定为第一部分，并以第二格式突出呈现该第一部分(例如高亮呈现文本333)。
在框230，查询平台110响应于接收到针对第一部分的第一交互请求，呈现第一交互控件(例如，一个或者多个交互控件340)，第一交互控件用于调用处理应用来处理与第一部分相关联的第二查询请求。第一交互请求例如可以包括针对第一部分的触发操作，例如长按操作、悬停操作，点击操作，双击操作等等。第一交互控件例如可任意用于调用至少一个处理应用。查询平台110例如可以直接将第一部分确定为第二查询请求。查询平台110例如还可以将第一部分填入预定的查询模板，并基于填充后的结果，确定第二查询请求。
处理应用可以为查询平台110基于第一应答和第一部分从被集成在查询平台110中的多个处理应用中选择的。也即，查询平台110可以基于第一应答和第一部分从被集成在查询平台110中的多个处理应用中，选择可以被第一交互控件调用的处理应用。处理应用可以包括 多种类型，例如，搜索引擎、其他数字助理、以及聊天群组，等等。示例性地，如果第一应答与物理知识相关，处理应用可以是查询平台110从多个处理应用中确定的用于回答与物理知识相关的信息的处理应用。
在一些实施例中，查询平台110可以响应于确定第一交互请求的持续时间满足第一时间段而呈现第一交互控件。第一交互控件例如可以以浮动方式被呈现在第一页面上层。进一步地，在一些实施例中，查询平台110可以响应于确定在第二时间段内未接收到针对第一交互控件的第二交互请求，隐藏第一交互控件。这里的第一时间段和第二时间段均可以是任意适当的时间段，例如1秒、3秒、5秒，等等。第二交互请求例如可以包括针对第一交互控件的触发操作，例如长按操作、悬停操作，点击操作，双击操作等等。示例性地，查询平台110可以响应于针对第一部分的悬停操作达到3秒，呈现第一交互控件。查询平台110可以响应于在5秒内未接收到针对第一交互控件的点击操作，隐藏第一交互控件。以此方式，可以自动弹出和隐藏交互控件，从而便于用户操作。
在一些实施例中，查询平台110还可以响应于接收到针对第一交互控件的第二交互请求，呈现处理应用的第二页面，并在第二页面中呈现处理应用针对第一部分(具体来说，是针对与第一部分相关联的第二查询请求)的第二应答。这里的针对第一交互控件的第二交互请求例如可以为针对第一交互控件呈现的多个选项中的目标选项的触发操作。第二页面例如可以为用户与处理应用对应的新的会话页面。
参考图3A和图3B，如图3A所示，查询平台110可以响应于接收到针对文本333(也即第一部分)的第一交互请求，呈现交互控件340(也即第一交互控件)。
交互控件340上可以呈现有多个选项，多个选项可以分别对应于多个处理应用。查询平台110可以响应于接收到针对目标选项的触发操作，调用目标选项对应的处理应用来处理与文本333相关联的第二查询请求。例如，查询平台110可以响应于接收到针对选项“详细展 开”的选择操作，调用该选项对应的处理应用来处理与文本333相关联的第二查询请求。
查询平台110例如还可以呈现如图300B所示的页面。在图300B的区域330中可以呈现有目标选项对应的处理应用对应的第二页面。第二页面例如可以包括第二查询请求351(其与文本333相关联)和针对第二查询请求351的第二应答(包括区域352所呈现的多个媒体项和文本353)。
在一些实施例中，处理应用可以包括不同于第一数字助手的第二数字助手(例如图3A中交互控件340中所示的选项“数字助手123”可以对应于第二数字助手)。查询平台110可以向第二数字助手转发第一页面中的上下文数据，以使得第二数字助手基于上下文数据来提供应答。第一页面中的上下文数据例如至少可以包括第一查询请求和第一应答。在一些实施例中，上下文数据还可以包括预定数目的用户与第一数字助手的历史查询请求和历史应答。由此，可以使得第二数字助手可以了解第二查询请求的上下文数据，并基于上下文数据，提供更为准确的应答。
在一些实施例中，查询平台110还可以响应于在第二页面中接收到第三交互请求，在第二页面中呈现由第二数字助手针对第三交互请求的应答。示例性地，查询平台110可以响应于在第二页面接收到用户输入，确定接收到第三交互请求。查询平台110例如还可以在第二页面中呈现与第二查询请求和/或第二应答相关联的选项(也可以被称之为快捷指令)。查询平台110可以响应于接收到针对某个选项的选择操作，确定接收到第三交互请求。以此方式，可以以更为方便并且有效的方式调用期望的处理应用。
在一些实施例中，处理应用可以包括搜索引擎(例如图3A中交互控件340中所示的选项“案例说明”、选项“详细展开”和选项“相似对话”三个选项各自对应的处理应用)。查询平台110可以利用第一部分创建搜索关键字，并在第二页面中呈现匹配于搜索关键字的搜索结果。查询平台110可以基于预定的关键词类型、关键词模板等来 基于第一部分创建搜索关键字。可以理解，如果第一部分本身包括至少一个关键字，查询平台110也可以直接在第二页面中呈现匹配于关键字的搜索结果。以此方式，可以直接调用搜索引擎的能力来提供实时搜索结果。
在一些实施例中，搜索引擎可以被部署在数据提供系统中，并且所述搜索结果指向所述数据提供系统中的数据。具体地，可以存在多种类型的数据提供系统，并且每个数据提供系统可以基于搜索来提供相应的数据。例如，数据提供系统可以提供匹配于关键字的文本、图像、音频、视频、短视频、应用、富媒体，等等类型的数据。备选地和/或附加地，可以将数据提供系统宽泛地理解为包括互联网环境中的一个或者多个网站、应用、工具、数据库等涉及的数据。此时，所提供的第二应答可以包括多种内容、并且以多种媒体类型来表示的数据。
在一些实施例中，处理应用还可以包括聊天应用(例如图3A中交互控件340中所示的选项“和他聊聊”可以对应于聊天应用中的聊天群组)。查询平台110可以向聊天群组转发第一页面中的上下文数据，并在第二页面中呈现来自聊天群组中的用户的消息。这个聊天群组可以是先前已经被创建好的，也可以是实时创建的。例如，如果第一查询请求指示查询物理知识，则聊天群组可以是先前已经存在的物理爱好者群，也可以是实时创建的物理爱好者群。以此方式，可以从其他用户获得期望查询问题的应答。
在一些实施例中，第二应答的内容可以是基于与第一应答相关联的上下文以及第一部分来确定的。具体地，可以获取与第一应答相关联的上下文，也即，可以获取用户与第一数字助手进行的一个或者多个轮次的先前交互、以及用户选择的第一部分来确定用户的具体问题，进而生成更加匹配于用户需求的第二应答。
在一些实施例中，第二应答的媒体类型可以是基于第一数字助手中的交互历史来确定的。具体地，可以基于用户与第一数字助手的交互历史来确定以哪种媒体类型来呈现第二应当。假设交互历史指示用户更倾向于查看文本数据，则可以以文本格式来呈现第二应答。假设 交互历史指示用户更倾向于查看视频数据，则可以以视频格式来呈现第二应答。此时，可以优先搜索视频格式的应答，备选地和/或附加地，可以基于各种生成技术(例如，文生视频、图生视频，等等)，来生成视频格式的第二应当。以此方式，可以按照更加有助于用户理解的媒体类型，来呈现第二应答。
在一些实施例中，查询平台110还可以响应于在第二页面中接收到用于退出处理应用的第四请求，返回第一页面。示例性地，参考图3A和图3B，查询平台110可以响应于接收到针对示例300B中的返回控件360的触发操作，确定接收到用于退出处理应用的第四请求。查询平台110可以返回呈现示例300A所示的第一页面。以此方式，可以便于用户在期望时迅速退出处理应用，进而返回先前的数字助手。
应当理解，附图(例如图3A和图3B)中示出的页面仅仅是示例，实际可以存在各种页面设计。页面中的各个图形元素可以具有不同的布置和不同的视觉表示，其中的一个或多个元素可以省略或被替换，并且还可以存在一个或多个其他元素。本公开的实施例在此方面不受限制。
综上所述，根据本公开的实施例，可以基于第一应答中的第一部分为用户推荐合适的处理应用。可以提升用户查询的效率，提供更加准确的结果，并且保证信息查询的连贯性。
根据本公开的一些实施例，还提供了一种用于查询的装置。图4示出了根据本公开的一些实施例的用于查询的装置400的框图。装置400可以被实现为或者被包括在查询平台110中。装置400中的各个模块/组件可以由硬件、软件、固件或者它们的任意组合来实现。
如图4所示，装置400包括第一应答呈现模块410，被配置为在第一数字助手的第一页面中，利用第一格式呈现第一应答，第一应答是基于第一查询请求来生成的。装置400还包括第二应答呈现模块420，被配置为利用第二格式呈现第一应答中的第一部分。装置400还包括第一控件呈现模块430，被配置为响应于接收到针对第一部分的第一交互请求，呈现第一交互控件，第一交互控件用于调用不同于 第一数字助手的处理应用来处理与第一部分相关联的第二查询请求。
在一些实施例中，装置400进一步包括：第二页面呈现模块，被配置为响应于接收到针对第一交互控件的第二交互请求，呈现处理应用的第二页面；以及第三应答呈现模块，被配置为在第二页面中呈现处理应用针对第一部分的第二应答。
在一些实施例中，处理应用包括不同于第一数字助手的第二数字助手，以及第三应答呈现模块被进一步配置为：向第二数字助手转发第一页面中的上下文数据，以使得第二数字助手基于上下文数据来提供应答。
在一些实施例中，装置400进一步包括：第四应答呈现模块，被配置为响应于在第二页面中接收到第三交互请求，在第二页面中呈现由第二数字助手针对第三交互请求的应答。
在一些实施例中，处理应用包括搜索引擎，以及第三应答呈现模块被进一步配置为：利用第一部分创建搜索关键字；以及在第二页面中呈现匹配于搜索关键字的搜索结果，搜索引擎被部署在数据提供系统中，并且搜索结果指向数据提供系统中的数据。
在一些实施例中，处理应用包括聊天应用，以及第三应答呈现模块被进一步配置为：向聊天应用中的聊天群组转发第一页面中的上下文数据；以及在第二页面中呈现来自聊天群组中的用户的消息。
在一些实施例中，装置400进一步包括：第二页面返回模块，被配置为响应于在第二页面中接收到用于退出处理应用的第四请求，返回第一页面。
在一些实施例中，第一部分是：由数字助手自动识别的，或者响应于选择请求来确定的。
在一些实施例中，第一数字助手和处理应用被集成在查询平台中，并且处理应用是由查询平台基于第一应答和第一部分来从被集成在查询平台中的多个处理应用中选择的。
在一些实施例中，第一交互控件响应于确定第一交互请求的持续时间满足第一时间段而被呈现，并且第一交互控件以浮动方式被呈现 在第一页面上层。
在一些实施例中，装置400进一步包括：控件隐藏模块，被配置为响应于确定在第二时间段内未接收到针对第一交互控件的第二交互请求，隐藏第一交互控件。
在一些实施例中，第二应答的内容是基于与第一应答相关联的上下文以及第一部分来确定的。
在一些实施例中，第二应答的媒体类型是基于第一数字助手中的交互历史来确定的。
装置400中所包括的单元和/或模块可以利用各种方式来实现，包括软件、硬件、固件或其任意组合。在一些实施例中，一个或多个单元和/或模块可以使用软件和/或固件来实现，例如存储在存储介质上的机器可执行指令。除了机器可执行指令之外或者作为替代，装置400中的部分或者全部单元和/或模块可以至少部分地由一个或多个硬件逻辑组件来实现。作为示例而非限制，可以使用的示范类型的硬件逻辑组件包括现场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准品(ASSP)、片上系统(SOC)、复杂可编程逻辑器件(CPLD)，等等。
应当理解，以上方法中的一个或多个步骤可以由适当的电子设备或电子设备的组合来执行。这样的电子设备或电子设备的组合例如可以包括图1中的查询平台110。
图5示出了其中可以实施本公开的一个或多个实施例的电子设备500的框图。应当理解，图5所示出的电子设备500仅仅是示例性的，而不应当构成对本文所描述的实施例的功能和范围的任何限制。图5所示出的电子设备500可以用于实现图1的查询平台110，和/或，图4的装置400。
如图5所示，电子设备500是通用计算设备的形式。电子设备500的组件可以包括但不限于一个或多个处理器或处理单元510、存储器520、存储设备530、一个或多个通信单元540、一个或多个输入设备550以及一个或多个输出设备560。处理单元510可以是实际或虚拟 处理器并且能够根据存储器520中存储的程序来执行各种处理。在多处理器系统中，多个处理单元并行执行计算机可执行指令，以提高电子设备500的并行处理能力。
电子设备500通常包括多个计算机存储介质。这样的介质可以是电子设备500可访问的任何可以获得的介质，包括但不限于易失性和非易失性介质、可拆卸和不可拆卸介质。存储器520可以是易失性存储器(例如寄存器、高速缓存、随机访问存储器(RAM))、非易失性存储器(例如，只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、闪存)或它们的某种组合。存储设备530可以是可拆卸或不可拆卸的介质，并且可以包括机器可读介质，诸如闪存驱动、磁盘或者任何其他介质，其可以能够用于存储信息和/或数据并且可以在电子设备500内被访问。
电子设备500可以进一步包括另外的可拆卸/不可拆卸、易失性/非易失性存储介质。尽管未在图5中示出，可以提供用于从可拆卸、非易失性磁盘(例如“软盘”)进行读取或写入的磁盘驱动和用于从可拆卸、非易失性光盘进行读取或写入的光盘驱动。在这些情况中，每个驱动可以由一个或多个数据介质接口被连接至总线(未示出)。存储器520可以包括计算机程序产品525，其具有一个或多个程序模块，这些程序模块被配置为执行本公开的各种实现方式的各种方法或动作。
通信单元540实现通过通信介质与其他计算设备进行通信。附加地，电子设备500的组件的功能可以以单个计算集群或多个计算机器来实现，这些计算机器能够通过通信连接进行通信。因此，电子设备500可以使用与一个或多个其他服务器、网络个人计算机(PC)或者另一个网络节点的逻辑连接来在联网环境中进行操作。
输入设备550可以是一个或多个输入设备，例如鼠标、键盘、追踪球等。输出设备560可以是一个或多个输出设备，例如显示器、扬声器、打印机等。电子设备500还可以根据需要通过通信单元540与一个或多个外部设备(未示出)进行通信，外部设备诸如存储设备、 显示设备等，与一个或多个使得用户与电子设备500交互的设备进行通信，或者与使得电子设备500与一个或多个其他计算设备通信的任何设备(例如，网卡、调制解调器等)进行通信。这样的通信可以经由输入/输出(I/O)接口(未示出)来执行。
根据本公开的示例性实现方式，提供了一种计算机可读存储介质，其上存储有计算机可执行指令，其中计算机可执行指令被处理器执行以实现上文描述的方法。根据本公开的示例性实现方式，还提供了一种计算机程序产品，计算机程序产品被有形地存储在非瞬态计算机可读介质上并且包括计算机可执行指令，而计算机可执行指令被处理器执行以实现上文描述的方法。
这里参照根据本公开实现的方法、装置、设备和计算机程序产品的流程图和/或框图描述了本公开的各个方面。应当理解，流程图和/或框图的每个方框以及流程图和/或框图中各方框的组合，都可以由计算机可读程序指令实现。
这些计算机可读程序指令可以提供给通用计算机、专用计算机或其他可编程数据处理装置的处理单元，从而生产出一种机器，使得这些指令在通过计算机或其他可编程数据处理装置的处理单元执行时，产生了实现流程图和/或框图中的一个或多个方框中规定的功能/动作的装置。也可以把这些计算机可读程序指令存储在计算机可读存储介质中，这些指令使得计算机、可编程数据处理装置和/或其他设备以特定方式工作，从而，存储有指令的计算机可读介质则包括一个制造品，其包括实现流程图和/或框图中的一个或多个方框中规定的功能/动作的各个方面的指令。
可以把计算机可读程序指令加载到计算机、其他可编程数据处理装置、或其他设备上，使得在计算机、其他可编程数据处理装置或其他设备上执行一系列操作步骤，以产生计算机实现的过程，从而使得在计算机、其他可编程数据处理装置、或其他设备上执行的指令实现流程图和/或框图中的一个或多个方框中规定的功能/动作。
附图中的流程图和框图显示了根据本公开的多个实现的系统、方 法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段或指令的一部分，模块、程序段或指令的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。在有些作为应用替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个连续的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或动作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
以上已经描述了本公开的各实现，上述说明是示例性的，并非穷尽性的，并且也不限于所公开的各实现。在不偏离所说明的各实现的范围和精神的情况下，对于本技术领域的普通技术人员来说许多修改和变更都是显而易见的。本文中所用术语的选择，旨在最好地解释各实现的原理、实际应用或对市场中的技术的改进，或者使本技术领域的其他普通技术人员能理解本文公开的各个实现方式。

Claims (17)

  1. 一种查询方法，包括：
    在第一数字助手的第一页面中，利用第一格式呈现第一应答，所述第一应答是基于第一查询请求来生成的；
    利用第二格式呈现所述第一应答中的第一部分；以及
    响应于接收到针对所述第一部分的第一交互请求，呈现第一交互控件，所述第一交互控件用于调用不同于所述第一数字助手的处理应用来处理与所述第一部分相关联的第二查询请求。
  2. 根据权利要求1所述的方法，进一步包括：
    响应于接收到针对所述第一交互控件的第二交互请求，呈现所述处理应用的第二页面；以及
    在所述第二页面中呈现所述处理应用针对所述第一部分的第二应答。
  3. 根据权利要求2所述的方法，其中所述处理应用包括不同于所述第一数字助手的第二数字助手，以及在所述第二页面中呈现所述第二应答包括：
    向所述第二数字助手转发所述第一页面中的上下文数据，以使得所述第二数字助手基于所述上下文数据来提供应答。
  4. 根据权利要求3所述的方法，进一步包括：响应于在所述第二页面中接收到第三交互请求，在所述第二页面中呈现由所述第二数字助手针对所述第三交互请求的应答。
  5. 根据权利要求2所述的方法，其中所述处理应用包括搜索引擎，以及在所述第二页面中呈现所述第二应答包括：
    利用所述第一部分创建搜索关键字；以及
    在所述第二页面中呈现匹配于所述搜索关键字的搜索结果，所述搜索引擎被部署在数据提供系统中，并且所述搜索结果指向所述数据提供系统中的数据。
  6. 根据权利要求2所述的方法，其中所述处理应用包括聊天应 用，以及在所述第二页面中呈现所述第二应答包括：
    向所述聊天应用中的聊天群组转发所述第一页面中的上下文数据；以及
    在所述第二页面中呈现来自所述聊天群组中的用户的消息。
  7. 根据权利要求2所述的方法，进一步包括：响应于在所述第二页面中接收到用于退出所述应用的第四请求，返回所述第一页面。
  8. 根据权利要求1所述的方法，其中所述第一部分是：
    由所述数字助手自动识别的，或者
    响应于选择请求来确定的。
  9. 根据权利要求1所述的方法，其中所述第一数字助手和所述处理应用被集成在查询平台中，并且所述处理应用是由所述查询平台基于所述第一应答和所述第一部分来从被集成在所述查询平台中的多个处理应用中选择的。
  10. 根据权利要求1所述的方法，其中所述第一交互控件响应于确定所述第一交互请求的持续时间满足第一时间段而被呈现，并且所述第一交互控件以浮动方式被呈现在所述第一页面上层。
  11. 根据权利要求10所述的方法，进一步包括：响应于确定在第二时间段内未接收到针对所述第一交互控件的第二交互请求，隐藏所述第一交互控件。
  12. 根据权利要求2所述的方法，其中所述第二应答的内容是基于与所述第一应答相关联的上下文以及所述第一部分来确定的。
  13. 根据权利要求2所述的方法，其中所述第二应答的媒体类型是基于所述第一数字助手中的交互历史来确定的。
  14. 一种用于查询的装置，包括：
    第一应答呈现模块，被配置为在第一数字助手的第一页面中，利用第一格式呈现第一应答，所述第一应答是基于第一查询请求来生成的；
    第二应答呈现模块，被配置为利用第二格式呈现所述第一应答中的第一部分；以及
    第一控件呈现模块，被配置为响应于接收到针对所述第一部分的第一交互请求，呈现第一交互控件，所述第一交互控件用于调用不同于所述第一数字助手的处理应用来处理与所述第一部分相关联的第二查询请求。
  15. 一种电子设备，包括：
    至少一个处理单元；以及
    至少一个存储器，所述至少一个存储器被耦合到所述至少一个处理单元并且存储用于由所述至少一个处理单元执行的指令，所述指令在由所述至少一个处理单元执行时使所述电子设备执行根据权利要求1至13中任一项所述的方法。
  16. 一种计算机可读存储介质，其上存储有计算机程序，所述计算机程序可由处理器执行以实现根据权利要求1至13中任一项所述的方法。
  17. 一种计算机程序产品，包括计算机程序，其中所述计算机程序在被处理器执行时实现根据权利要求1至13中任一项所述的方法。
PCT/CN2024/095797 2024-05-28 2024-05-28 用于查询的方法、装置、设备和存储介质 Pending WO2025245698A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2024/095797 WO2025245698A1 (zh) 2024-05-28 2024-05-28 用于查询的方法、装置、设备和存储介质
CN202480002188.5A CN119173867A (zh) 2024-05-28 2024-05-28 用于查询的方法、装置、设备和存储介质

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2024/095797 WO2025245698A1 (zh) 2024-05-28 2024-05-28 用于查询的方法、装置、设备和存储介质

Publications (1)

Publication Number Publication Date
WO2025245698A1 true WO2025245698A1 (zh) 2025-12-04

Family

ID=93889363

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2024/095797 Pending WO2025245698A1 (zh) 2024-05-28 2024-05-28 用于查询的方法、装置、设备和存储介质

Country Status (2)

Country Link
CN (1) CN119173867A (zh)
WO (1) WO2025245698A1 (zh)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20140133153A (ko) * 2013-05-10 2014-11-19 엘지전자 주식회사 이동 단말기 및 이동 단말기의 제어 방법
CN104391912A (zh) * 2014-11-18 2015-03-04 百度在线网络技术（北京）有限公司 基于应用互通的方法和装置
CN105095231A (zh) * 2014-04-29 2015-11-25 阿里巴巴集团控股有限公司 一种呈现搜索结果的方法和装置
CN105607807A (zh) * 2015-12-22 2016-05-25 惠州Tcl移动通信有限公司 一种基于移动终端的文字处理方法及系统
US20170192644A1 (en) * 2015-12-31 2017-07-06 Quixey, Inc. Accessing Additional Search Results Functionality Using Gestures
US20170192639A1 (en) * 2015-12-30 2017-07-06 Quixey, Inc. Using Search Results As Software Application Input Parameters

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20140133153A (ko) * 2013-05-10 2014-11-19 엘지전자 주식회사 이동 단말기 및 이동 단말기의 제어 방법
CN105095231A (zh) * 2014-04-29 2015-11-25 阿里巴巴集团控股有限公司 一种呈现搜索结果的方法和装置
CN104391912A (zh) * 2014-11-18 2015-03-04 百度在线网络技术（北京）有限公司 基于应用互通的方法和装置
CN105607807A (zh) * 2015-12-22 2016-05-25 惠州Tcl移动通信有限公司 一种基于移动终端的文字处理方法及系统
US20170192639A1 (en) * 2015-12-30 2017-07-06 Quixey, Inc. Using Search Results As Software Application Input Parameters
US20170192644A1 (en) * 2015-12-31 2017-07-06 Quixey, Inc. Accessing Additional Search Results Functionality Using Gestures

Also Published As

Publication number Publication date
CN119173867A (zh) 2024-12-20

Similar Documents

Publication Publication Date Title
US12475178B2 (en) Generating narrative query responses utilizing generative language models from search-based autosuggest queries
WO2024240105A1 (zh) 用于信息处理的方法、装置、设备和存储介质
WO2025209146A1 (zh) 用于图像编辑的方法、装置、设备、介质和程序产品
WO2025223031A1 (zh) 信息处理方法、装置、设备和存储介质
WO2025223030A1 (zh) 信息处理方法、装置、设备和存储介质
WO2025246492A1 (zh) 信息处理方法、装置、设备和存储介质
WO2026040472A1 (zh) 应用配置方法、信息处理方法、装置、设备和存储介质
EP4650980A1 (en) Query method and apparatus, device and storage medium
WO2026001060A1 (zh) 信息处理方法、装置、设备和存储介质
WO2025245698A1 (zh) 用于查询的方法、装置、设备和存储介质
WO2025071827A1 (en) Machine-learning through hybrid compute
CN113535927A (zh) 获取相似文本的方法、介质、装置和计算设备
WO2025231710A1 (zh) 用于处理查询请求的方法、装置、设备和存储介质
US12481704B2 (en) Ghosting for multimodal dialogs
WO2025108115A1 (zh) 数据处理的方法、装置、设备和存储介质
WO2026044466A1 (zh) 内容查询的方法、装置、设备、存储介质和程序产品
WO2026002003A1 (zh) 用于问答的方法、装置、设备和存储介质
WO2026077043A1 (zh) 任务处理的方法、装置、设备、存储介质和程序产品
WO2025236158A1 (zh) 用于对话交互的方法、装置、设备和存储介质
WO2026001142A1 (zh) 对话信息处理方法、装置、设备和存储介质
WO2026061216A1 (zh) 用于请求处理的方法、装置、设备、存储介质和程序产品
WO2025255789A1 (zh) 请求处理方法、装置、设备和存储介质
CN118197290A (zh) 模型输出处理的方法、装置、设备和可读介质
WO2025245697A1 (zh) 利用数字助手处理图像的方法、装置、设备和存储介质
WO2025222455A1 (zh) 用于确定提示词的方法、装置、设备和存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 24941016

Country of ref document: EP

Kind code of ref document: A1