Method and apparatus for generating response, device, and medium

Abstract

Provided are a method and apparatus for generating a response, a device, and a medium. The method comprises: acquiring a first data object; providing a plurality of candidate attitudes for a response to the first data object; and in response to receiving a first interaction request for a candidate attitude among the plurality of candidate attitudes, generating a second data object as the response to the first data object, wherein second content of the second data object is determined on the basis of first content of the first data object and the candidate attitude. By means of the exemplary implementation of the present disclosure, by providing a plurality of candidate attitudes, a user can be facilitated to select a desired attitude, thereby automatically generating a response. In this way, the complexity of user operations can be reduced, and the response is generated in a simpler and more efficient mode.

Description

Methods, apparatus, devices and media for generating responses Technical Field

[0001] Exemplary implementations of this disclosure generally relate to the field of computers, and more particularly to methods, apparatus, devices, and computer-readable storage media for generating responses. Background Technology

[0002] Machine learning techniques have been widely used to process various data objects. For example, a data object can be received and prompts can be built to generate responses for that data object using a machine learning model. However, this process involves a significant amount of manual work, and there is a desire to simplify the process and generate responses for the data object in a more convenient and efficient manner.

[0003] Summary of the Invention

[0004] In a first aspect of this disclosure, a method for generating a response is provided. In this method, a first data object is obtained. A plurality of candidate attitudes for a response to the first data object are provided. In response to receiving a first interaction request for a candidate attitude among the plurality of candidate attitudes, a second data object is generated as a response to the first data object, wherein a second content of the second data object is determined based on the first content of the first data object and the candidate attitudes.

[0005] In a second aspect of this disclosure, an apparatus for generating a response is provided. The apparatus includes: an acquisition module configured to acquire a first data object; a providing module configured to provide a plurality of candidate attitudes for a response to the first data object; and a generation module configured to, in response to receiving a first interaction request for a candidate attitude among the plurality of candidate attitudes, generate a second data object as a response to the first data object, wherein a second content of the second data object is determined based on the first content of the first data object and the candidate attitudes.

[0006] In a third aspect of this disclosure, an electronic device is provided. The electronic device 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, the instructions causing the electronic device to perform the method according to a first aspect of this disclosure when executed by the at least one processing unit.

[0007] In a fourth aspect of this disclosure, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, causes the processor to implement the method according to a first aspect of this disclosure.

[0008] In a fifth aspect of this disclosure, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the method according to a first aspect of this disclosure.

[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 implementation 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 various implementations of this disclosure will become more apparent in the following detailed description, taken in conjunction with the accompanying drawings. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:

[0011] Figure 1 shows a block diagram of an application environment according to an exemplary implementation of the present disclosure;

[0012] Figure 2 shows a block diagram for generating a response according to some implementations of this disclosure;

[0013] Figure 3 shows a block diagram illustrating the use of a machine learning model to generate a second data object according to some implementations of this disclosure;

[0014] Figure 4 shows a block diagram for determining prompt words according to some implementations of this disclosure;

[0015] Figure 5 shows a block diagram for extracting key information according to some implementations of this disclosure;

[0016] Figure 6 shows a block diagram for editing a second data object according to some implementations of this disclosure;

[0017] Figure 7 shows a block diagram for generating comments for videos according to some implementations of this disclosure;

[0018] Figure 8 shows a flowchart of a method for generating a response according to some implementations of this disclosure;

[0019] Figure 9 shows a block diagram of an apparatus for generating a response according to some implementations of the present disclosure; and

[0020] Figure 10 shows a block diagram of a device capable of implementing various implementations of the present disclosure. Detailed Implementation

[0021] Implementations of this disclosure will now be described in more detail with reference to the accompanying drawings. While some implementations 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 implementations set forth herein. Rather, these implementations are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and implementations of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0022] In the description of the implementation methods disclosed herein, the term "comprising" and similar terms should be understood as open inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "one implementation" or "the implementation" should be understood as "at least one implementation". The term "some implementations" should be understood as "at least some implementations". Other explicit and implicit definitions may also be included below. As used herein, the term "model" can represent the relationships between various data. For example, the aforementioned relationships can be obtained based on various currently known and / or future-developed technical solutions.

[0023] It is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0024] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure through appropriate means in accordance with relevant laws and regulations, and user authorization should be obtained.

[0025] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this disclosed technical solution, based on the prompt message.

[0026] As an optional but non-restrictive implementation, in response to a user's active request, a prompt message can be sent to the user, for example, via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose whether to "agree" or "disagree" to provide personal information to the electronic device.

[0027] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0028] The term "in response to" as used herein refers to a state in which a corresponding event occurs or a condition is satisfied. It will be understood that the timing of subsequent actions performed in response to such event or condition is not necessarily strongly correlated with the time when the event occurs or the condition is met. For example, in some cases, subsequent actions may be performed immediately upon the occurrence of the event or the fulfillment of the condition; while in others, they may be performed some time after the occurrence of the event or the fulfillment of the condition.

[0029] Example Environment

[0030] Machine learning techniques have been widely used to process various data objects. For example, a data object to be processed can be received, and prompts can be constructed to invoke a machine learning model to generate a response for that data object. Refer to Figure 1 for an application environment illustrating some implementations of this disclosure; Figure 1 shows a block diagram 100 of an application environment according to an exemplary implementation of this disclosure. For ease of description, an email application is used as an example below to describe the application environment of some implementations of this disclosure.

[0031] As shown in Figure 1, email application 110 can receive email 120. Users can click control 130 to reply to email 120. At this point, users need to manually enter text content. Although technical solutions using machine learning models to generate responses have been proposed, users still need to manually construct prompts to specify the content of the response email. This process involves a significant amount of manual work, and users may need to repeatedly adjust the prompts to obtain the desired response. Therefore, it is hoped that this process can be simplified, and responses to data objects can be generated in a more convenient and efficient manner.

[0032] Summary of generated response

[0033] To at least partially address the shortcomings of the prior art, a method for generating a response is proposed according to an exemplary implementation of this disclosure. Referring to Figure 2, which describes an outline of an exemplary implementation of this disclosure, a block diagram 200 for generating a response according to some implementations of this disclosure is shown. As shown in Figure 2, a first data object (e.g., an email in the inbox) can be obtained. To facilitate the generation of a reply email, multiple candidate attitudes 230 for the response to the first data object 210 can be provided. For example, page element 232 can represent content opposing the email, and page element 234 can represent content supporting the email, and so on. Here, candidate attitudes can include, for example, "positive," "negative," or "neutral," etc. Alternatively and / or additionally, other page elements can be provided, for example, page elements representing attitudes such as "not interested" and / or "need more information" can be further provided.

[0034] Users can click on the aforementioned page elements to select a candidate attitude from multiple candidate attitudes. In response to receiving a first interaction request for a candidate attitude among the multiple candidate attitudes 230, a second data object 220 can be generated as a response to the first data object 210. At this time, the second content of the second data object 220 (i.e., the body of the email) is determined based on the first content of the first data object 210 (e.g., the email title and / or body, etc.) and the candidate attitude. As shown in Figure 2, assuming a selection operation is received for page element 234, a second data object 220 (i.e., a reply email) can be generated. The generated email expresses a supportive attitude: "Great, I'll participate."

[0035] By utilizing the exemplary implementation of this disclosure, multiple candidate attitudes can be provided, allowing users to easily select their desired attitude and automatically generate a response. In this way, users do not need to manually input response content or generate prompts; instead, they can generate responses in a simpler and more efficient manner.

[0036] Detailed process of generating a response

[0037] Having described an overview of some implementations according to this disclosure, further details regarding the generation of responses will be described below. According to some implementations of this disclosure, a machine learning model can be used to determine the content of the response. Specifically, prompt words can be determined based on candidate attitudes, specifying the task to be performed on a first data object, and a second content of a second data object is obtained based on the machine learning model's response to the prompt words. See Figure 3 for a detailed description of the process, which shows a block diagram 300 illustrating the generation of a second data object using a machine learning model according to some implementations of this disclosure.

[0038] As shown in Figure 3, prompt word 310 can be determined based on candidate attitude 230. Prompt word 310 can instruct the machine learning model to generate a response to the first data object 210, specifying the attitude as "support". For example, prompt word 310 may include: "Please generate a reply email agreeing to the email content", etc. Alternatively, prompt word 310 may include: "Please generate a reply email disagreeing with the email content", etc. Prompt word 310 and the first data object 210 can be input into machine learning model 320 to generate a second data object 220. Alternatively and / or additionally, prompt word 310 can be generated using partial information from the first data object 210. In this case, prompt word 310 may include: "Please generate a reply email agreeing to the Saturday outing", etc.

[0039] Using the example implementations disclosed herein, users do not need to manually draft reply emails or manually construct prompts; instead, they can automatically generate reply emails within the email application through simple interactive operations.

[0040] According to some implementations of this disclosure, during the generation of the second data object 220, in order to refine the specific content of the response, a question 330 related to the second content of the second data object 220 can be provided, and in response to receiving a second interaction request for the question 330, the prompt word 310 is updated. Whether to ask the user to supplement information can be determined based on the chosen attitude; if supplementation is required, questions can be provided to allow the user to supplement the key points of the response. Continuing the above example, assuming the user objects to a weekend outing, the questions could include, but are not limited to: please provide reasons for objection, please provide candidate dates, please provide candidate locations, etc. Alternatively and / or additionally, a cloze test-style information supplement template can be provided, or more detailed information about the response can be obtained in other ways. Using the example implementations of this disclosure, the specific content of the response can be refined, and responses that are more in line with the user's intent can be generated.

[0041] According to some implementations of this disclosure, during the process of determining the prompt word 310, a prompt word template can be presented, which can specify at least one attribute of the prompt word 310. Further, in response to receiving a third interaction request for at least one attribute, a prompt word is generated. See Figure 4 for further details, which shows a block diagram 400 for determining the prompt word according to some implementations of this disclosure. As shown in Figure 4, a prompt word template for generating the content of the second data object 220 can be presented on page 410. Here, page element 440 can be clicked to select a candidate attitude, such as support or opposition, etc. Page elements 420, 422, and 424 can be clicked to specify other attributes of the prompt word.

[0042] For example, page element 420 can specify the tone of the generated response. Upon receiving an interaction request for page element 420, the desired tone can be selected from multiple candidates 430 (e.g., formal, casual, professional, etc.). Similarly, page element 422 can specify the tone of the generated response. Upon receiving an interaction request for page element 422, the desired length can be selected from multiple candidates (e.g., long, medium, short, etc.). And page element 424 can specify the language of the generated response. Upon receiving an interaction request for page element 424, the desired language can be selected from multiple candidates (e.g., Simplified Chinese, English, etc.). In this way, users can specify multiple aspects of the response, thereby generating a response that better meets user expectations.

[0043] According to some implementations of this disclosure, key information in the first content of the first data object can be further determined, and the part associated with the key information can be highlighted in the response. Specifically, the key content corresponding to the key information in the second content can be presented using a first format, and other content in the second content other than the key content can be presented using a second format. See Figure 5 for further details, which shows a block diagram 500 for extracting key information according to some implementations of this disclosure.

[0044] As shown in Figure 5, key information 510 can be extracted from the first data object 210 in various ways. For example, key information 510 can be determined based on syntactic analysis and semantic analysis of the first content in the first data object 210. Alternatively and / or additionally, machine learning models can be used to extract key information 510. Here, key information may include, for example, information item 512 indicating the date ("this Saturday"), information item 514 indicating the location (the gate of Park A), information item 516 indicating the time ("9:00 AM"), and so on.

[0045] Furthermore, different formats can be used to present different content in the second data object. More information is described in Figure 6, which shows a block diagram 600 for editing the second data object according to some implementations of this disclosure. As shown in Figure 6, in page 610, key content corresponding to key information in the second content can be presented using a first format 620, and other content besides the key content in the second content can be presented using a second format 622. Specifically, content corresponding to the key time "9 o'clock" can be highlighted using an underline format, and other non-key parts of the generated content can be presented in a regular format.

[0046] It should be understood that the underline is merely an example; alternatively and / or additionally, other colors (such as red, blue, etc.), fonts, font sizes, background colors, etc., can be used to present the key content "9 points". Using the example implementation method disclosed herein, key content related to key information in the response can be presented in a more prominent manner. This approach can draw the user's attention to key content, thereby supporting the user in performing subsequent editing operations.

[0047] According to some implementations of this disclosure, candidate content for the key content can be presented, and in response to receiving a fourth interaction request for the candidate content, the key content can be updated using the candidate content. Continuing to refer to Figure 6, when a user answers a question, if the user thinks 9 o'clock is too early, the machine learning model can automatically generate multiple candidate content corresponding to the key content "9 o'clock" (e.g., 9 o'clock, 10 o'clock, 11 o'clock, etc.). For example, page element 630 including multiple candidate content can be presented so that the user can select a suitable time.

[0048] Suppose a user selects "10 o'clock". In response to receiving an interaction request for that candidate content, "9 o'clock" can be updated to "10 o'clock". At this point, a message like "9 o'clock is too early, can it be changed to 10 o'clock?" can be automatically generated. Using the example implementation method of this disclosure, candidate content for key information can be automatically provided to support users in updating the second content of the second data object 220 using simple click, selection, and other interaction requests.

[0049] According to some implementations of this disclosure, users can edit the content of a second data object. Specifically, in response to receiving a fifth interaction request for the second content of the second data object, the second content of the second data object is updated based on the fifth interaction request. For example, users can add, delete, or modify the second content to obtain a desired response. Using the example implementations of this disclosure, machine learning models can be used to generate the main body of the response, and users can generate responses with only simple editing operations.

[0050] According to some implementations of this disclosure, in response to receiving a sixth interaction request for confirming a second data object, the second data object is submitted as a response to the first data object. As shown in Figure 6, the user can click page element 640 to confirm and send the generated email, and can click page element 642 to cancel the email. At this time, the email application can detect the interaction request with the aforementioned page elements in order to perform the corresponding action. In this way, the process of generating and sending a response can be automated, thereby reducing the complexity of user operations.

[0051] According to some implementations of this disclosure, the method described above can be implemented in an application that provides the first data object. It should be understood that although the details of generating a response are described above using an email application as a specific application environment, alternatively and / or additionally, the method can be implemented in other types of applications. For example, the method can be implemented in an instant messaging application, where the first data object can be a message sent by another user, and the above method can be used to automatically generate a response to the message. As another example, the method can be implemented in a social networking application, where the first data object can be an article published by another user, and the above method can be used to automatically generate a response to the article. Yet another example, the method can be implemented in a video application, where the first data object can be a video, and the above method can be used to automatically generate comments for the video.

[0052] According to some implementations of this disclosure, the first data object and the second data object may have the same modality or different modalities; that is, the first modality of the first data object is different from the second modality of the second data object. For example, in an email application scenario, both the first data object and the second data object may be text modal; as another example, in a social network application scenario, the first data object may include text and images, and the second data object may include only text. Using the example implementations of this disclosure, it is possible to support the generation of response data across multiple modalities.

[0053] Figure 7 illustrates a block diagram 700 for generating video comments according to some implementations of this disclosure. As shown in Figure 7, in the video application 710, a video 720 and candidate attitudes 760 for the video can be provided. Users can watch the video and enter their attitude towards it (e.g., 0-5 stars, where 0 stars indicates dislike and 5 stars indicates support). A comment 730 can then be automatically generated, such as "This is a very good movie…", and the user can edit the comment 730 by clicking page element 740 to post it or by clicking page element 750 to cancel it. Alternatively and / or additionally, the user can use a swipe gesture to enter a "3-star" attitude, in which case the generated comment could include "This movie is pretty good…".

[0054] Using the example implementation of this disclosure, by providing multiple candidate attitudes, users can easily select their desired attitude, thereby automatically generating a response. In this way, users do not need to input the response content themselves or manually generate prompts, but can generate responses in a simpler and more efficient manner.

[0055] Example process

[0056] Figure 8 shows a flowchart of a method 800 for generating a response according to some implementations of this disclosure. At block 810, a first data object is obtained. At block 820, multiple candidate attitudes for the response to the first data object are provided. At block 830, in response to receiving a first interaction request for a candidate attitude among the multiple candidate attitudes, a second data object is generated as a response to the first data object, the second content of the second data object being determined based on the first content of the first data object and the candidate attitudes.

[0057] According to some implementations of this disclosure, the second content of the second data object is determined based on: determining a prompt word based on candidate attitudes, the prompt word specifying the task to be performed on the first data object; and obtaining the second content of the second data object based on the response of a machine learning model to the prompt word.

[0058] According to some implementations of this disclosure, determining the prompt word includes: presenting a prompt word template, the prompt word template specifying at least one attribute of the prompt word; and generating the prompt word in response to receiving a second interaction request for at least one attribute.

[0059] According to some implementations of this disclosure, determining the prompt word further includes: providing a question associated with the second content of the second data object; and updating the prompt word in response to receiving a third interactive request for the question.

[0060] According to some implementations of this disclosure, the method 800 further includes: determining key information in the first content of the first data object; presenting key content in the content corresponding to the key information using a first format; and presenting other content in the second content other than the key content using a second format.

[0061] According to some implementations of this disclosure, the method 800 further includes: presenting candidate content for key content; and updating the key content using the candidate content in response to receiving a fourth interaction request for the candidate content.

[0062] According to some implementations of this disclosure, the method 800 further includes: in response to receiving a fifth interaction request for the second content of the second data object, updating the second content of the second data object based on the fifth interaction request.

[0063] According to some implementations of this disclosure, the method 800 further includes: in response to receiving a sixth interaction request for acknowledging a second data object, submitting the second data object as a response to the first data object.

[0064] According to some implementations of this disclosure, method 800 is implemented in an application for providing a first data object.

[0065] According to some implementations of this disclosure, the first modality of the first data object is different from the second modality of the second data object.

[0066] Example devices and equipment

[0067] Figure 9 shows a block diagram of an apparatus 900 for generating a response according to some implementations of the present disclosure. The apparatus 900 includes: an acquisition module 910 configured to acquire a first data object; a providing module 920 configured to provide a plurality of candidate attitudes for the response to the first data object; and a generation module 930 configured to generate a second data object as a response to the first data object in response to receiving a first interaction request for a candidate attitude among the plurality of candidate attitudes, wherein a second content of the second data object is determined based on the first content of the first data object and the candidate attitudes.

[0068] According to some implementations of this disclosure, the second content of the second data object is determined based on: determining a prompt word based on candidate attitudes, the prompt word specifying the task to be performed on the first data object; and obtaining the second content of the second data object based on the response of a machine learning model to the prompt word.

[0069] According to some implementations of this disclosure, the generation module is further configured to: present a prompt word template, the prompt word template specifying at least one attribute of the prompt word; and generate the prompt word in response to receiving a second interaction request for at least one attribute.

[0070] According to some implementations of this disclosure, the generation module is further configured to: provide a question associated with the second content of the second data object; and update the prompt word in response to receiving a third interactive request for the question.

[0071] According to some implementations of this disclosure, the device further includes an interaction module configured to: determine key information in the first content of the first data object; present key content in the content corresponding to the key information using a first format; and present other content in the second content other than the key content using a second format.

[0072] According to some implementations of this disclosure, the interaction module is further configured to: present candidate content for key content; and update the key content using the candidate content in response to receiving a fourth interaction request for the candidate content.

[0073] According to some implementations of this disclosure, the interaction module is further configured to: update the second content of the second data object based on the fifth interaction request in response to receiving a fifth interaction request for the second content of the second data object.

[0074] According to some implementations of this disclosure, the interaction module is further configured to: in response to receiving a sixth interaction request for acknowledging the second data object, submit the second data object as a response to the first data object.

[0075] According to some implementations of this disclosure, the apparatus is implemented in an application for providing a first data object.

[0076] According to some implementations of this disclosure, the first modality of the first data object is different from the second modality of the second data object.

[0077] Figure 10 shows a block diagram of a device 1000 capable of implementing various implementations of the present disclosure. It should be understood that the computing device 1000 shown in Figure 10 is merely exemplary and should not constitute any limitation on the functionality and scope of the implementations described herein. The computing device 1000 shown in Figure 10 can be used to implement the methods described above.

[0078] As shown in Figure 10, the computing device 1000 is in the form of a general-purpose computing device. Components of the computing device 1000 may include, but are not limited to, one or more processors or processing units 1010, memory 1020, storage devices 1030, one or more communication units 1040, one or more input devices 1050, and one or more output devices 1060. The processing unit 1010 may be a physical or virtual processor and is capable of performing various processes according to programs stored in memory 1020. In a multiprocessor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing capability of the computing device 1000.

[0079] Computing device 1000 typically includes multiple computer storage media. Such media can be any available media accessible to computing device 1000, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 1020 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 1030 can be removable or non-removable media and may include machine-readable media, such as flash drives, disks, or any other media capable of storing information and / or data (e.g., training data for training) and accessible within computing device 1000.

[0080] The computing device 1000 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not shown in FIG. 10, 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. The memory 1020 may include a computer program product 1025 having one or more program modules configured to perform various methods or actions of various implementations of this disclosure.

[0081] The communication unit 1040 enables communication with other computing devices via a communication medium. Additionally, the components of the computing device 1000 can function as a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, the computing device 1000 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network node.

[0082] Input device 1050 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 1060 can be one or more output devices, such as a monitor, speaker, printer, etc. Computing device 1000 can also communicate with one or more external devices (not shown) via communication unit 1040 as needed. These external devices include storage devices, display devices, etc., and can communicate with one or more devices that enable user interaction with computing device 1000, or with any device (e.g., network card, modem, etc.) that enables computing device 1000 to communicate with one or more other computing devices. Such communication can be performed via input / output (I / O) interface (not shown).

[0083] According to exemplary implementations 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 exemplary implementations 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. According to exemplary implementations of this disclosure, a computer program product is provided that stores a computer program thereon, which, when executed by a processor, implements the methods described above.

[0084] 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.

[0085] 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. 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.

[0086] 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.

[0087] 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.

[0088] 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 method for generating a response, comprising: Get the first data object; Provide multiple candidate attitudes for the response to the first data object; as well as In response to receiving a first interaction request for a candidate attitude among the plurality of candidate attitudes, a second data object is generated as a response to the first data object, wherein the second content of the second data object is determined based on the first content of the first data object and the candidate attitude.

2. The method of claim 1, wherein the second content of the second data object is determined based on the following: Based on the candidate attitudes, a prompt word is determined, the prompt word specifying the task to be performed on the first data object; and Based on the machine learning model's response to the prompt words, the second content of the second data object is obtained.

3. The method of claim 2, wherein determining the prompt word further comprises: Provide questions related to the second content of the second data object; as well as In response to receiving a second interactive request for the question, the prompt word is updated.

4. The method of claim 2, wherein determining the prompt word comprises: Present a prompt word template, wherein the prompt word template specifies at least one attribute of the prompt word; as well as The prompt word is generated in response to receiving a third interaction request for the at least one attribute.

5. The method of claim 1, further comprising: Determine the key information in the first content of the first data object; The key content corresponding to the key information in the second content is presented using a first format; as well as The second format is used to present content other than the key content in the second content.

6. The method of claim 5, further comprising: Candidate content to present the key content; as well as In response to receiving a fourth interaction request for the candidate content, the key content is updated using the candidate content.

7. The method of claim 1, further comprising: In response to receiving a fifth interaction request for the second content of the second data object, the second content of the second data object is updated based on the fifth interaction request.

8. The method of claim 1, further comprising: In response to receiving a sixth interaction request to confirm the second data object, the second data object is submitted as a response to the first data object.

9. The method of claim 1, wherein the method is implemented in an application for providing the first data object.

10. The method of claim 1, wherein the first modality of the first data object is different from the second modality of the second data object.

11. An apparatus for generating a response, comprising: The acquisition module is configured to acquire the first data object. A module is provided, configured to provide multiple candidate attitudes for a response to the first data object; as well as A generation module is configured to generate a second data object as a response to the first data object in response to receiving a first interaction request for a candidate attitude among the plurality of candidate attitudes, wherein the second content of the second data object is determined based on the first content of the first data object and the candidate attitude.

12. An electronic device, comprising: At least one processing unit; as well as At least one memory, coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions... When executed by the at least one processing unit, the electronic device performs the method according to any one of claims 1 to 10.

13. A computer-readable storage medium having a computer program stored thereon, the computer program causing the processor to implement the method according to any one of claims 1 to 10 when executed by a processor.

14. A computer program product comprising a computer program, wherein the computer program, when executed by a processor, implements the method according to any one of claims 1 to 10.

Images