Information processing method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides an information processing method and device, electronic equipment and a storage medium, and the information processing method comprises the steps: responding to a first operation for target content, and displaying at least one alternative prompt word in a second session interface; wherein the target content comprises session content of the user account in the first session interface and / or input content of the user account in the second session interface, and in response to a second operation on the alternative cue word, determining a target cue word; and based on the target cue word, executing corresponding processing on the target content.

Description

Technical Field

[0001] The present disclosure relates to but is not limited to the field of information technology, and in particular to an information processing method, device, electronic device and storage medium. Background Art

[0002] With the development of artificial intelligence (AI) models, the execution capabilities of AI models are getting stronger and stronger. For example, AI models are becoming more and more capable of recognizing natural languages. For another example, AI models can perform various text processing operations based on input content.

[0003] However, in a conversation scenario with an AI model, the accuracy of the user's input questions or the AI ​​model's recognition bias of the user's input questions may cause the results returned by the AI ​​model to be different from what the user needs, affecting the user experience, or requiring the user to input multiple times to instruct the AI ​​model to perform the operations the user wants. Summary of the invention

[0004] The present disclosure provides an information processing method, apparatus, device and storage medium.

[0005] A first aspect of the present disclosure provides an information processing method, including:

[0006] In response to a first operation on a target content, displaying at least one candidate prompt word in a second conversation interface; wherein the target content includes a conversation content of a user account in the first conversation interface, and / or input content of the user account in the second conversation interface;

[0007] In response to a second operation on the candidate prompt word, determining a target prompt word;

[0008] Based on the target prompt word, corresponding processing is performed on the target content.

[0009] Optionally, in response to the first operation on the target content, displaying at least one candidate prompt word in the second conversation interface includes:

[0010] Based on the target content, determining a target conversation scenario;

[0011] Based on the target conversation scenario, at least one candidate prompt word related to the target content is displayed in the second conversation interface.

[0012] Optionally, determining a target conversation scenario based on the target content includes:

[0013] Based on the target content, determining the target conversation scenario from a plurality of preset conversation scenarios, or,

[0014] Determine the target conversation scenario based on the capabilities involved in the target content, or,

[0015] The target conversation scenario is determined based on text processing requirements related to the target content.

[0016] Optionally, in response to the first operation on the target content, displaying at least one candidate prompt word in the second conversation interface includes:

[0017] Inputting the target content into a prompt word generation model to obtain at least one candidate prompt word output by the prompt word generation model;

[0018] The alternative prompt words are displayed in the second conversation interface.

[0019] Optionally, the input content of the second conversation interface includes:

[0020] Inputting the information to be processed in the second conversation interface;

[0021] or,

[0022] The conversation content of the second conversation interface.

[0023] Optionally, performing a corresponding operation on the target content based on the target prompt word includes:

[0024] Based on the target prompt word, a corresponding content processing interface is called to process the target content, wherein different target prompt words correspond to different content processing interfaces.

[0025] Optionally, the method further comprises:

[0026] When the current conversation ends, the prompt word generation model is updated based on the conversation content in the second conversation interface.

[0027] Optionally, the method further includes:

[0028] Displaying the execution result of the target content on the second conversation interface;

[0029] According to a third operation acting on the execution result, the execution result is shared to the first conversation interface.

[0030] A second aspect of the present disclosure provides an information processing device, including:

[0031] a first display module, configured to display at least one candidate prompt word in the second conversation interface in response to a first operation on a target content; wherein the target content includes a conversation content of a user account in the first conversation interface and / or input content of the user account in the second conversation interface;

[0032] A determination module, configured to determine a target prompt word in response to a second operation on the candidate prompt word;

[0033] An execution module is used to perform corresponding processing on the target content based on the target prompt word.

[0034] Optionally, the first display module includes:

[0035] A determination unit, configured to determine a target conversation scenario based on the target content;

[0036] A display unit is used to display at least one candidate prompt word related to the target content in the second conversation interface based on the target conversation scenario.

[0037] Optionally, the determining unit is used to:

[0038] Based on the target content, determining the target conversation scenario from a plurality of preset conversation scenarios, or,

[0039] Determine the target conversation scenario based on the capabilities involved in the target content, or,

[0040] The target conversation scenario is determined based on text processing requirements related to the target content.

[0041] Optionally, the first display module is used to:

[0042] Inputting the target content into a prompt word generation model to obtain at least one candidate prompt word output by the prompt word generation model;

[0043] Optionally, the input content of the second conversation interface includes:

[0044] Inputting the information to be processed in the second conversation interface;

[0045] or,

[0046] The conversation content of the second conversation interface.

[0047] Optionally, the execution module is used to:

[0048] Based on the target prompt word, a corresponding content processing interface is called to process the target content; wherein different target prompt words correspond to different content processing interfaces.

[0049] Optionally, the device further comprises:

[0050] The updating module updates the prompt word generation model based on the conversation content in the second conversation interface when the current conversation ends.

[0051] Optionally, the device further comprises:

[0052] A second display module, configured to display the execution result of the target content on the second conversation interface;

[0053] A sharing module is used to share the execution result to the first conversation interface according to a third operation acting on the execution result.

[0054] A third aspect of the present disclosure provides an electronic device, including:

[0055] processor;

[0056] a memory for storing processor-executable instructions;

[0057] The processor is configured to: implement the method provided by any one of the technical solutions in the first aspect when running the executable instructions.

[0058] A fourth aspect of an embodiment of the present disclosure provides a computer-readable storage medium, wherein the readable storage medium stores an executable program, wherein when the executable program is executed by a processor, the method provided by any one of the solutions in the first aspect is implemented.

[0059] The technical solution provided by the embodiment of the present disclosure generates at least one alternative prompt word based on the conversation content of the user account in the first conversation interface and / or the input content of the user account in the second conversation interface. Since the conversation content of the first conversation interface and the input content of the second conversation interface can reflect the functions that the user may currently need the AI ​​model to perform to a certain extent. Therefore, based on the conversation content of the first conversation interface and the input content of the second conversation interface, the alternative prompt words displayed on the second conversation interface are generated, which can make the generated alternative prompt words closer to user needs. In this way, the user can instruct the AI ​​model to perform the operation required by the user by selecting the alternative prompt words displayed on the second conversation interface, thereby improving the communication efficiency between the user and the AI ​​model.

[0060] In addition, since the user does not need to manually enter prompt words through the input method in the above process, the convenience of user conversation with the AI ​​model is improved, thereby improving the user experience.

[0061] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0063] Figure 1 It is a flowchart of an information processing method according to an exemplary embodiment.

[0064] Figure 2 The diagram is a schematic diagram of a first conversation interface according to an exemplary embodiment.

[0065] Figure 3 The figure is a schematic diagram of a first conversation interface and a second conversation interface according to an exemplary embodiment.

[0066] Figure 4 The figure is a schematic diagram of a first conversation interface and a second conversation interface according to another exemplary embodiment.

[0067] Figure 5 The figure is a schematic diagram of a first conversation interface and a second conversation interface according to another exemplary embodiment.

[0068] Figure 6 It is a flowchart of an information processing method according to another exemplary embodiment.

[0069] Figure 7 The diagram is a schematic diagram of a first conversation interface and a second conversation interface in a product research scenario according to an exemplary embodiment.

[0070] Figure 8 The figure is a schematic diagram of a first conversation interface and a second conversation interface according to another exemplary embodiment.

[0071] Fig. 9 The figure is a schematic diagram of a first conversation interface and a second conversation interface according to another exemplary embodiment.

[0072] Fig.10 The figure is a schematic diagram of a first conversation interface and a second conversation interface according to another exemplary embodiment.

[0073] Fig.11 It is a flowchart of an information processing method according to another exemplary embodiment.

[0074] Fig.12 is a schematic structural diagram of an information processing device according to another exemplary embodiment.

[0075] Fig.13The diagram is a schematic structural diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0076] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the embodiments of the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the embodiments of the present disclosure as detailed in the appended claims.

[0077] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0078] like Figure 1 As shown, the embodiment of the present disclosure provides an information processing method, which is executed by an electronic device, including:

[0079] S101: In response to a first operation on a target content, displaying at least one candidate prompt word in a second conversation interface; wherein the target content includes a conversation content of a user account in the first conversation interface, and / or input content of the user account in the second conversation interface;

[0080] S102: In response to a second operation on the candidate prompt word, determining a target prompt word;

[0081] S103: Based on the target prompt word, perform corresponding processing on the target content.

[0082] The above-mentioned electronic device may be a terminal device running an AI model, or a terminal device capable of establishing a connection with a server running an AI model, or a server device running an AI model.

[0083] Exemplarily, the terminal device may be a terminal device that runs an instant messaging application, or the server device may be a server device that provides an instant messaging application service.

[0084] For example, the instant messaging application may include, but is not limited to: an instant messaging application for work communication, a social application for daily life social interaction, a shopping application for application shopping scenarios, etc. The social application may include a social application for stranger social interaction and / or acquaintance social interaction.

[0085] Exemplarily, the terminal device may be a smart phone, a tablet computer, a laptop computer, an intelligent robot running an AI model, and intelligent office equipment, etc.

[0086] The above-mentioned user accounts include: a first user account and a second user account. The conversation content in the first conversation interface may be the conversation content between the first user account and the second user account. The input content of the second conversation interface may be the natural language input or file input of the first user account in the second conversation interface.

[0087] Through the above-mentioned first conversation interface, the first user account can have a conversation with the second user account. Through the above-mentioned second conversation interface, the first user can instruct the AI ​​model to perform corresponding processing operations by inputting content.

[0088] The above-mentioned AI model may be an AI model that can perform different processing operations on text.

[0089] In some embodiments, the AI ​​model may be a single model trained end-to-end. In other embodiments, the AI ​​model may also be composed of multiple modules (or models), and different modules are trained separately or uniformly.

[0090] The AI ​​model may include, but is not limited to: a deep learning model and / or a machine learning model.

[0091] Exemplarily, the AI ​​model includes but is not limited to at least one of the following:

[0092] Convolutional Neural Networks;

[0093] Feedback neural network;

[0094] Generative Adversarial Networks (GANs);

[0095] Large Language Models (LLMs).

[0096] Of course, the above is just an example of an AI model, and any of the above examples can be specifically implemented.

[0097] The first conversation interface and the second conversation interface may be two conversation interfaces in the same application, or may be conversation interfaces of two applications that can be associated.

[0098] When the first conversation interface and the second conversation interface are two conversation interfaces of the same application installed in the electronic device, the first conversation interface and the second conversation interface may be displayed simultaneously or one of them may be displayed selectively.

[0099] Exemplarily, when the electronic device displays the first conversation interface or the second conversation interface, a fourth operation performed by the first user on the first conversation interface or the second conversation interface may be detected, and based on the detected fourth operation, the first conversation interface and the second conversation interface may be simultaneously displayed on the electronic device.

[0100] It is also possible that when the electronic device displays the first conversation interface and the second conversation interface at the same time, a fifth operation acting on the first conversation interface or the second conversation interface is detected, and when the fifth operation acting on one of the first conversation interface and the second conversation interface is detected, the display of the conversation interface indicated by the fifth operation is canceled.

[0101] In some embodiments, the first conversation interface may be a point-to-point conversation interface between two user accounts, or a group conversation interface between multiple user accounts. The group conversation interface may include a temporary group conversation interface and / or a formal group conversation interface.

[0102] For example, reference Figure 2 , Figure 2 A schematic diagram of a first conversation interface is shown in FIG. Figure 2 When the first conversation interface shown is displayed, if a user input to a specified control displayed on the first conversation interface is detected, a user input to a specified control displayed on the first conversation interface may be displayed on the electronic device at the same time. Figure 3 The first session interface and the second session interface are shown.

[0103] The designated control may be any control that starts the second conversation interface or performs a function corresponding to the second conversation interface. Figure 2 When the electronic device displays Figure 3 When the first conversation interface and the second conversation interface are shown, if an input operation on the delete control in the upper right corner of the second conversation interface is detected, the display of the second conversation interface is canceled (ie, the second conversation interface is hidden).

[0104] In some embodiments, if the application of the first session interface is configured with a specified function, the second session interface may be started by default when the first session interface is started.

[0105] The conversation content in the first conversation interface in the embodiment of the present disclosure includes, but is not limited to, chat content between the first user account and the second user account, and / or file information of files such as pictures and documents input into the first conversation interface by the first user account and the second user account.

[0106] The chat content between the first user account and the second user account includes but is not limited to chat content in text form, voice form and / or picture form.

[0107] The first operation acting on the target content includes but is not limited to a click operation, a selection operation or a share operation.

[0108] In some embodiments, the session content related to the target content may be historical session content and / or current session content.

[0109] In one embodiment, the target content obtained from the first conversation interface includes one of the following:

[0110] All conversation contents in the first conversation interface;

[0111] The conversation content currently displayed in the first conversation interface;

[0112] The conversation content selected in the first conversation interface;

[0113] The conversation content of the specified user account in the first conversation interface, wherein the specified user account includes: the first user account or the second user account;

[0114] The conversation content of the specified time period in the first conversation interface;

[0115] The session content of the specified user account in the first session interface during the specified time period.

[0116] Exemplarily, when a selection-all operation on all conversation contents in the first conversation interface is detected, all conversation contents between the first user account and the second user account from the first conversation to the current conversation are taken as target contents.

[0117] For example, refer to Figure 4 When the first conversation interface is a conversation interface of the first conversation group, if a select-all operation on all conversation contents in the first conversation interface is detected, all conversation contents of all user accounts participating in the conversation in the first conversation group from the time when the first conversation group is established to the current time are taken as target contents.

[0118] Based on this, the electronic device will take all conversation contents in the first conversation group as target contents to generate at least one alternative prompt word, and when detecting the target prompt word input in the second conversation interface, according to the capabilities of the AI ​​involved in the target prompt word, call the corresponding AI model to perform the text processing operation indicated by the target prompt word on all conversation contents in the first conversation group.

[0119] For example, in some cases, the first user may need to process the current conversation content in the first conversation interface, and in this case, a selection operation may be performed on the current conversation content in the first conversation interface. Accordingly, when the electronic device detects the first user's selection operation on the current conversation content, the electronic device uses the current conversation content in the first conversation interface selected by the first user as the target content.

[0120] The current conversation content may be the conversation content of the first conversation interface within one hour or within one day, which is not limited in the embodiment of the present disclosure.

[0121] It should be noted that, when the current conversation content is large and cannot be fully displayed on one interface, the first user can select the desired conversation content by simply sliding the content displayed in the first conversation interface.

[0122] Based on this, the AI ​​model can obtain the conversation content currently displayed in the first conversation group, and use the conversation content currently displayed in the first conversation group as the target content to generate at least one alternative prompt word, and when the target prompt word input in the second conversation interface is detected, the corresponding IA model is called to execute the function indicated by the target prompt word on the conversation content currently displayed in the first conversation group according to the capabilities involved in the target prompt word.

[0123] For example, since not all conversation contents include the information needed by the first user, the first user can also share the conversation contents needed to the second conversation interface. Based on this, when the electronic device detects the first user's sharing operation on part of the conversation contents in the first conversation interface, the conversation contents indicated by the sharing operation are used as the target contents.

[0124] For example, when the first user needs to translate the first document input by the second user account in the first conversation interface, the first document can be shared to the second conversation interface. Accordingly, the electronic device can detect the first document shared to the second conversation interface, and at this time, the electronic device can use the first document as the target content.

[0125] For example, refer to Figure 5 When the first user needs to summarize the second conversation content displayed in the first conversation interface, the second conversation content can be shared to the second conversation interface. Accordingly, when the electronic device detects that the first user shares the second conversation content to the second conversation interface, the electronic device generates candidate prompt words using the second conversation content as the target content, and summarizes the second conversation content when the target prompt word "summarize the conversation content" is detected to be input in the second conversation interface.

[0126] For example, since there are multiple user accounts participating in the conversation during the conversation, when the first user needs to perform text processing operations on the conversation content of some user accounts, the conversation content of the specified conversation account can also be selected. Accordingly, when the electronic device detects the selection operation on the first user account or the second user account, the conversation content of the user account indicated by the selection operation is used as the target content.

[0127] It should be noted that, in some cases, there may be multiple second user accounts. In this case, the designated user account may be any one or more user accounts among the multiple second user accounts.

[0128] For example, in Figure 5 In the first conversation interface, when the first user needs to use the conversation content of "Zhao San" as the target content, he can select all the conversation contents of "Zhao San" in the second conversation group. Accordingly, when the electronic device detects the selection operation of the conversation content of "Zhao San", it will use the conversation content of "Zhao San" in the second conversation group as the target content to generate candidate prompt words, and execute the function indicated by the target prompt word on the conversation content of "Zhao San" based on the detected target prompt word.

[0129] Exemplarily, considering the timeliness of the conversation content, the conversation content of all conversation accounts in a specified period of time in the first conversation interface may also be used as the target content.

[0130] For example, the session content of all user accounts participating in the session in the first session interface on the current day is used as the target content, or the session content of all user accounts participating in the session in the first session interface within 2 hours from the current time is used as the target content.

[0131] Exemplarily, the current conversation content of one or more accounts specified in the first conversation interface may be used as the target content, or the conversation content of one or more user accounts specified in the first conversation interface within 2 hours from the current time may be used as the target content.

[0132] The above merely lists several exemplary ways of acquiring the target content from the first conversation interface, and does not constitute a limitation on the target content of the embodiment of the present disclosure.

[0133] It should be noted that, when the target content determined from the first conversation interface is text content, keywords may be extracted from the target content, and at least one candidate prompt word related to the extracted keyword may be displayed in the second conversation interface based on the extracted keyword.

[0134] For example, if the keyword "conference" is extracted from the target content multiple times, at least one candidate prompt word related to conference room reservation is displayed on the second conversation interface.

[0135] When the target content determined from the first conversation interface is a picture, the text in the picture and other objects included in the picture may be recognized, and related candidate prompt words may be generated and displayed in the second conversation interface based on the recognized text and objects.

[0136] For example, when the target content obtained from the first conversation interface is a picture, and a humidifier and text related to the parameters of the humidifier are identified from the picture, it can be determined that the picture is a product introduction picture. At this time, alternative prompt words related to product research on the humidifier can be displayed in the second conversation interface.

[0137] When the target content determined from the first conversation interface is a document file, such as a word document or an Excel document, alternative prompt words related to document operations that can be performed on the word document or the Excel document can be displayed in the second conversation interface.

[0138] When the target content determined from the first conversation interface is speech, and the speech is recognized to be in English or French, alternative prompt words related to speech processing such as "translate speech" and "speech to text" may be displayed on the second conversation interface.

[0139] Exemplarily, when the first conversation interface is a conversation interface of a group conversation, accounts of other group members who have a conversation with the first user account are all second user accounts.

[0140] For example, in Figure 2 In the “cloud service development team” shown, all user accounts except the user account “Li Si” are second user accounts.

[0141] The second conversation interface obtained above is a conversation interface for the first user account to conduct a conversation with the AI ​​model. Based on the second conversation interface, the AI ​​model can obtain the input content of the first user account, and perform corresponding processing operations or execute corresponding functions based on the input content of the first user account in the second conversation interface.

[0142] The second operation may be a selection operation of any candidate prompt word among the at least one candidate prompt word. For example, the selection operation may include a click operation, a slide operation, or a check operation.

[0143] In some embodiments, an alternative prompt word may correspond to an executable function or a device capability of the electronic device. The executable function may be a function based on an AI model. The device capability may be a capability based on an AI model.

[0144] The candidate prompt words displayed in the second conversation interface may be related operations that can be performed on the target content, and may be indicator words that confirm that the electronic device has the ability to perform the related operations.

[0145] For example, when the determined target content is a document, the operations that the electronic device can perform on the document include: summarizing the document, translating the document, and extracting the main content from the document, etc. Therefore, when the determined target content is a document, the alternative prompt words displayed in the second conversation interface may include: summarizing the document, translating the document, and extracting the main content, etc.

[0146] For another example, when the determined target content is a picture, the operations that the electronic device can perform on the picture include: editing, content recognition, and text extraction, etc. Therefore, when the determined target content is a picture, the alternative prompt words displayed in the second conversation interface may include: picture editing, content recognition, and text extraction, etc.

[0147] For example, refer to Figure 3 The alternative prompt words displayed on the second conversation interface may include: help me summarize the above content points, help me create a new schedule, help me translate the text, and help me identify the picture text, etc.

[0148] Exemplarily, “Help me summarize the main points of the above content” corresponds to the ability of the electronic device or AI model to summarize the main points of the content.

[0149] As another example, “help me create a new schedule” corresponds to the ability of an electronic device or AI model to call a schedule application to generate a schedule.

[0150] Also exemplarily, the “help me translate this text” corresponds to the ability of the electronic device or AI model to translate between different languages.

[0151] When the first user needs to summarize the conversation content in the first conversation interface, the alternative prompt word "Help me summarize the main points of the above content" displayed in the second conversation interface can be selected through the second operation. After the electronic device detects a click operation, a sliding operation, or a check operation on the alternative prompt word "Help me summarize the main points of the above content", the alternative prompt word "Help me summarize the main points of the above content" is input into the second conversation interface, so that the AI ​​model can perform a summary operation on the target content, and display the execution result in the second conversation interface.

[0152] For example, when it is detected that the first user needs to book a conference room, the alternative prompt word generated by the electronic device or AI model may be "free conference room". When it is detected that the first user selects the alternative prompt word "free conference room", "free conference room" is input in the second conversation interface. Accordingly, after obtaining the alternative prompt word "free conference room" from the second conversation interface, the AI ​​model can query unreserved conference rooms and display the query results on the second conversation interface.

[0153] In the embodiment of the present disclosure, at least one alternative prompt word is generated based on the conversation content of the first user account and / or the second user account in the first conversation interface, and / or the input content of the first user account in the second conversation interface. Since the conversation content of the first conversation interface and the input content of the second conversation interface can reflect the function that the user currently needs the AI ​​model to perform to a certain extent, the alternative prompt words displayed on the second conversation interface are generated based on the conversation content of the first conversation interface and the input content of the second conversation interface, so that the generated alternative prompt words can be closer to the user's needs, so that the user can instruct the AI ​​model to perform the operation required by the user by selecting the alternative prompt words displayed on the second conversation interface, thereby improving the communication efficiency between the user and the AI ​​model.

[0154] In addition, since the user does not need to manually enter prompt words through the input method in the above process, the convenience of user conversation with the AI ​​model is improved, thereby improving the user experience.

[0155] refer to Figure 6 In one embodiment, S101 includes:

[0156] S1011: Determine a target conversation scenario based on the target content;

[0157] S1012: Based on the target conversation scenario, display at least one candidate prompt word related to the target content in the second conversation interface.

[0158] Exemplarily, after obtaining the target content from the first conversation interface or the second conversation interface, the target content can be input into the target model, and features of the input target content can be extracted through the target model. Based on the features extracted from the target content, the conversation scenario indicated by the target content can be determined, and the conversation scenario indicated by the target content can be used as the target conversation scenario.

[0159] In some embodiments, different target conversation scenarios require different AI capabilities.

[0160] In some embodiments, different target conversation scenarios occur in different scenarios and require different AI capabilities with different probabilities.

[0161] Taking into account that the first user requires the AI ​​model to have different capabilities in different conversation scenarios, after determining the target conversation scenario, at least one alternative prompt word related to the target content can be generated based on the target conversation scenario, and the generated at least one alternative prompt word can be displayed in the second conversation interface.

[0162] The candidate prompt words related to the target content refer to: indicator words of processing operations that can be performed on the target content.

[0163] For example, if the target content is the conversation content of "Zhang San", since the conversation content is text information, the processing operation that can be performed is a text processing operation, so the displayed candidate prompt words are indicator words that can perform text processing operations on the conversation content of "Zhang San". For example, the displayed candidate prompt words are translating the conversation content and extracting time information from the conversation content.

[0164] When the determined target content is a picture, the candidate prompt words related to the target content may be indicator words of related processing operations that can be performed on the picture.

[0165] For example, when the target conversation scenario is determined to be a conversation content organization scenario, at least one alternative prompt word related to the conversation content organization scenario is generated based on the currently acquired target content; when the target conversation scenario is determined to be a product research scenario, at least one alternative prompt word related to the product research scenario is generated based on the currently acquired target content.

[0166] In one embodiment, S1011 includes:

[0167] Based on the target content, a target conversation scenario is determined from a plurality of preset conversation scenarios, or,

[0168] Determine the target conversation scenario based on the abilities involved in the target content, or,

[0169] Determine the target conversation scenario based on the text processing requirements involved in the target content.

[0170] Exemplarily, multiple conversation scenarios may be pre-set in the electronic device. After obtaining the target content, if the target content is the chat content of the first user account and / or the second user account obtained from the first conversation interface, keywords may be extracted from the chat content, and based on the extracted keywords, a target conversation scenario matching the extracted keywords may be determined from the preset conversation scenarios.

[0171] For example, if the target content obtained from the first conversation interface contains words related to conference rooms or other office facilities, the target conversation scenario can be determined to be an office facility reservation scenario. If the target content obtained from the first conversation interface mentions XX product multiple times, the target conversation scenario can be determined to be a product research scenario.

[0172] For example, considering that different conversation scenarios require different capabilities of the AI ​​model, it is also possible to first obtain the capabilities of the AI ​​model, and determine the functions that can be performed on the target content based on the capabilities of the AI ​​model, and then determine the target conversation scenario based on the functions that the AI ​​model can perform on the target content. The capabilities may include at least capabilities related to text, pictures, and / or voice.

[0173] For example, when the AI ​​model has the capabilities of organizing conversation content and generating work summaries based on conversation content, the target conversation scenario can be determined as a conversation content organization scenario or a work summary generation scenario based on the currently acquired target content.

[0174] Exemplarily, considering that different types of target content require different text processing requirements, the target conversation content may also be determined based on the type of the target content.

[0175] For example, when the target content is the chat content of the first user account and / or the second user account obtained from the first conversation interface or the second conversation interface, the target conversation scenario can be determined to be a conversation content arrangement scenario or a work summary generation scenario. When the target content is a product image or a product introduction document obtained from the first conversation interface or the second conversation interface, the target conversation scenario can be determined to be a product research scenario.

[0176] In some embodiments, one or more alternative prompt words in an office scene may be determined based on the target content. Alternatively, one or more alternative prompt words may be determined based on different subdivided office scenes. For example, different alternative prompt words may be configured for office scenes in different industries. For another example, different alternative prompt words may be given based on different office environments (e.g., indoor office or office on a business trip).

[0177] In some embodiments, one or more candidate prompt words in the play scene may be determined according to the play scene, for example, candidate prompt words related to meal reservation, car reservation and / or travel plan planning in the play scene.

[0178] In some embodiments, one or more alternative prompt words are given according to the learning scenario. Further subdivided, different alternative prompt words can be generated according to different learning groups, different learning subjects, and different learning stages. For example, for the examination stage, it is prompted whether to generate alternative prompt words such as prompt labels.

[0179] In one embodiment, S1012 includes at least one of the following:

[0180] In the case where the target conversation scenario is a conversation content arrangement scenario, at least one first candidate prompt word is displayed in the second conversation interface, wherein different first candidate prompt words are used to indicate that different arrangement operations are performed on the conversation content;

[0181] In a scenario where the target conversation scenario is a work summary generation scenario, displaying at least one second candidate prompt word in the second conversation interface, wherein different second candidate prompt words are used to indicate different requirements for the generated work summary;

[0182] When the target conversation scenario is an office facility reservation scenario, at least one third candidate prompt word is displayed in the second conversation interface, wherein different third candidate prompt words are used to indicate different requirements for office facilities;

[0183] When the target conversation scenario is a product research scenario, a fourth candidate prompt word at least related to the product being researched is displayed in the second conversation interface.

[0184] Exemplarily, if the target content obtained is the conversation content obtained from the first conversation interface, and the target conversation scenario is determined to be a conversation content arrangement scenario, it means that the first user may need to summarize and arrange the conversation content in the first conversation interface. At this time, at least one alternative prompt word that can indicate different arrangement operations to be performed on the conversation content can be displayed in the second conversation interface, so that the first user can select which arrangement operation to perform on the conversation content.

[0185] For example, when the target conversation scenario is a conversation content arrangement scenario, the first candidate prompt words displayed in the second conversation interface may include: conversation content summary, generating a schedule in chronological order, summarizing pending items, and adding pending items to the schedule, etc.

[0186] For example, if the target conversation scenario is determined to be a work summary generation scenario based on the target content, it means that the first user may need to summarize the conversation content in the first conversation interface and generate a summary report. At this time, alternative prompt words related to the format requirements and content requirements of the summary report can be displayed in the second conversation interface.

[0187] For example, if the target conversation scenario is a work summary generation scenario, the second alternative prompt words displayed in the second conversation interface may include: generating a daily report based on the conversation content, generating a weekly report based on the conversation content, generating a weekly report based on the daily report, and organizing daily and weekly reports in XX format, etc.

[0188] Exemplarily, when the target conversation scenario is determined to be an office facility reservation scenario based on the target content, it means that the first user may need to make an appointment to use the office facility. At this time, information such as the type of office facilities required by the first user, the usage time, and the usage duration can be obtained from the target content, and at least one alternative prompt word related to the office facility reservation can be displayed in the second conversation interface.

[0189] For example, when it is determined based on the target content that the first user needs to hold a meeting between 14:00 and 15:00 on XX / XX / XX, the third candidate prompt word displayed in the second conversation interface may include: book a meeting room, etc. At this time, after detecting the operation of booking a meeting room, the electronic device may query the reservation status of the meeting room based on the selected prompt word, and provide a bookable meeting room and / or a time period for the bookable meeting room, which can be selected by the user to realize the meeting reservation function.

[0190] In some embodiments, after completing the meeting reservation, a prompt word "generate schedule" can be generated. After detecting the prompt word acting on "generate schedule", the terminal device or server automatically generates a schedule, which is convenient for schedule reminders before the meeting time.

[0191] In some embodiments, after completing the meeting reservation, the electronic device can automatically generate a schedule based on the AI ​​model.

[0192] Exemplarily, when the target conversation scenario determined based on the target content is a product research scenario, at least one candidate prompt word related to the product being researched may be displayed in the second conversation interface.

[0193] For example, if the target conversation scenario is a product research scenario, the fourth candidate prompt words displayed in the second conversation interface may include: searching for products related to XX product, generating a product report, generating a product information table, and summarizing product information, etc.

[0194] In one embodiment, S101 includes:

[0195] Inputting the target content into the prompt word generation model to obtain at least one candidate prompt word output by the prompt word generation model;

[0196] The alternative prompt words are displayed in the second conversation interface.

[0197] Exemplarily, a prompt word generation model may be pre-installed in the electronic device. After the target content is obtained, the obtained target content may be input into the prompt word generation model, so that the prompt word generation model may output at least one alternative prompt word based on the input target content, and all alternative prompt words output by the prompt word generation model, or the top N alternative prompt words, are displayed in the second conversation interface, where N is an integer greater than or equal to 1 and less than 5.

[0198] When displaying the top N candidate prompt words that are ranked high, the top N candidate prompt words may be displayed sequentially in the second conversation interface.

[0199] In addition, when displaying candidate prompt words, different candidate prompt words may be displayed in different display modes according to the rankings of different candidate prompt words.

[0200] For example, the candidate prompt words with a higher ranking are displayed in a larger font size, and the candidate prompt words with a lower ranking are displayed in a smaller font size.

[0201] In one case, the target model for determining the conversation scenario and the prompt word generation model can be two independent models.

[0202] For example, when the target model and the prompt word generation model used to determine the conversation scenario are two independent models, after the target model determines the target conversation scenario corresponding to the target content based on the target content input into the target model, the determined target conversation scenario and target content can be input into the prompt word generation model, so that the prompt word generation mode generates one or more alternative prompt words related to the target content based on the target conversation scenario.

[0203] In another case, the target model and prompt word generation model for determining the conversation scene can be the conversation scene determination module and prompt word generation module of the same model. Based on this, the target content can be first input into the conversation scene determination module to obtain the target conversation scene output by the conversation scene determination module based on the target content, and then the target conversation scene can be input into the prompt word generation module to obtain at least one candidate prompt word related to the target content generated by the prompt word generation module based on the target conversation scene.

[0204] In another embodiment, the prompt word generation model may be one model or multiple models. When the prompt word generation model includes multiple models, one model corresponds to one conversation scenario.

[0205] Exemplarily, the prompt word generation model may include: a first model for generating alternative prompt words related to conversation content organization, a second model for generating alternative prompt words related to work summary, a third model for generating alternative prompt words related to office facility reservation, and a fourth model for generating alternative prompt words related to product research.

[0206] Based on this, when the target conversation scenario determined is a conversation content arrangement scenario, the target content can be input into the first model so that the first model outputs a first candidate prompt word based on the target content. When the target conversation scenario determined is a work summary generation scenario, the target content can be input into the second model so that the second model outputs a second candidate prompt word based on the target content. When the target conversation scenario determined is an office facility reservation scenario, the target content can be input into the third model so that the third model outputs a third candidate prompt word based on the target content. When the target conversation scenario determined is a product research scenario, the target content can be input into the fourth model so that the fourth model outputs a fourth candidate prompt word based on the target content.

[0207] It should be noted that the first model, the second model, the third model and the fourth model mentioned above may also be four parallel modules included in the prompt word generation model.

[0208] In another embodiment, multiple preset prompt words may be pre-stored for each preset conversation scenario. After the target conversation scenario is determined based on the target content, the degree of association between each of the multiple preset prompt words corresponding to the target conversation scenario and the currently acquired target content may be determined, and the N preset prompt words with the highest degree of association with the target content may be displayed as alternative prompt words in the second conversation interface.

[0209] For example, when the target conversation scenario is determined to be a conversation content organization scenario based on the target content, the degree of association between each preset prompt word corresponding to the conversation content organization scenario and the target content is determined, and the five preset prompt words with the highest association with the target content are displayed as alternative prompt words in the second conversation interface.

[0210] In one embodiment, the input content of the second conversation interface includes:

[0211] Input the information to be processed in the second conversation interface;

[0212] or,

[0213] The conversation content of the second conversation interface.

[0214] Exemplarily, when the first user requires the AI ​​model to perform a text processing operation on the information to be processed, the information to be processed can be imported into the second conversation interface based on the import control key in the second conversation interface.

[0215] At this time, the electronic device may generate at least one candidate prompt word based on the information to be processed imported into the second conversation interface, and display the at least one candidate prompt word in the second conversation interface.

[0216] The above-mentioned information to be processed includes, but is not limited to: pictures, documents, videos, voices, installation files of applications or mini-programs, and web page links, etc.

[0217] When a second operation on any one of the at least one displayed alternative prompt word is detected, the alternative prompt word indicated by the second operation is input into the second conversation interface as the target prompt word, so that the AI ​​model can execute the function indicated by the target prompt word on the information to be processed.

[0218] For example, when the first user needs to extract and translate the text in the picture, the image to be processed can be imported into the second conversation interface through the import control key in the second conversation interface. Accordingly, when the electronic device detects the import operation of the image to be processed, it uses the imported image to be processed as the target content, generates at least one alternative prompt word, and displays at least one alternative prompt word in the second conversation interface for the first user to select. When the selection operation of the alternative prompt word "Help me identify the text in the picture" is detected, the alternative prompt word "Help me identify the text in the picture" is input into the second conversation interface as the target prompt word, so that the AI ​​model can perform text recognition operation on the imported image to be processed, and display the text recognition result on the second conversation interface.

[0219] For example, when the first user needs to extract content from a web page, he can enter the link of the web page in the second conversation interface. Accordingly, when the electronic device detects the web page link entered in the second conversation interface, it can display alternative prompt words such as "open link", "extract text" and "extract picture" on the second conversation interface. When the selection operation of the alternative prompt word "extract picture" is detected, the alternative prompt word "extract picture" is input into the second conversation interface as the target prompt word, so that the AI ​​model can extract all pictures from the web page indicated by the web page link and display the extracted pictures in the second conversation interface.

[0220] It should be noted that the above-mentioned information to be processed can be an input picture from the first user account or the second user account in the first conversation interface, or it can be a local picture stored in the electronic device or a network picture downloaded by the electronic device. The embodiment of the present disclosure does not limit the source of the picture.

[0221] The above merely lists several exemplary implementation methods of acquiring the target content from the second conversation interface, and does not constitute a limitation on the method of acquiring the target content.

[0222] In one embodiment, S103 includes:

[0223] Based on the target prompt word, the corresponding content processing interface is called to process the target content, wherein different target prompt words correspond to different content processing interfaces.

[0224] Exemplarily, the electronic device may pre-store interface information of multiple AI models with content processing capabilities. Based on this, when the electronic device detects that a target prompt word is input in the second conversation interface, it determines the AI ​​model that can perform the operation indicated by the target prompt word on the target content according to the capabilities involved in the target prompt word, and calls the interface of the AI ​​model, that is, calls the corresponding content processing interface, to implement the call of the corresponding AI model, and then the AI ​​model can perform the processing operation indicated by the target prompt word on the target content based on the target prompt word.

[0225] For example, the above-mentioned AI models may include: a conversation organization model that can organize conversation content, a work summary model that can summarize work, an office facility reservation model that can make office facility reservations, and a product information collection model that can collect product information.

[0226] When the current conversation scenario is determined to be a conversation content organization scenario based on the acquired target content, the interface of the AI ​​model capable of conversation content organization is called to implement the call to the conversation organization model, thereby enabling the conversation organization model to perform the conversation content organization operation indicated by the target prompt word on the target content based on the target prompt word.

[0227] When the current conversation scenario is determined to be a work summary generation scenario based on the acquired target content, the interface of the AI ​​model capable of performing work summary is called to implement the call to the work summary model, thereby enabling the work summary model to summarize the target content based on the target prompt words and generate a work summary document.

[0228] When the current conversation scenario is determined to be an office facility reservation scenario based on the acquired target content, the interface of the AI ​​model that can implement office facility reservation can be called to implement the call of the office facility reservation model, and then the office facility reservation model can query the current usage and available reservation time of the office facilities indicated by the target content based on the target prompt words.

[0229] When the current conversation scenario is determined to be a product research scenario based on the acquired target content, the interface of the AI ​​model capable of performing product information query can be called to implement the call of the product research model, thereby enabling the product research model to perform information search, query and sorting operations on the products indicated by the target content based on the target prompt words.

[0230] The above-mentioned conversation arrangement model, work summary model, office facility reservation model and product research model can be four independent models, or four modules of one model. When the above-mentioned conversation arrangement model, work summary model, office facility reservation model and product research model are four modules of one model, after calling the model, the electronic device needs to input the acquired target content into the module with the capabilities involved in the target prompt word to realize the processing operation of the target content.

[0231] refer to Figure 7 , Figure 7 The figure shows a text sorting operation of a product research module based on target prompt words output in a product research scenario.

[0232] In one embodiment, when the current conversation ends, the prompt word generation model is updated based on the conversation content in the second conversation interface.

[0233] For example, reference Figure 8 , Fig. 9 and Fig.10 Considering that the alternative prompt words generated based on the target content may not meet the needs of the first user in all cases, when all the alternative prompt words displayed in the second conversation interface are not the alternative prompt words required by the first user, the first user can also manually enter the first prompt word in the second conversation interface to indicate the processing requirements for the target content.

[0234] For example, refer to Fig. 9 , the electronic device determines, based on the target content, that the candidate prompt words displayed in the second conversation interface are Fig. 9 When the first user selects the alternative prompt words shown in , and the processing operation that the first user needs the AI ​​model to perform is to determine how many time points are involved in the conversation content of "Li Si", since the alternative prompt words displayed on the second conversation interface cannot meet the needs of the first user. At this time, the user can manually enter the first prompt word "which time points are involved above" in the second conversation interface.

[0235] refer to Fig.10 , the electronic device determines the candidate prompt words displayed in the second conversation interface based on the target content as Fig.10 When the alternative prompt words shown in the second conversation interface are displayed, and the text processing operation that the first user needs the AI ​​model to perform is to create new schedules for the conversation content of "Li Si" according to the corresponding publishing time. Since the alternative prompt words displayed on the second conversation interface will not meet the needs of the first user, at this time, the user can manually enter the first prompt word "create new schedules according to the corresponding publishing time" in the second conversation interface.

[0236] Based on the above situation, at the end of the current session, the electronic device can also collect the first prompt words manually input by the user into the second session interface and the target content corresponding to each first prompt word, and then train the prompt word generation model based on the first prompt words and the corresponding target content to increase the probability that the alternative prompt words generated by the prompt word generation model are the prompt words required by the first user.

[0237] In one embodiment, the method further comprises:

[0238] Displaying the execution result of the target content on the second session interface;

[0239] According to the third operation acting on the execution result, the execution result is shared to the first conversation interface.

[0240] Exemplarily, after the AI ​​model performs corresponding processing operations on the target content based on the detected target prompt word, it will display the execution result in the second conversation interface. Based on this, when the first user needs to share the execution result displayed in the second conversation interface with the second user account through the first conversation interface, a third operation can also be performed on the execution result displayed in the second conversation interface. Accordingly, when the electronic device detects the third operation, it inputs the execution result displayed in the second conversation interface indicated by the third operation into the first conversation interface.

[0241] The third operation mentioned above may be a screenshot operation or other sharing operations, which is not limited in the embodiment of the present disclosure.

[0242] For example, refer to Fig. 9 and Fig.10 When the electronic device detects a screenshot operation on the second conversation interface, the screenshot generated by the screenshot operation can be input into the first conversation interface.

[0243] refer to Figure 8 and Fig.11 The present disclosure also provides an information processing method, including:

[0244] After determining the target content based on the user's selection, the target content is analyzed based on the prompt word generation model and alternative prompt words are generated for the user to choose. The user can ask questions to the chatGPT (ChatGenerative Pre-trained Transformer) based on the alternative prompt words so that chatGPT can output the text processing results required by the user.

[0245] The conversation scenarios include:

[0246] 1) Conversation content organization scenario.

[0247] Scenario description: Select the conversation content you want to summarize, select the target prompt word and send it to chatGPT for conversation summary, convert the generated conversation summary into a document, email, to-do list or schedule, and complete chat messages can be quickly archived into conversation groups.

[0248] Alternative prompts: Please summarize the conversation, extract the core ideas and brief conclusions; summarize and generate a corresponding schedule according to the timeline; summarize the things that need me to do and add them to the to-do list; return the types of issues involved in the conversation, feedback time, feedback person, feedback content, and sort them out to me in chronological order.

[0249] 2) Work summary generation scenario.

[0250] Scenario description: Improve the content and summarize the selected conversation content.

[0251] Alternative prompts: Use the text provided as the basis for your Chinese weekly report to generate a concise summary that highlights the most important content. The report should be written in markdown format and should be easy to read and understand to meet the needs of a general audience. In particular, focus on providing insights and analysis that will be useful to stakeholders and decision makers. Any additional information or sources can be used as needed during the weekly report generation process.

[0252] Based on the daily report content provided, generate a concise weekly report that highlights the most important content. The report should be written in markdown format and should be easy to read and understand. This weekly report is used to report to superiors, so pay attention to the writing style.

[0253] 3) Meeting room reservation scenario.

[0254] refer to Figure 4 , Figure 4 A schematic diagram of a conference room reservation scenario is provided. Scenario description: Understand everyone's free time, and create a new multi-person schedule with chatGPT and initiate a schedule invitation to reserve an available conference room.

[0255] Alternative prompts: Translate the conversation into English, and help me check whether XXX, XXX and 11 others are free from 14:00 to 15:00 tomorrow. If they are all free, please make an appointment for them with the theme of "Requirements Review" and reserve a vacant meeting room in Building 5.

[0256] 4) Product research scenarios.

[0257] Scenario description: Provide existing forms and document template formats to form a competitive product research report.

[0258] Alternative prompt words: Help me find the products or software mentioned below and summarize the update log of the latest version; refine the template of this form and generate the following products or software for me.

[0259] like Fig.12 As shown, the embodiment of the present disclosure provides an information processing device, including:

[0260] The first display module 1201 is configured to display at least one candidate prompt word in the second conversation interface in response to a first operation on the target content; wherein the target content includes the conversation content of the user account in the first conversation interface and / or the input content of the user account in the second conversation interface;

[0261] A determination module 1202, configured to determine a target prompt word in response to a second operation on the candidate prompt word;

[0262] The execution module 1203 is used to perform corresponding processing on the target content based on the target prompt word.

[0263] Optionally, the first display module 1201 includes:

[0264] A determination unit, configured to determine a target conversation scenario based on the target content;

[0265] The display unit is used to display at least one candidate prompt word related to the target content in the second conversation interface based on the target conversation scenario.

[0266] Optionally, a determination unit is configured to:

[0267] Based on the target content, a target conversation scenario is determined from a plurality of preset conversation scenarios, or,

[0268] Determine the target conversation scenario based on the abilities involved in the target content, or,

[0269] Determine the target conversation scenario based on the text processing requirements involved in the target content.

[0270] Optionally, the first display module 1201 is used to:

[0271] Inputting the target content into the prompt word generation model to obtain at least one candidate prompt word output by the prompt word generation model;

[0272] The alternative prompt words are displayed in the second conversation interface.

[0273] Optionally, the input content of the second conversation interface includes:

[0274] Input the information to be processed in the second conversation interface;

[0275] or,

[0276] The conversation content of the second conversation interface.

[0277] Optionally, the execution module 1203 is used to:

[0278] Based on the target prompt word, the corresponding content processing interface is called to process the target content; wherein different target prompt words correspond to different content processing interfaces.

[0279] Optionally, the device further comprises:

[0280] The updating module updates the prompt word generation model based on the conversation content in the second conversation interface when the current conversation ends.

[0281] Optionally, the device further includes:

[0282] A second display module, configured to display the execution result of the target content on the second conversation interface;

[0283] A sharing module is used to share the execution result to the first conversation interface according to a third operation acting on the execution result.

[0284] An embodiment of the present disclosure further provides an electronic device, including:

[0285] processor;

[0286] a memory for storing processor-executable instructions;

[0287] The processor is configured to implement the information processing method of any embodiment of the present disclosure when running the executable instructions.

[0288] The electronic device may at least be the aforementioned server and / or terminal device.

[0289] The memory may include various types of storage media, which are non-transitory computer storage media that can continue to remember information stored thereon after the communication device loses power.

[0290] The processor can be connected to the memory through a bus or the like to read the executable program stored in the memory, for example, to implement the following Figure 1 and / or Figure 6 The method shown.

[0291] The embodiments of the present disclosure further provide a computer-readable storage medium, wherein the computer-readable storage medium stores an executable program, wherein when the executable program is executed by a processor, the information processing method of any embodiment of the present disclosure is implemented. Figure 1 and / or the method shown in 6.

[0292] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0293] The present disclosure provides an electronic device, comprising: a processor; a memory for storing processor executable instructions; wherein the processor is configured to: when running the executable instructions, implement the table processing method provided by any of the above technical solutions, for example, Figure 1 and / or Figure 6 The method shown.

[0294] like Fig.13 As shown, an embodiment of the present disclosure shows a structure of an electronic device. For example, the electronic device 1300 can be provided as a network side device. Fig.13 The electronic device 1300 includes a processing component 1322, which further includes one or more processors, and a memory resource represented by a memory 1332 for storing instructions executable by the processing component 1322, such as an application. The application stored in the memory 1332 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 1322 is configured as an executable program to perform any of the aforementioned methods for applying to the access device, such as Figure 1 and / or Figure 6 The method shown.

[0295] The electronic device 1300 may also include a power supply component 1326 configured to perform power management of the electronic device 1300, a wired or wireless network interface 1350 configured to connect the electronic device 1300 to a network, and an input / output (I / O) interface 1358. The electronic device 1300 may operate based on an operating system stored in the memory 1332, such as Windows Server TM, Mac OS X TM, Unix TM, Linux TM, FreeBSD TM or the like.

[0296] In an exemplary embodiment, an embodiment of the present disclosure provides a computer-readable storage medium, which stores an executable program, wherein the executable program, when executed by a processor, implements the information processing method provided by any of the aforementioned technical solutions.

[0297] The computer-readable storage medium may specifically be: a non-temporary computer-readable storage medium.

[0298] Exemplarily, for example, the memory 1332 includes an executable program, and the above instructions can be executed by the processing component 1322 of the electronic device 1300 to complete the above method.

[0299] The non-transitory computer-readable storage medium may be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

[0300] Those skilled in the art will readily appreciate other implementations of the disclosed embodiments after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosed embodiments, which follow the general principles of the disclosed embodiments and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The specification and examples are to be considered as exemplary only, and the true scope and spirit of the disclosed embodiments are indicated by the following claims.

[0301] It should be understood that the embodiments of the present disclosure are not limited to the precise structures described above and shown in the drawings, and various modifications and changes may be made without departing from the scope thereof. The scope of the embodiments of the present disclosure is limited only by the appended claims.

Claims

1. An information processing method, characterized in that: Executed by an electronic device, the method includes: In response to a first operation on a target content, displaying at least one candidate prompt word in a second conversation interface; wherein the target content includes a conversation content of a user account in the first conversation interface, and / or input content of the user account in the second conversation interface; In response to a second operation on the candidate prompt word, determining a target prompt word; Based on the target prompt word, corresponding processing is performed on the target content.

2. The method according to claim 1, characterized in that The step of displaying at least one candidate prompt word in the second conversation interface in response to the first operation on the target content includes: Based on the target content, determining a target conversation scenario; Based on the target conversation scenario, at least one candidate prompt word related to the target content is displayed in the second conversation interface.

3. The method according to claim 2, characterized in that The determining a target conversation scenario based on the target content includes: Based on the target content, determining the target conversation scenario from a plurality of preset conversation scenarios, or, Determine the target conversation scenario based on the capabilities involved in the target content, or, The target conversation scenario is determined based on text processing requirements related to the target content.

4. The method according to claim 1, characterized in that: The step of displaying at least one candidate prompt word in the second conversation interface in response to the first operation on the target content includes: Inputting the target content into a prompt word generation model to obtain at least one candidate prompt word output by the prompt word generation model; The alternative prompt words are displayed in the second conversation interface.

5. The method according to claim 1, characterized in that The input content of the second conversation interface includes: Inputting the information to be processed in the second conversation interface; or, The conversation content of the second conversation interface.

6. The method according to claim 1, characterized in that The performing corresponding operations on the target content based on the target prompt word includes: Based on the target prompt word, a corresponding content processing interface is called to process the target content; wherein different target prompt words correspond to different content processing interfaces.

7. The method according to claim 4, characterized in that The method further comprises: When the current conversation ends, the prompt word generation model is updated based on the conversation content in the second conversation interface.

8. The method according to claim 1, characterized in that The method further comprises: Displaying the execution result of the target content on the second conversation interface; According to a third operation acting on the execution result, the execution result is shared to the first conversation interface.

9. An information processing device, characterized in that: The device comprises: a first display module, configured to display at least one candidate prompt word in the second conversation interface in response to a first operation on a target content; wherein the target content includes a conversation content of a user account in the first conversation interface and / or input content of the user account in the second conversation interface; A determination module, configured to determine a target prompt word in response to a second operation on the candidate prompt word; An execution module is used to perform corresponding processing on the target content based on the target prompt word.

10. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to: implement the information processing method described in any one of claims 1 to 8 when running the executable instructions.

11. A computer-readable storage medium, characterized in that: The readable storage medium stores an executable program, wherein the executable program, when executed by a processor, implements the information processing method according to any one of claims 1 to 8.

Images