Interaction method, readable storage medium and electronic equipment

Abstract

The invention relates to the technical field of artificial intelligence, in particular to an interaction method, a readable storage medium and electronic equipment. In the method, the electronic equipment can display multiple levels of tags, and the next level of tag belongs to the sub-field of the previous level of tag; after the electronic equipment obtains the labels selected by the user at all the levels, the label content selected by the user is fused, and a fusion prompt is generated. And after the electronic equipment receives the fusion prompt and the material associated with the fusion prompt, generating an output conforming to the intention of the user and displaying the output on the interactive interface. It can be understood that due to the fact that the multi-level labels displayed by the electronic device relate to detailed division of the specific field, fusion prompts related to the intention of the user can be generated, the situation that the user manually inputs complex and lengthy characters from zero to construct the wanted prompts is avoided, and then the efficiency of constructing the required prompts is improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to an interaction method, a readable storage medium, and an electronic device. Background Art

[0002] With the development of artificial intelligence technology, the functions of the answering system developed based on the big model are becoming increasingly powerful. When users interact with the answering system, the answering system can provide users with a variety of functions. For example, the answering system can perform text translation, article continuation, code generation, poetry creation, avatar generation, painting creation, oral practice, professional question answering, etc. according to user needs.

[0003] At present, in some cases, when a user needs to obtain information content corresponding to a certain material, the user can interact with the answering system. The user can first construct a prompt that can express his or her intention, and input the constructed prompt and the material into the answering system, so that the answering system outputs the information content corresponding to the material based on the specific conditions or requirements specified by the user's prompt.

[0004] However, when users interact with the answering system, in order to obtain satisfactory output results, they need to edit complex and lengthy text corresponding to their own intentions in the input box, which is cumbersome for users. Summary of the invention

[0005] In order to solve the above problems, the present application provides an interactive method, a readable storage medium and an electronic device, which are used to solve the problem of cumbersome user operations.

[0006] In a first aspect, an embodiment of the present application provides an interaction method, which is applied to an electronic device, comprising: displaying a first interface, the first interface including at least one first-level prompt tag; receiving an operation of a user selecting a first prompt tag, the at least one first-level prompt tag including a first prompt tag; displaying at least one second-level prompt tag related to the first prompt tag; receiving a selection operation of a user selecting a second prompt tag, the at least one second-level prompt tag including a second prompt tag; displaying a first prompt message, the first prompt message including a first prompt content corresponding to the first prompt tag, the first prompt message also including a second prompt content corresponding to the second prompt tag; and displaying a first processing result corresponding to the first prompt message.

[0007] It is understandable that after the electronic device displays the first-level prompt tag on the interface (for example, the first-level prompt tag is the main tag below), the user can select the required prompt tag on the interface according to his own intention. At this time, the electronic device displays at least one second-level prompt tag related to the first prompt tag on the interface (for example, the second-level prompt tag is the sub-tag below). The user can continue to select the second prompt tag from the at least one second-level prompt tag displayed according to his own intention, for example, the multiple sub-tags selected by the user below. At this time, after receiving the user's selection operation of selecting the second prompt tag, the electronic device displays the first prompt information, for example, the first prompt information is the fusion prompt below, and the first prompt information includes the first prompt content corresponding to the first prompt tag and the second prompt content of the second prompt tag. It is understandable that since the second-level prompt tag displayed by the electronic device is a detailed division of the specific field of the first-level prompt tag, the first prompt information, when including the first prompt content corresponding to the first prompt tag and the second prompt content of the second prompt tag, can better reflect the user's own intention, avoiding the user from manually entering complex and lengthy text from scratch to construct the desired prompt, thereby improving the efficiency of constructing the required prompt. Furthermore, when the first processing result is obtained according to the first prompt information, it also avoids the problem that when users edit text by themselves, they are unable to enter appropriate prompts due to different expression habits, or are unable to express their own intentions due to the simpler prompt templates provided, which in turn leads to inaccurate output of the electronic device and less information available to users.

[0008] In a possible implementation of the first aspect above, the first processing result includes at least one of the following: translation results, retrieval results, search results, question and answer results, text polishing results, article continuation results, code generation results, copywriting results, poetry writing results, avatar generation results, painting creation results, meeting minutes results, and voice dialogue results.

[0009] It can be understood that the interactive method proposed in the embodiment of the present application can be applied in a wide range of scenarios, so that processing results corresponding to a variety of scenarios can be obtained, including translation results, retrieval results, search results, question and answer results, text polishing results, article continuation results, code generation results, copywriting results, poetry writing results, avatar generation results, painting creation results, meeting minutes results, and voice dialogue results, thereby meeting the user's usage needs.

[0010] In a possible implementation of the first aspect, the method further includes: in response to receiving an operation of a user selecting a first prompt tag, displaying first prompt content.

[0011] It can be understood that when the electronic device receives the user's operation of selecting the first prompt label, the first prompt content is displayed at this time, which can give the user a more intuitive feeling of the connection between the prompt label and the prompt content, and also help the user to select the required second prompt label from the second-level prompt label according to their own intentions, so that the subsequently displayed first prompt information is more in line with the user's intentions.

[0012] In a possible implementation of the first aspect, the method further includes: in response to receiving an operation of a user selecting a second prompt tag, displaying second prompt content.

[0013] It can be understood that when the electronic device receives the user's operation of selecting the second prompt label, the second prompt content is displayed. The second prompt content is the content corresponding to the second prompt label. At this time, the user can more intuitively feel whether the second prompt label selected by the user is consistent with his own intention, thereby improving the efficiency of the user in obtaining the required first prompt content according to the prompt label selected according to his own intention.

[0014] In a possible implementation of the first aspect, displaying the first prompt information includes: in response to receiving an operation of selecting a second prompt tag by a user, additionally displaying the second prompt content in the first prompt content.

[0015] It can be understood that when the electronic device generates the first prompt content corresponding to the first prompt label, in response to receiving the user's operation of selecting the second prompt label, the second prompt content is added and displayed in the first prompt content. Since the second prompt content is the content corresponding to the second prompt label, and the second prompt label is a detailed division of the specific field corresponding to the first prompt label, the second prompt content is added and displayed in the first prompt content. The obtained first prompt information can express the user's own intentions more carefully and meet the user's needs.

[0016] In a possible implementation of the first aspect above, displaying the first prompt information also includes: after adding the second prompt content to the first prompt content, receiving a first modification operation from the user; and displaying the first prompt information, the first prompt information including the prompt content after the user performs the first modification operation.

[0017] It is understandable that after the second prompt content is added to the first prompt content, the user can also edit the generated prompt content in the input box to obtain a personalized prompt, so that the prompt received when the electronic device interacts can better meet the user's own intention. In addition, the construction method of the required prompt is more flexible and can be customized according to user needs to cope with more complex scenarios.

[0018] In a possible implementation of the first aspect above, the method further includes: after displaying the first prompt content, receiving a second modification operation of the user on the first prompt content; and the first prompt information includes the prompt content after the user performs the second modification operation.

[0019] It can be understood that after the corresponding first prompt content is displayed, the user's second modification operation on the first prompt content is received, that is, the user can also make text editing adjustments to the generated first prompt content in the input box at this time, so that the displayed first prompt information includes the prompt content after the user performs the second modification operation, thereby displaying a personalized prompt.

[0020] In a possible implementation of the first aspect, displaying the first prompt information includes: after receiving an operation of selecting the second prompt tag from the user, receiving a triggering operation of selecting a confirmation button from the user, and displaying the first prompt information.

[0021] It is understandable that a selection confirmation button may be pre-set, and the first prompt information is displayed only after receiving a trigger operation of the user on the selection confirmation button, thereby simplifying the interaction between the user and the electronic device.

[0022] In a possible implementation of the first aspect above, corresponding to the first prompt label being text translation, at least one second-level prompt label includes at least one of the following: Chinese to English, English to Chinese, Chinese to French, French to Chinese, thesis, classical Chinese, law, finance, fairy tales, and recommended classics to be translated; or corresponding to the first prompt label being picture translation, at least one second-level prompt label includes at least one of the following: restaurant, airport, museum, man, woman, child; or corresponding to the first prompt label being language translation, at least one second prompt label includes at least one of the following: academic conference, live broadcast of an event, museum explanation, teacher, student, audience, and commentator.

[0023] It is understandable that the electronic device can provide the first prompt label as text translation or image translation, and provide the user with multiple second-level prompt labels corresponding to the above text translation and image translation, so that the generated prompt is more in line with the user's translation needs.

[0024] In a possible implementation of the first aspect, corresponding to the first prompt tag being text polishing, at least one second prompt tag includes at least one of the following: formal, elegant, daily, legal, financial, biological, wrong word correction, vocabulary optimization, sentence rewriting; or

[0025] Corresponding to the first prompt label of article continuation, at least one second prompt label includes at least one of the following: formal, beautiful, daily, law, finance, biology, Chinese, English, Japanese, foreign language practice, knowledge quiz, sentiment analysis, lively, serious, gentle, Chinese, English, Japanese; or corresponding to the first prompt label of copywriting, at least one second prompt label includes at least one of the following: Teacher's Day, Mother's Day, opening ceremony, warm, playful, formal, Chinese, English, Japanese; or corresponding to the first prompt label of poetry writing, at least one second prompt label includes at least one of the following: modern, classical, pentasyllabic regulated verse, praising the motherland, praising spring, expressing emotions, etc., Chinese, English, Japanese.

[0026] It can be understood that the electronic device can provide a first prompt label for text polishing, article continuation, copywriting or poetry writing, and provide the user with multiple second-level prompt labels corresponding to the above-mentioned text polishing, article continuation, copywriting or poetry writing, so that the generated prompts are more in line with the user's needs in the text direction.

[0027] In a possible implementation of the first aspect above, corresponding to the first prompt tag being code generation, at least one second prompt tag includes at least one of the following: python, c++, java, dictionary tree, quick sort algorithm, network flow, database code style, web page code style.

[0028] It can be understood that the electronic device can provide a first prompt tag for code generation, and provide the user with multiple second-level prompt tags corresponding to the above code generation, which is thoughtful in code writing.

[0029] In a possible implementation of the first aspect above, corresponding to the first prompt tag being avatar generation, at least one second prompt tag includes at least one of the following: cartoons, oil paintings, realism, women, men, cats, gardens, sky, and oceans; or corresponding to the first prompt tag being painting creation, at least one second prompt tag includes at least one of the following: cartoons, oil paintings, realism, seaside towns, ancient temples in the mountains, skyscrapers, Monet, Van Gogh, Renoir, etc.

[0030] It can be understood that the electronic device can provide a first prompt tag for avatar generation and painting creation, and provide the user with multiple second-level prompt tags corresponding to the above avatar generation and painting creation, taking the painting aspect into consideration.

[0031] In a possible implementation of the first aspect above, it also includes: corresponding to the first prompt label being meeting minutes, at least one second prompt label includes at least one of the following: academic conference, work meeting, interview, law, finance, artificial intelligence, full record, content summary; or corresponding to the first prompt label being voice dialogue, at least one second prompt label includes at least one of the following: foreign language practice, knowledge quiz, sentiment analysis, serious, lively, peaceful, gentle, Chinese, English, and Japanese.

[0032] It can be understood that the electronic device can provide the first prompt label for the meeting minutes and the voice conversation, and provide the user with multiple second-level prompt labels corresponding to the above-mentioned meeting minutes and the voice conversation, taking the voice scene into consideration.

[0033] In a possible implementation of the first aspect above, it also includes: generating a first processing result based on the first prompt information.

[0034] It can be understood that the first processing result can be generated conveniently and quickly according to the first prompt information.

[0035] In a possible implementation of the first aspect, generating a first processing result based on the first prompt information includes: acquiring a to-be-processed material input by a user; and processing the to-be-processed material based on the first prompt information to obtain the first processing result.

[0036] It can be understood that obtaining the to-be-processed material input by the user and processing the to-be-processed material based on the first prompt information can effectively obtain the desired first processing result.

[0037] In a second aspect, an embodiment of the present application provides an electronic device, comprising: a memory for storing instructions, and one or more processors. When the instructions are executed by the one or more processors, the processors execute any one of the interaction methods in the above-mentioned first aspect and various implementations of the first aspect.

[0038] In a third aspect, an embodiment of the present application provides a computer-readable storage medium having instructions stored thereon, which execute, on an electronic device, any one of the interaction methods described in the first aspect and various implementations of the first aspect.

[0039] Among them, the beneficial effects of the second and third aspects can refer to the relevant beneficial effects of the first aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1A According to some embodiments of the present application, a schematic diagram of a scenario in which a user uses the answering system 0 of the electronic device 100 to perform text translation is shown;

[0041] Figure 1B According to some embodiments of the present application, a schematic diagram of the interaction between a user and an interactive interface of a dialogue system is shown;

[0042] Figure 2 According to some embodiments of the present application, a schematic diagram of an interactive interface 003 for providing alternative prompt contents to a user by a dialogue system 0 is shown;

[0043] Figure 3A According to some embodiments of the present application, a schematic diagram of a main label display of a dialogue system 00 is shown;

[0044] Figure 3B According to some embodiments of the present application, a schematic diagram of a sub-label display of a dialogue system 00 is shown;

[0045] Figure 3C According to some embodiments of the present application, a schematic diagram of a dialogue system 00 displaying content required by a user is shown;

[0046] Figure 4A According to some embodiments of the present application, a schematic diagram of a user performing personalized construction is shown;

[0047] Figure 4B According to some embodiments of the present application, a schematic diagram of a dialogue system 00 outputting required content is shown;

[0048] Figure 5A According to some embodiments of the present application, a schematic diagram of an interactive method process of outputting user-required content using a two-level tag answering system 00 in an electronic device 100 is shown;

[0049] Figure 5B According to some embodiments of the present application, a user input schematic diagram is shown;

[0050] Figure 5C According to some embodiments of the present application, a schematic diagram of a user modifying a main label prompt is shown;

[0051] Figure 6 According to some embodiments of the present application, a schematic diagram of a system architecture for implementing an interaction process is shown;

[0052] Figure 7 According to some embodiments of the present application, another schematic diagram of a framework for implementing an interaction process is shown;

[0053] Fig. 8A According to some embodiments of the present application, a block diagram schematic diagram is shown for implementing the display of each sub-label based on the mapping relationship between the main label, the sub-field, and the sub-label as an example;

[0054] Figure 8BAccording to some embodiments of the present application, a schematic diagram of a prompt fusion algorithm for fusing a main tag selected by a user and each sub-tag is shown;

[0055] Figure 8C According to some embodiments of the present application, a schematic diagram of fusing three sub-tags with a main tag is shown as an example;

[0056] Fig. 9 According to some embodiments of the present application, a schematic diagram of the hardware structure of an electronic device 100 is shown. DETAILED DESCRIPTION

[0057] Illustrative embodiments of the present application include, but are not limited to, an interactive method, a readable storage medium, and an electronic device.

[0058] It can be understood that the answering system proposed in the present application can be a separate software or can be applied as a function in a software. For example, the answering system can be an intelligent customer service or language assistant on an application software in an electronic device, and can also be used as an answering software or intelligent robot software.

[0059] The technical solution of the present application is described in detail below with reference to the accompanying drawings.

[0060] Figure 1A According to some embodiments of the present application, a schematic diagram of a scenario in which a user uses the answering system 0 of the electronic device 100 to perform text translation is shown. Figure 1A As shown, the user edited a constructed prompt a1 in the input box (i.e., text box) k1 in the interactive interface 001 of the answering system 0: "Suppose you are a translator, please use your translation talent to translate the following passage into English. It should be noted that the translation should be as natural, fluent and authentic as possible, and use beautiful and elegant expressions. The following passage is from the Chinese classical text "The Analects of Confucius":", as well as the classical Chinese material a2 associated with the constructed prompt a1: "The Master said 'xxx xxx'". The prompt a1 uses text to describe the requirements of the answering system 0 when translating the classical Chinese material a2: "Translate into English naturally, fluently and authentically, and use beautiful and elegant expressions". When the answering system 0 receives the prompt a1 and the classical Chinese material a2, it will translate the classical Chinese material a2 into content that meets the user's specific requirements based on the prompt a1. Figure 1B As shown, on the interactive interface 002 between the user and the answering system displayed on the electronic device 100, the user 01 sends input content A1 to the answering system 0. After receiving the input content A1 from the user 01, the answering system 0 outputs the English translation B1 "The master said 'xxxxxx'".

[0061] refer to Figure 1A and Figure 1B When users interact with the answering system, they need to edit complex and lengthy texts as prompts, which is cumbersome.

[0062] In some embodiments, some answering systems will provide users with alternative prompt content to reduce user input. However, currently only relatively single prompt content can be provided, and the prompt content is relatively rough, and users cannot obtain prompt content that better matches their intentions, resulting in inaccurate results output by the answering system based on the prompt content, less useful information available to users, and poor user experience. For example, there are specific user-selectable prompt content corresponding to categories such as "text translation", "language detection", "travel plan", and "fitness plan". However, the templates of the alternative prompt content of each category are relatively single, and involve fewer details related to the specific category, which cannot meet user needs.

[0063] Specifically, for example, Figure 2 An interactive interface 003 is shown in which a dialogue system provides alternative prompt content to the user. When the user needs to input to the dialogue system, when the user selects the prompt template t1 of the "text translation" category from the interface 003, "Now you are a translator, your goal is to translate Chinese into English, now please translate the sentence [xxxxx]", at this time, the user only needs to enter the specific sentence to be translated in "[xxxxxx]" in the prompt template t1, and the prompt corresponding to the text translation can be constructed. When the user selects the prompt template t2 of the "travel plan" category from the interface 003, "You are now a professional tour guide, make a travel plan for me in [xxxx], and the itinerary must have [xxxx] attractions", at this time, the user only needs to enter the specific travel itinerary requirements in "[xxxxxx]" in the prompt template t2, and the prompt corresponding to the travel plan can be constructed.

[0064] However, users can only enter text related to their own intentions in the "[xxxxxx]" in the prompt template, and cannot add or modify more text content related to their own intentions. For example, for the aforementioned "text translation", you can only enter the specific sentence to be translated in "[xxxxxx]", and cannot add other translation requirements, such as "translate the classical Chinese text"; for another example, for the aforementioned "travel plan", you can only enter the specific tourist city location and the specific attraction name in "[xxxxxx]", and cannot add other travel requirements, such as "need to refer to the ticket price of the attraction platform". Understandably, the types of alternative prompt content are relatively single, and the specific prompt content is relatively rough and cannot meet the user's own requirements, resulting in the user's inability to input the desired prompt to the answering system based on the alternative prompt content, so that the output content of the answering system cannot meet the user's needs, and the user experience is poor.

[0065] Therefore, in order to solve the problem that users cannot quickly input prompts that meet their needs into the answering system, the present application proposes an interactive method, in which the answering system can display multi-level labels, where the next-level labels belong to the sub-field of the previous-level labels, that is, the displayed multi-level labels can divide the same field more finely. For example, the answering system can display 2-level labels to the user, and the 2-level labels include main labels and sub-labels. Figure 3A As shown in FIG. 1 , in the label box k2 on the interactive interface 004, the answering system 00 displays main labels of multiple fields such as "text translation", "image translation", "language translation", and "painting creation" to the user. It can be understood that each main label has multiple sub-labels corresponding to multiple sub-fields associated with it. Figure 3B In the interactive interface 005 shown, after the user selects the desired main label "text translation", the label box k2 will display multiple sub-labels corresponding to the multiple sub-fields associated with the selected "text translation", including the sub-labels "Chinese to English", "English to Chinese", "Chinese to French", etc. corresponding to the "language direction" sub-field, the sub-labels "thesis", "classical Chinese", "law", etc. corresponding to the "style" sub-field, the sub-labels "The Analects", "xx", etc. corresponding to the "source" sub-field, and other situations will not be repeated here.

[0066] At this point, the answering system will obtain the tags selected by the user at each level, and will also fuse the tags selected by the user to generate a fusion prompt. Figure 3B , the user selects the required sub-tags "Chinese to English", "Classical Chinese", "The Analects" from the multiple sub-tags. At this time, the answering system 00 will merge the selected main tag "text translation" and the specific contents of the selected sub-tags "Chinese to English", "Classical Chinese", "The Analects" to generate a fusion prompt containing these specific contents (i.e., key elements). For example, Figure 3B The input box k1 shown in the figure shows a fusion prompt "Now I will let you act as a translator. Your goal is to translate a Chinese classical text from The Analects into English. Please do not translate with a translation accent, but translate it in a natural, fluent and authentic way, and use beautiful and elegant expressions. Please translate the following passage: ". The "translator" in the fusion prompt corresponds to the main label "text translation", and "translation of Chinese classical text from The Analects into English" corresponds to the sub-labels "Chinese to English", "Classical Text", and "The Analects". It is understandable. Figure 3B The fusion prompt displayed in the figure adds the content corresponding to the selected sub-tags "Chinese to English", "Classical Chinese", and "The Analects" to the content of the main tag prompt corresponding to the original main tag "Text Translation".

[0067] When the user sends the fusion prompt and the material associated with the fusion prompt as input to the answering system, the answering system generates output that meets the user's intention based on the user's input and displays it on the interactive interface. Figure 3B Continue to input the material corresponding to the fusion prompt in the input box k1, such as the specific classical Chinese material "Zi said 'xxx xxx'" to be translated, and then send the content in the input box to the answering system 00, such as Figure 3C In the interactive interface 006 shown in FIG. 1 , after the user has completed the classical Chinese material, the following Figure 3C The input content A2 shown is sent to the answering system 00. After receiving the input content A2 sent by the user 01, the answering system 00 will output the English translation B2 "The master said'xxxxxx'".

[0068] It can be understood that the answering system involves a detailed division of specific fields in the multi-level labels displayed to the user. The user can select the sub-labels corresponding to the target scene, detailed task content, and some detailed instructions related to his own intention according to his own intention, such as the second-level label content such as "text translation", "Chinese to English", "classical Chinese", "The Analects" mentioned above. The way to construct the required prompts is flexible and can handle complex scenarios. The answering system generates fusion prompts related to the user's intentions based on the labels selected by the user, avoiding the user from manually entering complex and lengthy text from scratch to construct the desired prompts, thereby improving the efficiency of constructing the required prompts. In addition, it avoids the user from being unable to enter appropriate prompts due to different expression habits when editing the text by himself, or being unable to express his own intentions due to the relatively simple prompt template provided, which leads to inaccurate output of the answering system and less information available to the user. In addition, after improving the accuracy of the output results of the answering system, the number of interactions between the user and the answering system can also be reduced.

[0069] In addition, after the answering system generates a fusion prompt, the user can also edit the generated fusion prompt in the input box to get a personalized prompt, so that the prompt received by the answering system can better meet its own intentions. Moreover, this construction method is more flexible and can be customized according to user needs to cope with more complex scenarios.

[0070] For example, Figure 3B The user can modify the generated fusion prompt in the input box k1, such as Figure 3B The sentence "Use beautiful and elegant expressions" was changed to "Use the most popular expressions at present" Figure 4A The content in the input box k1 shown in the figure can be personalized. Figure 4BAs shown, after user 01 sends the input content including the personalized prompt to the answering system 00, the answering system 00 can translate the English text that better meets the user's needs.

[0071] It is understandable that since the user makes modifications on the generated fusion prompts, the user does not need to manually input all the requirements and can quickly get the desired prompts. The way of constructing the required prompts is more flexible, making the output of the answering system more in line with user needs and thus able to cope with more complex scenarios.

[0072] It is understandable that in some embodiments, the specific categories involved in the above main label display may include Figure 3A and Figure 3B The text translation, image translation, language translation, painting creation, etc. mentioned in the text translation, image translation, language translation, painting creation, etc. may also include but are not limited to text polishing, article continuation, code generation, copywriting, poetry writing, avatar generation (image), painting creation (image), meeting minutes (voice), voice dialogue (voice), etc. In addition, the sub-labels corresponding to the sub-fields involved in the main label of each category may include but are not limited to scene, field (industry field), style (text style, article style, dialogue style, copywriting style, code style, avatar style, poetry writing style, painting style), text behavior, character, protagonist, artist, intention, language, language (programming language), algorithm, intention, etc.

[0073] In other embodiments, there may be more levels of tags. For example, for the sub-tags mentioned above, there may be further associated secondary sub-tags, such as Figure 3B The sub-tag "Classical Chinese" shown in can also include sub-sub-tags, Tang Dynasty, Song Dynasty, Ming Dynasty, etc., as well as monosyllabic words, disyllabic words, etc.

[0074] Understandably, there are many categories involved in the main labels and multi-field sub-labels. At this time, more detailed label categories can be provided to users to help them expand their thinking, supplement prompt details, and display more fine-grained situational prompts to users to meet the usage needs of business scenarios.

[0075] It can be understood that the electronic devices mentioned in this application that can use the answering system include but are not limited to mobile phones, tablet computers, vehicle-mounted equipment, augmented reality (AR) / virtual reality (VR) devices, ultra-mobile personal computers (UMPC), netbooks, personal digital assistants (PDA), servers, industrial computers, smart homes, patrol robots, etc. This application does not impose any limitations here.

[0076] In conjunction with the accompanying drawings, the specific process of the answering system 00 generating a fusion prompt according to the user selecting a desired tag from the multi-level tags and obtaining a personalized prompt based on the fusion prompt is described below. For ease of understanding, the answering system 00 is described below by taking the display of a level 2 tag as an example.

[0077] Figure 5A According to some embodiments of the present application, a schematic diagram of an interactive method process for an answering system 00 using a two-level tag in an electronic device 100 to output the content required by the user is shown. It can be understood that the answering system 00 can output the content required by the user according to the generated fusion prompt or personalized prompt. For the convenience of explanation, the answering system 00 generates a fusion prompt according to the user's selected tag, and the user adjusts the fusion prompt to generate a personalized prompt, and outputs the content required by the user according to the personalized prompt. The specific process is as follows:

[0078] S501: receiving a user input operation.

[0079] In some embodiments, the user can make inputs in the interactive interface with the answering system 00, and the answering system 00 can receive the user's input operation and then make a subsequent response.

[0080] It is understandable that in some implementations, the user can use text input or voice input. When the user uses voice input, the answering system 00 recognizes the user's voice content and displays the voice content in the form of text in the input box of the interactive interface. In other implementations, the user can also just click on the input box of the interactive interface. It is understandable that there are many user input operations that can be supported, which will not be repeated here.

[0081] For example, when a user is using the answering system 00, or using the answering system 00 function in a certain software, the user can click on the input box on the interactive interface of the answering system 00, or enter a text in the input box. Figure 5B The input box k1 shown in FIG. 1 displays 'How do you say this sentence in English?' At this time, the answering system 00 receives the user's input operation.

[0082] S502: In response to a user input operation, display a main label.

[0083] In some embodiments, after receiving a user input operation, the answering system 00 may display a main label to the user based on the user's input information.

[0084] It can be understood that the main label displayed by the answering system 00 can be a main label category obtained based on the user history record, or a default main label category, or a main label category matched after the answering system 00 recognizes the information (such as text) input by the user, and the answering system 00 can also update the main label category based on the information input by the user.

[0085] For example, after receiving the user input, the answering system 00 will pop up a pop-up window such as Figure 5B The label box k2 shown in the figure, the main labels of multiple fields such as "text translation", "image translation", "language translation", "painting creation" in the label box k2 can be the default main labels, or they can be displayed by the answering system 00 according to the user's historical usage, or they can be updated by the answering system 00 according to the information input by the user.

[0086] S503, judging whether the user has selected the main tab. If the user has selected the main tab, proceed to S504; otherwise, proceed to S509.

[0087] In some embodiments, if the user does not select the main tag displayed by the system, that is, the answering system 00 does not receive the user's selection of the main tag, it means that the user does not intend to use the tag to automatically generate prompts. At this time, the user can continue to perform text editing operations in the input box of the interactive interface to construct personalized prompts, so as to interact with the answering system 00 in the future. At this time, the answering system 00 enters S509. If the user selects a main tag according to his own intention, the answering system 00 receives the user's selection of the main tag and enters S504.

[0088] For example, Figure 3A As shown, the user selects the main tag "text translation" in the tag box k2. At this time, the answering system 00 receives the user's selection of the main tag "text translation" and enters S504.

[0089] It is understandable that in some embodiments, when the user selects a main tag displayed by the answering system 00, the answering system 00 will display the main tag prompt corresponding to the main tag in the input box, wherein the main tag prompt includes the prompt content of the corresponding main tag. Figure 3AThe main label prompt corresponding to the "text translation" main label selected by the user is displayed in the input box k1 shown in the figure. The main label prompt corresponding to the "text translation" main label in the figure is "Now I let you act as a translator. Your goal is to translate a text in the source language into the target language. Please do not translate with a translation accent, but translate in a natural, fluent and authentic way, and use beautiful and elegant expressions. Please translate the following paragraph: ". It can be understood that displaying the main label prompt corresponding to the main label at this time can provide users with an intuitive feeling of the connection between the label and the prompt content, and also help users to select subsequent sub-labels according to their own intentions.

[0090] S504: In response to the user selecting a main label, displaying a corresponding sub-label.

[0091] In some embodiments, the answering system 00 displays multiple sub-field labels related to the main label selected by the user to the user.

[0092] For example, referring to the above Figure 3B In the label box k2, the description of each sub-field corresponding to the main label "text translation" and the label corresponding to each sub-field is not repeated here. It can be understood that Figure 3B The sub-tags associated with the main "Text Translation" tag shown involve the target language, translation style, translation source, etc., meeting the translation business scenarios from multiple angles.

[0093] S505: Determine whether a sub-label selection operation is received. If a sub-label selection operation is received, proceed to S506; otherwise, proceed to S508.

[0094] In some embodiments, if the user does not select the sub-tag displayed by the answering system 00, that is, the answering system 00 does not receive the user's selection of the sub-tag, it means that the user does not intend to use the sub-tag to further generate prompts. At this time, the user can continue to edit and modify the text in the input box of the interactive interface based on the main tag prompt generated in the input box, and the answering system 00 will execute S508. If the user selects the desired sub-tag according to his own intention, the answering system 00 receives the user's selection of the sub-tag operation, and the answering system 00 will execute S506.

[0095] It is understandable that the user can select at least one tag (i.e., sub-tag) corresponding to a sub-field, and the user can also select at least one tag corresponding to multiple sub-fields at the same time, and this application does not limit this. Figure 3BAs shown, the user selects one label "Chinese to English", "Classical Chinese", and "The Analects" corresponding to multiple sub-fields. After receiving the user's selection of these three sub-labels, the answering system 00 enters S506. It can be understood that the user can select the sub-labels corresponding to the target scene, detailed task content, and some detailed instructions related to his or her intention according to his or her intention, so that different fusion prompts are generated when the user selects different labels at each level, and the method of constructing the required prompts is flexible.

[0096] S506: Display a fusion prompt according to the main label and the sub-label.

[0097] It is understandable that the answering system 00 will pre-store the tag prompt corresponding to each tag. It is understandable that the tag prompt is a specific description related to the user's intention, and the tag is an overview of the tag prompt. Each main tag will have a corresponding tag prompt, and each sub-tag will also have a corresponding tag prompt. For example, Figure 3B Taking the "Text Translation" main label and a sub-label "Chinese to English" associated with "Text Translation" selected by the user as an example, the main label prompt corresponding to the pre-stored "Text Translation" main label is "Now I will let you act as a translator. Your goal is to translate a paragraph of text in the source language into the target language. Please do not translate with a translation accent, but translate in a natural, fluent and authentic way, and use beautiful and elegant expressions. Please translate the following paragraph:". It can be seen that the "Text Translation" main label is an overview of the specific content of the aforementioned main label prompt. The sub-label prompt corresponding to the pre-stored "Chinese to English" sub-label is "The source language is Chinese and the target language is English", and it can also be seen that the "Chinese to English" sub-label is an overview of the sub-label prompt.

[0098] In some embodiments, when the answering system 00 receives a sub-tag selected by the user, for example, the answering system 00 receives a plurality of sub-tags selected by the user, the answering system 00 will fuse the main tag prompt corresponding to the main tag with the sub-tag prompt corresponding to each sub-tag, generate a fusion prompt, and display it in the input box of the interactive interface. It is understandable that the fusion prompt includes not only the prompt content corresponding to the main tag, but also the prompt content corresponding to the sub-tag. It is understandable that the prompt content corresponding to the included sub-tag can be the content corresponding to the sub-tag added to the main tag prompt when the sub-tag prompt is fused with the main tag prompt. At this time, the answering system 00 will display the prompt content of the corresponding sub-tag, so that the user can more intuitively feel whether the sub-tag selected by him is consistent with his own intention, thereby improving the efficiency of the user in selecting sub-tags.

[0099] In some implementations, the answering system 00 may pre-store the tag prompts corresponding to each tag, and combine the prompts corresponding to the tags selected by the user through a prompt fusion algorithm (such as a language model, etc.) to form a fusion prompt. It is understandable that other methods may also be used for fusion, which is not limited here.

[0100] It can be understood that since users can select the corresponding label from the displayed multi-level labels according to their own intentions, the answering system can generate the same prompt for the same intentions of different users, thereby avoiding the situation where different users have different user experiences due to different expression habits of different users and the answering system's responses to different expressions of the same intention differ.

[0101] For example, for the above Figure 3B In the example, the user selects the main tag "text translation" and the three subtags "Chinese to English", "Classical Chinese", and "The Analects". The answering system 00 merges the main tag prompt corresponding to the main tag "text translation", the subtag prompt corresponding to the subtag "Chinese to English", the subtag prompt corresponding to the subtag "Classical Chinese", and the subtag prompt corresponding to the subtag "The Analects" to generate a merged prompt. Figure 3B The input box k1 shown shows that specifically "Now I will let you act as a translator. Your goal is to translate a passage from the Chinese classical text of The Analects into English. Please do not translate with a translation tone, but translate naturally, fluently and authentically, and use beautiful and elegant expressions. Please translate the following passage: ".

[0102] Optionally, S507, receiving a text adjustment operation performed by the user based on the fusion prompt, and displaying a personalized prompt.

[0103] In some embodiments, in order to make the prompt in the input box more in line with the user's own intention, the user can perform text adjustment operations on the fused prompt in the input box to construct the required personalized prompt. At this time, the answering system 00 will receive the user's text adjustment operation based on the fused prompt and display the personalized prompt.

[0104] For example, in the above Figure 4A In the fusion prompt, the user modifies Figure 3B In the input box k1, delete "beautiful and elegant" and enter the text "most popular at the moment" through the input method. The answering system 00 receives the text "most popular at the moment" input by the user and displays the following: Figure 4A The personalized prompt shown in the prompt box k1.

[0105] S508, receiving a text adjustment operation performed by the user based on the main label prompt, and displaying a personalized prompt.

[0106] In some embodiments, the user can directly adjust the text based on the main label prompt to construct the desired personalized prompt. It is understandable that since the user does not need to continue to select a sub-label, it means that the current main label prompt meets the user's intention, so the user can adjust the text of the main label prompt based on the main label prompt, which also speeds up the construction of a prompt that satisfies the user.

[0107] For example, users Figure 3A The "elegant and elegant" text shown in the figure is adjusted to the "most popular at the moment" text. At this time, the answering system 00 receives the text adjustment operation performed by the user based on the main label prompt and displays the following Figure 5C The personalized prompt in the input box k1 is shown.

[0108] S509, receiving a text description operation directly performed by the user and displaying a personalized prompt.

[0109] In some embodiments, the user does not select a main tag, but directly uses a text description in the input box. The answering system receives the text description directly provided by the user and displays a personalized prompt.

[0110] S510, displaying the content required by the user according to the input personalized prompt.

[0111] In some embodiments, after a personalized prompt is displayed in the input box of the answering system 00, the user can continue to supplement the material related to the input prompt content and interact with the answering system 00. The answering system 00 displays the content the user wants based on the received prompt and the associated material. For example, the specific material may include text, pictures, audio, video, etc.

[0112] For example, refer to Figure 4A In the input box k1 shown, the user can continue to input the classical Chinese text to be translated in the input box k1, and then send all the text in the box to the answering system 00. Figure 4B The answering system 00 displays the content B3 required by the user based on the input content A3 sent by the user.

[0113] It can be understood that the execution order of the above steps S501 to S510 is only an illustration. In other embodiments, other execution orders may be adopted, and some steps may be split or combined, which is not limited here.

[0114] It can be understood that for the above step S501, the answering system 00 can also provide a display label control on the interactive interface. When the receiving user enables the display label control on the interactive interface, the answering system 00 directly pops up the default or historical label box, and then the user directly selects the label. The specific form is not repeated here.

[0115] It is understandable that in other embodiments, when the answering system displays the main label prompt or the fusion prompt, the user can supplement the related materials and send the main label prompt or the fusion prompt to the answering system 00 for interaction without performing personalized construction; for example, in the above step S505, after the user does not select a sub-label, or after the fusion label is generated in step S506, the user can directly interact with the answering system 00.

[0116] It is understandable that in other embodiments, when the user selects a tag, the answering system 00 may not display a new prompt in the input box every time, and may provide a select confirm button. When the user determines that the tags at each level have been selected, the select confirm button is pressed, and the final prompt is generated in the input box. For example, for level 2 tags, when the user selects a main tag, the main tag prompt will not be displayed in the input box. At this time, the user can continue to select sub-tags. Only when the user presses the select confirm button to indicate that the selection is complete, the prompt of the corresponding selected tag will be displayed in the input box.

[0117] In addition, in some other embodiments, after receiving the user's selection of the main tag, when multiple sub-tags associated with the main tag are displayed, the main tag prompt corresponding to the main tag will also be displayed in the input box. At this time, the user can modify the main tag prompt to obtain a modified main tag prompt, that is, modification prompt 1. Then, after the user selects one or more sub-tags from the displayed associated multiple sub-tags, the input box will add the content corresponding to the selected sub-tag to the modification prompt 1 in the original input box. For example, when the user modifies the main tag prompt, the answering system 00 will receive the user's modification of the main tag prompt, and display the modification prompt 1 in the input box. When the answering system 00 receives the user's selection of a sub-tag, the answering system 00 will merge the modification prompt 1 with the sub-tag prompts corresponding to each sub-tag, generate a fused prompt, and display it in the input box of the interactive interface.

[0118] It is understandable that after the answering system displays the labels to the user, it will generate a fusion prompt based on the multi-level labels selected by the user. In addition, the answering system can also receive the user's modification operation on the displayed prompt, so as to display personalized prompts that are more in line with the user's own intentions, which is conducive to handling a variety of complex scenarios. Thus, it avoids the user from manually entering complex and lengthy text from scratch to construct the desired prompts, thereby improving the construction efficiency. In addition, it avoids the problem that the output of the answering system is unsatisfactory due to the user's different expression habits when editing the text by themselves and being unable to enter appropriate prompts or being unable to express their own intentions due to the relatively simple prompt templates provided, and the number of interactions between the user and the answering system can also be reduced.

[0119] The following is an introduction to the system architecture diagram of the answering system 00 for implementing integrated prompts or personalized prompts, and outputting according to specific prompts. Figure 6 According to some embodiments of the present application, a schematic diagram of a system architecture 600 is shown. Figure 6 As shown, the system architecture 600 includes a main label display module 601, a sub-label display module 602, a prompt fusion module 603, and an intelligent interaction module 604. Specifically, the functions of each module are as follows:

[0120] The main label display module 601 is used to display the main label to the user according to the user input, and is also used to display the corresponding main label prompt in the input box according to the main label selected by the user, and the main label prompt includes the prompt content corresponding to the main label. For example, the main label display module 601 receives the information input by the user in the input box, analyzes the user's intention in real time, and displays several main labels to the user for the user to choose. After the user selects the main label, the system will display the preset main label prompt corresponding to the main label in the input box. For details, please refer to the aforementioned step S502 and its related description, which will not be repeated here.

[0121] The sub-label display module 602 is used to display the sub-labels of multiple sub-fields associated with the main label to the user according to the main label selected by the user, and is also used to input the main label prompt corresponding to the main label selected by the user and the sub-label prompt corresponding to the sub-label selected by the user to the prompt fusion module 603. It can be understood that different main labels have different fields and corresponding sub-labels. The user can select multiple sub-labels at the same time, and each sub-label has its corresponding preset sub-label prompt in the system. After the user selects a sub-label, the sub-label display module 602 will input the main label prompt corresponding to the main label and the sub-label prompts corresponding to several sub-labels selected by the user into the prompt fusion module 603. For details, please refer to the aforementioned step S504 and its related description, which will not be repeated here.

[0122] The prompt fusion module 603 is used to receive multiple input prompts, and use a prompt fusion model (e.g., a language model, a rule-based fusion algorithm, etc.) to fuse them into a fused prompt, which includes the prompt content of the corresponding main label and the prompt content of the corresponding sub-label, and outputs it to the input box of the interactive interface for display to the user. For example, the main label prompt and several sub-label prompts input by the sub-label display module 602 are received, and the main label prompt (or the modified main label prompt) and several sub-label prompts are generated into a fused prompt through the prompt fusion model, and displayed on the interactive interface. For details, please refer to the aforementioned step S506 and its related description, which will not be repeated here.

[0123] The intelligent interaction module 604 (i.e., the intelligent interaction system) is used to output the required content to the user according to the input prompt (for example, the input prompt is a fusion prompt, or a personalized prompt obtained after the user adjusts it) and the material associated with the input prompt. It can be understood that in some embodiments, the intelligent interaction module 604 displays the required content to the user according to the input fusion prompt and the material associated with the fusion prompt. In other embodiments, after the prompt fusion module 603 generates a fusion prompt, the user can realize personalized construction of the fusion prompt in the input box through text adjustment operations, and the intelligent interaction module 604 displays the content required by the user according to the received personalized prompt and the associated material. For details, please refer to the aforementioned steps S507, S508, S509 and S510 and their related descriptions, which will not be repeated here.

[0124] It can be understood that the system architecture 600 shown above is only an example. In other embodiments, other modules may be included, and some modules may be split or merged, which is not limited here.

[0125] Figure 7 According to some embodiments of the present application, another specific interaction process is shown in the interactive block diagram, in which the fusion of the unmodified main label prompt and several sub-label prompts is used as an example for explanation. The details are as follows:

[0126] Corresponds to Figure 7 ①, ② in it:

[0127] ① The answering system uses the main tag display module 601 to display several main tags to the user on the interactive interface according to the user input; the user selects one of the main tags according to his or her own needs, and the main tag determination module 601a determines the main tag that meets the requirements based on the main tag selected by the user, and records the main tag as Lm.

[0128] ② After receiving the user's selection of the main tag, the main tag prompt determination module 601b will obtain the corresponding main tag prompt based on the determined main tag, and display the main tag prompt corresponding to the main tag to the user in the input box of the interactive interface, and record the main tag prompt as Pz.

[0129] Corresponds to Figure 7 ③ in it:

[0130] ③ Based on the main label Lm, the answering system displays the labels of multiple associated sub-fields to the user through the sub-label display module 602, and the sub-label list display module 602a displays the sub-label list; the user selects several sub-labels according to his own needs, sub-label 1, ..., sub-label n. The multiple sub-labels selected by the user, sub-label 1, ..., sub-label n, can be recorded as Ls1, Ls2, ..., Lsn, respectively, and each sub-label 1 (i.e. Ls1), sub-label 2 (i.e. Ls2), ..., sub-label n (i.e. Lsn) corresponds to a sub-label prompt, sub-label prompt 1, sub-label prompt 2, ..., sub-label prompt n, and each sub-label prompt is recorded as Ps1, Ps2, ..., Psn.

[0131] Corresponds to Figure 7 ④ in it:

[0132] ④ The answering system inputs the main label prompt and several sub-label prompts selected by the user into the prompt fusion module 603 at the same time, and fuses them into one prompt (i.e., the fused prompt). The fused prompt display module 603a displays the fused prompt to the user, and the fused prompt is recorded as Pf.

[0133] Corresponds to Figure 7 ⑤ in the above:

[0134] ⑤ Based on the integrated prompts, the user can continue to make personalized modifications. The personalized prompt display module 605 displays personalized prompts according to the user's modification operations, and then inputs the personalized prompts and related materials into the large language model (LLM) 604a for interaction. The large language model 604a outputs the content that the user wants.

[0135] Understandably, the above Figure 7 This is just an example. In other embodiments, other modules may be included, and the specific contents of each module may be split or some modules may be merged, which is not limited here.

[0136] Understandably, the tag recommendation method of "main tag - multi-domain sub-tag" and the construction method of fusing multiple prompts to generate fused prompts can help users expand their thinking, simplify operations, and improve prompt construction efficiency. In addition, the method of generating fused prompts is relatively flexible, and can be customized according to user needs, which can cope with more complex scenarios. The generated fused prompts are stable, diverse in form, and high in quality.

[0137] The following will Figure 6 The sub-label display module 602 or the above Figure 7The sub-label display module mentioned in ③ in the above is a specific process description for recommending sub-labels corresponding to multiple fields corresponding to the main label selected by the user.

[0138] It is understandable that there may be a variety of associated information between the main tag, sub-field, and sub-tag. For example, there may be preset mapping relationships, associated information in historical records, semantic correlation, and association between tags, etc. between the main tag, sub-field, and sub-tag. At this time, a multi-field sub-tag recommendation algorithm may be used to generate a multi-field sub-tag list corresponding to the main tag based on the input main tag using the various associated information of the main tag, sub-field, and sub-tag. The multi-field sub-tag recommendation algorithm may be any known recommendation algorithm, for example, a recommendation algorithm based on mapping, a recommendation algorithm based on associations in historical records, and the like.

[0139] For example, Fig. 8A According to some embodiments of the present application, a block diagram is shown for implementing the recommendation of each sub-tag based on the mapping relationship between the main tag, sub-field, and sub-tag. Fig. 8A As shown, the sub-label display module may include a main label-sub-domain-sub-label mapping database 801a and a mapping-based recommendation algorithm 802a.

[0140] Specifically, the main tag-sub-field-sub-tag mapping database 801a is used to store the mapping relationship between the main tag, sub-field, and sub-tag. It can be understood that the sub-tag display module can obtain the main tag (i.e., Lm) selected by the user. At this time, the mapping-based recommendation algorithm 802a is used to generate a sub-tag list corresponding to the main tag according to the main tag-sub-field-sub-tag mapping database 801a and the main tag selected by the user.

[0141] Understandably, Fig. 8A This is just an example of the mapping relationship between the main tag, sub-field, and sub-tag. In actual application, it can also be a combination of many other relationships, which will not be described in detail here. It can be understood that the recommendation method based on multi-field sub-tags can recommend multiple sub-tags of multiple related fields based on the main tag.

[0142] The following will Figure 6 The prompt fusion module 603 in the above Figure 7 The prompt fusion module mentioned in ④ is elaborated in detail.

[0143] Figure 8BAccording to some embodiments of the present application, a schematic diagram of fusing a main tag and each sub-tag selected by a user based on a tip fusion algorithm 801b in a tip fusion module is shown. Specifically, the tip fusion module includes a tip fusion algorithm 801b, which is used to fuse multiple input tips to generate a fused tip. Figure 8B In the example, the prompt fusion algorithm 801b is used to fuse the main tag prompt and the sub-tag prompts 1, ..., and sub-tag prompts n selected by the user corresponding to the main tag prompt, thereby obtaining a fused prompt. The prompt fusion algorithm may use a language model or a rule-based fusion algorithm. Figure 8C FIG. 4 shows a schematic diagram of merging three sub-labels with a main label as an example. Figure 8C As shown, the main label is "text translation", sub-label 1 is "Chinese to English", sub-label 2 is "Classical Chinese", and sub-label 3 is "The Analects". The main label prompt corresponding to the main label "text translation" is "Now I let you act as a translator. Your goal is to translate a passage in the source language into the target language. Please do not translate with a translation accent, but translate in a natural, fluent and authentic manner, and use beautiful and elegant expressions. Please translate the following passage:", the sub-label prompt corresponding to sub-label 1 "Chinese to English" is "The source language is Chinese and the target language is English", the sub-label prompt corresponding to sub-label 2 "Classical Chinese" is "This passage is in Classical Chinese", and the sub-label prompt corresponding to sub-label 3 "The Analects" is "This passage comes from The Analects". At this time, the prompt fusion algorithm 801b will fuse the main label and multiple sub-label prompts to obtain a fused prompt, such as Figure 8C As shown, it is "Now I ask you to act as a translator. Your goal is to translate a passage of classical Chinese from The Analects into English. Please do not translate in a translator's tone, but translate naturally, fluently and authentically, and use beautiful and elegant expressions. Please translate the following passage: ".

[0144] For further understanding, the main tags mentioned above and the multiple sub-tags corresponding to the sub-fields associated with the main tags are described in detail below:

[0145] The corresponding main tag is text translation: sub-field 1 is language orientation, and the corresponding sub-tags are: Chinese to English, English to Chinese, Chinese to French, French to Chinese, etc.; sub-field 2 is style, and the corresponding sub-tags are: essays, classical Chinese, law, finance, fairy tales, etc.; sub-field 3 is source, and the corresponding sub-tags are: The Analects, A Dream of Red Mansions, etc.

[0146] The corresponding main label is image translation: sub-domain 1 is scene, and the corresponding sub-labels are: restaurant, airport, museum, etc.; sub-domain 2 is person, and the corresponding sub-labels are: man, woman, child, etc.

[0147] The corresponding main tag is language translation: sub-field 1 is scene, and the corresponding sub-tags are: academic conference, event live broadcast, museum explanation, etc.; sub-field 2 is characters, and the corresponding sub-tags are: teachers, students, audience, commentators, etc.

[0148] The corresponding main label is text polishing: sub-domain 1 is style, and the corresponding sub-labels are: formal, elegant, daily, etc.; sub-domain 2 is domain (industry domain), and the corresponding sub-labels are: law, finance, biology, etc.; sub-domain 3 is behavior, and the corresponding sub-labels are: wrong word correction, vocabulary optimization, sentence rewriting, etc.

[0149] The corresponding main tag is article continuation: sub-domain 1 is style, and the corresponding sub-tags are: formal, elegant, daily, etc.; sub-domain 2 is field (industry field), and the corresponding sub-tags are: law, finance, biology, etc.; sub-domain 3 is language, and the corresponding sub-tags are: Chinese, English, Japanese, etc. The corresponding main tag is dialogue question and answer: sub-domain 1 is intention, and the corresponding sub-tags are: foreign language training, knowledge question and answer, sentiment analysis, etc.; sub-domain 2 is style, and the corresponding sub-tags are: lively, serious, gentle, etc.; sub-domain 3 is language, and the corresponding sub-tags are: Chinese, English, Japanese, etc.

[0150] The corresponding main label is copywriting: sub-field 1 is scene, and the corresponding sub-labels are: Teacher's Day, Mother's Day, opening ceremony, etc.; sub-field 2 is style, and the corresponding sub-labels are: warm, playful, formal, etc.; sub-field 3 is language, and the corresponding sub-labels are: Chinese, English, Japanese, etc.

[0151] The corresponding main tag is poetry writing: sub-field 1 is style, and the corresponding sub-tags are: modern, classical, pentasyllabic regulated verse, etc.; sub-field 2 is scene, and the corresponding sub-tags are: singing praises to the motherland, praising spring, expressing emotions, etc.; sub-field 3 is language, and the corresponding sub-tags are: Chinese, English, Japanese, etc.

[0152] The corresponding main tag is code generation: sub-domain 1 is language, and the corresponding sub-tags are: python, c++, java, etc.; sub-domain 2 is algorithm, and the corresponding sub-tags are: dictionary tree, quick sort algorithm, network flow, etc.; sub-domain 3 is style, and the corresponding sub-tags are: database code style, Code style, web page code style, etc.

[0153] The corresponding main tag is avatar generation (image): sub-domain 1 is style, and the corresponding sub-tags are: comics, oil painting, realism, etc.; sub-domain 2 is protagonist, and the corresponding sub-tags are: female, male, cat, etc.; sub-domain 3 is background, and the corresponding sub-tags are: garden, sky, ocean, etc.

[0154] The corresponding main tag is painting creation (image): sub-field 1 is style, and the corresponding sub-tags are: comics, oil paintings, realism, etc.; sub-field 2 is content, and the corresponding sub-tags are: seaside town, ancient temple in the mountains, skyscrapers, etc.; sub-field 3 is artist, and the corresponding sub-tags are: Monet, Van Gogh, Renoir, etc.

[0155] The corresponding main label is meeting minutes (voice): sub-field 1 is scene, and the corresponding sub-labels are: academic conference, work meeting, interview, etc.; sub-field 2 is field (industry field), and the corresponding sub-labels are: law, finance, artificial intelligence, etc.; sub-field 3 is intention, and the corresponding sub-labels are: full record, content summary, etc.

[0156] The corresponding main label is voice dialogue (voice): sub-domain 1 is intention, and the corresponding sub-labels are: foreign language training, knowledge quiz, sentiment analysis, etc.; sub-domain 2 is style, and the corresponding sub-labels are: serious, lively, peaceful, gentle, etc.; sub-domain 3 is language, and the corresponding sub-labels are: Chinese, English, Japanese, etc.

[0157] It is understandable that specific tags will involve different scenarios, for example, refer to the specific main tags and corresponding sub-tag categories described above. Moreover, after the answering system receives prompts for different scenarios and the corresponding materials, the content required by the user is also different. For example, in the translation scenario, the translation results are output; in the retrieval scenario, the retrieval results are output; in the search scenario, the search results are output; in the question and answer scenario, the question and answer results are output; in the text polishing scenario, the text polishing results are output; in the article continuation scenario, the article continuation results are output; in the code generation scenario, the code generation results are output; in the copywriting scenario, the copywriting results are output; in the poetry writing scenario, the poetry writing results are output; in the avatar generation scenario, the avatar generation results are output; in the painting creation scenario, the painting creation results are output; in the meeting minutes scenario, the meeting minutes results are output; in the voice dialogue scenario, the voice dialogue results are output. It is understandable that the interactive method proposed in the embodiment of the present application can be applied to a wide range of scenarios, so that processing results corresponding to a variety of scenarios can be obtained, thereby meeting the user's usage needs.

[0158] Fig. 9 According to an embodiment of the present application, a schematic diagram of the hardware structure of an electronic device 100 is shown, and the hardware structure is demonstrated by taking the electronic device 100 as a mobile phone as an example.

[0159] The electronic device 100 is provided with a dialogue system and an interactive method can be used. Fig. 9 In the drawings, similar parts have the same reference numerals. Fig. 9As shown, the electronic device 100 may include a processor 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, an earphone interface 170D, a sensor module 180, a button 190, a motor 191, an indicator 192, a camera 193, a display screen 194, and a subscriber identification module (SIM) card interface 195, etc. The sensor module 180 may include a pressure sensor 180A, a gyroscope sensor 180B, an air pressure sensor 180C, a magnetic sensor 180D, an acceleration sensor 180E, a distance sensor 180F, a proximity light sensor 180G, a fingerprint sensor 180H, a temperature sensor 180J, a touch sensor 180K, an ambient light sensor 180L, a bone conduction sensor 180M, etc.

[0160] It is to be understood that the structure illustrated in the embodiment of the present invention does not constitute a specific limitation on the electronic device 100. In other embodiments of the present application, the electronic device 100 may include more or fewer components than shown in the figure, or combine some components, or separate some components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0161] The processor 110 may include one or more processing units, for example, a processing module or processing circuit including a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processor (DSP), a microprocessor (MCU), an artificial intelligence (AI) processor, or a programmable logic device (field programmable gate array, FPGA). Different processing units may be independent devices or integrated into one or more processors. The processor 110 may be used to execute the interaction method proposed in the present application.

[0162] The memory can be used to store data, software programs and modules, and can be a volatile memory (volatile memory), such as a random-access memory (RAM); or a non-volatile memory (non-volatile memory), such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD); or a combination of the above types of memory, or it can also be a removable storage medium, such as a secure digital (SD) memory card.

[0163] The charging management module 140 may include a power source, a power management component, etc. The power source may be a battery. The power management component is used to manage the charging of the power source and the power supply of the power source to other modules. The charging management module is used to receive charging input from the charger; the power management module is used to connect the power source, the charging management module and the processor 110.

[0164] The mobile communication module 150 may include, but is not limited to, an antenna, a power amplifier, a filter, a low noise amplifier (LNA), etc. The mobile communication module 150 may provide a solution for wireless communications including 2G / 3G / 4G / 5G, etc., applied to the electronic device 100. The mobile communication module 150 may receive electromagnetic waves through an antenna, filter, amplify, and process the received electromagnetic waves, and transmit them to a modulation and demodulation processor for demodulation. The mobile communication module 150 may also amplify the signal modulated by the modulation and demodulation processor, and convert it into electromagnetic waves for radiation through the antenna.

[0165] The wireless communication module 160 may include an antenna, and transmit and receive electromagnetic waves via the antenna. The wireless communication module 160 may provide wireless communication solutions including wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), infrared technology (IR), etc., which are applied to the electronic device 100.

[0166] In some embodiments, the mobile communication module 150 and the wireless communication module 160 of the electronic device 100 may also be located in the same module.

[0167] The camera 193 is used to capture still images or videos. The optical image generated by the lens is projected onto the photosensitive element. The photosensitive element converts the optical signal into an electrical signal, which is then passed to an image signal processor (ISP) to be converted into a digital image signal. The electronic device 100 can achieve a shooting function through the ISP, the camera 193, a video codec, a graphic processing unit (GPU), a display screen, and an application processor.

[0168] The display screen includes a display panel. The display panel can be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode or an active-matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), a Mini LED, a Micro LED, a Micro OLED, a quantum dot light-emitting diode (QLED), etc. In the present application, the display screen can be used to display such as FIG. 3A to FIG. 4B , Figure 5B , Figure 5C The interactive interface shown.

[0169] The audio module 170 can convert digital audio information into analog audio signal output, or convert analog audio input into digital audio signal. The audio module 170 can also be used to encode and decode audio signals. In some embodiments, the audio module 170 can be arranged in the processor 110, or some functional modules of the audio module 170 can be arranged in the processor 110.

[0170] The interface module includes an external memory interface, a universal serial bus (USB) interface, and a subscriber identification module (SIM) card interface. The external memory interface can be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the electronic device 100. The external memory card communicates with the processor 110 via the external memory interface to implement a data storage function. The universal serial bus interface is used for the electronic device 100 to communicate with other mobile phones. The subscriber identification module card interface is used to communicate with a SIM card installed in the electronic device 100, for example, to read a phone number stored in the SIM card, or to write a phone number into the SIM card.

[0171] In some embodiments, the electronic device 100 further includes buttons, motors, and indicators. The buttons may include volume buttons, power on / off buttons, and the like. The motor is used to make the electronic device 100 vibrate, for example, when the electronic device 100 of the user of the electronic device or the developer receives a new IM APP message, vibration is generated to prompt the user of the electronic device or the developer to check the message. The indicator may include a laser indicator, a radio frequency indicator, an LED indicator, and the like.

[0172] It is understandable that the structure illustrated in the embodiment of the present invention does not constitute a specific limitation on the electronic device 100 .

[0173] The various embodiments of the mechanism disclosed in the present application can be implemented in hardware, software, firmware or a combination of these implementation methods. The embodiments of the present application can be implemented as a computer program or program code executed on a programmable system, which includes at least one processor, a storage system (including volatile and non-volatile memory and / or storage elements), at least one input device and at least one output device.

[0174] Program code can be applied to input instructions to perform the functions described in this application and generate output information. The output information can be applied to one or more output devices in a known manner. For the purposes of this application, a processing system includes any system having a processor such as, for example, a digital signal processor (DSP), a microcontroller, an application specific integrated circuit (ASIC), or a microprocessor.

[0175] Program code can be implemented with the runtime environment (i.e., programming language) corresponding to a high-level programming language or an object-oriented development language to communicate with the processing system. When necessary, program code can also be implemented with assembly language or machine language. In fact, the mechanism described in this application is not limited to the scope of the runtime environment (i.e., programming language) corresponding to any specific development language. In either case, the language can be a compiled language or an interpreted language.

[0176] In some cases, the disclosed embodiments may be implemented in hardware, firmware, software, or any combination thereof. The disclosed embodiments may also be implemented as instructions carried or stored on one or more temporary or non-temporary machine-readable (e.g., computer-readable) storage media, which may be read and executed by one or more processors. For example, instructions may be distributed over a network or through other computer-readable media. Therefore, machine-readable media may include any mechanism for storing or transmitting information in a machine (e.g., computer) readable form, including, but not limited to, floppy disks, optical disks, optical disks, read-only memories (CD-ROMs), magneto-optical disks, read-only memories (ROMs), random access memories (RAMs), erasable programmable read-only memories (EPROMs), electrically erasable programmable read-only memories (EEPROMs), magnetic or optical cards, flash memory, or a tangible machine-readable memory for transmitting information (e.g., carrier waves, infrared signals, digital signals, etc.) using the Internet in electrical, optical, acoustic, or other forms of propagation signals. Therefore, machine-readable media include any type of machine-readable media suitable for storing or transmitting electronic instructions or information in a machine (e.g., computer) readable form.

[0177] In the accompanying drawings, some structural or method features may be shown in a specific arrangement and / or order. However, it should be understood that such a specific arrangement and / or order may not be required. Instead, in some embodiments, these features may be arranged in a manner and / or order different from that shown in the illustrative drawings. In addition, the inclusion of structural or method features in a particular figure does not mean that such features are required in all embodiments, and in some embodiments, these features may not be included or may be combined with other features.

[0178] It should be noted that the units / modules mentioned in the various device embodiments of the present application are all logical units / modules. Physically, a logical unit / module can be a physical unit / module, or a part of a physical unit / module, or can be implemented as a combination of multiple physical units / modules. The physical implementation method of these logical units / modules themselves is not the most important. The combination of functions implemented by these logical units / modules is the key to solving the technical problems proposed by the present application. In addition, in order to highlight the innovative part of the present application, the above-mentioned device embodiments of the present application do not introduce units / modules that are not closely related to solving the technical problems proposed by the present application, which does not mean that there are no other units / modules in the above-mentioned device embodiments.

[0179] It should be noted that in the examples and description of this patent, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "including one" do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0180] Although the present application has been illustrated and described with reference to certain preferred embodiments thereof, it will be apparent to those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the present application.

Claims

1. An interactive method, applied to an electronic device, characterized in that: include: Displaying a first interface, wherein the first interface includes at least one first-level prompt label; receiving an operation of selecting a first prompt tag by a user, wherein the at least one first-level prompt tag includes the first prompt tag; Display at least one second-level prompt label related to the first prompt label; receiving an operation of the user selecting a second prompt tag, wherein the at least one second-level prompt tag includes the second prompt tag; Displaying first prompt information, wherein the first prompt information includes first prompt content corresponding to the first prompt label, and the first prompt information also includes second prompt content corresponding to the second prompt label; A first processing result corresponding to the first prompt information is displayed.

2. The method according to claim 1, characterized in that The first processing result includes at least one of the following: Translation results, retrieval results, search results, question and answer results, text polishing results, article continuation results, code generation results, copywriting results, poetry writing results, avatar generation results, painting creation results, meeting minutes results, and voice dialogue results.

3. The method according to claim 1 or 2, characterized in that: Also includes: In response to receiving an operation of the user selecting a first prompt tag, the first prompt content is displayed.

4. The method according to any one of claims 1 to 3, characterized in that: Also includes: In response to receiving an operation of the user selecting the second prompt label, the second prompt content is displayed.

5. The method according to claim 4, characterized in that The displaying of the first prompt information includes: In response to receiving an operation of the user selecting the second prompt label, the second prompt content is additionally displayed in the first prompt content.

6. The method according to claim 5, characterized in that The displaying of the first prompt information further includes: After the second prompt content is added and displayed in the first prompt content, a first modification operation by the user is received; The first prompt information is displayed, where the first prompt information includes prompt content after the user performs the first modification operation.

7. The method according to claim 3, characterized in that The method further comprises: After displaying the first prompt content, receiving a second modification operation of the user on the first prompt content; and The first prompt information includes prompt content after the user performs the second modification operation.

8. The method according to any one of claims 1 to 7, characterized in that: The displaying of the first prompt information includes: After receiving the user's operation of selecting the second prompt label, receiving the user's triggering operation of selecting a confirmation button, and displaying the first prompt information.

9. The method according to any one of claims 1 to 8, characterized in that Corresponding to the first prompt label being text translation, the at least one second-level prompt label includes at least one of the following: Chinese to English, English to Chinese, Chinese to French, French to Chinese, thesis, classical Chinese, law, finance, fairy tales, and recommended masterpieces to be translated; or Corresponding to the first prompt label being a picture translation, the at least one second-level prompt label includes at least one of the following: restaurant, airport, museum, man, woman, child; or Corresponding to the first prompt label being language translation, the at least one second prompt label includes at least one of the following: academic conference, event live broadcast, museum explanation, teacher, student, audience, and commentator.

10. The method according to any one of claims 1 to 8, characterized in that Corresponding to the first prompt label being text polishing, the at least one second prompt label includes at least one of the following: formal, elegant, daily, legal, financial, biological, wrong word correction, vocabulary optimization, sentence rewriting; or Corresponding to the first prompt label being article continuation, the at least one second prompt label includes at least one of the following: formal, beautiful, daily, law, finance, biology, Chinese, English, Japanese, foreign language training, knowledge quiz, sentiment analysis, lively, serious, gentle, Chinese, English, Japanese; or Corresponding to the first prompt label being copywriting, the at least one second prompt label includes at least one of the following: Teacher's Day, Mother's Day, Opening Ceremony, Tender, Playful, Formal, Chinese, English, Japanese; or Corresponding to the first prompt tag being poetry writing, the at least one second prompt tag includes at least one of the following: modern, classical, pentasyllabic regulated verse, praising the motherland, praising spring, expressing emotions, etc., Chinese, English, and Japanese.

11. The method according to any one of claims 1 to 8, characterized in that Corresponding to the first prompt tag being code generation, the at least one second prompt tag includes at least one of the following: python, c++, java, dictionary tree, quick sort algorithm, network flow, database code style, and web page code style.

12. The method according to any one of claims 1 to 8, characterized in that Corresponding to the generation of the first prompt tag as an avatar, the at least one second prompt tag includes at least one of the following: cartoon, oil painting, realistic, female, male, cat, garden, sky, and ocean; or Corresponding to the first prompt label being painting creation, the at least one second prompt label includes at least one of the following: cartoon, oil painting, realism, seaside town, ancient temple in the mountains, skyscraper, Monet, Van Gogh, Renoir, etc.

13. The method according to any one of claims 1 to 8, characterized in that Also includes: Corresponding to the first prompt label being meeting minutes, the at least one second prompt label includes at least one of the following: academic conference, work meeting, interview, law, finance, artificial intelligence, full record, content summary; or Corresponding to the first prompt label being voice dialogue, the at least one second prompt label includes at least one of the following: foreign language practice, knowledge quiz, sentiment analysis, serious, lively, peaceful, gentle, Chinese, English, and Japanese.

14. The method according to any one of claims 1 to 13, characterized in that Also includes: The first processing result is generated based on the first prompt information.

15. The method according to claim 14, characterized in that The generating the first processing result based on the first prompt information includes: Acquire the material to be processed input by the user; Based on the first prompt information, the material to be processed is processed to obtain the first processing result.

16. An electronic device, characterized in that: include: memory for storing instructions, and One or more processors, when the instructions are executed by the one or more processors, the processors perform the interaction method according to any one of claims 1-15.

17. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, which execute the interaction method as described in any one of claims 1 to 15 on an electronic device.

Images