Card generation method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses a card generation method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring a keyword corresponding to information to be identified; based on the keyword, generating a service recommendation scheme corresponding to the to-be-identified information; determining a plurality of corresponding services based on the service recommendation scheme; multiple cards corresponding to the multiple services are generated, and different services correspond to different cards. Through the method, a plurality of cards meeting user requirements can be generated, so that the planning time of the user is reduced, and the planning efficiency and satisfaction are improved.

Description

Technical Field

[0001] The present application belongs to the field of computer technology, and specifically relates to a card generation method, device, electronic device and storage medium. Background Art

[0002] Cards are a new service display technology that is widely used to display service content on pan-terminal devices. For example, cards can be embedded in various super apps or interactive scenarios to better meet user needs and provide intelligent service capabilities. The related card generation method does not meet user needs well when generating cards corresponding to user input information. Summary of the invention

[0003] In view of the above problems, the present application proposes a card generation method, device, electronic device and storage medium to improve the above problems.

[0004] In a first aspect, an embodiment of the present application provides a card generation method, the method comprising: obtaining keywords corresponding to the information to be identified; based on the keywords, generating a service recommendation scheme corresponding to the information to be identified; based on the service recommendation scheme, determining a corresponding plurality of services; generating a plurality of cards corresponding to the plurality of services, wherein different services correspond to different cards.

[0005] In a second aspect, an embodiment of the present application provides a card generation device, which includes: a keyword acquisition unit, used to acquire keywords corresponding to the information to be identified; a service generation unit, used to generate a service recommendation scheme corresponding to the information to be identified based on the keywords; a service determination unit, used to determine the corresponding multiple services based on the service recommendation scheme; a card generation unit, used to generate multiple cards corresponding to the multiple services, wherein different services correspond to different cards.

[0006] In a third aspect, an embodiment of the present application provides an electronic device, comprising one or more processors and a memory; one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to execute the above-mentioned method.

[0007] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which a program code is stored, wherein the above method is executed when the program code is run.

[0008] The embodiments of the present application provide a card generation method, device, electronic device and storage medium. Keywords corresponding to the information to be identified are obtained, and then based on the keywords, service recommendation schemes corresponding to the information to be identified are generated, and then based on the service recommendation schemes, multiple corresponding services are determined, thereby generating multiple cards corresponding to multiple services, wherein different services correspond to different cards. Through the above method, multiple cards that meet user needs can be generated, thereby reducing the user's planning time and improving planning efficiency and satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0010] Figure 1 A flowchart of a card generation method proposed in an embodiment of the present application is shown;

[0011] Figure 2 A flowchart of a card generation method proposed in another embodiment of the present application is shown;

[0012] Figure 3 A schematic diagram showing another embodiment of the present application of selecting text from a microblog;

[0013] Figure 4 A schematic diagram showing dragging selected text to a time-space hole in another embodiment of the present application is shown;

[0014] Figure 5 A schematic diagram showing a sidebar of an electronic device in another embodiment of the present application is shown;

[0015] Figure 6 A schematic diagram showing multiple functional components corresponding to "Xiaobu Screen Recognition" in another embodiment of the present application is shown;

[0016] Figure 7 A schematic diagram showing an information input interface in another embodiment of the present application is shown;

[0017] Figure 8 A flowchart of a card generation method proposed in another embodiment of the present application is shown;

[0018] Fig. 9 A schematic diagram showing a method of displaying extracted keywords in a pop-up window in another embodiment of the present application is shown;

[0019] Fig.10 A schematic diagram showing a service recommendation scheme generated in yet another embodiment of the present application is shown;

[0020] Fig.11 A schematic diagram showing a service recommendation scheme generated in yet another embodiment of the present application is shown;

[0021] Fig.12 A schematic diagram of a card generated in yet another embodiment of the present application is shown;

[0022] Fig.13 A schematic diagram of a card generated in yet another embodiment of the present application is shown;

[0023] Fig.14 A schematic diagram showing jumping to a corresponding application in yet another embodiment of the present application is shown;

[0024] Fig.15 A schematic diagram showing a jump display invitation text in another embodiment of the present application is shown;

[0025] Fig.16 A flowchart of a card generation method proposed in another embodiment of the present application is shown;

[0026] Fig.17 A schematic diagram showing operated cards and cards to be assembled in another embodiment of the present application is shown;

[0027] Fig.18 A structural block diagram of a card generating device proposed in an embodiment of the present application is shown;

[0028] Fig.19 A structural block diagram of a card generating device proposed in an embodiment of the present application is shown;

[0029] Fig. 20 A structural block diagram of an electronic device for executing a card generation method according to an embodiment of the present application is shown;

[0030] Fig.21 A storage unit in an embodiment of the present application is shown for storing or carrying a program code for implementing a card generation method according to an embodiment of the present application. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0032] With the continuous development of electronic technology and computer technology, terminal devices such as mobile phones, tablet computers, and smart wearable devices have become popular. Terminal devices can use a variety of services provided by applications to achieve corresponding functions.

[0033] In some scenarios, the terminal device can display related services to the user in the form of cards. For example, if the terminal device is a mobile phone, the chat APP of the mobile phone can receive a video card provided by a video APP sent by a contact. If it is detected that the user clicks on the video card, the mobile phone can jump to the video APP corresponding to the video card to provide the user with the corresponding video playback service.

[0034] The inventors found in their research on displaying related services to users in the form of cards that, generally, when displaying related services to users in the form of cards, only one corresponding card can be generated based on the user's input, so that the generated card cannot meet the user's needs well.

[0035] Therefore, the inventors proposed the card generation method, device, electronic device and storage medium in the present application. Keywords corresponding to the information to be identified are obtained, and then based on the keywords, service recommendation schemes corresponding to the information to be identified are generated, and then based on the service recommendation schemes, multiple corresponding services are determined, thereby generating multiple cards corresponding to multiple services, wherein different services correspond to different cards. Through the above method, multiple cards that meet user needs can be generated, thereby reducing the user's planning time and improving planning efficiency and satisfaction.

[0036] The embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0037] See also Figure 1 , a card generation method provided in an embodiment of the present application is applied to an electronic device, the method comprising:

[0038] Step S110: Obtain keywords corresponding to the information to be identified.

[0039] In the embodiments of the present application, the information to be identified can be understood as information that needs to be identified, and the information to be identified can be information in various forms, such as pictures, text, or pictures + text, etc., which are not specifically limited here. Among them, when the information to be identified is text information, the information to be identified can be one of a paragraph, a conversation, an article, etc., which are not specifically limited here.

[0040] As one way, the information to be identified can be obtained from any page that supports dragging selected text, such as web pages, microblogs, public accounts, text messages, and emails. As another way, a chat screenshot or a picture containing specified content can be used as the information to be identified.

[0041] Optionally, the information to be identified may be obtained through a variety of ways. As one of the ways, the electronic device may obtain the information to be identified from a preset storage area in response to an information acquisition instruction. As another way, the electronic device may download the information to be identified from a search engine or a browser. As yet another way, the electronic device may obtain the information to be identified from other electronic devices, which is not specifically limited here.

[0042] After the information to be identified is obtained, corresponding keywords can be obtained from the information to be identified according to preset rules. The keywords corresponding to the information to be identified can be words or phrases extracted to represent the user's intention.

[0043] In an embodiment of the present application, the preset rules may be pre-set rules for keyword extraction, wherein different forms of information to be identified may correspond to different preset rules. For example, if the information to be identified is text information, the corresponding preset rules may be grammatical composition rules; if the information to be identified is image or picture information, the corresponding preset rules may be image recognition rules, etc.

[0044] After determining the keywords of the information to be identified, the electronic device can display the keywords of the information to be identified to obtain user feedback information based on the keywords displayed by the electronic device. Specifically, after determining the keywords of the information to be identified, the keywords of the information to be identified can be displayed, and then the user can judge whether the determined keywords are incorrect based on the displayed keywords of the information to be identified. If the user determines that the keywords are incorrect, the determined keywords can be modified, or the information to be identified can be modified. Among them, modifying the information to be identified can be understood as adding more descriptive information to the information to be identified.

[0045] In an embodiment of the present application, for an electronic device, after the electronic device displays a determined keyword, if a new word or new information to be identified is received, it can be determined that the keyword of the currently determined information to be identified is incorrect.

[0046] Optionally, after the keywords of the information to be identified are displayed, a feedback prompt box may be displayed on the current display interface, and the user may input feedback information in the feedback prompt box.

[0047] Step S120: Based on the keywords, a service recommendation scheme corresponding to the information to be identified is generated.

[0048] In the embodiment of the present application, the service recommendation scheme refers to a service chain scheme related to the user intent corresponding to the keyword, wherein the service chain may be composed of information related to multiple services including a preset execution order. Optionally, the service recommendation scheme may be understood as a planning scheme generated corresponding to the information to be identified, such as a travel planning scheme or a dinner planning scheme.

[0049] Among them, services can be understood as services provided by applications in electronic devices to users to achieve a specific function. For example, a chat app can provide chat services with contacts. Among them, the contact can refer to friends, groups, public accounts, robots or mini-programs that the user has added in the chat app. For another example, a video app can provide services such as playing, sharing, leaving messages, and collecting various video files.

[0050] Alternatively, a service can also be understood as providing one or more services related to a certain device to a user. For example, a mobile phone can provide a user with a remote control service for controlling TV volume, brightness, channel switching, powering off or powering on, etc. For another example, a mobile phone can also provide a user with system services such as voice assistant and screenshot, which are not limited in any way in the embodiments of the present application.

[0051] It is understandable that service recommendation, which can also be called personalized service recommendation or service suggestion, generally refers to an information service method that actively recommends one or more services to users on the user interface (UI) to promote users to use various services more effectively. The service in the embodiment of the present application is an object that can provide information or interactive functions to users. In the initial state, the electronic device can display a service recommendation area on the UI to recommend various services to users; or it can display the service recommendation area or close the service recommendation area based on the user's instructions. The service recommendation area may be located in any area on the UI, and the embodiment of the present application does not limit this. For example, the service recommendation area may be located in the page displayed in the status bar or the drop-down status bar, the negative one screen, the adjacent area of ​​the area where the global search function is located, and so on. Exemplarily, the service recommendation area can be directly displayed on the desktop UI, and the service recommendation area can also be displayed on the display interface that slides out from the side. The user can call the display interface through preset instructions to obtain the service recommendation area.

[0052] In the aforementioned service recommendation area, keywords corresponding to the information to be identified can be input, so that the service recommendation plan corresponding to the information to be identified can be displayed in the service recommendation area. For example, if the keywords input in the service recommendation area are Huaiyang cuisine, weekend dinner, cooking method recommendation, etc., then the service recommendation plan output in the service recommendation area can be a May Day dinner plan for relatives and friends, and the service recommendation plan can include dinner invitation copy, dish list, shopping list, cooking method and other contents.

[0053] As a method, based on the keyword, generating a service recommendation scheme corresponding to the information to be identified may include: inputting the keyword into a pre-trained service recommendation model, and obtaining the service recommendation scheme corresponding to the information to be identified output by the service recommendation model. Among them, the service recommendation model may be a ChatGPT (ChatGenerative Pre-trained Transformer) model. In an embodiment of the present application, an electronic device may call the ChatGPT model through a model calling interface. Among them, the ChatGPT model in the embodiment of the present application is pre-trained, and is used to understand the user's intention based on the input information to be identified, and output keywords corresponding to the information to be identified. Optionally, the service recommendation model may also be other neural network models that can generate corresponding service recommendation schemes based on the input keywords, which is not specifically limited here.

[0054] As another way, generating a service recommendation scheme corresponding to the information to be identified based on the keyword may include: generating a service recommendation scheme corresponding to the information to be identified based on the keyword and a preset mapping table, wherein the preset mapping table may pre-store a correspondence between the keyword and the service recommendation scheme.

[0055] After obtaining the keywords of the information to be identified, the service recommendation scheme corresponding to the keywords can be queried from the preset mapping table. Optionally, in the preset mapping table, a group of keywords can correspond to multiple service recommendation schemes. In the case where a group of keywords can correspond to multiple service recommendation schemes, the service recommendation scheme corresponding to the information to be identified can be determined based on the user's selection. Specifically, after querying multiple service recommendation schemes corresponding to the currently determined keywords, the multiple service recommendation schemes can be displayed at the same time, so that the user can select one or more service recommendation schemes from the multiple service recommendation schemes as the service recommendation schemes corresponding to the information to be identified according to their own needs.

[0056] Furthermore, when there are multiple service recommendation schemes corresponding to the currently determined keyword, the service recommendation scheme corresponding to the information to be identified can be determined from the multiple service recommendation schemes in combination with the information to be identified. Specifically, the degree of association between the information to be identified and the multiple service recommendation schemes can be calculated through a neural network model, and then the service recommendation scheme corresponding to the information to be identified can be determined from the multiple service recommendation schemes according to the respective degrees of association of the multiple service recommendation schemes. The higher the degree of association, the higher the possibility that the service recommendation scheme is the service recommendation scheme corresponding to the information to be identified.

[0057] When determining the service recommendation scheme corresponding to the information to be identified from multiple service recommendation schemes based on the degree of association, the multiple service recommendation schemes can be arranged in descending order of the degree of association, so that the service recommendation scheme with the highest degree of association or the service recommendation scheme ranked in the front specified position can be used as the service recommendation scheme corresponding to the information to be identified.

[0058] Step S130: Determine a plurality of corresponding services based on the service recommendation scheme.

[0059] In the embodiment of the present application, different services can be divided into three categories, namely application services, direct services and rich information services. Among them, application services refer to third-party applications (Application, APP), and users can obtain corresponding application services by clicking on the icon corresponding to the APP on the UI. Usually, each application service can also include multiple sub-services. In the embodiment of the present application, the services that users can obtain and use with one click in these sub-services are called direct services. In addition to the sub-services included in these application services belonging to direct services, direct services can also include some services that can be used by clicking without downloading and installing, such as ride code services. Users can obtain the corresponding direct service by clicking on the icon corresponding to the direct service. The direct service is a point-and-use service. Unlike application services and direct services, which have corresponding icons, rich information services do not have corresponding icons. Rich information services refer to services that directly display information. Rich information services are used to provide information display services to users. Users can obtain information by browsing rich information services.

[0060] When determining the corresponding multiple services based on the service recommendation scheme, the multiple services can be at least one of the three types of services mentioned above, that is, the multiple services can all be application services or direct services or rich information services; or, some of the multiple services can be application services, and some of the services can be direct services; or, some of the multiple services can be application services, and some of the services can be rich information services; or, some of the multiple services can be rich information services, and some of the services can be direct services; or, some of the multiple services can be application services, some of the services can be direct services, and some of the services can be rich information services, and some of the services can be direct services, etc.

[0061] Furthermore, a type of service may include one or more services, or may include zero services, which is not specifically limited here.

[0062] As a method, determining the corresponding multiple services based on the service recommendation scheme can be understood as splitting the service recommendation scheme into multiple services, each service being used to implement some steps in the service recommendation scheme. Among them, when splitting the service recommendation scheme into multiple services, the service recommendation scheme can be split into multiple services according to the preset information output rules. Among them, the preset information output rules are pre-set rules for outputting multiple services. For example, the preset information output rules can output multiple services according to the information items of the service recommendation scheme. Exemplarily, if the service recommendation scheme consists of information items such as dinner invitation copy, menu list, shopping list, and preparation method, when splitting the service recommendation scheme into multiple services, the service recommendation scheme can be split into 4 services according to the aforementioned 4 types of information items, and one information item corresponds to one service.

[0063] Optionally, in the embodiments of the present application, the service can also be understood as a ubiquitous service. Among them, the ubiquitous service is to provide active service experience around people's life scenes and behavioral habits through powerful perception and interaction capabilities and computing and decision-making capabilities. Such service experience is called "user-centric ubiquitous service".

[0064] Step S140: Generate a plurality of cards corresponding to the plurality of services, wherein different services correspond to different cards.

[0065] In the embodiment of the present application, a card is a form of information presented by an electronic device to a user, and may include pictures, text, links, controls, and other information related to the same topic, such as weather cards, stock cards, and news cards.

[0066] As a method, the card can also be the entrance to the application (application, APP) corresponding to the card. The user can operate the card to open the application corresponding to the card, so that the electronic device presents the interface of the application corresponding to the card to the user, so that the user can view more detailed information on the interface. Furthermore, after opening the application corresponding to the card, the user can also perform corresponding operations on the interface of the application to meet their own needs. For example, the application corresponding to the weather card is weather. The user can open the application weather by operating the weather card, so that the electronic device presents the weather interface to the user. The user can set the information displayed on the weather card, or view the weather conditions of a certain city, etc., by operating the weather interface to meet their own needs.

[0067] As another way, the card can also be the entrance to one or more services provided by the application corresponding to the card. The user can open the services provided by the application corresponding to the card by operating the card, so that the electronic device presents the service interface of the application corresponding to the card to the user.

[0068] Among them, the application can be a native application or a third-party application in the electronic device, which is not specifically limited here. Among them, the native application refers to an application that is pre-installed in the electronic device, which is an application that comes with the electronic device. When the electronic device is turned on for the first time, the desktop of the electronic device will present the icon of the native application. Third-party applications are different from native applications. Third-party applications refer to applications produced by a third party and need to be installed by the user on the electronic device. Optionally, the electronic device can be any one of a mobile phone, a tablet computer, a desktop, a laptop, a notebook computer, an ultra-mobile personal computer (Ultra-mobile Personal Computer, UMPC), a handheld computer, a netbook, a personal digital assistant (Personal Digital Assistant, PDA), a wearable electronic device, a smart watch and other devices, which is not specifically limited here.

[0069] In an embodiment of the present application, when generating multiple cards corresponding to multiple services, multiple cards corresponding to multiple services may be generated according to a preset card template. Different types of services may have different preset card templates. The card may be a ubiquitous card.

[0070] When a plurality of cards corresponding to a plurality of services are generated, the content displayed in the cards may be partial display content corresponding to each service, that is, only important information in each service may be displayed in the cards.

[0071] As a method, each service can be represented by a card of at least one size, and the card sizes corresponding to different types of services can be different, such as the size of the card representing the rich information service or the direct service is larger than the size of the card representing the application service. For example, the rich information service can be represented by a 2*2 card, and can also be represented by a 1*2 card; the direct service can be represented by a 1*2 card; and the application service can be represented by a 1*1 card.

[0072] The present application provides a card generation method, which obtains keywords corresponding to the information to be identified, then generates a service recommendation scheme corresponding to the information to be identified based on the keywords, and then determines the corresponding multiple services based on the service recommendation scheme, thereby generating multiple cards corresponding to the multiple services, wherein different services correspond to different cards. Through the above method, multiple cards that meet user needs can be generated, thereby reducing the user's planning time and improving planning efficiency and satisfaction.

[0073] See also Figure 2 , a card generation method provided in an embodiment of the present application is applied to an electronic device, the method comprising:

[0074] Step S210: Obtain keywords corresponding to the information to be identified.

[0075] As a method, before obtaining the keywords corresponding to the information to be identified, the step further includes: obtaining the information to be identified.

[0076] The information to be identified may be obtained in a variety of ways, including: obtaining the information to be identified through a space-time hole; or, obtaining the information to be identified through an intent recognition control; or, obtaining the information to be identified through an intent input control; or, obtaining the information to be identified through a microphone.

[0077] As one of the ways, in the method of obtaining the information to be identified through the space-time hole, the space-time hole is a concept built around the front camera of the electronic device. The space-time hole is an invisible view set in the front camera area of ​​the electronic device for receiving drag events. Among them, the drag event refers to the event that the user selects text from any page that supports dragging text, such as a web page, Weibo, public account, text message, email, etc., and drags it to the space-time hole. Exemplarily, dragging the information to be identified to the space-time hole can be as follows Figure 3 and Figure 4 As shown, Figure 3 This is a schematic diagram of selecting text from a Weibo post. Figure 4 A diagram showing dragging the selected text to a space-time hole. The space-time hole can be set at Figure 4 The area where the front camera of the electronic device is located, that is, Figure 4The area included in the dotted box.

[0078] After dragging the selected text to the space-time hole, the electronic device obtains the information to be identified.

[0079] As another method, in the method of obtaining the information to be identified through the intent recognition control, the intent recognition control is a functional component of an application in the sidebar of the electronic device. The user can select text and copy it on any page such as WeChat, web pages, Weibo, public accounts, text messages, emails, etc., open the "Xiaobu Screen Recognition" application in the sidebar, and then find the intent recognition control, so that the intent recognition control can be clicked to obtain the copied text to obtain the information to be identified. Exemplarily, the sidebar of the electronic device can be Figure 5 The area included in the dotted box in the sidebar of the electronic device may include multiple applications. Figure 5 After clicking the "Xiaobu Screen Recognition" application in the sidebar shown in the figure, multiple functional components corresponding to "Xiaobu Screen Recognition" will be displayed, including functional components such as "text extraction", "image recognition" and "intention recognition". For example, the schematic diagram of multiple functional components corresponding to "Xiaobu Screen Recognition" can be as follows: Figure 6 shown.

[0080] As another method, in the method of obtaining the information to be identified through the intention input control, the intention input control can be an intention input dialog box. Specifically, the user can enter the information input interface, and then the user can enter the information to be identified through the intention input control in the information input interface, or the user can select the information to be identified from the multiple keywords to be selected displayed in the information input interface. Exemplarily, the schematic diagram of the information input interface can be as follows Figure 7 As shown, in Figure 7 The interface shown in the figure includes an intention input control 201 and an intention selection area 202. A variety of keywords to be selected can be displayed in the intention selection area 202. The user can select some keywords from the multiple keywords to be selected as the information to be identified according to needs; or, the user can also input the information to be identified through the intention input control 201.

[0081] Step S220: Based on the keyword, determine the prompt information corresponding to the information to be identified.

[0082] In an embodiment of the present application, the prompt information is a prompt script designed based on keywords. The prompt script can be understood as a prompt used to allow the ChatGPT model to enter a certain dialogue mode. In the ChatGPT model, the prompt script generally refers to an input text paragraph or phrase, which serves as the starting point or guide for generating the model output. The prompt script can be a question, a text description, a dialogue or any form of text input. The ChatGPT model will generate the corresponding output text based on the context and semantic information provided by the prompt script. The ChatGPT model in the embodiment of the present application is the aforementioned model for generating service recommendation solutions.

[0083] Different scenarios correspond to different prompt messages.

[0084] For example, in the party planning scenario, the prompt information may be:

[0085] You are an AI assistant. Your task is to understand and infer the user's intention based on the user's input or instructions, and give some orderly and reasonable service process recommendations accordingly. The types of services include only the following six:

[0086] 1. Keywords: Extract keyword information including specific time and cuisine from the input content, such as "Hui cuisine, New Year's Eve dinner, cooking method recommendation";

[0087] 2. Theme title: dinner party plan based on time and personnel relationship;

[0088] 3. Dinner invitation: Give a brief invitation based on the information provided by the keywords;

[0089] 4. Menu: Recommend 3 or 4 dishes based on the information provided by the keyword;

[0090] 5. Shopping list: Make a list of all ingredients and seasonings for dishes;

[0091] 6. Preparation method: Preparation steps for the menu.

[0092] In the travel planning scenario, the prompt information can be:

[0093] You are a rich travel guide. Your task is to give reasonable service recommendations based on the user's input of the origin and destination. There are three scenarios for the destination: domestic long-distance travel, domestic surrounding travel, and international travel:

[0094] (1) Domestic long-distance travel:

[0095] Transportation Guide: Recommend reasonable transportation methods such as bus, airline, train and high-speed rail;

[0096] Note: Dress according to weather conditions, bring items and other issues;

[0097] Attractions recommendation: Destination attractions recommendation and tour routes;

[0098] Food recommendation: local specialties;

[0099] (2) International Travel:

[0100] Visa application: the information required for the visa application process at the destination, as well as the visa duration and required conditions;

[0101] Air tickets: Recommended air ticket guide to choose the nearest airport and choose the best time based on the time difference between the origin and destination;

[0102] Accommodation: A platform where local accommodation can be booked;

[0103] Attractions recommendation: Destination attractions recommendation and tour routes;

[0104] Food recommendation: local specialties;

[0105] (3) Domestic tours:

[0106] Transportation Guide: For local tours, you can depart and return on the same day. We will provide suggestions on self-driving or public transportation and travel time based on the time.

[0107] Attractions recommendation: Destination attractions recommendation and tour routes;

[0108] Food recommendation: local specialties.

[0109] Of course, the above prompt information is just two examples. The prompt information corresponding to the party planning scenario and the travel planning scenario can also be other information, which is not specifically limited here.

[0110] As a method, prompt information corresponding to different scenes can be preset, and then the current scene can be determined based on the keywords corresponding to the current information to be identified, and then the prompt information corresponding to the current scene can be determined.

[0111] Step S230: Based on the prompt information and the keywords, a service recommendation scheme corresponding to the information to be identified is generated.

[0112] In the embodiment of the present application, after the prompt information and keywords corresponding to the information to be identified are determined, a service recommendation scheme corresponding to the information to be identified can be generated based on the prompt information and keywords corresponding to the information to be identified.

[0113] As one approach, when generating a service recommendation scheme corresponding to the information to be identified based on the prompt information and the keywords, the service recommendation scheme may be generated according to the composition rule of the prompt information and the information to be identified.

[0114] For example, in the party planning scenario, the prompt message is: You are an AI assistant. Your task is to understand and infer the user's intention based on the user's input or instructions, and give some orderly and reasonable service process recommendations accordingly. The types of services include only the following six:

[0115] 1. Keywords: Extract keyword information including specific time and cuisine from the input content, such as "Hui cuisine, New Year's Eve dinner, cooking method recommendation";

[0116] 2. Theme title: dinner party plan based on time and personnel relationship;

[0117] 3. Dinner invitation: Give a brief invitation based on the information provided by the keywords;

[0118] 4. Menu: Recommend 3 or 4 dishes based on the information provided by the keyword;

[0119] 5. Shopping list: Make a list of all ingredients and seasonings for dishes;

[0120] 6. Preparation method: Preparation steps for the menu.

[0121] The information to be identified is: May Day is coming soon, and I plan to invite some relatives and friends to my home for a dinner party. The cuisine will mainly be Huaiyang cuisine. Do you think it's okay?

[0122] The corresponding service recommendation solution generated can be:

[0123] 1.Keywords: Huaiyang cuisine, weekend gathering, recommended cooking methods.

[0124] 2. Theme title: May Day dinner plan for relatives and friends.

[0125] 3. Dinner invitation: A cup of wine in the spring breeze, a lamp under the rainy night for ten years. Come on, old friends, come to my house on May 1st, let’s drink together and reminisce about the past.

[0126] 4. Menu: beef tenderloin with Hangzhou pepper and white-robed shrimp.

[0127] 5. Shopping list: Ingredients: Hangzhou pepper, beef tenderloin, green onion, ginger, shrimp, eggs; Seasoning: light soy sauce, salt, chicken essence, oyster sauce, starch.

[0128] 6. Production method:

[0129] Beef tenderloin with pepper:

[0130] - Cut the beef into thin slices, add cooking wine, salt, light soy sauce, dark soy sauce, sugar, chicken essence and starch, mix well and marinate for 10 minutes;

[0131] - Remove the seeds from the green pepper and cut it into small pieces. Chop the ginger and garlic and set aside for 5 minutes;

[0132] - Heat the pan with cold oil, add minced ginger and garlic, stir-fry until fragrant, add beef and stir-fry until it changes color for 12 minutes;

[0133] -Add green pepper and stir-fry evenly, add a small amount of water and simmer for 2 minutes;

[0134] -Finally, add chopped green onion and stir-fry evenly for 1 minute.

[0135] White robe shrimp:

[0136] -Wash the white shrimps and marinate with salt, cooking wine and starch for 10 minutes.

[0137] - Beat the eggs, add a little salt and starch, and stir evenly for 6 minutes.

[0138] -Cut the tofu skin into small pieces and cut the green garlic into sections and set aside for 5 minutes.

[0139] - Heat the pan with cold oil, add minced ginger and sauté until fragrant, then add shrimps and stir-fry until they change color for 10 minutes.

[0140] -Add tofu skin and stir-fry evenly, then add a small amount of water and simmer for 2 minutes.

[0141] - Pour in the egg liquid, stir fry evenly, add salt, light soy sauce, sugar and chicken essence to season for 3 minutes.

[0142] -Finally, add the green garlic and stir-fry evenly for 1 minute.

[0143] As another way, when generating a service recommendation scheme corresponding to the information to be identified based on the prompt information and keywords, the corresponding service recommendation scheme may also be generated according to the composition rules of the prompt information and the keywords.

[0144] For example, in the travel planning scenario, the prompt information is:

[0145] You are a rich travel guide. Your task is to give reasonable service recommendations based on the user's input of the origin and destination. There are three scenarios for the destination: domestic long-distance travel, domestic surrounding travel, and international travel:

[0146] (1) Domestic long-distance travel:

[0147] Transportation Guide: Recommend reasonable transportation methods such as bus, airline, train and high-speed rail;

[0148] Note: Dress according to weather conditions, bring items and other issues;

[0149] Attractions recommendation: Destination attractions recommendation and tour routes;

[0150] Food recommendation: local specialties;

[0151] (2) International Travel:

[0152] Visa application: the information required for the visa application process at the destination, as well as the visa duration and required conditions;

[0153] Air tickets: Recommended air ticket guide to choose the nearest airport and choose the best time based on the time difference between the origin and destination;

[0154] Accommodation: A platform where local accommodation can be booked;

[0155] Attractions recommendation: Destination attractions recommendation and tour routes;

[0156] Food recommendation: local specialties;

[0157] (3) Domestic tours:

[0158] Transportation Guide: For local tours, you can depart and return on the same day. We will provide suggestions on self-driving or public transportation and travel time based on the time.

[0159] Attractions recommendation: Destination attractions recommendation and tour routes;

[0160] Food recommendation: local specialties.

[0161] If the keyword is: Beijing to the United States, then the corresponding service recommendation solution can be:

[0162] Visa application: You need to apply for a tourist visa to the United States. When applying, you need to provide your passport, visa application form, photo and other information. The visa period is generally 6 months to 1 year, and you need to meet financial, work, family and other conditions;

[0163] Air tickets: It is recommended to depart from Beijing Capital International Airport or Tianjin Binhai International Airport. Choose the best time based on the time difference. Recommended air ticket guides include Ctrip, Qunar and other platforms;

[0164] Accommodation: You can book local accommodation on platforms such as Booking and Airbnb. It is recommended to book in advance;

[0165] Recommended attractions: There are many tourist attractions in the United States. We recommend the Statue of Liberty in New York, the Golden Gate Bridge in San Francisco, Las Vegas and other famous attractions. The tour route can be arranged according to personal preferences and time.

[0166] Food recommendation: The United States has a rich variety of special foods, such as hamburgers, barbecue, grilled chicken wings, etc., and there are also various international cuisines to choose from.

[0167] Step S240: Determine a plurality of corresponding services based on the service recommendation scheme.

[0168] In the embodiment of the present application, when determining the corresponding multiple services based on the service recommendation scheme, a corresponding number of services can be generated according to the number of services included in the prompt information. For example, in the party planning scenario, the prompt information includes 6 types of services, so when determining the corresponding multiple services based on the service recommendation scheme, 6 services can be determined.

[0169] Step S250: Generate multiple cards corresponding to the multiple services, wherein different services correspond to different cards.

[0170] A card generation method provided in the present application can generate multiple cards that meet user needs, thereby reducing the user's planning time and improving planning efficiency and satisfaction.

[0171] See also Figure 8 , a card generation method provided in an embodiment of the present application is applied to an electronic device, the method comprising:

[0172] Step S310: input the information to be identified into a pre-trained intention recognition model, and obtain keywords corresponding to the information to be identified output by the intention recognition model.

[0173] In an embodiment of the present application, the pre-trained intent recognition model may be a ChatGPT model, which is used to output keywords corresponding to the information to be recognized based on the input information to be recognized. The intent recognition model may be called through a corresponding calling interface, and the calling interfaces of ChatGPT models for different purposes may be different.

[0174] Optionally, the intent recognition model may also be a natural language understanding (NLU) model.

[0175] In the embodiment of the present application, after determining the keywords corresponding to the information to be identified, the keywords can be displayed, for example, Fig. 9 As shown, in Fig. 9 In the process, the extracted keywords are displayed in the form of a pop-up window, and the pop-up window may also include a "one-click copy" component and a "generate service" component, wherein the "one-click copy" component is used to copy the keywords, and the "generate service" component is used to generate corresponding service recommendation solutions.

[0176] Step S320: Based on the keyword, determine the prompt information corresponding to the information to be identified.

[0177] Step S330: input the prompt information and the keywords into a pre-trained service recommendation model, and obtain a service recommendation solution corresponding to the information to be identified output by the service recommendation model.

[0178] In an embodiment of the present application, after the prompt information and keywords corresponding to the information to be identified are determined, the prompt information and the keywords can be input into the service recommendation model together, and then the service recommendation model can output the corresponding service recommendation plan.

[0179] For example, in a party planning scenario, the input prompt information is the prompt information in the above embodiment; the input keywords are: Huaiyang cuisine, weekend party, cooking method recommendation; the service recommendation model outputs:

[0180] out:

[0181] {

[0182] "title":"Huaiyang cuisine, weekend gatherings, recommended recipes",

[0183] "topic":"May Day Friends Dinner Plan",

[0184] "Invitation":"A cup of wine in the spring breeze, a lamp for ten years in the rain, come on, old friends, come to my house on May 1st, drink together and reminisce about the past.",

[0185] "recipes":{"Ingredients":["Hangzhou pepper","Beef fillet","Scallion","Ginger","Shrimp","Egg"],"seasonings":["Light soy sauce","Salt","Chicken bouillon","Oyster sauce","Starch"]},"products":[{"name":"Hangzhou pepper beef fillet","step":[{"content":"Cut the beef into thin slices, add cooking wine, salt, light soy sauce, dark soy sauce, sugar, chicken bouillon and starch, mix well and marinate;","time":"600"},{"content":"Remove the seeds from the green pepper and cut it into small pieces, add the ginger , mince garlic and set aside;","time":"150"},{"content":"Heat the pan with cold oil, add minced ginger and garlic, stir-fry until fragrant, add beef and stir-fry until it changes color;","time":"720"},{"content":"Add green pepper and stir-fry evenly, add a small amount of water and simmer","time":"120"},{"content":"Finally, add chopped green onion and stir-fry evenly. ","time":"60"}],"introduction":"Beef tenderloin with pepper is a traditional dish in Hangzhou, Zhejiang, China. It is mainly made of beef and green pepper, and has a fresh and spicy taste. . "},{"name":"White robe shrimp","step":[{"content":"Wash the white robe shrimp, marinate with salt, cooking wine and starch;","time":"600"},{"content":"Break the eggs, add a little salt and starch, and stir evenly;","time":"360"},{"content":"Cut the tofu skin into small pieces, and cut the green garlic into sections for later use;","time":"300"},{"content":"Heat the pan with cold oil, add the minced ginger and stir-fry until fragrant, add the shrimp and stir-fry until it changes color","time":"600"},{"c ontent":"Add tofu skin and stir-fry evenly, add a small amount of water and simmer;","time":"120"},{"content":"Pour in egg liquid, stir-fry evenly, add salt, soy sauce, sugar, and chicken essence to season;","time":"180"},{"content":"Finally, add green garlic and stir-fry evenly;","time":"60"}],"introduction":"White robe shrimp is a traditional dish in Guangdong, China. It is mainly composed of shrimp and egg white. The outer layer is coated with starch and fried until golden brown. It has a crispy taste and is served with sweet and sour sauce or other sauces. "

[0186] }]

[0187] }"

[0188] Another exemplary example:

[0189] In the travel planning scenario, the input prompt information is the prompt information in the above embodiment. If the input keyword is: Beijing to the United States; the service recommendation model outputs:

[0190] out:

[0191] {"visa":"You need to apply for a tourist visa to the United States. When applying, you need to provide your passport, visa application form, photo and other information. The visa period is generally 6 months to 1 year, and you need to meet financial, work, family and other conditions.",

[0192] "traffic":"It is recommended to depart from Beijing Capital International Airport or Tianjin Binhai International Airport, and choose the best time according to the time difference. Recommended air ticket guides include Ctrip, Qunar and other platforms.",

[0193] "stay":"You can book local accommodation on platforms such as Booking and Airbnb. It is recommended to book in advance.",

[0194] "attractions":"There are many tourist attractions in the United States. We recommend the Statue of Liberty in New York, the Golden Gate Bridge in San Francisco, Las Vegas and other famous attractions. The tour route can be arranged according to personal preferences and time.",

[0195] "specialties":"The United States has a wealth of specialties, such as hamburgers, barbecue, grilled chicken wings, etc., and there are also various international cuisines to choose from.",

[0196] "type":"International Tour"

[0197] }

[0198] For example, if the input keyword is: Nanjing to Changzhou, the service recommendation model outputs:

[0199] out:

[0200] {"traffic":"It is recommended to drive there, which takes about 1.5 hours; or take the high-speed rail, which takes about 30 minutes.","attractions":"Changzhou Dinosaur Park, Tianning Temple, Hongmei Park, Bell Tower and other attractions are worth visiting. Suggested tour route: first visit Changzhou Dinosaur Park, then go to Tianning Temple and Hongmei Park, and finally visit the Bell Tower.","specialties":"Changzhou's specialties include Jinling duck, sweet and sour fish, glutinous rice lotus root, etc., which are recommended to taste.",

[0201] "type":"Domestic Tour"

[0202] }

[0203] For example, if the input keyword is: Shanghai to Hainan, the service recommendation model outputs:

[0204] out:{"traffic":"It is recommended to take a plane, as there are more flights and the time is short; you can also take the high-speed rail, but it will take longer.",

[0205] "attractions":"Famous attractions in Hainan include Boundary Island, Tianya Haijiao, Yalong Bay, etc. The recommended tour route is: Haikou-Sanya-Boundary Island-Yalong Bay-Tianya Haijiao.",

[0206] "specialties":"Hainan's specialties include coconut chicken, Wenchang chicken, Hainan rice noodles, etc.",

[0207] "precautions":"Pay attention to sun protection and avoid heat stroke; pay attention to food hygiene and avoid food poisoning.",

[0208] "type":"Domestic long-distance travel"

[0209] }

[0210] After the service recommendation model outputs the service recommendation plan, the service recommendation plan can be displayed. For example, in the party planning scenario, the generated service recommendation plan can be as follows: Fig.10 As shown, in Fig.10 It can include party invitations, menu lists, shopping lists, cooking methods and other services; in the travel planning scenario, the generated service recommendation solutions can be as follows Fig.11 As shown, in Fig.11 This can include services such as weather, item preparation, itinerary planning, transportation, restaurant recommendations, etc.

[0211] Step S340: Determine a plurality of corresponding services based on the service recommendation scheme.

[0212] In the embodiment of the present application, after the corresponding service recommendation scheme is generated, the service chain in the service recommendation scheme can be identified, and the corresponding ubiquitous service can be associated to obtain the corresponding multiple services.

[0213] Step S350: Generate multiple cards corresponding to the multiple services, wherein different services correspond to different cards.

[0214] For example, in the party planning scenario, based on Fig.10 The weekend family dinner plan shown can generate cards corresponding to the "dinner invitation", "dish list", "shopping list" and "preparation method" services, such as Fig.12 shown.

[0215] In the travel planning scenario, based on Fig.11The surrounding travel recommendation shown can generate cards corresponding to the services of "weather", "item preparation", "trip planning", "transportation" and "restaurant recommendation", such as Fig.13 shown.

[0216] Step S360: In response to the operation on the card, enter the application corresponding to the card, where different cards correspond to different applications.

[0217] In the embodiment of the present application, different cards may correspond to different applications, and when an operation acting on a card corresponding to an application is detected, the application corresponding to the card may be entered. For example, when an operation acting on a "shopping list" card is detected, the application may be redirected to the shopping cart of the shopping app, such as Fig.14 As shown in the figure, when an operation on the "dish list" card is detected, you can jump to the note to view it. The operation can be a click operation or a slide operation, which is not specifically limited here.

[0218] As another way, in response to the operation on the card, all the to-be-displayed information corresponding to the card is displayed.

[0219] Due to the size limitation of the card, not all information can be displayed in the card. Therefore, when you need to view all the information to be displayed, you can jump to view all the information to be displayed by clicking on the card. For example, when an operation on the "dinner invitation" card is detected, you can jump to display all the invitation texts, such as Fig.15 shown.

[0220] A card generation method provided in the present application can generate multiple cards that meet user needs, thereby reducing the user's planning time and improving planning efficiency and satisfaction; at the same time, through operations acting on different cards, information related to different cards can be displayed differently, thereby improving the diversity of card display.

[0221] See also Fig.16 , a card generation method provided in an embodiment of the present application is applied to an electronic device, the method comprising:

[0222] Step S410: Obtain keywords corresponding to the information to be identified.

[0223] Step S420: Based on the keywords, a service recommendation scheme corresponding to the information to be identified is generated.

[0224] Step S430: Determine a plurality of corresponding services based on the service recommendation scheme.

[0225] Step S440: Generate multiple cards corresponding to the multiple services, where different services correspond to different cards.

[0226] Step S450: displaying the plurality of cards in sequence according to a preset order.

[0227] In the embodiment of the present application, the preset order may be the execution order of multiple services or the time order of the entire service recommendation plan.

[0228] After the corresponding multiple cards are generated, the corresponding cards can be displayed at the corresponding time point according to the preset order.

[0229] Furthermore, in the embodiment of the present application, the card can be displayed on the desktop or negative one screen of the electronic device, which is not specifically limited here. Among them, the negative one screen refers to sliding the screen to the right on the main screen of the electronic device until sliding to the user interface of the leftmost split screen. The negative one screen can be used to place some quick service functions and notification messages, such as global search, quick entry to a certain page of the application (payment code, WeChat, etc.), instant information and reminders (express information, expenditure information, commuting conditions, taxi travel information, schedule information, etc.) and attention to dynamics (football stands, basketball stands, stock information, etc.).

[0230] Multiple cards may be included in the desktop or the negative one screen. The cards included in the desktop are different from the cards included in the negative one screen. The difference here may be at least one of different card types, different card displayed contents, different card corresponding applications, different cards corresponding services, etc.

[0231] Step S460: In response to the operation on the card, a card to be assembled corresponding to the card is generated.

[0232] In the embodiment of the present application, the card to be assembled is a card associated with the currently operated card, for example, the currently operated card is a recipe card, and when it is detected that the start cooking in the recipe card is clicked, a countdown card can be automatically generated. Among them, the countdown card is the card to be assembled.

[0233] Step S470: displaying the card and the card to be assembled.

[0234] The card in the embodiment of the present application refers to the card operated in step S460. When displaying the operated card and the card to be assembled, the operated card and the card to be assembled can be displayed in the same interface, for example, Fig.17 Of course, the operated cards and the cards to be assembled can also be displayed in a stacked manner, which is not specifically limited here.

[0235] As another way, a target card is displayed, where the target card is a card obtained by fusing the card and the card to be assembled.

[0236] Of course, when displaying the operated cards and the cards to be assembled, the operated cards and the cards to be assembled can be merged first, and then the merged cards can be displayed. Among them, when the operated cards and the cards to be assembled are merged, they can be merged according to a preset fusion rule.

[0237] The card generation method provided in this application can better explore user needs, thereby better serving user operations and enhancing service capabilities.

[0238] See also Fig.18 , an embodiment of the present application provides a card generating device 500, the device 500 comprising:

[0239] The keyword acquisition unit 510 is used to acquire keywords corresponding to the information to be identified.

[0240] As a method, the keyword acquisition unit 510 is specifically used to input the information to be identified into a pre-trained intention recognition model, and obtain the keywords corresponding to the information to be identified output by the intention recognition model.

[0241] The service generating unit 520 is configured to generate a service recommendation scheme corresponding to the information to be identified based on the keyword.

[0242] As a method, the service generation unit 520 is specifically used to determine the prompt information corresponding to the information to be identified based on the keyword; and generate a service recommendation solution corresponding to the information to be identified based on the prompt information and the keyword.

[0243] The service determination unit 530 is configured to determine a plurality of corresponding services based on the service recommendation scheme.

[0244] The card generating unit 540 is configured to generate a plurality of cards corresponding to the plurality of services, wherein different services correspond to different cards.

[0245] See also Fig.19 , the device 500 further includes:

[0246] The operation unit 550 is used to respond to the operation on the card and enter the application corresponding to the card, where different cards correspond to different applications; or, respond to the operation on the card and display all the to-be-displayed information corresponding to the card.

[0247] As a method, the operation unit 550 is also used to display the multiple cards in sequence according to a preset order; generate a card to be assembled corresponding to the card in response to an operation acting on the card; and display the card and the card to be assembled.

[0248] As another way, the operation unit 550 is also used to display a target card, where the target card is a card obtained by merging the card and the card to be assembled.

[0249] The information acquisition unit 560 is used to acquire the information to be identified through a spatiotemporal hole; or, to acquire the information to be identified through an intention recognition control; or, to acquire the information to be identified through an intention input control; or, to acquire the information to be identified through a microphone.

[0250] It should be noted that the device embodiment in the present application corresponds to the aforementioned method embodiment. The specific principles in the device embodiment can be found in the contents of the aforementioned method embodiment and will not be repeated here.

[0251] The following will be combined Fig. 20 An electronic device provided by the present application is described.

[0252] See also Fig. 20 Based on the above-mentioned card generation method and device, the embodiment of the present application also provides another electronic device 800 that can execute the above-mentioned card generation method. The electronic device 800 includes one or more (only one is shown in the figure) processors 802, a memory 804 and a network module 806 that are coupled to each other. Among them, the memory 804 stores a program that can execute the content of the above-mentioned embodiment, and the processor 802 can execute the program stored in the memory 804.

[0253] Among them, the processor 802 may include one or more processing cores. The processor 802 uses various interfaces and lines to connect various parts of the entire electronic device 800, and executes various functions and processes data of the electronic device 800 by running or executing instructions, programs, code sets or instruction sets stored in the memory 804, and calling data stored in the memory 804. Optionally, the processor 802 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 802 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing display content; and the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 802, but may be implemented separately through a communication chip.

[0254] The memory 804 may include a random access memory (RAM) or a read-only memory (ROM). The memory 804 may be used to store instructions, programs, codes, code sets or instruction sets. The memory 804 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the following various method embodiments, etc. The data storage area may also store data (such as a phone book, audio and video data, chat record data) created by the electronic device 800 during use.

[0255] The network module 806 is used to receive and send electromagnetic waves, realize the mutual conversion between electromagnetic waves and electrical signals, so as to communicate with a communication network or other devices, such as communicating with electronic devices. The network module 806 may include various existing circuit elements for performing these functions, such as antennas, radio frequency transceivers, digital signal processors, encryption / decryption chips, user identity modules (SIM) cards, memories, etc. The network module 806 may communicate with various networks such as the Internet, corporate intranets, wireless networks, or communicate with other devices via wireless networks. The above-mentioned wireless networks may include cellular telephone networks, wireless local area networks, or metropolitan area networks. For example, the network module 806 may exchange information with a base station.

[0256] Please refer to Fig.21 , which shows a structural block diagram of a computer-readable storage medium provided in an embodiment of the present application. The computer-readable storage medium 900 stores program codes, which can be called by a processor to execute the method described in the above method embodiment.

[0257] The computer-readable storage medium 900 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read-only memory), an EPROM, a hard disk, or a ROM. Optionally, the computer-readable storage medium 900 includes a non-transitory computer-readable storage medium. The computer-readable storage medium 900 has storage space for program code 910 that performs any method step in the above method. These program codes can be read from or written to one or more computer program products. The program code 910 can be compressed, for example, in an appropriate form.

[0258] The present application provides a card generation method, device, electronic device and storage medium, which obtains keywords corresponding to the information to be identified, then generates a service recommendation scheme corresponding to the information to be identified based on the keywords, and then determines the corresponding multiple services based on the service recommendation scheme, thereby generating multiple cards corresponding to the multiple services, wherein different services correspond to different cards. Through the above method, multiple cards that meet user needs can be generated, thereby reducing the user's planning time and improving planning efficiency and satisfaction.

[0259] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation modes, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the present invention and the claims, all of which are within the protection of the present invention.

Claims

1. A card generation method, characterized in that: The method comprises: Obtain keywords corresponding to the information to be identified; Based on the keywords, generating a service recommendation scheme corresponding to the information to be identified; Based on the service recommendation scheme, determining a corresponding plurality of services; A plurality of cards corresponding to the plurality of services are generated, wherein different services correspond to different cards.

2. The method according to claim 1, characterized in that After generating a plurality of cards corresponding to the plurality of services, the method further includes: In response to the operation on the card, the application corresponding to the card is entered, and different cards correspond to different applications; or, In response to the operation on the card, all the to-be-displayed information corresponding to the card is displayed.

3. The method according to claim 2, characterized in that The method further comprises: Displaying the plurality of cards in sequence according to a preset order; In response to an operation on the card, generating a card to be assembled corresponding to the card; The cards and the cards to be assembled are displayed.

4. The method according to claim 3, characterized in that The displaying of the cards and the cards to be assembled comprises: A target card is displayed, where the target card is a card obtained by fusing the card and the card to be assembled.

5. The method according to claim 1, characterized in that The generating, based on the keyword, a service recommendation scheme corresponding to the information to be identified includes: Based on the keyword, determining prompt information corresponding to the information to be identified; Based on the prompt information and the keywords, a service recommendation scheme corresponding to the information to be identified is generated.

6. The method according to claim 1, characterized in that Before obtaining the keywords corresponding to the information to be identified, the following step is also included: Acquire the information to be identified through the space-time hole; or, Acquire the information to be identified through the intention identification control; or, Acquire the information to be identified through the intention input control; or, The information to be identified is obtained through a microphone.

7. The method according to claim 1 or 6, characterized in that: The step of obtaining keywords corresponding to the information to be identified includes: The information to be identified is input into a pre-trained intention recognition model, and keywords corresponding to the information to be identified output by the intention recognition model are obtained.

8. A card generating device, characterized in that: The device comprises: A keyword acquisition unit, used to acquire keywords corresponding to the information to be identified; A service generating unit, configured to generate a service recommendation scheme corresponding to the information to be identified based on the keyword; A service determination unit, configured to determine a plurality of corresponding services based on the service recommendation scheme; The card generating unit is used to generate a plurality of cards corresponding to the plurality of services, wherein different services correspond to different cards.

9. An electronic device, characterized in that: The method comprises one or more processors; one or more programs are stored in the memory and configured to execute the method according to any one of claims 1 to 7 by the one or more processors.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program code, wherein when the program code is executed by a processor, the method according to any one of claims 1 to 7 is executed.

Images