A template information display method and device

By detecting the matching of the characters entered by the user and the template wake-up characters, and displaying the template selection box, the problem of the big model platform understanding user information deviation is solved, and accurate information acquisition is achieved in specific scenarios, improving response accuracy and user experience.

CN117539579BActive Publication Date: 2024-12-31BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202311553284.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-11-20
Publication Date
2024-12-31
Estimated Expiration
2043-11-20

AI Technical Summary

Technical Problem

The big model platform has deviations when understanding the user's input information, resulting in inaccurate responses and inaccurate information that cannot accurately obtain the information expected by users.

Method used

By detecting the matching of the characters entered by the user and the preset template wake-up characters, if it matches, the template selection box for multiple target input templates is displayed. The user can select the appropriate template to guide the input information, ensuring that the big model platform obtains in specific interactive scenarios Expected information.

Benefits of technology

It improves the accuracy of the response of the big model platform to user input, ensures that the big model can obtain the correct information in specific scenarios, and improves user experience and interaction efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117539579B_ABST
    Figure CN117539579B_ABST
Patent Text Reader

Abstract

The present disclosure provides a template information display method and device, which relates to the field of computer technology, and in particular to the field of data processing. The specific implementation scheme is: obtaining the input characters input by the user in the interactive interface when the user uses the interactive service provided by the large model platform; detecting whether the input characters are the same as the preset template wake-up characters; when the input characters are the same as the template wake-up characters, displaying a template selection box containing template information of multiple target input templates to the user in the interactive interface. The large model platform involved in the template information display scheme provided in the embodiment of the present disclosure is a platform designed based on a large model, which can be used for conversational communication with users. The above-mentioned large model can be a pre-trained model, and the above-mentioned large model can be a large language model. Applying the template information display scheme provided in the embodiment of the present disclosure can improve the accuracy of the large model platform in responding to users.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, in particular to the field of data processing technology, and more particularly to a template information display method and device. Background Art

[0002] The big model platform provides interactive services and can interact with users based on the big model, such as conversational communication and answering questions. For example, the medical big model platform provides health interaction services. Users can input health questions into the platform, and the platform can respond to the users’ questions and provide users with health assistance information, etc. The above-mentioned big model is a pre-trained model, and the above-mentioned big model can be a big language model.

[0003] However, due to the limited interactive capabilities of the current big model, the meaning of the user input information understood by the big model may deviate from the meaning the user actually wants to express, making it difficult for the big model platform to make a correct response to the user. Summary of the invention

[0004] The present disclosure provides a template information display method and device.

[0005] According to one aspect of the present disclosure, a template information display method is provided, comprising:

[0006] Obtaining input characters entered by the user in the interactive interface when the user uses the interactive service provided by the big model platform;

[0007] Detecting whether the input character is the same as a preset template wake-up character;

[0008] When the input character is the same as the template wake-up character, a template selection box containing template information of multiple target input templates is displayed to the user on the interactive interface, wherein each of the target input templates is a template set for an interactive scenario between the large model platform and the user, and guides the user to input information.

[0009] According to another aspect of the present disclosure, a template information display device is provided, comprising:

[0010] A character acquisition module is used to acquire input characters entered by the user in the interactive interface when the user uses the interactive service provided by the large model platform;

[0011] A character detection module, used to detect whether the input character is the same as a preset template wake-up character;

[0012] An information display module is used to display a template selection box containing template information of multiple target input templates to the user in the interactive interface when the input character is the same as the template wake-up character, wherein each of the target input templates is a template set for an interactive scenario for interaction between the large model platform and the user, and guides the user to input information.

[0013] According to another aspect of the present disclosure, there is provided an electronic device, comprising:

[0014] at least one processor; and

[0015] a memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned template information display method.

[0017] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the above-mentioned template information display method.

[0018] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, wherein the computer program implements the above-mentioned template information display method when executed by a processor.

[0019] As can be seen from the above, when the scheme provided by the embodiment of the present disclosure is used to display template information, if it is detected that the input character entered by the user is a template wake-up character, a template selection box containing template information of multiple target input templates is displayed to the user in the interactive interface.

[0020] Since each target input template is set for an interactive scenario between the big model platform and the user, and the target input template is used to guide the user to input information, when the user selects the template information in the template selection box, the big model platform can determine the input template corresponding to the template information selected by the user, and then use the input template to guide the user to input the information that the big model platform expects to obtain in the interactive scenario corresponding to the input template. In this way, the big model platform can obtain the information it expects to obtain and can make an accurate response to the user. Therefore, the template information display scheme provided by the embodiment of the present disclosure can improve the accuracy of the big model platform's response to the user.

[0021] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0023] Figure 1 A schematic diagram of a flow chart of a first template information display method provided in an embodiment of the present disclosure;

[0024] Figure 2a A schematic diagram of a first interactive interface provided in an embodiment of the present disclosure;

[0025] Figure 2b A schematic diagram of a second interactive interface provided by an embodiment of the present disclosure;

[0026] Figure 3 A schematic diagram of a flow chart of a second template information display method provided in an embodiment of the present disclosure;

[0027] Figure 4a A schematic diagram of a third interactive interface provided in an embodiment of the present disclosure;

[0028] Figure 4b A schematic diagram of a fourth interactive interface provided in an embodiment of the present disclosure;

[0029] Figure 4c A fifth interactive interface schematic diagram provided in an embodiment of the present disclosure;

[0030] Figure 4d A sixth interactive interface schematic diagram provided in an embodiment of the present disclosure;

[0031] Figure 4e A seventh interactive interface schematic diagram provided in an embodiment of the present disclosure;

[0032] Figure 4f A schematic diagram of an eighth interactive interface provided by an embodiment of the present disclosure;

[0033] Figure 5 A schematic diagram of the structure of a template information display device provided in an embodiment of the present disclosure;

[0034] Figure 6 It is a block diagram of an electronic device used to implement the template information display method of the embodiment of the present disclosure. DETAILED DESCRIPTION

[0035] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0036] First, the large model platform and the interaction scenarios between the large model platform and users mentioned in the solutions provided in the embodiments of the present disclosure are explained.

[0037] The big model platform is a platform designed based on the big model. The platform is divided into two parts. One part is the interactive part that receives user information and feeds back information to the user, and the other part is the information processing part that processes information. The interactive part is deployed on the front-end terminal device, and the information processing part is deployed on the back-end server.

[0038] The front-end terminal device includes an interactive interface in which users can input information, and the large model platform can also display the results of information processing in the interactive interface.

[0039] The big model platform can be a platform used in different fields such as medical care, education or online transactions.

[0040] During the interaction between the user and the big model platform, after the user enters information in the interactive interface of the terminal device, the terminal device can send the information entered by the user to the server. After receiving the information, the server uses the big model to process the information and obtain the processing result. The server then feeds back the processing result to the terminal device. After receiving the processing result, the terminal device displays the processing result in the interactive interface, so that the user can check the processing result, thereby realizing the interaction between the user and the big model platform.

[0041] Secondly, the execution subject of the template information display solution provided by the embodiment of the present disclosure is explained.

[0042] The executor of the template information display solution provided by the embodiment of the present disclosure is the above-mentioned terminal device, which can be a portable device such as a mobile phone or a laptop computer, or a fixed device such as a desktop computer or an all-in-one computer, or an intelligent robot.

[0043] The template information display method is described in detail below through a specific embodiment.

[0044] In one embodiment of the present disclosure, see Figure 1 , a flow chart of a first template information display method is provided. In this embodiment, the method includes the following steps S101-S103.

[0045] Step S101: Obtain input characters entered by the user in the interactive interface when the user uses the interactive service provided by the large model platform.

[0046] Specifically, any one of the following three implementations may be used to obtain the input characters.

[0047] In a first implementation manner, the terminal device may detect characters contained in a character input area in the interactive interface as the above-mentioned input characters.

[0048] In the second implementation, an input method program may be installed in the terminal device, and when the user inputs information in the interactive interface, the terminal device may call the input method program and display the input area of ​​the input method in the interactive interface. In this way, when the user selects the character input area in the interactive interface and focuses the screen on the character input area, the terminal device can obtain the characters input by the user through the input area of ​​the input method.

[0049] In a third implementation, the terminal device may also be connected to a keyboard, so that when the user selects a character input area, the input characters entered by the user through the keyboard may be obtained.

[0050] In addition, the terminal device can be pre-set with a template wake-up character, or obtain the template wake-up character set by the server from the server, so that the user can be informed of the template wake-up character before the user enters the character. After the user knows the template wake-up character, when entering the character, the user can decide whether to use the input template according to his own needs. If the user needs to use the input template, the user can enter the template wake-up character.

[0051] The template wake-up characters are pre-set characters. For example, the template wake-up characters may be “ / ”, “~”, “ / / ”, “~~”, etc.

[0052] When the terminal device informs the user of the template wake-up character, the template wake-up character can be notified to the user through a variety of methods such as a pop-up window, a bubble box, and an in-station message.

[0053] For example, see Figure 2a , showing an interactive interface UI1, in Figure 2a In the interface shown, a bubble box 202 is displayed above the character input area 201, and the bubble box 202 contains prompt information, which reads: Inputting the template wake-up character " / " can wake up the input template.

[0054] Step S102: Detect whether the input character is the same as a preset template wake-up character.

[0055] Specifically, after obtaining the input character, the input character can be matched with the template wake-up character. If the input character matches the template wake-up character, it means that the input character is the same as the template wake-up character, and the input character is the template wake-up character, which also means that the user needs to use the input template. At this time, execute step S103; if the input character does not match the template wake-up character, it means that the input character is not the template wake-up character, which also means that the user does not need to use the input template.

[0056] Step S103: When the input character is the same as the template wake-up character, a template selection box containing template information of multiple target input templates is displayed to the user on the interactive interface.

[0057] Among them, each target input template is a template set for an interactive scenario between the large model platform and the user, which guides the user to input information.

[0058] The big model platform can be a platform used in a certain field, so that when users interact with the big model platform, the big model platform can provide users with interactive services in the field corresponding to the platform, and there can be multiple interactive scenarios in a field. For example, in the medical field, the interactive scenarios can include auxiliary consultation scenarios, image question and answer scenarios, image area positioning scenarios, etc. The interactive scenario in which the big model platform interacts with users can be any scenario in the field corresponding to the big model platform. In order to facilitate users to input information with the big model platform in various interactive scenarios, the big model platform can set a target input template for each interactive scenario to guide users to input the information that the big model platform expects users to input in the interactive scenario.

[0059] The template information of the target input template may include the name and identifier of the target input template, the scene name of the interaction scene corresponding to the target input template, and the like.

[0060] Specifically, the terminal device may display the template selection box to the user on the interactive interface in any of the following three implementation modes.

[0061] In the first implementation method, when the terminal device detects that the input character is a template wake-up character, it can send a request to the server to obtain the template information of the target input template. In response to the acquisition request, the server sends the template information of multiple target input templates to the terminal device. In this way, after the terminal device obtains the template information of multiple target input templates, it can generate a template selection box containing the template information of multiple target input templates, thereby displaying the template selection box to the user in the interactive interface.

[0062] In the second implementation method, a template selection box containing template information of multiple target input templates can be stored in the server, so that when the terminal device detects that the input character is a template wake-up character, it can send a request to the server to obtain the template selection box. In response to the acquisition request, the server sends the stored template selection box information to the terminal device. After the terminal device obtains the template selection box information, it can directly display the template selection box to the user on the interactive interface based on the template selection box information. In this way, there is no need for the terminal to generate the template selection box, thereby improving the efficiency of the terminal device in displaying the template selection box on the interactive interface.

[0063] In the third implementation method, during the interaction between the large model platform and the user, the terminal device can obtain the template information of multiple target input templates sent by the server before detecting whether the input character is a template wake-up character, thereby generating a template selection box containing the template information of multiple target input templates, or directly obtain the information of the template selection box sent by the server, so that when the terminal device detects that the input character is a template wake-up character, the template selection box can be directly displayed on the interactive interface.

[0064] In one embodiment of the present disclosure, a plurality of input templates may be stored in the server, and the server may select all or part of the templates from the stored input templates as target input templates.

[0065] For example, the target input template may be determined in any of the following two ways.

[0066] In the first implementation, the target input template may be determined based on at least one of the following information recorded in the large model platform:

[0067] User historical interaction information, user interest information, and historical template usage information.

[0068] Among them, the above-mentioned user historical interaction information is the interaction information when the user interacted with the big model platform in the past. For example, it can be the information input by the user in the previous interaction process, the information that the big model platform responded to the user in the previous interaction process, and so on.

[0069] The above user-interested information is the information of interest that the user inputs in the big model platform.

[0070] The above historical template information is template information of input templates used by the user in previous interaction processes.

[0071] The large model platform determines the target input template based on the above information. In fact, it can be considered that the server determines the target input template based on the above information. After determining the target input template, the server can send the information of the target input template to the terminal device, or generate a template selection box containing the template information of the target input template, thereby sending the information of the template selection box to the terminal device.

[0072] The above three types of information can all reflect the user's preferences when interacting with the large model platform. In this way, the target input template can be determined based on at least one of the above three types of information, and the template information of personalized input templates can be recommended to the user when the template selection box is displayed. This can avoid the user from viewing a large amount of useless template information that is irrelevant to themselves when viewing the template information, avoid information overload displayed by the large model platform and the inconvenience of users selecting template information, thereby improving the convenience of users selecting input templates and improving the user's interactive experience.

[0073] The specific implementation method of determining the target input template according to the above three types of information can be found in the subsequent embodiments, which will not be described in detail here.

[0074] In a second implementation, the target input template may be a preset fixed template, so that the template selection box displayed to the user each time contains the template information of the fixed template.

[0075] See also Figure 2b , showing an interactive interface UI2 with a template selection box. When the user enters the template wake-up character, the interactive interface can be changed from the above Figure 2a The interface changes to Figure 2b The interface shown.

[0076] exist Figure 2b In the interface shown, the character input area 201 includes the template wake-up character “ / ” input by the user and a send button 201 a.

[0077] A template selection box 203 is displayed above the character input area 201. The template selection box contains template information of four target input templates. The template information of each target input template contains the scene name of the interactive scene corresponding to the target input template, namely: auxiliary diagnosis, image question and answer, and image area positioning.

[0078] from Figure 2b It can be seen from the interface shown that the template selection box 203 and the character input area 201 belong to the same interactive interface rather than different interfaces. This can avoid the user switching back and forth between the template selection interface and the character input interface during the interaction with the large model platform, thereby simplifying the user's operation and improving the convenience of the user's interaction with the large model platform.

[0079] Other implementations of displaying the template selection box to the user may refer to subsequent embodiments and will not be described in detail here.

[0080] As can be seen from the above, when the scheme provided by the embodiment of the present disclosure is used to display template information, if it is detected that the input character entered by the user is a template wake-up character, a template selection box containing template information of multiple target input templates is displayed to the user in the interactive interface. Since each target input template is set for an interactive scenario in which the large model platform interacts with the user, and the target input template is used to guide the user to input information, when the user selects the template information in the template selection box, the large model platform can determine the input template corresponding to the template information selected by the user, and then use the input template to guide the user to input the information that the large model platform expects to obtain in the interactive scenario corresponding to the input template. In this way, the large model platform can obtain the information it expects to obtain, and can also make an accurate response to the user. Therefore, the template information display scheme provided by the embodiment of the present disclosure can improve the accuracy of the large model platform's response to users.

[0081] In one embodiment of the present disclosure, before a user interacts with the big model platform, the big model platform can perform user verification, which can prevent the user information of the user recorded by the big model platform from being obtained by other users and causing information or user privacy leakage.

[0082] For example, an application developed based on the big model platform can be installed in the terminal device, and the user uses the application to interact with the big model platform. When the user logs in to the application, the user can be authenticated. After the user is authenticated, the terminal device displays the interactive interface provided by the application, so that the user can interact with the big model platform based on the interactive interface.

[0083] In another embodiment of the present disclosure, after the user interacts with the big model platform, the big model platform can collect the user's evaluation information on the interaction process and optimize the big model platform according to the user's evaluation information.

[0084] For example, the terminal device can display a preset evaluation interface to the user, and the user enters evaluation information for the interaction process in the evaluation interface. The terminal device can then obtain the information entered by the user in the evaluation interface and send the evaluation information to the server, so that the staff who maintains the server can optimize the large model platform based on the user's evaluation information.

[0085] After the template selection box is displayed to the user, the user can perform operations in the interface where the template selection box is displayed.

[0086] In one embodiment of the present disclosure, see Figure 3 , a flow chart of a second template information display method is provided. In this embodiment, the method includes the following steps S301-S304.

[0087] Step S301: Obtain input characters entered by the user in the interactive interface when the user uses the interactive service provided by the large model platform.

[0088] Step S302: Detect whether the input character is the same as the preset template wake-up character.

[0089] Step S303: When the input character is the same as the template wake-up character, a template selection box containing template information of multiple target input templates is displayed to the user on the interactive interface.

[0090] The above steps S301 to S303 are respectively Figure 1 In the illustrated embodiment, steps S101 to S103 are the same and will not be described in detail here.

[0091] Step S304: In response to the user's selection operation of selecting template information in the template selection box, the template selection box is hidden, and the information items to be filled in the target input template indicated by the template information selected by the user are displayed in the character input area.

[0092] Each target input template may include corresponding information items to be filled in, which are used to guide the user on what information needs to be entered in the interaction scenario corresponding to the target input template.

[0093] Specifically, after the terminal device displays the template selection box to the user in the interactive interface, the user can view the template information of each target input template in the template selection box, and thus determine the target input template he or she wants to select according to his or her own needs, and select the template information of the target input template he or she wants.

[0094] In response to the user's selection operation of selecting template information in the template selection box, the terminal device hides the template selection box, and determines the template information selected by the user based on the user's selection operation, thereby determining the target input template corresponding to the template information selected by the user, and then pastes the information items to be filled in the target input template into the character input area.

[0095] After the terminal device determines the target input template corresponding to the template information selected by the user, the target input template corresponding to the template information selected by the user is referred to as the selected template. The information items to be filled in the selected template can be pasted in the character input area in the following two implementation methods.

[0096] In the first implementation method, the terminal device can send a request to the server to obtain the information items to be filled in the selected template. In response to the acquisition request, the server sends the information items to be filled in the selected template to the terminal device. After the terminal device receives the information items to be filled in sent by the server, it can paste the received information items to be filled in the character input area.

[0097] In the second implementation method, when the terminal device obtains the template information of the target input template or the information of the template selection box from the server, it can synchronously obtain the information items to be filled in contained in each target input template. In this way, after the terminal device determines that the template has been selected, it can search for the information items to be filled in the selected template among the obtained information items to be filled in, and then paste the found information items to be filled in the character input area.

[0098] After the terminal device displays the information items to be filled in the character input area, the user can fill in the information in the information items to be filled in. After the terminal device obtains the information of each information item to be filled in entered by the user, it can send the information entered by the user to the server. After the server receives the information entered by the user, it can use the large model to process the received information and feedback the processing results to the terminal device. After receiving the processing results, the terminal device can respond to the user based on the processing results.

[0099] See also Figure 4a , showing an interactive interface UI3 in which a character input area displays information items to be filled in. When the terminal device displays the above Figure 2b When the interface is displayed, the user clicks the fourth target in the template selection box to enter the template information of the template, that is, the template information of "Assisted Diagnosis". The interface displayed by the terminal device can be selected from the above Figure 2b The interface changes to Figure 4a The interface shown.

[0100] exist Figure 4a The interface shown includes a character input area 401, and the character input area 401 displays three information items to be filled in the target input template corresponding to the auxiliary diagnosis, namely: detection purpose, blood pressure value and heart rate. Among them, the detection purpose and blood pressure value are required items, and the heart rate is not a required item. In this way, when filling in the information, the user can only fill in the detection purpose and blood pressure value.

[0101] In addition, the character input area 401 also displays the target input template corresponding to the auxiliary diagnosis, which also includes other auxiliary information, and the content is: help me analyze the results. In this way, the character input area 401 not only displays the information items to be filled in, but also displays other auxiliary information, which is more in line with the user's input grammar habits, thereby helping the user to input information.

[0102] After the user has filled in the information according to the information items to be filled in, he can click the send button 401a in the character input area 401, so that the terminal device can send the information entered by the user to the server, and the server then uses the big model to understand and analyze the information entered by the user in the interactive scenario corresponding to the auxiliary diagnosis, and make a corresponding response. And when analyzing the information entered by the user, the big model platform can analyze it based on the context information entered by the user.

[0103] From the above, it can be seen that in the template information display scheme provided by the embodiment of the present disclosure, after the template selection box is displayed to the user, the user can select the template information contained in the template selection box, so that the terminal device can display the information items to be filled in the character input area to guide the user to enter the information that the big model platform expects the user to enter, so that the big model platform can also make an accurate response to the user. Therefore, applying the scheme provided by the embodiment of the present disclosure to display template information can improve the accuracy of the big model platform's response to the user.

[0104] In the process of users interacting with the large model platform, in addition to interacting with the large model platform by inputting characters, users can also interact with the large model platform by inputting other forms of information.

[0105] In view of the above situation, in one embodiment of the present disclosure, after displaying the template selection box to the user, in response to the user's selection operation of selecting template information in the template selection box, an attachment upload control corresponding to the target input template indicated by the template information selected by the user can be displayed.

[0106] Specifically, the terminal device loads the attachment upload control in the above interaction interface, thereby displaying the attachment upload control. The interaction interface can load one or more attachment upload controls.

[0107] In one embodiment of the present disclosure, the attachment upload control may include at least one of the following controls:

[0108] Image upload control, video upload control, document upload control.

[0109] In response to the user's selection operation, the large model platform can display at least one of the three upload controls mentioned above, so that the user can use the displayed control to upload images, videos, documents and other information. The large model platform can interact with the user based on images, videos, documents and other information, thereby expanding the scope of application of the large model platform and meeting the different interaction preferences of users.

[0110] Specifically, when the terminal device obtains the template information of the target input template or the information of the template selection box from the server, it can obtain the correspondence between each target input template and the attachment upload control, so that after determining the input template selected by the user, the terminal device can determine the attachment upload control corresponding to the input template selected by the user, thereby calling and displaying the determined attachment upload control. The user can use the displayed attachment upload control to upload attachments.

[0111] In response to the user selecting the template information in the template selection box, the terminal device may only display the above-mentioned attachment upload control; or may only display the information items to be filled in mentioned in the above-mentioned public embodiment; or may display the attachment upload control and the information items to be filled in.

[0112] See also Figure 4b , showing an interactive interface UI4 showing an attachment upload control 402 and a character input area 401 containing information items to be filled in. Figure 2b When the interface is displayed, the user clicks the template information of the first target input template contained in the template selection box, that is, the template information where "Auxiliary Diagnosis" is located. If the target input template corresponding to the auxiliary diagnosis contains information items to be filled in, and the template has a corresponding relationship with the attachment upload control, the interface displayed by the terminal device can be changed from the above Figure 2b The interface changes to Figure 4b The interface shown.

[0113] Figure 4b The interface shown is the same as above Figure 4a Compared with the interface shown, Figure 4b The interface also displays an attachment upload control 402, which displays the following upload prompt information:

[0114] Drag your file here or click Upload;

[0115] File format: xls / xlsx;

[0116] The size should not exceed 5MB.

[0117] In addition, the attachment upload control 402 also includes a download template sub-control 402a. The user can click the download template sub-control 402a to download the attachment template, so that the user can create an attachment according to the downloaded attachment template.

[0118] From the above, it can be seen that when the solution provided by the embodiment of the present disclosure is used to display template information, after the user selects the template information, the terminal device can display the attachment upload control corresponding to the target input template indicated by the template information selected by the user, so that the user can use the displayed control to upload the attachment, so that the big model platform can interact with the user based on the information in the attachment uploaded by the user, thereby expanding the scope of application of the big model platform and satisfying the different interaction preferences of users.

[0119] The following is the above Figure 1 The specific implementation method of determining the target input template according to the three types of information, namely, user historical interaction information, user interest information, and historical template usage information, mentioned in step S103 in the illustrated embodiment is described.

[0120] In one embodiment of the present disclosure, the large model platform extracts target keywords from the recorded user historical interaction information and / or user interest information, and determines the input template corresponding to the target keyword as the target input template based on the correspondence between the preset keywords and the input template.

[0121] Specifically, the input template is set for the interaction scenario between the large model platform and the user. For each input template, the server can obtain the keywords related to the interaction scenario corresponding to the input template that are manually input, thereby setting the correspondence between the keywords and the input template. In this way, when the large model platform determines the target input template, that is, when the server determines the target input template, it can perform keyword extraction on the recorded user history interaction information and / or user interest information to obtain the target keyword, and then search for the target keyword among the keywords corresponding to each input model. If the corresponding relationship is found to contain the above-mentioned target keyword, the input template contained in the corresponding relationship is determined to be the input template corresponding to the target keyword, and the input template is used as the target input template.

[0122] Keyword extraction from user historical interaction information and / or user interested information can be implemented using keyword extraction algorithms, models, etc., which will not be described in detail here.

[0123] From the above, it can be seen that, by applying the template information display scheme provided by the embodiment of the present disclosure, what is displayed in the template selection box is the template information of the template input template determined based on the user's historical interaction information and / or the user's information of interest. Since the user's historical interaction information and / or the user's information of interest can both characterize and reflect the user's preferences when interacting with the large model platform, the target input template is determined based on the user's historical interaction information and / or the user's information of interest. When the template selection box is displayed, the template information of the personalized input template can be recommended to the user, thereby improving the convenience of the user in selecting the input template and improving the user's interactive experience.

[0124] In another embodiment of the present disclosure, the large model platform predicts the input template that the user expects to select based on the recorded historical template usage information as the target input template.

[0125] Specifically, when the large model platform predicts the input template that the user expects to select based on the above historical template usage information, that is, when the server predicts the input template that the user expects to select based on the above historical template usage information, it can determine the historical input template used by the user, so that the historical input template can be directly determined as the target input template.

[0126] In addition, the above historical template usage information may also include the number of times the historical input template has been used. The server may use multiple historical input templates that have been used more than a preset number of times or have been used the most times as target input templates.

[0127] The above historical template usage information may also include a usage time period of the historical input template. The server may determine the most recently used multiple historical input templates as target input templates according to the usage time periods of the various historical input templates.

[0128] The server may also analyze the user's usage habits of the input templates based on the historical template usage information, and predict the input template that the user may be interested in using based on the user's usage habits, as the target input template.

[0129] For example, if a user often uses a certain input template, referred to as a common template, when determining a target input template, not only the common template can be determined as the target input template, but also other templates that are similar to the common template can be determined as the target input template.

[0130] When determining a template that is similar to a commonly used template, it can be determined based on the number and meaning of the information items to be filled in the template. For example, for each information item to be filled in contained in the commonly used template, an information item to be filled in with a similar meaning can be found in another template. In this way, the other template can be determined to be another template that is relatively similar to the commonly used template.

[0131] From the above, it can be seen that when the scheme provided by the embodiment of the present disclosure is used to display template information, the historical template usage information can reflect the template usage habits of the user when interacting with the large model platform. In this way, the input template that the user expects to select can be predicted based on the historical template usage information, and the input template that conforms to the user's template usage habits can be predicted as the target input template. Therefore, the template information display scheme provided by the embodiment of the present disclosure can recommend template information of personalized input templates to users, thereby improving the convenience of users in selecting input templates and improving the user's interactive experience.

[0132] The following is the above Figure 1 The implementation method of presenting the template selection box to the user mentioned in step S103 in the illustrated embodiment is described below.

[0133] In one embodiment of the present disclosure, when the terminal device displays the template selection box to the user, the template selection box containing template information of multiple target input templates is popped up in a first dynamic transition manner.

[0134] The first dynamic transition mode may be any dynamic transition mode, for example, a mode of flying from outside the screen into the screen, a gradual display mode, etc.

[0135] In this solution, the terminal device pops up a template selection box in a first dynamic transition manner, which can increase the fun of the interaction process between the user and the large model platform, thereby enhancing the user's interactive experience.

[0136] When the terminal device pops up the template selection box in the first dynamic transition mode, the template selection box containing multiple template information can be regarded as a whole for dynamic transition. In addition, the terminal device can also regard the template information and the template selection box as different entities for dynamic transition. In this case, the template selection box can be displayed in any of the following two implementation methods.

[0137] In a first implementation manner, the terminal device pops up a blank template selection box in a first dynamic transition manner, and during the dynamic transition of the blank template selection box, displays template information of multiple target input templates in the blank template selection box in a second dynamic transition manner.

[0138] The blank template selection box is an information box that does not contain template information.

[0139] The second dynamic transition mode mentioned above may also be any dynamic transition mode.

[0140] The first dynamic transition mode may be the same as or different from the second dynamic transition mode.

[0141] The method of popping up the blank template selection box in the first dynamic transition mode can be referred to the above embodiment, which will not be described again here.

[0142] The blank template selection box pops up in the area of ​​the interface provided by the terminal device in the first dynamic transition mode, and when the template information of multiple target input templates is displayed in the second dynamic transition mode, it pops up in the part of the blank template selection box in the second dynamic transition mode.

[0143] For example, a blank template selection box pops up in the interface in a bottom-up manner, and template information of multiple target input templates pops up in the blank template selection box in a right-to-left manner.

[0144] The way in which template information pops up in the blank template selection box is similar to the way in which the blank template selection box pops up in the interface, which will not be repeated here.

[0145] In addition, the final position of the blank template selection box and the template information can be predetermined, so that when the terminal device displays the template selection box to the user, the blank template selection box pops up to its predetermined selection box position in a first dynamic transition manner, and the template information of the target input template pops up to its predetermined information position in a second dynamic transition manner.

[0146] For example, the selection box position may be the exact center of the interface, the position adjacent to the template selection box and the character input area, etc.; the information position may be the position at a preset distance from the left border of the blank template selection box, the exact center of the blank template selection box, etc.

[0147] The preset distance may be a distance that is estimated in advance but underestimated, such as a distance of 12 pixels.

[0148] In this solution, the blank template selection box is dynamically popped up synchronously with the template information, which can further enhance the fun of the interaction process between the user and the large model platform, thereby enhancing the user's interactive experience.

[0149] In a second implementation, the terminal device pops up a blank template selection box in a first dynamic transition manner, and after the dynamic transition of the blank template selection box is completed, displays template information of multiple target input templates in the blank template selection box in a second dynamic transition manner.

[0150] See also Figure 4c , providing an interactive interface UI5 ​​after a blank template selection box pops up in a first dynamic transition manner.

[0151] After the terminal device detects that the input character is a template wake-up character, it can pop up a blank template selection box and template information in the following two steps:

[0152] Step 1: Pop up a blank template selection box in the first dynamic transition mode. At this time, the terminal device displays the following Figure 4c The interface shown includes a character input area 401 and a blank template selection box 403.

[0153] Step 2: The template information of multiple target input templates is popped up in the second dynamic transition mode. At this time, the interface displayed by the terminal device is Figure 4c The interface shown changes to the above Figure 2b The interface shown.

[0154] In this solution, a blank template selection box and template information are popped up in two steps, which can further enhance the fun of the interaction process between the user and the large model platform, thereby enhancing the user's interactive experience.

[0155] In addition to the display methods provided in the above embodiments, in one embodiment of the present disclosure, when the terminal device displays the template selection box to the user, a template selection box containing template information of multiple target input templates pops up from a starting position determined according to the character input area.

[0156] The above starting position is determined according to the character input area. For example, the starting position may be the upper boundary, the lower boundary, the position at a preset distance from the upper boundary of the character input area, etc.

[0157] Specifically, before displaying the template selection box to the user, the terminal device can determine the location of the character input area, and determine the above-mentioned starting position based on the location of the character input area. In this way, when the terminal device displays the template selection box to the user, a template selection box containing template information of multiple target input templates can pop up from the determined starting position.

[0158] For example, the terminal device can determine that the upper boundary of the character input area is the above-mentioned starting position, and the template selection box can be popped up from bottom to top. In this way, the template selection box pops up according to the starting position, that is, a template selection box containing template information of multiple target input templates pops up from bottom to top from the upper boundary of the character input area. In this way, the template selection box is finally displayed above the character input area, and the user can clearly view the template selection box, thereby simplifying the process of user selecting a template.

[0159] In this solution, the terminal device determines the starting position according to the character input area, and when displaying the template selection box to the user, the template selection box pops up from the starting position. It can be seen that the starting position of the pop-up template selection box is set according to the character input area, so that the character input area is associated with the template selection box. When the user needs to select a template, the template selection box pops up directly from the starting position determined according to the character input area. In this way, the user does not need to switch interfaces to select a template, which can improve the fluency of user interaction, simplify user operations, reduce the user's operating burden, and improve the user's interactive experience.

[0160] In addition to the display methods provided in the above embodiments, in one embodiment of the present disclosure, when the terminal device displays the template selection box to the user, the template selection box containing template information of multiple target input templates is displayed in areas other than the character input area.

[0161] Specifically, the terminal device may predetermine the position of the character input area and determine other areas in the interface except the character input area, so that when the template selection box is displayed to the user, the template selection box may be directly displayed in the determined other areas.

[0162] Since the template selection box is located outside the character input area, even though the template selection box is displayed in the interface, the user can still input characters normally in the character input area, thereby ensuring the flexibility of user character input and improving the user's interactive experience with the large model platform.

[0163] In addition to the display methods provided in the above embodiments, in one embodiment of the present disclosure, when the terminal device detects whether the input character is a preset template wake-up character, it can detect whether the input character is the same as the template wake-up character when the screen focus is on the character input area and the character input area belongs to the question and answer area.

[0164] When it is detected that the character input area is a question and answer area and the input character is a template wake-up character, a selection box display event is triggered, and a handler for the selection box display event is called to render a container element corresponding to the template selection box.

[0165] The screen focus is the area that the terminal device records itself paying attention to in the displayed interactive interface.

[0166] The above selection box display event is an event pre-set by the terminal device for displaying a template selection box, and the triggering condition of the selection box display event is: the character input area is a question and answer area, and the input character is a template wake-up character.

[0167] The container element corresponding to the template selection box is a pre-set element used to represent the template selection box.

[0168] The above-mentioned container element can be set by the terminal device or by the server. In the case where the above-mentioned container element is set by the server, the terminal device can obtain the above-mentioned container element from the server before detecting the input character, so that after detecting that the input character is a template wake-up character, the above-mentioned container element is directly rendered in the interactive interface, or the terminal device can send a request to the server to obtain the above-mentioned container element after detecting the input character, thereby obtaining the above-mentioned container element fed back by the server, and then rendering the above-mentioned container element in the interactive interface.

[0169] Specifically, before detecting whether the input character is the same as the template wake-up character, the terminal device can obtain the screen focus recorded by itself and detect whether the area where the screen focus is located is the character input area. If so, the area attributes of the character input area can be obtained to determine whether the area attributes of the character input area are the question and answer area.

[0170] If it is determined that the character input area belongs to the question and answer area, it means that the user is interacting with the big data platform at this time. In this way, after obtaining the input character, it can be detected whether the input character is the same as the template wake-up character. In other words, after obtaining the input character, it is detected whether the screen focus is focused on the character input area and whether the character input area belongs to the question and answer area. In this way, when it is detected that the screen focus is focused on the character input area and the character input area belongs to the question and answer area, it is detected whether the input character is the same as the template wake-up character.

[0171] If the input character is determined to be a template wake-up character, a selection box display event is triggered, and a selection box display event handler is called to render a container element corresponding to the template selection box.

[0172] Calling the handler of the selection box display event to render the container element corresponding to the template selection box can be implemented using screen rendering algorithms, programs, etc., which will not be described in detail here.

[0173] It can be seen from the above that when the scheme provided by the embodiment of the present disclosure is applied to display template information, the terminal device gives priority to the area where the screen is focused. Therefore, if the screen is focused on the character input area, and the character input area belongs to the question and answer area, it means that the user is interacting with the big data platform. In this way, when the screen is focused on the character input area, and the character input area belongs to the question and answer area, it is detected whether the input character is the same as the preset template wake-up character. If the input character is the same as the template wake-up character, a selection box display event is triggered, and the handler of the selection box display event is called to render the container element corresponding to the template selection box, so that the template selection box can be accurately and timely displayed in the interface.

[0174] After the terminal device displays the template selection box to the user, the user may temporarily not need or want to use the input template.

[0175] In view of the above situation, in one embodiment of the present disclosure, after the template selection box is displayed to the user, the template selection box can be hidden in any of the following three ways.

[0176] In the first implementation, if a deletion operation of the user on the input characters is detected, the template selection box is hidden.

[0177] Specifically, the user can send a character deletion instruction through the input area provided by the input method application or a keyboard external to the terminal device. When the terminal device receives the character deletion instruction sent by the user, it detects the user's deletion operation and hides the template selection box.

[0178] In addition, since the terminal device has displayed the template selection box to the user, the above input character is the template wake-up character, wherein the template wake-up character can be composed of one or more characters, so the above input character may also be one or more characters.

[0179] When the template wake-up character is one character, that is, the input character is one character, if a deletion operation of the user on the input character is detected, that is, the user deletes the entire template wake-up character, the template selection box is hidden.

[0180] When the template wake-up character contains multiple characters, that is, the input character is multiple characters, if it is detected that the user has deleted all the characters, the template selection box is hidden; if it is detected that the user has deleted some characters, the template selection box can be hidden or not.

[0181] In this implementation, if the user deletes the characters he / she input, it means that the user does not want to call the template. Therefore, if the user's deletion operation on the input characters is detected, the template selection box can be hidden. It can be seen that the operation of hiding the template selection box in this implementation is in line with the user's actual intention to delete the characters, which can improve the user experience of using the large model platform.

[0182] In the second implementation, if it is detected that the user inputs characters again, the template selection box is hidden.

[0183] Specifically, when the terminal device obtains the input characters entered by the user, it can obtain the characters entered by the user in the character input area in real time or periodically. If other characters except the template wake-up characters that have been entered are obtained after the template selection box is displayed, it means that the user has entered the characters again. The obtained characters include the template wake-up characters and other characters. Therefore, the role of the template wake-up characters at this time is actually to be combined with other characters to form complete information, rather than to wake up the template. Therefore, in this case, the template selection box needs to be hidden. It can be seen that the operation of hiding the template selection box in this implementation method is also in line with the user's actual intention of entering characters again, thereby improving the user experience of using the large model platform.

[0184] In a third implementation, when the template selection box includes a hidden control, if a click operation of the user clicking the hidden control is detected, the template selection box is hidden.

[0185] See also Figure 4d , showing the interactive interface UI6 when the template selection box is displayed to the user. Figure 4d The interface shown includes a character input area 401 and a template selection box 403 . The template selection box 403 includes a hidden control 403 a . After the user clicks the hidden control 403 a , the terminal device hides the template selection box 403 .

[0186] In this implementation, if a user click operation to hide the control is detected, it means that the user does not want to call the template. In this case, the template selection box can be hidden. It can be seen that the operation of hiding the template selection box in this implementation is in line with the user's actual intention of clicking the hidden control, which can improve the user experience of using the large model platform.

[0187] The user's demand for using input templates is sometimes constantly changing, and the template information included in the template selection box may not be the template information of the input template that the user expects to use in this interaction process.

[0188] In response to the above situation, in one embodiment of the present disclosure, the template selection box may include a template search subbox for searching template information of the input template that the user expects to use; or the template selection box may include a template filter subbox for filtering template information of the input template that the user does not want to use.

[0189] In the case where the template selection box includes a template search sub-box, after the terminal device displays the template selection box to the user, it can obtain the search term entered by the user in the template search sub-box, determine a first template related to the search term from among multiple preset input templates, and update the template information displayed in the template selection box based on the template information of the first template.

[0190] See also Figure 4e , showing the interactive interface UI7 when the user displays the template selection box. Figure 4e The interface shown includes a character input area 401 and a template selection box 403 . The template selection box 403 includes a template search subbox 403 b , and the user can input a search term in the template search subbox 403 b .

[0191] Specifically, various input templates are stored in the server. After obtaining the search term input by the user, the terminal device can send the search term to the server. The server then determines the first template related to the search term from multiple input templates and sends the template information of the first template to the terminal device, so that the terminal device can update the template information displayed in the template selection box based on the template information of the first template.

[0192] In addition, after the server determines the first template, the first template may include the target input template. Therefore, the server can determine the template to be updated in the first template except the target input template, so that the server sends the template information of the template to be updated to the terminal device, and the server can notify the terminal device which template information of the target input template in the template selection box is the template information of the first template. In this way, after the terminal device receives the template information of the template to be updated and determines the template information of the first template already included in the template selection box, the template information displayed in the template selection box can be updated based on the received template information and the determined template information.

[0193] When the server determines the first template related to the search term among multiple input templates, since each input template corresponds to an interaction scenario, the input template whose corresponding interaction scenario is associated with the search term may be determined as the first template.

[0194] For example, the first template may be determined by any one of the following two implementations.

[0195] In the first implementation method, for each input template, the manually input keywords related to the interaction scenario corresponding to the input template can be obtained, so that the keywords corresponding to each input template can be determined. If there is an input template corresponding to the keyword containing the search term, the input template is determined to be the first template.

[0196] In the second implementation method, the scene semantics of the interaction scene corresponding to each input template can be obtained in advance. In this way, after obtaining the above-mentioned search terms, the semantics of the search terms can be obtained, and the similarity between the semantics of the search terms and the scene semantics of the interaction scene corresponding to each input template can be calculated, thereby determining the multiple input templates with a similarity exceeding a threshold or with the highest similarity as the first template.

[0197] It can be seen that when the template selection box includes a template search subbox, the first template is the template that the user searches for and expects to use. Updating the template information displayed in the template selection box based on the template information of the first template can facilitate the user to select a template, thereby improving the user's interactive experience with the large model platform.

[0198] When the template selection box includes a template filter subbox, after the terminal device displays the template selection box to the user, it can obtain the filter word entered by the user in the template filter subbox, determine the second template related to the filter word in the target data template, and update the template information displayed in the template selection box based on the template information of the associated template.

[0199] The associated templates are templates in the target input template except the second template.

[0200] See also Figure 4f , showing the interactive interface UI8 when the user displays the template selection box. Figure 4f The interface shown includes a character input area 401 and a template selection box 403 . The template selection box 403 includes a template filtering subbox 403 c , and the user can input filtering words in the template filtering subbox 403 c .

[0201] The implementation method of determining the second template related to the filter word is the same as the implementation method of determining the first template related to the search word, which will not be repeated here.

[0202] After determining the second template in the target input template, other templates except the second template in the target input template may be determined, that is, associated templates may be determined, so that when updating the template information displayed in the template selection box, the template information of the associated template may be displayed preferentially.

[0203] It can be seen that when the template selection box contains a template filtering subbox, the second template is the template that the user wishes to filter out, then the remaining associated templates in the target input template are the templates that the user wishes to use. In this way, the template information displayed in the template selection box is updated based on the template information of the associated templates, which can facilitate the user to select a template, thereby improving the user's interactive experience with the large model platform.

[0204] Corresponding to the above-mentioned template information display method, the embodiment of the present disclosure also provides a template information display device.

[0205] In one embodiment of the present disclosure, see Figure 5 , a schematic diagram of the structure of a first template information display device is provided. In this embodiment, the above device includes:

[0206] The character acquisition module 501 is used to acquire the input characters input by the user in the interactive interface when the user uses the interactive service provided by the large model platform;

[0207] A character detection module 502 is used to detect whether the input character is the same as a preset template wake-up character;

[0208] The information display module 503 is used to display a template selection box containing template information of multiple target input templates to the user in the interactive interface when the input character is the same as the template wake-up character, wherein each of the target input templates is a template set for an interactive scenario for interaction between the large model platform and the user, and guides the user to input information.

[0209] As can be seen from the above, when the scheme provided by the embodiment of the present disclosure is used to display template information, if it is detected that the input character entered by the user is a template wake-up character, a template selection box containing template information of multiple target input templates is displayed to the user in the interactive interface. Since each target input template is set for an interactive scenario in which the large model platform interacts with the user, and the target input template is used to guide the user to input information, when the user selects the template information in the template selection box, the large model platform can determine the input template corresponding to the template information selected by the user, and then use the input template to guide the user to input the information that the large model platform expects to obtain in the interactive scenario corresponding to the input template. In this way, the large model platform can obtain the information it expects to obtain, and can also make an accurate response to the user. Therefore, the template information display scheme provided by the embodiment of the present disclosure can improve the accuracy of the large model platform's response to users.

[0210] In one embodiment of the present disclosure, the device further includes:

[0211] The operation response module is used to hide the template selection box in response to the user's selection operation of selecting the template information in the template selection box, and display the information items to be filled in the target input template indicated by the template information selected by the user in the character input area.

[0212] From the above, it can be seen that in the template information display scheme provided by the embodiment of the present disclosure, after the template selection box is displayed to the user, the user can select the template information contained in the template selection box, so that the terminal device can display the information items to be filled in the character input area to guide the user to enter the information that the big model platform expects the user to enter, so that the big model platform can also make an accurate response to the user. Therefore, applying the scheme provided by the embodiment of the present disclosure to display template information can improve the accuracy of the big model platform's response to the user.

[0213] In one embodiment of the present disclosure, the operation response module includes:

[0214] The dynamic transition submodule is used to pop up a template selection box containing template information of multiple target input templates in a first dynamic transition mode.

[0215] In this solution, the terminal device pops up a template selection box in a first dynamic transition manner, which can increase the fun of the interaction process between the user and the large model platform, thereby enhancing the user's interactive experience.

[0216] In one embodiment of the present disclosure, the dynamic transition submodule is specifically used to:

[0217] A blank template selection box is popped up in a first dynamic transition manner, and during the dynamic transition process of the blank template selection box, template information of multiple target input templates is displayed in the blank template selection box in a second dynamic transition manner.

[0218] In this solution, the blank template selection box is dynamically popped up synchronously with the template information, which can further enhance the fun of the interaction process between the user and the large model platform, thereby enhancing the user's interactive experience.

[0219] In one embodiment of the present disclosure, the dynamic transition submodule is specifically used to:

[0220] A blank template selection box is popped up in the first dynamic transition mode, and after the dynamic transition of the blank template selection box is completed, template information of multiple target input templates is displayed in the blank template selection box in the second dynamic transition mode.

[0221] In this solution, a blank template selection box and template information are popped up in two steps, which can further enhance the fun of the interaction process between the user and the large model platform, thereby enhancing the user's interactive experience.

[0222] In one embodiment of the present disclosure, the information display module 503 includes:

[0223] The template pop-up submodule is used to pop up a template selection box containing template information of multiple target input templates from a starting position determined according to the character input area in the interactive interface.

[0224] In this solution, the terminal device determines the starting position according to the character input area, and when displaying the template selection box to the user, the template selection box pops up from the starting position. It can be seen that the starting position of the pop-up template selection box is set according to the character input area, so that the character input area is associated with the template selection box. When the user needs to select a template, the template selection box pops up directly from the starting position determined according to the character input area. In this way, the user does not need to switch interfaces to select a template, which can improve the fluency of user interaction, simplify user operations, reduce the user's operating burden, and improve the user's interactive experience.

[0225] In one embodiment of the present disclosure, the template pop-up submodule is specifically used to:

[0226] A template selection box containing template information of multiple target input templates pops up from the upper boundary of the character input area in the interactive interface from bottom to top.

[0227] In this solution, the terminal device displays a template selection box above the character input area, and the user can clearly view the template selection box, thereby simplifying the process of selecting a template for the user.

[0228] In one embodiment of the present disclosure, the character detection module 502 is specifically used to:

[0229] When the screen is focused on the character input area and the character input area belongs to the question and answer area, detecting whether the input character is the same as the preset template wake-up character;

[0230] The information display module 503 is specifically used for:

[0231] A selection box display event is triggered, and a handler for the selection box display event is called to render a container element corresponding to the template selection box on the interactive interface.

[0232] It can be seen from the above that when the scheme provided by the embodiment of the present disclosure is applied to display template information, the terminal device gives priority to the area where the screen is focused. Therefore, if the screen is focused on the character input area, and the character input area belongs to the question and answer area, it means that the user is interacting with the big data platform. In this way, when the screen is focused on the character input area, and the character input area belongs to the question and answer area, it is detected whether the input character is the same as the preset template wake-up character. If the input character is the same as the template wake-up character, a selection box display event is triggered, and the handler of the selection box display event is called to render the container element corresponding to the template selection box, so that the template selection box can be accurately and timely displayed in the interface.

[0233] In one embodiment of the present disclosure, the target input template is determined according to at least one of the following information recorded in the large model platform:

[0234] User historical interaction information, user interest information, and historical template usage information.

[0235] The above three types of information can all reflect the user's preferences when interacting with the large model platform. In this way, the target input template can be determined based on at least one of the above three types of information, and the template information of personalized input templates can be recommended to the user when the template selection box is displayed. This can avoid the user from viewing a large amount of useless template information that is irrelevant to themselves when viewing the template information, avoid information overload displayed by the large model platform and the inconvenience of users selecting template information, thereby improving the convenience of users selecting input templates and improving the user's interactive experience.

[0236] In one embodiment of the present disclosure, the target input template is determined in the following manner:

[0237] Target keywords are extracted from the user historical interaction information and / or the user interest information recorded in the large model platform, and an input template corresponding to the target keyword is determined according to the correspondence between the preset keywords and the input template as the target input template.

[0238] From the above, it can be seen that, by applying the template information display scheme provided by the embodiment of the present disclosure, what is displayed in the template selection box is the template information of the template input template determined based on the user's historical interaction information and / or the user's information of interest. Since the user's historical interaction information and / or the user's information of interest can both characterize and reflect the user's preferences when interacting with the large model platform, the target input template is determined based on the user's historical interaction information and / or the user's information of interest. When the template selection box is displayed, the template information of the personalized input template can be recommended to the user, thereby improving the convenience of the user in selecting the input template and improving the user's interactive experience.

[0239] In one embodiment of the present disclosure, the target input template is determined in the following manner:

[0240] According to the historical template usage information recorded in the large model platform, the input template that the user expects to select is predicted as the target input template.

[0241] From the above, it can be seen that when the scheme provided by the embodiment of the present disclosure is used to display template information, the historical template usage information can reflect the template usage habits of the user when interacting with the large model platform. In this way, the input template that the user expects to select can be predicted based on the historical template usage information, and the input template that conforms to the user's template usage habits can be predicted as the target input template. Therefore, the template information display scheme provided by the embodiment of the present disclosure can recommend template information of personalized input templates to users, thereby improving the convenience of users in selecting input templates and improving the user's interactive experience.

[0242] In one embodiment of the present disclosure, the device further includes:

[0243] The first hiding module is used to hide the template selection box if a deletion operation of the user on the input character is detected after the template selection box containing the template information of multiple target input templates is displayed to the user.

[0244] In this solution, if the user deletes the characters he / she input, it means that the user does not want to call the template. Therefore, if the user's deletion operation on the input characters is detected, the template selection box can be hidden. It can be seen that the operation of hiding the template selection box in this implementation method is in line with the user's actual intention to delete the characters, which can improve the user experience of using the large model platform.

[0245] In one embodiment of the present disclosure, the device further includes:

[0246] The second hiding module is used to hide the template selection box if it is detected that the user inputs characters again after the template selection box containing template information of multiple target input templates is displayed to the user.

[0247] In this solution, the operation of hiding the template selection box also meets the user's actual intention of inputting characters again, thereby improving the user's experience of using the large model platform.

[0248] In one embodiment of the present disclosure, the device further includes:

[0249] The third hiding module is used to hide the template selection box after the template selection box containing template information of multiple target input templates is displayed to the user, if the template selection box contains a hidden control and a click operation of the user clicking on the hidden control is detected.

[0250] In this solution, if a user click operation to hide the control is detected, it means that the user does not want to call the template. In this case, the template selection box can be hidden. It can be seen that the operation of hiding the template selection box in this implementation method is in line with the user's actual intention of clicking the hidden control, which can improve the user experience of using the large model platform.

[0251] In one embodiment of the present disclosure, the template selection box includes a template search subbox;

[0252] The device also includes:

[0253] A search term acquisition module, configured to acquire a search term input by a user in the template search sub-box after the interactive interface displays a template selection box containing template information of a plurality of target input templates to the user;

[0254] A first template determination module, used to determine a first template related to the search term from among a plurality of preset input templates;

[0255] The first updating module is used to update the template information displayed in the template selection box based on the template information of the first template.

[0256] In this solution, when the template selection box includes a template search subbox, the first template is the template that the user searches for and expects to use. The template information displayed in the template selection box is updated based on the template information of the first template, which can facilitate the user to select a template, thereby improving the user's interactive experience with the large model platform.

[0257] In one embodiment of the present disclosure, the template selection box includes a template filtering subbox;

[0258] The device also includes:

[0259] A filter word acquisition module, used to obtain the filter word input by the user in the template filter sub-box after the interactive interface displays a template selection box containing template information of multiple target input templates to the user;

[0260] A second template determination module, used to determine a second template related to the filter word in the target input template;

[0261] The second updating module is used to update the template information displayed in the template selection box based on the template information of the associated template, wherein the associated template is a template in the target input template except the second template.

[0262] In this solution, when the template selection box contains a template filtering subbox, the second template is the template that the user wishes to filter out, then the remaining associated templates in the target input template are the templates that the user wishes to use. In this way, the template information displayed in the template selection box is updated based on the template information of the associated templates, which can facilitate the user to select a template, thereby improving the user's interactive experience with the large model platform.

[0263] In one embodiment of the present disclosure, the device further includes:

[0264] The attachment upload module is used to display an attachment upload control corresponding to the target input template indicated by the template information selected by the user in the template selection box in the interactive interface in response to the user's selection operation of selecting the template information in the template selection box.

[0265] In this solution, after the user selects the template information, the terminal device can display the attachment upload control corresponding to the target input template indicated by the template information selected by the user, so that the user can use the displayed control to upload the attachment, and the large model platform can interact with the user based on the information in the attachment uploaded by the user, thereby expanding the scope of application of the large model platform and meeting the different interaction preferences of users.

[0266] In one embodiment of the present disclosure, the attachment upload control includes at least one of the following controls:

[0267] Image upload control, video upload control, document upload control.

[0268] In this solution, the terminal device can display at least one of the three upload controls mentioned above in response to the user's selection operation, so that the user can use the displayed control to upload images, videos, documents and other information. The big model platform can interact with the user based on images, videos, documents and other information, thereby expanding the scope of application of the big model platform and meeting the different interaction preferences of users.

[0269] In one embodiment of the present disclosure, the information display module 503 is specifically used to:

[0270] A template selection box containing template information of multiple target input templates is displayed in other areas of the interactive interface except the character input area.

[0271] In this solution, since the template selection box is located outside the character input area, even though the template selection box is displayed in the interface, the user can still input characters normally in the character input area, thereby ensuring the flexibility of the user in inputting characters and improving the user's interactive experience with the large model platform.

[0272] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0273] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0274] Figure 6 A schematic block diagram of an example electronic device 600 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0275] like Figure 6 As shown, the electronic device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 can also be stored. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0276] Multiple components in the electronic device 600 are connected to the I / O interface 605, including: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a disk, an optical disk, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the electronic device 600 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0277] The computing unit 601 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 601 performs the various methods and processes described above, such as the template information display method. For example, in some embodiments, the template information display method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the template information display method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the template information display method in any other appropriate manner (e.g., by means of firmware).

[0278] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0279] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0280] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0281] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0282] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0283] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0284] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0285] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A template information display method, applied to a terminal device, comprising: Obtaining input characters entered by the user in the interactive interface when the user uses the interactive service provided by the big model platform; Detecting whether the input character is the same as a preset template wake-up character; In the case where the input character is the same as the template wake-up character, a template selection box containing template information of multiple target input templates is displayed to the user on the interactive interface, wherein each of the target input templates is a template set for an interactive scenario between the large model platform and the user, and guides the user to input information. The large model platform is a platform designed based on a large model, which is divided into two parts: one is an interactive part that receives user information and feeds back information to the user, and the other is an information processing part that processes information. The interactive part is deployed on the terminal device at the front end, and the information processing part is deployed in the server at the background. The multiple target input templates are all or part of the templates stored in the server.

2. The method according to claim 1, further comprising: In response to the user's selection operation of selecting the template information in the template selection box, the template selection box is hidden, and the information items to be filled in contained in the target input template indicated by the template information selected by the user are displayed in the character input area.

3. The method according to claim 1 or 2, wherein: The step of displaying a template selection box containing template information of multiple target input templates to the user on the interactive interface includes: A template selection box containing template information of multiple target input templates is popped up in a first dynamic transition manner.

4. The method according to claim 3, wherein: The popping up of a template selection box containing template information of a plurality of target input templates in a first dynamic transition manner includes: Popping up a blank template selection box in a first dynamic transition manner, and during the dynamic transition process of the blank template selection box, displaying template information of multiple target input templates in the blank template selection box in a second dynamic transition manner; or A blank template selection box is popped up in the first dynamic transition mode, and after the dynamic transition of the blank template selection box is completed, template information of multiple target input templates is displayed in the blank template selection box in the second dynamic transition mode.

5. The method according to claim 1 or 2, wherein: The step of displaying a template selection box containing template information of multiple target input templates to the user on the interactive interface includes: A template selection box containing template information of a plurality of target input templates pops up from a starting position determined according to the character input area in the interactive interface.

6. The method according to claim 5, wherein: The popping up of a template selection box containing template information of a plurality of target input templates from a starting position determined according to the character input area in the interactive interface comprises: A template selection box containing template information of multiple target input templates pops up from the upper boundary of the character input area in the interactive interface from bottom to top.

7. The method according to claim 1 or 2, wherein: The detecting whether the input character is the same as a preset template wake-up character includes: When the screen is focused on the character input area and the character input area belongs to the question and answer area, detecting whether the input character is the same as the preset template wake-up character; The step of displaying a template selection box containing template information of multiple target input templates to the user on the interactive interface includes: A selection box display event is triggered, and a handler for the selection box display event is called to render a container element corresponding to the template selection box on the interactive interface.

8. The method according to claim 1 or 2, wherein: The target input template is determined according to at least one of the following information recorded in the large model platform: User historical interaction information, user interest information, and historical template usage information.

9. The method according to claim 8, wherein: The target input template is determined as follows: Extracting target keywords from the user historical interaction information and / or the user interest information recorded in the large model platform, and determining an input template corresponding to the target keyword as the target input template according to a correspondence between preset keywords and input templates; and / or According to the historical template usage information recorded in the large model platform, the input template that the user expects to select is predicted as the target input template.

10. The method according to claim 1 or 2, after the interactive interface displays a template selection box containing template information of multiple target input templates to the user, further comprising: If a deletion operation of the user on the input character is detected, hiding the template selection box; and / or If it is detected that the user inputs characters again, the template selection box is hidden; and / or In the case where the template selection box includes a hidden control, if a click operation of the user clicking on the hidden control is detected, the template selection box is hidden.

11. The method according to claim 1 or 2, wherein: The template selection box includes a template search subbox; After the interactive interface displays a template selection box containing template information of multiple target input templates to the user, the following further includes: Obtaining the search term entered by the user in the template search subbox; Determining a first template related to the search term from among a plurality of preset input templates; The template information displayed in the template selection box is updated based on the template information of the first template.

12. The method according to claim 1 or 2, wherein: The template selection box includes a template filtering sub-box; After the interactive interface displays a template selection box containing template information of multiple target input templates to the user, the following further includes: Obtaining the filter word entered by the user in the template filter subbox; Determining a second template related to the filter word in the target input template; The template information displayed in the template selection box is updated based on the template information of the associated template, wherein the associated template is a template in the target input template except the second template.

13. The method according to claim 1 or 2, further comprising: In response to a user selecting a template information in the template selection box, an attachment upload control corresponding to a target input template indicated by the template information selected by the user is displayed on the interactive interface.

14. The method according to claim 13, wherein: The attachment upload control includes at least one of the following controls: Image upload control, video upload control, document upload control.

15. The method according to claim 1 or 2, wherein: The step of displaying a template selection box containing template information of multiple target input templates to the user on the interactive interface includes: A template selection box containing template information of multiple target input templates is displayed in other areas of the interactive interface except the character input area.

16. A template information display device, applied to a terminal device, comprising: A character acquisition module is used to acquire input characters entered by the user in the interactive interface when the user uses the interactive service provided by the large model platform; A character detection module, used to detect whether the input character is the same as a preset template wake-up character; An information display module is used to display a template selection box containing template information of multiple target input templates to the user in the interactive interface when the input character is the same as the template wake-up character, wherein each of the target input templates is a template set for an interactive scenario between the large model platform and the user, and guides the user to input information. The large model platform is a platform designed based on the large model, which is divided into two parts: one is an interactive part that receives user information and feeds back information to the user, and the other is an information processing part that processes information. The interactive part is deployed on the terminal device at the front end, and the information processing part is deployed in the server at the background. The multiple target input templates are all or part of the templates stored in the server.

17. The apparatus according to claim 16, further comprising: The operation response module is used to hide the template selection box in response to the user's selection operation of selecting the template information in the template selection box, and display the information items to be filled in the target input template indicated by the template information selected by the user in the character input area.

18. The device according to claim 17, wherein: The operation response module includes: The dynamic transition submodule is used to pop up a template selection box containing template information of multiple target input templates in a first dynamic transition mode.

19. The device according to claim 18, wherein: The dynamic transition submodule is specifically used for: Popping up a blank template selection box in a first dynamic transition manner, and during the dynamic transition process of the blank template selection box, displaying template information of multiple target input templates in the blank template selection box in a second dynamic transition manner; or A blank template selection box is popped up in the first dynamic transition mode, and after the dynamic transition of the blank template selection box is completed, template information of multiple target input templates is displayed in the blank template selection box in the second dynamic transition mode.

20. The device according to claim 16 or 17, wherein: The information display module includes: The template pop-up submodule is used to pop up a template selection box containing template information of multiple target input templates from a starting position determined according to the character input area in the interactive interface.

21. The device according to claim 20, wherein: The template pop-up submodule is specifically used for: A template selection box containing template information of multiple target input templates pops up from the upper boundary of the character input area in the interactive interface from bottom to top.

22. The device according to claim 16 or 17, wherein: The character detection module is specifically used for: When the screen is focused on the character input area and the character input area belongs to the question and answer area, detecting whether the input character is the same as the preset template wake-up character; The information display module is specifically used for: A selection box display event is triggered, and a handler for the selection box display event is called to render a container element corresponding to the template selection box on the interactive interface.

23. The device according to claim 16 or 17, wherein: The target input template is determined according to at least one of the following information recorded in the large model platform: User historical interaction information, user interest information, and historical template usage information.

24. The device according to claim 23, wherein: The target input template is determined as follows: Extracting target keywords from the user historical interaction information and / or the user interest information recorded in the large model platform, and determining an input template corresponding to the target keyword as the target input template according to a correspondence between preset keywords and input templates; and / or According to the historical template usage information recorded in the large model platform, the input template that the user expects to select is predicted as the target input template.

25. The apparatus according to claim 16 or 17, further comprising: A first hiding module, configured to hide the template selection box if a deletion operation of the user on the input character is detected after the template selection box containing the template information of the plurality of target input templates is displayed to the user; and / or A second hiding module is used to hide the template selection box if it is detected that the user inputs characters again after the template selection box containing the template information of the multiple target input templates is displayed to the user; and / or The third hiding module is used to hide the template selection box after the template selection box containing template information of multiple target input templates is displayed to the user, if the template selection box contains a hidden control and a click operation of the user clicking on the hidden control is detected.

26. The device according to claim 16 or 17, wherein: The template selection box includes a template search subbox; The device also includes: A search term acquisition module, configured to acquire a search term input by a user in the template search sub-box after the interactive interface displays a template selection box containing template information of a plurality of target input templates to the user; A first template determination module, used to determine a first template related to the search term from among a plurality of preset input templates; The first updating module is used to update the template information displayed in the template selection box based on the template information of the first template.

27. The device according to claim 16 or 17, wherein: The template selection box includes a template filtering sub-box; The device also includes: A filter word acquisition module, used to obtain the filter word input by the user in the template filter sub-box after the interactive interface displays a template selection box containing template information of multiple target input templates to the user; A second template determination module, used to determine a second template related to the filter word in the target input template; The second updating module is used to update the template information displayed in the template selection box based on the template information of the associated template, wherein the associated template is a template in the target input template except the second template.

28. The apparatus according to claim 16 or 17, further comprising: The attachment upload module is used to display an attachment upload control corresponding to the target input template indicated by the template information selected by the user in the template selection box in the interactive interface in response to the user's selection operation of selecting the template information in the template selection box.

29. The device according to claim 28, wherein The attachment upload control includes at least one of the following controls: Image upload control, video upload control, document upload control.

30. The device according to claim 16 or 17, wherein: The information display module is specifically used for: A template selection box containing template information of multiple target input templates is displayed in other areas of the interactive interface except the character input area.

31. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 15.

32. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-15.

33. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 15.