Information interaction method and device based on large language model, equipment and storage medium
By setting target shortcut buttons and group chat functions in the chat interface, the cumbersome user information input and AI-generated content authenticity supervision problems are solved, and convenient information interaction and high accuracy are achieved.
Patent Information
- Application Number
- CN202411221647.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-02
- Publication Date
- 2024-11-08
AI Technical Summary
When users chat with large language models, the information input steps in the prior art are cumbersome, which affects the user experience, and it is difficult to implement the authenticity and accuracy of AI-generated content.
Provides an information interaction method based on a large language model. By setting target shortcut keys in the chat interface, users can quickly select user ID and large language model ID, enter it directly into the input box, and support multiple large language models in group chat. Interaction and comments can be used to improve the convenience and accuracy of information interaction.
It simplifies the information interaction process between users and large language models, saves operation time, and improves the comprehensiveness, authenticity and accuracy of information through the collaborative participation of multiple large language models, and reduces the generation of false content.
Smart Images

Figure CN118915942A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of artificial intelligence technology, and in particular to an information interaction method, apparatus, device and storage medium based on a large language model. Background Art
[0002] At present, the update and iteration speed of large language model technology is accelerating and gradually becoming mature, and is recognized and used by more and more users. However, when users chat with large language models, they still use the conventional information input operations used by existing instant messaging software. The operation steps are relatively cumbersome, which affects the user experience.
[0003] In addition, as more and more AI-generated content continues to grow, the supervision of the authenticity and accuracy of Internet content information will face new challenges.
[0004] Usually, users can communicate with a large language model by inputting messages into the large language model. In this process, it is often a dialogue between the user and the large language model. The user can only obtain the information provided by the large language model, which makes the information that the user can obtain in the process of communicating with the large language model very limited. Summary of the invention
[0005] The purpose of this application is to provide an information interaction method, device, equipment and storage medium based on a large language model.
[0006] To achieve the above objectives, this application provides the following solutions:
[0007] In a first aspect, the present application provides an information interaction method based on a large language model, comprising:
[0008] Displaying a chat interface including conversation content between one or more users and one or more large language models;
[0009] In response to a first operation of a user on a target shortcut key in the chat interface, displaying a display list including a user identifier and a large language model identifier;
[0010] In response to a user selecting a target user identifier and / or a target large language model identifier in the display list, inputting the target user identifier and / or the target large language model identifier into an input box of the chat interface;
[0011] In response to a user's sending operation on the input box, the content in the input box of the chat interface is sent to a user terminal corresponding to the target user identifier and / or a large language model corresponding to the target large language model.
[0012] Optionally, the information interaction method based on the large language model further includes:
[0013] In response to the selection operation, the target user identifier and / or the target large language model identifier with the added identification identifier is input into the input box.
[0014] Optionally, the information interaction method based on the large language model further includes:
[0015] Receive a reply message sent by the user terminal corresponding to the target user identifier and / or the large language model corresponding to the target large language model identifier regarding the content in the input box, and display the reply message on the chat interface.
[0016] Optionally, before the step of sending the content in the input box of the chat interface to the user terminal corresponding to the target user identifier and / or the large language model corresponding to the target large language model in response to the user's sending operation on the input box, the step further includes:
[0017] In response to a user inputting a reply message to a chat message sent by a user or a large language model in the chat interface, the large language model identifier and / or user identifier corresponding to the reply message is input into the input box and / or additional information is input in the input box.
[0018] Optionally, before the step of sending the content in the input box of the chat interface to the user terminal corresponding to the target user identifier and / or the large language model corresponding to the target large language model in response to the user's sending operation on the input box, the step further includes:
[0019] Receiving a selection operation of a user for a select all option in the display list;
[0020] When the select all option is a select all identifier option, adding select all identifier information indicating all user identifiers and large language model identifiers to the input box;
[0021] When the select all option is a user identifier select all option, adding user identifier select all information indicating all user identifiers to the input box;
[0022] When the select all option is a large language model identifier select all option, large language model identifier select all information indicating all large language model identifiers is added to the input box.
[0023] Optionally, the chat interface includes: a chat interface of an intelligent group; the step of displaying the chat interface including the conversation content between one or more users and one or more large language models includes:
[0024] In response to the user's selection operation for the smart group opening option, the chat interface of the smart group is displayed, wherein the smart group includes at least one user and multiple large language models, or the smart group includes multiple users and at least one language model.
[0025] Optionally, the information interaction method based on the large language model further includes:
[0026] In response to a user sending operation on the content in the input box, the content is sent to a user terminal and / or at least one or more large language models corresponding to at least one or more users in the smart group;
[0027] Receive reply messages sent by user terminals corresponding to at least one or more users and / or at least one or more large language models, and display the chat messages on the chat interface.
[0028] Optionally, the information interaction method based on the large language model further includes:
[0029] In response to a user input request to open a hot conversation display interface, the hot conversation display interface is displayed, where the hot conversation display interface includes: conversation content between the user and the large language model published to the display platform.
[0030] Optionally, the chat interface includes: a popular conversation display interface; the information interaction method based on the large language model also includes:
[0031] Receive a user's comment message on any conversation content in the hot conversation display interface, and send the comment message to the display platform, so that the display platform publishes the comment message to the hot conversation display interface.
[0032] In a second aspect, the present application provides an information interaction device based on a large language model, comprising:
[0033] A display module, used to display a chat interface including conversation contents between one or more users and one or more large language models;
[0034] In response to a first operation of a user on a target shortcut key in the chat interface, displaying a display list including a user identifier and a large language model identifier;
[0035] An input module, configured to input the target user identifier and / or the target large language model identifier into an input box of the chat interface in response to a user selecting the target user identifier and / or the target large language model identifier in the display list;
[0036] An interaction module is used to send the content in the input box of the chat interface to the user terminal corresponding to the target user identifier and / or the large language model corresponding to the target large language model in response to the user's sending operation on the input box.
[0037] Optionally, the input module is further used to:
[0038] In response to the selection operation, the target user identifier and / or the target large language model identifier with the added identification identifier is input into the input box.
[0039] Optionally, the display module is further used for:
[0040] Receive a reply message sent by the user terminal corresponding to the target user identifier and / or the large language model corresponding to the target large language model identifier regarding the content in the input box, and display the reply message on the chat interface.
[0041] Optionally, the input module is further used for:
[0042] In response to a user inputting a reply message to a chat message sent by a user or a large language model in the chat interface, the large language model identifier and / or user identifier corresponding to the reply message is input into the input box and / or additional information is input in the input box.
[0043] Optionally, the input module is further used for:
[0044] Receiving a selection operation of a user for a select all option in the display list;
[0045] When the select all option is a select all identifier option, adding select all identifier information indicating all user identifiers and large language model identifiers to the input box;
[0046] When the select all option is a user identifier select all option, adding user identifier select all information indicating all user identifiers to the input box;
[0047] When the select all option is a large language model identifier select all option, large language model identifier select all information indicating all large language model identifiers is added to the input box.
[0048] Optionally, the chat interface includes: a chat interface of a smart group; the display module is further used for:
[0049] In response to the user's selection operation for the smart group opening option, the chat interface of the smart group is displayed, wherein the smart group includes at least one user and multiple large language models, or the smart group includes multiple users and at least one language model.
[0050] Optionally, the interaction module is further used to:
[0051] In response to a user sending operation on the content in the input box, the content is sent to a user terminal and / or at least one or more large language models corresponding to at least one or more users in the smart group;
[0052] Receive reply messages sent by user terminals corresponding to at least one or more users and / or at least one or more large language models, and display the chat messages on the chat interface.
[0053] Optionally, the display module is further used for:
[0054] In response to a user input request to open a hot conversation display interface, the hot conversation display interface is displayed, where the hot conversation display interface includes: conversation content between the user and the large language model published to the display platform.
[0055] Optionally, the chat interface includes: a hot conversation display interface; the interaction module is further used to:
[0056] Receive a user's comment message on any conversation content in the hot conversation display interface, and send the comment message to the display platform, so that the display platform publishes the comment message to the hot conversation display interface.
[0057] In a third aspect, the present application provides an information interaction system based on a large language model, the information interaction system based on a large language model comprising: a server and a user terminal, the user terminal being connected to the server in communication via an API interface provided by the server;
[0058] The user terminal comprises:
[0059] A display module, used to display a chat interface including conversation contents between one or more users and one or more large language models;
[0060] In response to a first operation of a user on a target shortcut key in the chat interface, displaying a display list including a user identifier and a large language model identifier;
[0061] An input module, configured to input the target user identifier and / or the target large language model identifier into an input box of the chat interface in response to a user selecting the target user identifier and / or the target large language model identifier in the display list;
[0062] An interaction module, configured to send the content in the input box of the chat interface to a user terminal corresponding to the target user identifier and / or a large language model corresponding to the target large language model in response to a user sending operation on the input box;
[0063] The server comprises:
[0064] a processing module, configured to, in response to at least one first chat message sent by a first user terminal or a request to establish an intelligent group, input at least one first chat message into at least one large language model to obtain at least one first reply message, or connect at least one large language model to the intelligent group and send at least one first chat message to the large model;
[0065] Sending at least one first reply message to the first user terminal, or sending at least one first reply message to the smart group established by the first user terminal;
[0066] a publishing module, configured to publish the chat message and the reply message to a display interface in response to a display request sent by the first user terminal, so that at least one second user terminal obtains the chat message and the reply message from the display interface, the reply message at least including the first reply message, and the chat message at least including the first chat message;
[0067] In response to the comment content sent by at least one of the second user terminals to the chat message and the reply message, the comment content is published to the display interface, or the smart group joined by at least one of the second users.
[0068] In a fourth aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of any one of the above-mentioned information interaction methods based on a large language model.
[0069] In a fifth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any one of the above-mentioned information interaction methods based on a large language model.
[0070] In a sixth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of any one of the above-mentioned information interaction methods based on a large language model.
[0071] According to the specific embodiments provided in this application, this application discloses the following technical effects:
[0072] The present application provides an information interaction method, apparatus, device and storage medium based on a large language model. By setting a target shortcut key in a chat interface between a user and a large language model, the user can operate it to quickly open a dialogue target selection list containing a user identifier and a large language model identifier. The user can select the identifier in the selection list to input the user identifier and / or the large language model identifier into an input box, thereby sending the content in the input box to the specified large language model and / or user, so that the user can conveniently select the object to which the input content is to be sent in the chat interface with the large language model.
[0073] The present application sets a target shortcut button on the group chat dialogue interface between the user and the large language model. The user can directly open the target selection list to select the dialogue target by clicking the target shortcut button, instead of having to click the input box to open the input method window, click the symbol button in the input method window to open the symbol window, and then click the @ symbol inside to complete the operation, or long press the @ symbol in the input method window, slide to select the @ symbol, and then release it to complete the operation and open the dialogue target selection list. Therefore, the prior art requires three steps to open the dialogue target selection list, while the technical solution of the present application enables the user to directly click the target shortcut button, and only one step is required to complete the operation that the prior art requires three steps to complete, which brings great convenience to the user and saves operation time.
[0074] This application also solves the problem of authenticity and accuracy of AIGC content information:
[0075] As AI generates more and more content, the supervision of the authenticity and accuracy of Internet content information will face new challenges. This application enables users to participate in the comments on AIGC, which is content generated by AI, and the large language model also participates in the conversations, chats, messages, replies, comments, and replies to comments with users, and even multiple large language models have conversations, chats, messages, replies, comments, and replies to comments. The reply content of other large language models is analyzed and summarized, and incorrect reply content is corrected. It can also obtain the user's evaluation of the content of the large language model from the user's reply, comment and like data on the reply content of the large language model, correct its erroneous content and update it to the database, so that users can better distinguish right from wrong in the conversations, chats, and comments between large language models and between large language models, and correct errors in time to reduce or avoid the generation of false and untrue content.
[0076] This application also solves the problem that a single large language model is not good at certain aspects:
[0077] Since the content data and quantity of training samples of different large language models are not exactly the same, each large language model has its own characteristics and strengths. Multiple large language models participating in answering questions, replying to messages and replying to comments in the same chat interface will make up for the deficiencies or errors of the large language models and can effectively improve the comprehensiveness, authenticity and accuracy of AIGC content information. BRIEF DESCRIPTION OF THE DRAWINGS
[0078] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0079] Figure 1 A flowchart of an information interaction method based on a large language model provided in one embodiment of the present application;
[0080] Figure 2 One of the interface schematic diagrams of an information interaction method based on a large language model provided in one embodiment of the present application;
[0081] Figure 3 A second interface diagram of an information interaction method based on a large language model provided in an embodiment of the present application;
[0082] Figure 4 A third interface diagram of an information interaction method based on a large language model provided in an embodiment of the present application;
[0083] Figure 5 A fourth interface diagram of an information interaction method based on a large language model provided in an embodiment of the present application;
[0084] Figure 6 A fifth interface diagram of an information interaction method based on a large language model provided in an embodiment of the present application;
[0085] Figure 7 A sixth interface diagram of an information interaction method based on a large language model provided in an embodiment of the present application;
[0086] Figure 8 A seventh interface diagram of an information interaction method based on a large language model provided in an embodiment of the present application;
[0087] Fig. 9 An eighth interface diagram of an information interaction method based on a large language model provided in an embodiment of the present application;
[0088] Fig.10 A ninth interface diagram of an information interaction method based on a large language model provided in an embodiment of the present application;
[0089] Fig.11 A tenth interface diagram of an information interaction method based on a large language model provided in an embodiment of the present application;
[0090] Fig.12 A schematic diagram of the structure of an information interaction system based on a large language model provided in one embodiment of the present application;
[0091] Fig.13 A schematic diagram of functional modules of an information interaction device based on a large language model provided in one embodiment of the present application;
[0092] Fig.14 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION
[0093] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0094] like Figure 1 As shown, some embodiments of the present application provide an information interaction method based on a large language model, which includes the following steps 101 to 104. Among them:
[0095] Step 101: display a chat interface containing conversation content between one or more users and one or more large language models.
[0096] It should be noted that the execution subject of some embodiments of the present application is a user terminal, which is a terminal device installed with a client having a large language model. The user can communicate with the large language model through the chat interface provided by the user terminal. Of course, the chat interface can also be a chat interface of an intelligent group, which can include at least two users and at least one large language model, or at least one user and at least two large language models, so that the large language model and the user in the intelligent group can communicate through the chat interface.
[0097] The user terminal is connected to a server, which is used to provide data support for the user terminal. The server is deployed with an electronic device with a large language model, which can be a physical server or a cloud server, so that the server can provide service data based on the large language model to the user terminal. Among them, a large language model refers to a machine model with language interaction capabilities, such as LLM (Large Language Model). This model uses a deep learning model trained with a large amount of text data, which can generate natural language text or understand the meaning of language text. The large language model can handle a variety of natural language tasks, such as text classification, question and answer, dialogue, etc., and is an important path to artificial intelligence. At present, the large language model adopts a Transformer architecture and pre-training objectives (such as Language Modeling) similar to the small model. The difference from the small model is the increase in model size, training data and computing resources.
[0098] In the embodiments of this application, refer to Fig. 9 The user can open the chat interface with the large language model by clicking any large language model logo in the interface, such as "Large Language Model A" and "Large Language Model B". Of course, the user can also enter the chat interface of the smart group by clicking "Smart Group" in the interface.
[0099] Step 102: In response to a first operation of a user on a target shortcut key in the chat interface, a display list including a user identifier and a large language model identifier is displayed.
[0100] In an embodiment of the present application, the target shortcut key is a function key for opening a display list containing a user identifier and a large language model identifier. The target shortcut key is directly set in the chat interface without the user switching to other interfaces or opening other interfaces. The first operation can be an operation in the form of clicking, long pressing, sliding, voice, etc. on the user's target shortcut key. It can be set according to actual needs and is not limited here. The user identifier is identification information used to identify the user account. Each user identifier uniquely corresponds to a user account. The user account can log in to the terminal device to make the user identifier indicate the terminal device. The large language model identifier is identification information used to identify the large language model. Each large language model identifier uniquely corresponds to a large language model deployed in a server. The user identifier may include at least one of a user avatar and a user nickname, and the large language model identifier includes at least one of a large language model LOGO and a large language model name.
[0101] For example, refer to Figure 2 , where the target shortcut key can be the "@" style key next to the input box in the chat interface. The user can click the "@" key to open the display list. The display list can refer to Figure 4 , where the partition displays the user ID and the large language model ID. Since the display area in the display list is limited, the ID of each partition can be switched by setting a sliding page turning function. For example, the user can turn the page to view the user ID or the large language model ID by sliding. Furthermore, the user ID is in the form of a user avatar plus a user nickname, and the large language model ID is in the form of a large language model name and a large language model logo.
[0102] Step 103: In response to the user selecting the target user identifier and / or the target large language model identifier in the display list, the target user identifier and / or the target large language model identifier is input into an input box of the chat interface.
[0103] In an embodiment of the present application, after the user determines the user identifier and / or large language model identifier that needs to be indicated after viewing the display list, the user can determine the required target user identifier and / or target large language model through a selection operation, and then the target user identifier and / or target large language model can be entered into the input box.
[0104] For example, refer to Figure 3 , where the user can select the target user ID and / or the target large language model ID by selecting the operation, and after the user clicks OK, refer to Figure 4 , the display list will be closed, and the target user ID and target large language model ID will be added to the input box.
[0105] Step 104: In response to the user's sending operation on the input box, the content in the input box of the chat interface is sent to the user terminal corresponding to the target user identifier and / or the large language model corresponding to the target large language model.
[0106] In an embodiment of the present application, after the target user identifier and / or target large language model identifier selected by the user is added to the input bar, the user can continue to enter content in the input box. Of course, before the user selects and determines the target user identifier and / or target large language model identifier, the user can also enter content in the input bar. After the user determines that the content in the input box has been entered, the user clicks the send button to send the content in the input box to the user terminal corresponding to the target user identifier and / or the large language model corresponding to the target large language model. Of course, the content in the input box will also be displayed in the chat content of the chat interface.
[0107] The embodiment of the present application sets a target shortcut key in the chat interface between the user and the large language model, so that the user can operate it to quickly open a dialogue target selection list containing a user identifier and a large language model identifier. The user can select the identifier in the selection list to input the user identifier and / or the large language model identifier into the input box, thereby sending the content in the input box to the specified large language model and / or user, so that the user can conveniently select the object to which the input content is to be sent in the chat interface with the large language model.
[0108] Optionally, the step 104 includes: in response to the selection operation, inputting the target user identifier and / or the target large language model identifier after adding the identification identifier into the input box.
[0109] In an embodiment of the present application, after the user selects the target large language model identifier and / or user identifier in the display list, the target user identifier and / or large language model identifier with an identification identifier can be entered in the input box. The identification identifier is an identifier used to identify the required specified object. That is to say, through the identification identifier, the user and the system can identify which identifier in the content of the input box is used to specify the content sending object. Correspondingly, for the large language model identifier and user identifier without an identification identifier added to the input box, it is just normal input content and does not have the function of specifying the content sending object.
[0110] For example, refer to Figure 4 The identification mark can be a specific symbol such as "@", ".", ">", etc. The user can indicate the user or the large language model by adding indication information + user representation, or indication information + large language model identification in the input content, such as @the first large language model, @user 1, @user 2, etc.
[0111] Optionally, the information interaction method based on the large language model also includes: receiving a reply message sent by the user terminal corresponding to the target user identifier and / or the large language model corresponding to the target large language model identifier in response to the content in the input box, and displaying the reply message on the chat interface.
[0112] In an embodiment of the present application, after instructing that the content in the input box is sent to the user terminal corresponding to the target user identifier and / or the large language model corresponding to the target large language model identifier, if a reply message returned by the large language model and / or the user terminal is received, it can be displayed in the chat interface.
[0113] Optionally, before step 105, it also includes: in response to the user's reply message input to the chat message sent by the user or the large language model in the chat interface, inputting the large language model identifier and / or user identifier corresponding to the reply message into the input box and / or inputting additional information in the input box.
[0114] In the embodiment of the present application, the chat message can be a reply message sent by the user and the large language model to the chat interface, an input message of the user, etc. Usually, the display form of the chat message will be the form of the large language model LGO or the large language model name + message content, or the form of the user avatar or the user nickname + message content, which can be regarded as a chat message. As long as the message is displayed in the chat interface, it can be the chat message, which can be set according to actual needs and is not limited here. The reply message input can be the user's click, long press, slide and other operations on the chat message in the chat interface, which can be set according to actual needs and is not limited here.
[0115] Specifically, the user can make a third input for the large language model in the chat interface or the reply message sent by the user to add the large language model identifier of the large language model from which the reply message comes, or the user identifier of the user from whom the reply message comes, to the input box. Optionally, the selected reply message can also be entered in the input box, which can be set according to actual needs and is not limited here.
[0116] The user can add the large language model identifier corresponding to the large language model to the input bar by long pressing the large language model name or LOGO or the corresponding message content. The user can also drag the message content sent by the user to the chat interface or the user avatar or the user nickname to the input bar to add the user's corresponding user identifier to the input bar. Furthermore, when adding content to the input bar, the message content in the chat message can also be attached to the vicinity of the content already entered in the input bar for use as a reference content. The referenced content can be displayed in a display style that is different from the input content, such as font color or background color.
[0117] Optionally, before step 105, the method further includes:
[0118] Step 201: receiving a user's selection operation for a select all option in the display list.
[0119] Step 202: When the select all option is a select all identifier option, add identifier select all information indicating all user identifiers and large language model identifiers to the input box.
[0120] Step 203: When the select all option is a user identifier select all option, user identifier select all information indicating all user identifiers is added to the input box.
[0121] Step 204: When the select all option is a large language model identifier select all option, large language model identifier select all information indicating all large language model identifiers is added to the input box.
[0122] In the embodiments of this application, refer to Figure 5 The display list may include information for indicating all user identifiers and large language model identifiers. After the user selects the option to select all identifiers, refer to Figure 6 You can enter "@all" in the input box to select all information, so that the content in the input box is sent to all large language models and users in the display list.
[0123] Reference Figure 7 The display list may also include a large language model identifier selection option and a user identifier selection option for all large language models indicated by the user. Accordingly, after the user selects, refer to Figure 8 Based on the user selection operation, for example, user identification all-selection information of "@everyone" or large language model identification all-selection information of "@all large language models" will be added to the input box.
[0124] The embodiment of the present application sets the options of selecting all user identifiers, selecting all identifiers, and selecting all large language model identifiers in the display list, so that the user can conveniently send the input content indication to all users and / or all large language models in the display list.
[0125] Optionally, the chat interface includes: a chat interface of a smart group; the step 101 includes: in response to a user's selection operation for a smart group activation option, displaying the chat interface of the smart group, wherein the smart group includes at least one user and multiple large language models, or the smart group includes multiple users and at least one language model.
[0126] In the embodiment of the present application, the user can Fig. 9 . Click the "Group Chat" option in the chat interface of the smart group. It is worth noting that the smart group can include one user or multiple large language models, one large language model and multiple users, or multiple large language models and multiple users, thereby realizing the chat process between multiple dialogue subject objects.
[0127] Optionally, the information interaction method based on the large language model further includes:
[0128] Step 301, in response to a user sending operation for content in an input box, sending the content to a user terminal and / or at least one or more large language models corresponding to at least one or more users in the smart group;
[0129] Step 302: Receive a reply message sent by a user terminal corresponding to at least one or more users and / or at least one or more large language models, and display the chat message on the chat interface.
[0130] In an embodiment of the present application, a user can send input content to each chat object in the smart group by adding content in the input box of the chat interface of the smart group, and the sent input content will be displayed in the chat interface.
[0131] Furthermore, the user can add the chat object (large language model and / or user) to be indicated in the input box through the target shortcut key provided in some embodiments of the present application, and then send the input content to the indicated chat object. It should be noted here that regardless of whether the user indicates the chat object, the users and large language models in the smart group can obtain the input content in the chat interface. The difference is that if the large language model is indicated, the indicated large language model will send a reply message to the chat interface of the smart group for the input content. If the user is indicated, the user terminal corresponding to the indicated user will display the corresponding prompt information.
[0132] Optionally, the information interaction method based on the large language model further includes: in response to a user input request to open a popular conversation display interface, displaying a popular conversation display interface, wherein the popular conversation display interface includes: conversation content between the user and the large language model published to the display platform.
[0133] In the embodiments of this application, refer to Fig. 9 The application interface may also include a "hot conversation" function option. Users can click on this function option to input a request to open the hot conversation display interface. The hot conversation display will display the conversation content between the user and the large language model posted on the display platform. These conversation contents can be sorted from high to low according to the number of views, or according to the user's browsing habits, the conversation content that conforms to the user's browsing habits can be placed in the front position. Of course, the sorting method of hot conversations can also be based on other rules, which can be set according to actual needs and are not limited here.
[0134] Optionally, the chat interface includes: a popular conversation display interface; the information interaction method based on a large language model also includes: receiving a user's comment message on any conversation content in the popular conversation display interface, and sending the comment message to the display platform, so that the display platform publishes the comment message to the popular conversation display interface.
[0135] In the embodiments of this application, refer to Fig.10, users can also enter comments on the conversation content posted on the display platform in the conversation display interface, and then the comment messages will be posted to the display platform. The large language model can also reply to the user's comment messages. Similarly, the reply messages of the large language model will also be posted on the display platform.
[0136] Further, the hot conversation display interface can be provided with a target shortcut key, which can be set next to the user's comment input field for the conversation content. For example, refer to Fig.11 , where a target shortcut key in the style of “@” can also be set on the right side of the input bar. The target shortcut key in the popular conversation display interface has the same function as the target quick connect key in the above embodiment of the present application, and will not be repeated here.
[0137] Reference Fig.12 , showing an information interaction system based on a large language model provided in an embodiment of the present application, comprising: a server 1 and a user terminal 2, wherein the user terminal 1 is connected to the server 2 in communication via an API interface provided by the server 2;
[0138] The user terminal 2 comprises:
[0139] A display module 21, used to display a chat interface including conversation contents between one or more users and one or more large language models;
[0140] In response to a first operation of a user on a target shortcut key in the chat interface, displaying a display list including a user identifier and a large language model identifier;
[0141] An input module 22, configured to input the target user identifier and / or the target large language model identifier into an input box of the chat interface in response to a user selecting the target user identifier and / or the target large language model identifier in the display list;
[0142] An interaction module 23, configured to send the content in the input box of the chat interface to a user terminal corresponding to the target user identifier and / or a large language model corresponding to the target large language model in response to a user sending operation on the input box;
[0143] The server 1 comprises:
[0144] The processing module 11 is used to respond to at least one first chat message sent by the first user terminal or a request to establish an intelligent group, input at least one first chat message to at least one large language model to obtain at least one first reply message, or connect at least one large language model to the intelligent group and send at least one first chat message to the large model;
[0145] Sending at least one first reply message to the first user terminal, or sending at least one first reply message to the smart group established by the first user terminal;
[0146] a publishing module 12, configured to publish the chat message and the reply message to a display interface in response to a display request sent by the first user terminal, so that at least one second user terminal obtains the chat message and the reply message from the display interface, the reply message at least including the first reply message, and the chat message at least including the first chat message;
[0147] In response to the comment content sent by at least one of the second user terminals to the chat message and the reply message, the comment content is published to the display interface, or the smart group joined by at least one of the second users.
[0148] Optionally, the server 1 further includes:
[0149] The security filtering module 13 is used to perform a security audit on the output content of the large language model; when the output content fails the security audit, a prompt message indicating that the audit has failed is sent to the user terminal, and the large language model is instructed to regenerate the output content.
[0150] In an embodiment of the present application, the security filtering module will perform a content security review on the output content output by the large language model, mainly checking the sensitive words and illegal words in the output content that do not meet the output content requirements. If the output content passes the security review, the output content can be sent to the user terminal or published to the display platform. If the output content fails the security review, the output content is directly intercepted and a prompt message is sent to the user terminal indicating that the output content has not passed the security review.
[0151] Optionally, the server 1 further includes:
[0152] Database 14 is used to store and manage user information, display content source data, comment messages, like information, forwarding records, and historical conversation content between users and the large language model.
[0153] In an embodiment of the present application, the database can store various interactive contents between the large language model and the user terminal, as well as content records such as likes, forwardings, and comments of users on the display platform on the published content, and support functions such as user management, message content management, smart group management, forwarding management, large model dialogue management, and security review.
[0154] Based on the same inventive concept, the embodiment of the present application also provides an information interaction device based on a large language model for implementing the information interaction method based on a large language model involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the one or more embodiments of the information interaction device based on a large language model provided below can refer to the limitations of the information interaction method based on a large language model above, and will not be repeated here.
[0155] In an exemplary embodiment, Fig.13 As shown, an information interaction device 40 based on a large language model is provided, comprising:
[0156] Display module 401, used to display a chat interface including conversation contents between one or more users and one or more large language models;
[0157] In response to a first operation of a user on a target shortcut key in the chat interface, displaying a display list including a user identifier and a large language model identifier;
[0158] An input module 402, configured to input the target user identifier and / or the target large language model identifier into an input box of the chat interface in response to a user selecting the target user identifier and / or the target large language model identifier in the display list;
[0159] The interaction module 403 is used to send the content in the input box of the chat interface to the user terminal corresponding to the target user identifier and / or the large language model corresponding to the target large language model in response to the user's sending operation on the input box.
[0160] Optionally, the input module 402 is further used for:
[0161] In response to the selection operation, the target user identifier and / or the target large language model identifier with the added identification identifier is input into the input box.
[0162] Optionally, the display module 401 is further used for:
[0163] Receive a reply message sent by the user terminal corresponding to the target user identifier and / or the large language model corresponding to the target large language model identifier regarding the content in the input box, and display the reply message on the chat interface.
[0164] Optionally, the input module 402 is further used for:
[0165] In response to a user inputting a reply message to a chat message sent by a user or a large language model in the chat interface, the large language model identifier and / or user identifier corresponding to the reply message is input into the input box and / or additional information is input in the input box.
[0166] Optionally, the input module 402 is further used for:
[0167] Receiving a selection operation of a user for a select all option in the display list;
[0168] When the select all option is a select all identifier option, adding select all identifier information indicating all user identifiers and large language model identifiers to the input box;
[0169] When the select all option is a user identifier select all option, adding user identifier select all information indicating all user identifiers to the input box;
[0170] When the select all option is a large language model identifier select all option, large language model identifier select all information indicating all large language model identifiers is added to the input box.
[0171] Optionally, the chat interface includes: a chat interface of a smart group, and the display module 401 is further used for:
[0172] In response to the user's selection operation for the smart group opening option, the chat interface of the smart group is displayed, wherein the smart group includes at least one user and multiple large language models, or the smart group includes multiple users and at least one language model.
[0173] Optionally, the interaction module 403 is further configured to:
[0174] In response to a user sending operation on the content in the input box, the content is sent to a user terminal and / or at least one or more large language models corresponding to at least one or more users in the smart group;
[0175] Receive reply messages sent by user terminals corresponding to at least one or more users and / or at least one or more large language models, and display the chat messages on the chat interface.
[0176] Optionally, the display module 401 is further used for:
[0177] In response to a user input request to open a hot conversation display interface, the hot conversation display interface is displayed, where the hot conversation display interface includes: conversation content between the user and the large language model published to the display platform.
[0178] Optionally, the chat interface includes: a hot conversation display interface; the interaction module 403 is also used to:
[0179] Receive a user's comment message on any conversation content in the hot conversation display interface, and send the comment message to the display platform, so that the display platform publishes the comment message to the hot conversation display interface.
[0180] The embodiment of the present application sets a target shortcut key in the chat interface between the user and the large language model, so that the user can operate it to quickly open a dialogue target selection list containing a user identifier and a large language model identifier. The user can select the identifier in the selection list to input the user identifier and / or the large language model identifier into the input box, thereby sending the content in the input box to the specified large language model and / or user, so that the user can conveniently select the object to which the input content is to be sent in the chat interface with the large language model.
[0181] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Fig.14 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store information interaction data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for information interaction based on a large language model is implemented.
[0182] Those skilled in the art will understand that Fig.14 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0183] In an exemplary embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.
[0184] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.
[0185] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.
[0186] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.
[0187] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).
[0188] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.
[0189] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0190] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.
Claims
1. An information interaction method based on a large language model, It is characterized in that The information interaction method based on the large language model includes: Displaying a chat interface including conversation content between one or more users and one or more large language models; In response to a first operation of a user on a target shortcut key in the chat interface, displaying a display list including a user identifier and a large language model identifier; In response to a user selecting a target user identifier and / or a target large language model identifier in the display list, inputting the target user identifier and / or the target large language model identifier into an input box of the chat interface; In response to a user's sending operation on the input box, the content in the input box of the chat interface is sent to a user terminal corresponding to the target user identifier and / or a large language model corresponding to the target large language model.
2. The information interaction method based on a large language model according to claim 1, It is characterized in that The information interaction method based on the large language model also includes: In response to the selection operation, the target user identifier and / or the target large language model identifier with the added identification identifier is input into the input box.
3. The information interaction method based on a large language model according to claim 1, It is characterized in that The information interaction method based on the large language model also includes: Receive a reply message sent by the user terminal corresponding to the target user identifier and / or the large language model corresponding to the target large language model identifier regarding the content in the input box, and display the reply message on the chat interface.
4. The information interaction method based on a large language model according to claim 1, It is characterized in that Before the step of sending the content in the input box of the chat interface to the user terminal corresponding to the target user identifier and / or the large language model corresponding to the target large language model in response to the user's sending operation on the input box, the step further includes: In response to a user inputting a reply message to a chat message sent by a user or a large language model in the chat interface, the large language model identifier and / or user identifier corresponding to the reply message is input into the input box and / or additional information is input in the input box.
5. The information interaction method based on a large language model according to claim 1, It is characterized in that Before the step of sending the content in the input box of the chat interface to the user terminal corresponding to the target user identifier and / or the large language model corresponding to the target large language model in response to the user's sending operation on the input box, the step further includes: Receiving a selection operation of a user for a select all option in the display list; When the select all option is a select all identifier option, adding select all identifier information indicating all user identifiers and large language model identifiers to the input box; When the select all option is a user identifier select all option, adding user identifier select all information indicating all user identifiers to the input box; When the select all option is a large language model identifier select all option, large language model identifier select all information indicating all large language model identifiers is added to the input box.
6. The information interaction method based on a large language model according to claim 1, It is characterized in that The chat interface includes: a chat interface of a smart group; The step of displaying a chat interface including the conversation content between one or more users and one or more large language models comprises: In response to the user's selection operation for the smart group opening option, the chat interface of the smart group is displayed, wherein the smart group includes at least one user and multiple large language models, or the smart group includes multiple users and at least one language model.
7. The information interaction method based on a large language model according to claim 6, It is characterized in that The information interaction method based on the large language model also includes: In response to a user sending operation on the content in the input box, the content is sent to a user terminal and / or at least one or more large language models corresponding to at least one or more users in the smart group; Receive reply messages sent by user terminals corresponding to at least one or more users and / or at least one or more large language models, and display the chat messages on the chat interface.
8. The information interaction method based on a large language model according to claim 1, It is characterized in that The information interaction method based on the large language model also includes: In response to a user input request to open a hot conversation display interface, the hot conversation display interface is displayed, where the hot conversation display interface includes: conversation content between the user and the large language model published to the display platform.
9. The information interaction method based on a large language model according to claim 8, It is characterized in that The chat interface includes: a popular conversation display interface; The information interaction method based on the large language model also includes: Receive a user's comment message on any conversation content in the hot conversation display interface, and send the comment message to the display platform, so that the display platform publishes the comment message to the hot conversation display interface.
10. An information interaction device based on a large language model, It is characterized in that The information interaction device based on the large language model includes: A display module, used to display a chat interface including conversation contents between one or more users and one or more large language models; In response to a first operation of a user on a target shortcut key in the chat interface, displaying a display list including a user identifier and a large language model identifier; An input module, configured to input the target user identifier and / or the target large language model identifier into an input box of the chat interface in response to a user selecting the target user identifier and / or the target large language model identifier in the display list; An interaction module is used to send the content in the input box of the chat interface to the user terminal corresponding to the target user identifier and / or the large language model corresponding to the target large language model in response to the user's sending operation on the input box.
11. An information interaction system based on a large language model, It is characterized in that The information interaction system based on the large language model includes: a server and a user terminal, wherein the user terminal is connected to the server through an API interface provided by the server; The user terminal comprises: A display module, used to display a chat interface including conversation contents between one or more users and one or more large language models; In response to a first operation of a user on a target shortcut key in the chat interface, displaying a display list including a user identifier and a large language model identifier; An input module, configured to input the target user identifier and / or the target large language model identifier into an input box of the chat interface in response to a user selecting the target user identifier and / or the target large language model identifier in the display list; An interaction module, configured to send the content in the input box of the chat interface to a user terminal corresponding to the target user identifier and / or a large language model corresponding to the target large language model in response to a user sending operation on the input box; The server comprises: a processing module, configured to, in response to at least one first chat message sent by a first user terminal or a request to establish an intelligent group, input at least one first chat message into at least one large language model to obtain at least one first reply message, or connect at least one large language model to the intelligent group and send at least one first chat message to the large model; Sending at least one first reply message to the first user terminal, or sending at least one first reply message to the smart group established by the first user terminal; a publishing module, configured to publish the chat message and the reply message to a display interface in response to a display request sent by the first user terminal, so that at least one second user terminal obtains the chat message and the reply message from the display interface, the reply message at least including the first reply message, and the chat message at least including the first chat message; In response to the comment content sent by at least one of the second user terminals to the chat message and the reply message, the comment content is published to the display interface, or the smart group joined by at least one of the second users.
12. A computer device, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the information interaction method based on a large language model described in any one of claims 1 to 9.
13. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the information interaction method based on a large language model described in any one of claims 1 to 9 are implemented.
Citation Information
Cited By
Model output result display method and device and data processing system
CN119556829A
Session message reply method and device, electronic equipment, storage medium and program product
CN120455426A
Information sharing method and device, equipment, storage medium and computer program product
CN120561365A
Comment content generation method and device and electronic equipment
CN121255319A
