Method and device for summarizing messages

Abstract

The invention discloses a message summarization method and device, and belongs to the technical field of data processing. The method comprises the steps that an application interface of a social application is displayed, the application interface comprises N session entries, and N is a positive integer; receiving a first input for at least one first session entry in the N session entries; in response to the first input, summarizing chat messages in an unread state in the at least one first session entry to obtain message summarizing information; and displaying the message summary information corresponding to each first session entry.

Description

Technical Field

[0001] This application belongs to the technical field of data processing, and particularly relates to a method and apparatus for summarizing messages. Background Art

[0002] Nowadays, in the social applications of electronic devices, a user usually joins multiple chat groups and adds multiple contacts. Therefore, if the user has frequent daily communications with other contacts, a large number of unread chat messages often accumulate in the social application. Among them, many unread chat messages may be simple expressions, repeated replies, or idle chat messages without substantial content, and there is no substantial content in these chat messages. If the user reads all unread chat messages one by one, the efficiency of this reading method is relatively low, and it is difficult to obtain important content in the unread messages in a timely manner. Summary of the Invention

[0003] The purpose of the embodiments of this application is to provide a method and apparatus for summarizing messages, which can solve the technical problem of relatively low reading efficiency when faced with a large number of unread messages.

[0004] In a first aspect, the embodiments of this application provide a method for summarizing messages, which includes:

[0005] Display an application interface of a social application, where the application interface includes N session entries, and N is a positive integer;

[0006] Receive a first input for at least one first session entry among the N session entries;

[0007] In response to the first input, summarize the chat messages in the at least one first session entry that are in an unread state to obtain message summary information;

[0008] Display the message summary information corresponding to each of the first session entries.

[0009] In a second aspect, the embodiments of this application provide a device for summarizing chat messages, which includes:

[0010] A first display module, configured to display an application interface of a social application, where the application interface includes N session entries, and N is a positive integer;

[0011] A first receiving module, configured to receive a first input for at least one first session entry among the N session entries;

[0012] A first summarizing module, configured to, in response to the first input, summarize the chat messages in the at least one first session entry that are in an unread state to obtain message summary information;

[0013] A second display module, configured to display the message summary information corresponding to each of the first session entries.

[0014] In a third aspect, an embodiment of the present application provides an electronic device, which includes a processor and a memory. The memory stores a program or instructions that can run on the processor. When the program or instructions are executed by the processor, the steps of the method provided in the first aspect are implemented.

[0015] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instructions are stored. When the program or instructions are executed by a processor, the steps of the method provided in the first aspect are implemented.

[0016] In a fifth aspect, an embodiment of the present application provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor, and the processor is configured to run a program or instructions to implement the method provided in the first aspect.

[0017] In a sixth aspect, an embodiment of the present application provides a computer program product, which is stored in a storage medium and is executed by at least one processor to implement the method provided in the first aspect.

[0018] In the method and apparatus for summarizing messages in the present application, when multiple session entries are displayed in the application interface of a social application, the system can receive a first input from a user for at least one of the first session entries, and then trigger a summary of the content of the unread messages in the selected at least one first session entry to generate corresponding message summary information. And the message summary information corresponding to each first session entry is displayed according to the session entry. In this way, the message summary information of the unread messages in each selected session entry can be clearly presented to the user, helping them quickly understand the core content of each session entry. Compared with the related art of checking unread messages one by one, through the present application, the user does not need to spend a lot of time browsing low-value content or frequently switch between multiple session entries, but can directly obtain key information quickly through the automatically generated message summary information, thereby improving the user's reading efficiency when facing a large number of unread messages. Description of the Drawings

[0019] Figure 1 is a flowchart of a method for summarizing messages provided in some embodiments of the present application;

[0020] Figure 2 is a schematic diagram of a display interface of an electronic device provided in some embodiments of the present application;

[0021] Figure 3 is a schematic diagram of a display interface of an electronic device provided in some embodiments of the present application;

[0022] Figure 4 It is a schematic diagram of the display interface of an electronic device provided by some embodiments of the present application;

[0023] Figure 5 It is a schematic diagram of the display interface of an electronic device provided by some embodiments of the present application;

[0024] Figure 6 It is a schematic structural diagram of a summary device for chat messages provided by some embodiments of the present application;

[0025] Figure 7 It is a schematic structural diagram of an electronic device provided by some embodiments of the present application;

[0026] Figure 8 It is a schematic diagram of the hardware structure of an electronic device provided by some embodiments of the present application. Detailed implementation manners

[0027] Next, the technical solutions in the embodiments of the present application will be clearly described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, rather than all, of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art belong to the scope of protection of the present application.

[0028] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, rather than to describe a specific order or sequence. It should be understood that such terms can be interchanged under appropriate circumstances so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. generally belong to the same category, and the number of objects is not limited. For example, the first object can be one or multiple. In addition, "and / or" in the specification and claims means at least one of the connected objects, and the character " / " generally indicates an "or" relationship between the associated objects before and after.

[0029] To solve the above technical problems, the present application provides a method for summarizing messages. Next, in conjunction with the accompanying drawings, the method for summarizing messages provided by the embodiments of the present application will be described in detail through specific embodiments and their application scenarios.

[0030] As Figure 1 shown, Figure 1 It is a schematic flowchart of a method for summarizing messages provided by an embodiment of the present application. The embodiment of the present application provides a method for summarizing messages, and the method may include:

[0031] S101, display an application interface of a social application, where the application interface includes N session entries, and N is a positive integer;

[0032] In this embodiment, a social application refers to an application program for realizing online communication and information sharing between users. The application interface of the social application refers to the main operation interface of the social application, and the application interface includes N conversation entries. Each conversation entry is an entrance to a conversation between a user and a contact or a chat group.

[0033] Exemplarily, the title of the conversation and the summary information of the conversation can be displayed in each conversation entry, where the title can be the name of the contact or the name of the chat group, and the summary information can be the most recent chat message in the conversation. As Figure 2 shown, the social application is a chat application program, and the application interface 201 of the chat application program includes 4 conversation entries, and the four conversation entries respectively include the conversation entries of Group 1 and Group 2, and the conversation entries of Contact 1 and Contact 2.

[0034] S102, receiving a first input to at least one first conversation entry among the N conversation entries;

[0035] In this embodiment, when the electronic device displays the application interface of the social application, the user can select at least one first conversation entry to perform message summary information by making a first input to the application interface. Among them, the first input is used to indicate selecting at least one first conversation entry from the N conversation entries in the social application and performing message summary information on the unread chat messages in the at least one first conversation entry.

[0036] Among them, the first input can be a touch input of the user on at least one first conversation entry in the application interface of the electronic device through a finger or a touch device such as a stylus. For example, the touch input can be a touch click operation, or a swipe operation, or other operations. The first input can also be an input operation performed by the user with the help of other input devices such as a mouse, a remote control device, and a keyboard connected to the electronic device.

[0037] In some embodiments of the present application, the above-mentioned first input is used to select at least one first session entry for message summary information, and the first input may be a first operation. Exemplarily, the above-mentioned first input includes but is not limited to: a long-press input by the user on at least one first session entry through a touch device such as a finger or a stylus, or a voice command input by the user, or a specific gesture input by the user, or other feasible inputs, which can be specifically determined according to actual usage requirements, and the embodiments of the present invention do not make limitations. The specific gesture in the embodiments of the present application may be any one of a click gesture, a swipe gesture, a drag gesture, a pressure recognition gesture, a long-press gesture, an area change gesture, a double-press gesture, and a double-click gesture; the click input in the embodiments of the present application may be a single-click input, a double-click input, or a click input of any number of times, etc., and may also be a long-press input or a short-press input. For example, the above-mentioned first input may be: a double-click input by the user on at least one first session entry in the application interface.

[0038] S103, in response to the first input, summarize the chat messages in the at least one first session entry that are in an unread state to obtain message summary information.

[0039] In the embodiments of the present application, when the electronic device's system receives the first input from the user for at least one first session entry, it can respond to this first input and extract the chat messages in the at least one first session entry that are in an unread state.

[0040] Exemplarily, when receiving the first input from the user, the system can respond to this first input and automatically open the chat page corresponding to each first session entry. After entering the chat page, the system can simulate the way of manual browsing and continuously swipe up from the currently displayed chat page to obtain the chat screenshots of the chat messages in the unread state in the chat page screen by screen. It will automatically stop obtaining chat screenshots until the system detects that there is no "unread message" prompt identifier in the chat page.

[0041] After obtaining the chat screenshots, the text information in the chat screenshots can be extracted through a multimodal model or an optical character recognition (ORC) model, and the extracted text information will be structured and stored according to three elements: the sender, the sending time, and the message content to form complete chat messages one by one.

[0042] After obtaining the complete chat messages, the chat messages in the at least one first session entry that are in an unread state can be summarized once to obtain the message summary information corresponding to each first session entry.

[0043] In some embodiments, the step of, in response to the first input, summarizing the chat messages in the at least one first session entry that are in an unread state to obtain message summary information includes:

[0044] Obtain input information, where the input information is used to indicate unread content in the summary conversation entries;

[0045] Display a reply statement generated according to the input information, where the reply statement is used to guide the user to perform the first input on the conversation entry to be summarized;

[0046] In the case of receiving the first input for the at least one first conversation entry, in response to the first input, summarize the chat messages in the at least one first conversation entry that are in the unread state according to the input information to obtain message summary information.

[0047] In this embodiment, when the electronic device displays the application interface of the social application, the user can input the input information to the electronic device. The input information can be a question or request input by the user and is used to interact with the electronic device. Among them, the input information can be input in text mode or voice mode. In text mode, the user can directly input text to the device through the keyboard, touchpad, screen, etc. of the electronic device. In voice mode, the user can perform voice input through a voice input device such as a microphone, and the device can convert the input voice into text format content.

[0048] In this embodiment, the input information can be used to indicate unread content in the summary conversation entries. Then, after the system receives the input information, it can generate and display a corresponding reply statement according to the input information, and the reply statement can be used to guide the user to screen out the conversation entries to be summarized through the first input.

[0049] Then, when the user sees the displayed reply statement, they can select at least one first conversation entry from the displayed N conversation entries to perform the first input according to the content indicated by the reply statement. Then the system will respond to the first input, extract the chat messages in the at least one first conversation entry that are in the unread state, and summarize each chat message in the at least one first conversation entry that is in the unread state once to obtain the message summary information corresponding to each first conversation entry.

[0050] After the electronic device receives the input information, it can transmit the input information to the language large model deployed in the electronic device, identify the user intention corresponding to the input information through the language large model, then generate a corresponding reply statement based on the user intention, and display the reply statement.

[0051] Exemplarily, as shown in the electronic device Figure 3In the application interface 201 of the social application shown, the user can wake up the voice assistant in the electronic device by voice and input information by voice. The input information can be "Please help me summarize these unread messages". Then, the voice assistant can transmit the input information to the language model, and the language model generates a reply statement "Please select the conversation entries you want to summarize and click the start summary button below or reply by voice to start summarizing". Subsequently, a first text box 301 is displayed in the application interface. The first text box includes the displayed input information and reply statement, and also includes the displayed start summary button 302.

[0052] Then, the user can select at least one first conversation entry to be summarized according to the reply statement and click the displayed 'Start Summary' button, and then the system will summarize the selected at least one first conversation entry.

[0053] In this embodiment, the reply statement generated according to the input information can be displayed, and the user is guided to select the conversation entries to be summarized through the displayed reply statement. This conversational method can guide the user to accurately select the conversation entries to be summarized, thereby improving the interaction efficiency between the user and the electronic device.

[0054] In some embodiments, the message summary information includes event summary. Summarizing the unread chat messages in the at least one first conversation entry according to the input information to obtain message summary information includes:

[0055] Generating first description information according to the input information, where the first description information is used to indicate summarizing the events in the chat messages;

[0056] Inputting the first description information and the unread chat messages into the language model, and the language model summarizes the events in the chat messages according to the first description information to obtain the event summary of at least one event.

[0057] In this embodiment, the events in the chat messages refer to: information segments centered around a specific theme, view, or behavior in the chat messages. For example, the events can include content such as transaction notifications, schedule arrangements, opinion discussions, product recommendations, and problem feedback.

[0058] After the system receives the input information and recognizes that the input information is used to indicate summarizing the unread content in the conversation entries, since summarizing the unread content in the conversation entries includes summarizing the events in the unread content, the system can modify the input information into a more detailed first task description according to the input information, and the first task description can be used to indicate summarizing the events in the chat messages.

[0059] Then, the system can input the unread chat messages and the first description information into the language large model as prompt words. The language large model summarizes the events in the chat messages according to the first description information to obtain event summaries.

[0060] Specifically, each event summary can be the summary information generated by extracting semantically independent event units from the chat messages and structuring each event. Each event summary can include an event title and event details. For example, the event title can be "Department regular meeting arrangement", "Product recommendation discussion", "Project delay suggestion", etc.; while the event details can be supplementary explanations of the event, including specific time, actions, opinion exchanges or background information, etc., to make the event semantically more complete.

[0061] In the embodiments of the present application, explicit description information can be generated according to the input information of the user to guide the language large model to focus on the events in the chat messages for extraction and summary, so as to more accurately identify and summarize the events in the chat messages, and help the user understand the core content of the chat messages more efficiently.

[0062] In some embodiments, the message summary information includes matter reminders. Summarizing the at least one unread chat message in the first session entry to obtain message summary information further includes:

[0063] Generating second description information according to the input information, where the second description information is used to indicate summarizing the matter reminders in the chat messages;

[0064] Determining at least one reminder identifier in the unread chat messages in the first session entry, where the reminder identifier is used to remind a specific user to view the chat messages;

[0065] Determining the chat messages associated with the at least one reminder identifier as reminder messages;

[0066] Inputting the second description information and the reminder messages into the language large model, and the language large model summarizes the reminder messages according to the second description information to obtain matter reminders.

[0067] In this embodiment, the matter reminder refers to the reminder information extracted from the chat messages and associated with the reminder identifier, and the structured reminder content generated based on the content of these reminder information. The matter reminder is used to remind a specific user to respond to or handle certain specific matters. Among them, the reminder identifier can be the symbol "@". For example, the chat message can be "@User A, please submit the PPT before 5 pm tomorrow".

[0068] After the system receives the input information and identifies that the input information is used to indicate summarizing the unread content in the conversation entries, since summarizing the chat messages in the unread state includes matter reminders, the system can modify the input information into a more detailed second task description according to the input information, and the second task description can be used to indicate summarizing the matter reminders in the chat messages.

[0069] Then, the system can use the chat messages in the unread state and the second description information as prompt words and input them into the language model. The language model can identify at least one reminder identifier in the chat messages according to the second description information, and then determine the chat messages associated with each reminder identifier, and determine the chat messages associated with the reminder identifier as reminder messages. Among them, the chat messages associated with the reminder identifier can be the chat messages containing the reminder identifier or the chat messages adjacent to the reminder identifier.

[0070] After identifying the reminder messages, the language model can summarize the reminder messages to obtain structured matter reminders. Exemplarily, each reminder identifier in the first conversation entry can correspond to a matter reminder. For example, when the reminder message associated with the reminder identifier is "@User A, please submit the visa materials before 3 pm tomorrow", the matter reminder can be "User A needs to submit the visa materials before 3 pm tomorrow"; when the reminder message associated with the reminder identifier is "@User B, has the client report you are responsible for been updated? It's due today", the matter reminder can be "User B needs to update the client report as soon as possible and submit it today".

[0071] In the embodiments of the present application, by identifying the reminder identifiers in the chat messages and obtaining the reminder messages associated with the reminder identifiers in the chat messages, the language model can be guided to summarize the reminder messages to obtain matter reminders, and the matter reminders can help users efficiently capture the to-do matters that are directive to them, avoid missing key messages, and improve the response efficiency of the to-do matters.

[0072] In some embodiments, the reminder messages include first reminder messages and second reminder messages, and determining the chat messages associated with the at least one reminder identifier as reminder messages includes:

[0073] Determining the chat messages containing the reminder identifier as the first reminder messages corresponding to the reminder identifier;

[0074] Determining at least one chat message before the first reminder message and at least one chat message after the first reminder message as the second reminder messages corresponding to the reminder identifier.

[0075] In this embodiment, when the system recognizes that a certain chat message contains a reminder identifier, since this chat message is a message directly sent to a certain user for reminder, this chat message can be directly determined as a reminder message, that is, the first reminder message. At the same time, considering that in the actual conversation process, the reminder content may be distributed in the chat messages adjacent to the first reminder message, the system will also determine at least one chat message before and after the first reminder message as reminder messages, as the second reminder messages. Finally, the first reminder message and the second reminder messages together constitute a complete reminder message set for generating item reminders.

[0076] Exemplarily, the reminder identifier can be the symbol "@". The system can traverse all unread chat messages in the first conversation entry, find the first reminder messages containing the reminder identifier, and record the position index i of each first reminder message to obtain the index set I:

[0077] I = {i1,…i m ...,i n}

[0078] where n is the total number of the first reminder messages, and i1 represents the index position of the first first reminder message.

[0079] Since everyone's speaking and chatting styles are different, the reminder identifier "@" may appear alone, or may appear in the previous or next message of the actual reminder content. In addition, the chat messages around the first reminder message also need to be obtained. Therefore, an expansion can be made to the reminder message, that is, obtain the position indexes of the previous and next j messages of the first reminder message to get the expanded index set j can be 3. The expanded message index is:

[0080]

[0081] The expanded message index set I e is:

[0082]

[0083] where, includes the mth first reminder message, the 3 second reminder messages before this first reminder message, and the 3 second reminder messages after this first reminder message. I e is the expanded message index set.

[0084] After obtaining the expanded index set, the reminder messages corresponding to the expanded index set and the second description information can be input into the language large model to obtain the item reminder output by the language large model.

[0085] In this embodiment, by extracting the first reminder message containing the reminder identifier and combining the second reminder messages adjacent to the first reminder message before and after, a matter reminder can be summarized. In this way, the matter reminder can more completely restore the reminder context, avoid missing key information, and thus improve the accuracy of the matter reminder.

[0086] In some embodiments, summarizing the unread chat messages in the at least one first session entry to obtain message summary information includes:

[0087] Dividing the unread chat messages in the first session entry into P portions of chat messages according to time sequence, where P is a positive integer;

[0088] Summarizing the first portion of chat messages through a language model to obtain a summary result of the first portion of chat messages;

[0089] Summarizing the summary result of the (k - 1)th portion of chat messages and the kth portion of chat messages through a language model to obtain a summary result of the kth portion of chat messages, updating k to k + 1, repeating this step until k is equal to P, and determining the summary result of the kth portion of chat messages as the message summary information, where k is a positive integer less than or equal to P.

[0090] In this embodiment, during the process of summarizing the unread chat messages, since the chat messages are summarized through a language model, and the language model is restricted by the maximum number of tokens during inference, the maximum length of a single input and output of the language model is limited, and the content exceeding the limit will be truncated, thus affecting the inference effect of the language model.

[0091] Therefore, during the process of summarizing the chat messages, if all the chat messages to be summarized are input into the language model at one time, these chat messages are very likely to exceed the limit of the maximum length of a single input and output of the language model, thus affecting the accuracy of the message summary information output by the language model.

[0092] To improve the accuracy of the message summary information, the unread chat messages in the first session entry can be divided into P portions of chat messages according to time sequence, and then each portion of chat messages is separately input into the language model for summarization. In this way, the length of a single portion of chat messages is relatively short, and the content input and output to the language model each time can be controlled not to exceed the maximum length limit.

[0093] Specifically, after dividing the unread chat messages in the first session entry into P portions of chat messages according to time sequence, the first portion of chat messages arranged in time sequence and the description information can be input into the language model, and the language model summarizes the first portion of chat messages according to the description information to obtain the summary result of the first portion of chat messages. Among them, the description information can be the first description information or the second description information.

[0094] After that, for the second portion of chat messages to the Pth portion of chat messages arranged in time sequence, the system can adopt a cyclic summary method, input each portion of chat messages, the summary result of the previous portion of chat messages, and the description information into the language model, and the language model summarizes the current portion of chat messages and the summary result of the previous portion of chat messages according to the description information to obtain the summary result of the current portion of chat messages. Until the summary information of the P portions of chat messages is completed, the summary result of the Pth portion of chat messages can be determined as the message summary information.

[0095] In the above way, by slicing the unread messages according to time sequence and adopting a cyclic summary method, the summary result of the previous portion of chat messages and the content of the current portion of chat messages can be gradually integrated for iterative generation, which can effectively maintain the context coherence of the summary content, avoid information omission or fragmentation, and improve the integrity and logic of the finally obtained message summary information.

[0096] In some embodiments, the dividing the unread chat messages in the first session entry into P portions of chat messages includes:

[0097] Determine the maximum length of a single input and output of the language model as the first length;

[0098] Determine the second length of the output statement of the language model;

[0099] Determine the template length of the prompt word corresponding to the language model;

[0100] Determine the first difference obtained by subtracting the second length from the first length and then subtracting the template length;

[0101] Divide the unread chat messages in the first session entry into P portions of chat messages so that the message length of each portion of chat messages is less than or equal to the first difference.

[0102] In this embodiment, before dividing the unread chat messages into P portions of chat messages, the system can first determine the maximum total input and output length supported by the language model in a single inference, and determine this maximum total input and output length as the first length, where the first length is determined by the performance of the language model itself. Then, the system can estimate the length of the output statements that the language model may generate and determine it as the second length. The system can also determine the template length of the prompt template in the prompt generation process, where the prompt template refers to a preset instruction structure for guiding the language model to perform a specific task, and the prompt template may include task descriptions, format requirements, or context examples.

[0103] Since the content of a single input and output of the language model includes the output statements, the prompt template, and a portion of chat messages, the first difference can be obtained by subtracting the second length and the template length from the first length. This first difference is used to represent the maximum length that a single input chat message can carry. Therefore, the message length of each portion of chat messages needs to be less than or equal to this first difference.

[0104] To ensure that the chat messages input each time do not exceed the first difference, the system can divide the unread chat messages into P portions and control the message length of each portion of chat messages to be less than the first difference, so as to ensure that each portion of chat messages can be completely input into the language model together with the prompt words and the summary results of the history.

[0105] Through the above method, the available input length of the language model can be accurately calculated before splitting the chat messages, ensuring that each portion of the divided chat messages is within the processing capacity of the language model, thereby avoiding the content being truncated or the model output being abnormal due to too long input content, and improving the accuracy of the message summary information.

[0106] S104, display the message summary information corresponding to each first session entry.

[0107] In this application, after summarizing the chat messages in each first session entry, the system can respectively display the message summary information corresponding to each first session entry.

[0108] Exemplarily, the message summary information can be displayed in the form of a card or a list in the application interface of the social application; the message summary information can be displayed in text form in the status bar of the electronic device; the message summary information corresponding to each first session entry can also be displayed in a push manner in the notification bar of the system; the message summary information corresponding to each first session entry can also be displayed in the form of a pop-up window.

[0109] In an embodiment of the present application, when multiple conversation entries are displayed in the application interface of a social application, the system can receive a first input from a user for at least one first conversation entry, and then trigger a summary of the content of the unread messages in the selected at least one first conversation entry to generate corresponding message summary information. And the message summary information corresponding to each first conversation entry is displayed according to the conversation entry. In this way, the message summary information of the unread messages in each selected conversation entry can be clearly presented to the user, helping them quickly understand the core content of each conversation entry. Compared with the related art of checking unread messages one by one, through the present application, the user does not need to spend a lot of time browsing low-value content or frequently switch between multiple conversation entries, but can directly obtain key information quickly through the automatically generated message summary information, thereby improving the user's reading efficiency when facing a large number of unread messages.

[0110] Specifically, in some embodiments, the displaying the message summary information corresponding to each of the first conversation entries includes:

[0111] For any second conversation entry among the at least one first conversation entry, display a first message card corresponding to the second conversation entry, where the first message card includes the conversation name of the second conversation entry, an event summary in the second conversation entry, and a matter reminder.

[0112] In this embodiment, after the user initiates the message summary information for at least one first conversation entry, the system will respectively summarize the chat messages in each first conversation entry to obtain the message summary information corresponding to each first conversation entry, and then for each first conversation entry, display a corresponding message card, which includes the conversation name of the conversation entry, the event summary in the conversation entry, and the matter reminder in the conversation entry.

[0113] Such as Figure 4 shown, after the user confirms the summary of the content in the conversation entry, the displayed first text box 301 will be enlarged and a first message card 401 will be displayed in the first text box, which includes the conversation name of the second conversation entry, the event summary in the second conversation entry, and the matter reminder. Such as Figure 4 shown in the first message card, the conversation name is Group 1, and below the conversation name, the time range of the summary message is also displayed as: 9:00 on January 24, 2025 - 10:00 on January 25, 2025. In addition, the event summary in the second conversation entry includes "Quarterly press conference arrangement" and "Business trip plan notice", and the matter summary in the second conversation entry includes "Everyone please submit the reimbursement form before getting off work today" and "Everyone note that the headquarters will conduct an office area inspection this Friday, please tidy up your workstations in advance".

[0114] With this display method of summarizing information through card-based messages, users can clearly view the core information of each conversation entry in the application interface of the social application, and quickly understand the important content in the chat messages without having to click on each conversation entry to read the unread chat messages one by one, thus improving the efficiency of information acquisition.

[0115] In some embodiments, after displaying the first message card corresponding to the second conversation entry, the method further includes:

[0116] Receiving a second input to the first message card;

[0117] In response to the second input, switching the displayed first message card to a second message card, where the second message card is the message card corresponding to the next first conversation entry of the second conversation entry.

[0118] In this embodiment, after displaying the first message card corresponding to the second conversation entry in the application interface of the social application, the user can perform a second input on the displayed first message card, and the second input is used to indicate switching the currently displayed message card to the message card corresponding to the next first conversation entry. Then, since the currently displayed first message card is the message card corresponding to the second conversation entry, the system, in response to the second input, can switch the currently displayed message card from the first message card to the second message card, and the second message card includes the conversation name, event summary, and matter reminder of the next first conversation entry of the second conversation entry.

[0119] As Figure 4 shown, after the user confirms summarizing the content in the conversation entry, the displayed first text box 301 will be enlarged and the first message card 401 will be displayed in the first text box. The first message card includes the conversation name of the second conversation entry, the event summary, and matter reminder in the second conversation entry. In addition, the first message card 401 further includes a conversation switching control 402, which is used to indicate switching the currently displayed message card to the message card corresponding to the next first conversation entry. Then, when the user performs a second input on the conversation switching control, the system will, in response to the second input, switch the currently displayed message card from the first message card to the second message card.

[0120] In the above embodiment, the system can realize the sequential switching between message cards by receiving and responding to the second input of the user to the first message card. In this way, users can flexibly select the message summary information content of the conversation entry they want to view, improving the reading coherence and flexibility of users.

[0121] In some embodiments, after displaying the first message card corresponding to the second session entry, the method further includes:

[0122] Receiving a third input to the first message card;

[0123] In response to the third input, classifying the events in at least one first session entry to obtain at least one event type;

[0124] Switching the displayed first message card to a third message card, where the third message card includes the topic name of one event type, the event summary of the events in the event type, and a matter reminder.

[0125] In this embodiment, after displaying the first message card corresponding to the second session entry in the application interface of the social application, the user can perform a third input on the displayed first message card, and this third input is used to indicate switching from displaying message summary information according to session entries to displaying message summary information according to event types. Then, since the currently displayed first message card is a message card that displays message summary information according to session entries, the system can, in response to the second input, classify the events in all first session entries to obtain at least one event type, and then determine the topic words of each event type, as well as the event summary and matter reminder of all events in each event type.

[0126] Subsequently, the system can regenerate message cards based on the event types. Each message card displays the topic word of one event type, as well as the event summary and matter reminder of all events in that event type.

[0127] Moreover, the system can switch the currently displayed message card from the first message card to a third message card, and the third message card includes the topic name of one event type, the event summary, and a matter reminder.

[0128] As Figure 4 shown, after the user confirms the summary of the content in the session entry, the displayed first text box 301 will be enlarged and displayed, and the first message card 401 will be displayed in the first text box. The first message card includes the session name of the second session entry, the event summary in the second session entry, and a matter reminder. In addition, the first message card 401 also includes a mode switching control 501, and this mode switching control is used to indicate switching from currently displaying message summary information according to session entries to displaying message summary information according to event types. Then, when the user performs a third input on the session switching control, the system will, in response to the third input, switch from currently displaying message summary information according to session entries to displaying message summary information according to event types. And display as Figure 5The third message card 502 shown, which includes the topic name "Meeting Arrangement" of the event type, as well as the event summary and matter reminder in the meeting arrangement.

[0129] In the above embodiment, the system can classify the events in multiple first session entries and generate a third message card from the perspective of the event type, enabling the user to view events of the same topic and related matter reminders across sessions. This display method improves the information integration ability and access efficiency.

[0130] Figure 6 It is a schematic structural diagram of a chat message summarization device 600 provided by another embodiment of the present application. As Figure 6 shown, the chat message summarization device may include:

[0131] A first display module 601 for displaying an application interface of a social application, where the application interface includes N session entries, and N is a positive integer;

[0132] A first receiving module 602 for receiving a first input for at least one first session entry among the N session entries;

[0133] A first summarization module 603 for summarizing the unread chat messages in the at least one first session entry in response to the first input to obtain message summary information;

[0134] A second display module 604 for displaying the message summary information corresponding to each of the first session entries.

[0135] In the present application, when multiple session entries can be displayed in the application interface of the social application, the system can receive a first input from the user for at least one first session entry among them, and then trigger the summarization of the content of the unread messages in the selected at least one first session entry to generate corresponding message summary information. And the message summary information corresponding to each first session entry is displayed according to the session entry. In this way, the message summary information of the unread messages in each selected session entry can be clearly presented to the user to help them quickly understand the core content of each session entry. Compared with the prior art of checking unread messages one by one, through the present application, the user does not need to spend a lot of time browsing low-value content or frequently switch between multiple session entries, but can directly quickly obtain key information through the automatically generated message summary information, thereby improving the user's reading efficiency when facing a large number of unread messages.

[0136] In another optional example, the first summarization module 603 includes:

[0137] A first acquisition unit, configured to acquire input information, where the input information is used to indicate unread content in a summary conversation entry;

[0138] A first display unit, configured to display a reply statement generated according to the input information, where the reply statement is used to guide a user to perform the first input on the conversation entry to be summarized;

[0139] A first summary unit, configured to, in response to receiving the first input on the at least one first conversation entry, summarize chat messages in an unread state in the at least one first conversation entry according to the input information to obtain message summary information.

[0140] In another optional example, the first summary unit is specifically configured to:

[0141] Generate first description information according to the input information, where the first description information is used to indicate summarizing events in the chat messages;

[0142] Input the first description information and the unread chat messages into a language large model, and the language large model summarizes events in the chat messages according to the first description information to obtain event summaries of at least one event.

[0143] In another optional example, the first summary unit is specifically configured to:

[0144] Generate second description information according to the input information, where the second description information is used to indicate summarizing matter reminders in the chat messages;

[0145] Determine at least one reminder identifier in the unread chat messages in the first conversation entry, where the reminder identifier is used to remind a specific user to view the chat messages;

[0146] Determine the chat messages associated with the at least one reminder identifier as reminder messages;

[0147] Input the second description information and the reminder messages into a language large model, and the language large model summarizes the reminder messages according to the second description information to obtain matter reminders corresponding to each reminder identifier in the first conversation entry.

[0148] In another optional example, the first summary unit is specifically configured to:

[0149] Determine the chat message containing the reminder identifier as the first reminder message corresponding to the reminder identifier;

[0150] Determine at least one chat message before the first reminder message and at least one chat message after the first reminder message as the second reminder message corresponding to the reminder identifier.

[0151] In another optional example, the first summarization module 603 further includes:

[0152] A partitioning unit for partitioning the unread chat messages in the first conversation entry into P portions of chat messages in chronological order, where P is a positive integer;

[0153] A second summarization unit for summarizing the first portion of chat messages through a language large model to obtain a summarization result of the first portion of chat messages;

[0154] A third summarization unit for summarizing the summarization result of the (k - 1)-th portion of chat messages and the k-th portion of chat messages through a language large model to obtain a summarization result of the k-th portion of chat messages, updating k to k + 1, repeating this step until k is equal to P, and determining the summarization result of the k-th portion of chat messages as the message summarization information, where k is a positive integer less than or equal to P.

[0155] In another optional example, the partitioning unit is further configured to:

[0156] Determine the maximum length of a single input and output of the language large model as the first length;

[0157] Determine the second length of the output statement of the language large model;

[0158] Determine the template length of the prompt word corresponding to the language large model;

[0159] Determine the first difference obtained by subtracting the second length from the first length and then subtracting the template length;

[0160] Partition the unread chat messages in the first conversation entry into P portions of chat messages so that the message length of each portion of chat messages is less than or equal to the first difference.

[0161] In another optional example, the second display module 604 further includes:

[0162] A second display unit for, for any one of the at least one second conversation entry in the at least one first conversation entry, displaying a first message card corresponding to the second conversation entry, where the first message card includes the conversation name of the second conversation entry, the event summary in the second conversation entry, and the matter reminder.

[0163] In another optional example, the chat message summarization device further includes:

[0164] A first receiving unit, configured to receive a second input to the first message card;

[0165] A first switching unit, configured to, in response to the second input, switch the displayed first message card to a second message card, where the second message card is a message card corresponding to the next first session entry of the second session entry.

[0166] In another optional example, the chat message summarization device further includes:

[0167] A second receiving unit, configured to receive a third input to the first message card;

[0168] A classification unit, configured to, in response to the third input, classify events in at least one first session entry to obtain at least one event type;

[0169] A second switching unit, configured to switch the displayed first message card to a third message card, where the third message card includes a topic name of an event type, an event summary of the events in the event type, and a matter reminder.

[0170] The chat message summarization device in the embodiments of the present application may be an electronic device or a component in an electronic device, such as an integrated circuit or a chip. The electronic device may be a terminal or other devices other than the terminal. Exemplarily, the electronic device may be a mobile phone, a tablet computer, a notebook computer, a handheld computer, a vehicle-mounted electronic device, a Mobile Internet Device (MID), an augmented reality (AR) / virtual reality (VR) device, a robot, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc., and may also be a server, a Network Attached Storage (NAS), a personal computer (PC), a television (TV), a teller machine, or a self-service machine, etc. The embodiments of the present application do not make specific limitations.

[0171] The summarization device for chat messages in the embodiments of the present application can be a device with an operating system. The operating system can be the Android operating system, the IOS operating system, or other possible operating systems, which are not specifically limited in the embodiments of the present application.

[0172] The summarization device for chat messages provided in the embodiments of the present application can implement Figure 1 each process implemented by the method embodiments. To avoid repetition, details are not described herein again.

[0173] Optionally, as Figure 7 shown, the embodiments of the present application further provide an electronic device 100, including a processor 110, a memory 119, a program or instruction stored on the memory 119 and executable on the processor 110. When the program or instruction is executed by the processor 110, it implements each process of the method embodiment for summarizing the above messages and can achieve the same technical effects. To avoid repetition, details are not described herein again.

[0174] It should be noted that the electronic devices in the embodiments of the present application include the above-mentioned mobile electronic devices and non-mobile electronic devices.

[0175] Please refer to Figure 8 , Figure 8 which is a schematic diagram of the hardware structure of an electronic device for implementing the embodiments of the present application. The electronic device 100 includes, but is not limited to: a radio frequency unit 121, a network module 122, an audio output unit 123, an input unit 124, a sensor 125, a display unit 126, a user input unit 127, an interface unit 128, a memory 129, and a processor 120, etc.

[0176] Those skilled in the art can understand that the electronic device 100 may further include a power supply (such as a battery) for supplying power to each component. The power supply can be logically connected to the processor 120 through a power management system, so as to implement functions such as management of charging, discharging, and power consumption management through the power management system. Figure 8 The structure of the electronic device shown in

[0177] does not limit the electronic device. The electronic device may include more or fewer components than shown, or combine certain components, or have different component arrangements, which are not described herein again.

[0178] Among them, the display unit 126 is used to display the application interface of the social application, and the application interface includes N session entries, where N is a positive integer;

[0179] A processor 120, configured to summarize chat messages in an unread state among the at least one first session entry in response to the first input, so as to obtain message summary information;

[0180] A display unit 126, configured to display the message summary information corresponding to each of the first session entries.

[0181] In this application, when multiple session entries are displayed in the application interface of a social application, the system can receive a first input from a user for at least one of the first session entries, and then trigger summarization of the content of unread messages in the selected at least one first session entry to generate corresponding message summary information. And the message summary information corresponding to each first session entry is displayed according to the session entry. In this way, the message summary information of the unread messages in each selected session entry can be clearly presented to the user, helping them quickly understand the core content of each session entry. Compared with the related art of checking unread messages one by one, through this application, the user does not need to spend a lot of time browsing low-value content or frequently switch between multiple session entries, but can directly obtain key information quickly through the automatically generated message summary information, thereby improving the user's reading efficiency when facing a large number of unread messages.

[0182] In another optional example, the processor 120 is further configured to:

[0183] Obtain input information, where the input information is used to indicate summarizing unread content in a session entry;

[0184] Display a reply statement generated according to the input information, where the reply statement is used to guide the user to perform the first input on the session entry to be summarized;

[0185] In the case of receiving the first input for the at least one first session entry, in response to the first input, summarize chat messages in an unread state among the at least one first session entry according to the input information to obtain message summary information.

[0186] In another optional example, the processor 120 is specifically configured to:

[0187] Generate first description information according to the input information, where the first description information is used to indicate summarizing events in the chat messages;

[0188] Input the first description information and the chat messages in an unread state into a language large model, and the language large model summarizes events in the chat messages according to the first description information to obtain event summaries of at least one event.

[0189] In another optional example, the processor 120 is specifically configured to:

[0190] Generate second description information according to the input information, where the second description information is used to indicate summarizing the matter reminders in the chat messages;

[0191] Determine at least one reminder identifier in the unread chat messages in the first session entry, where the reminder identifier is used to remind a specific user to view the chat messages;

[0192] Determine the chat messages associated with the at least one reminder identifier as reminder messages;

[0193] Input the second description information and the reminder messages into a language large model, and the language large model summarizes the reminder messages according to the second description information to obtain the matter reminder corresponding to each reminder identifier in the first session entry.

[0194] In another optional example, the processor 120 is specifically configured to:

[0195] Determine the chat message containing the reminder identifier as the first reminder message corresponding to the reminder identifier;

[0196] Determine at least one chat message before the first reminder message and at least one chat message after the first reminder message as the second reminder message corresponding to the reminder identifier.

[0197] In another optional example, the processor 120 is specifically configured to:

[0198] Divide the unread chat messages in the first session entry into P portions of chat messages in chronological order, where P is a positive integer;

[0199] Summarize the first portion of chat messages through a language large model to obtain a summary result of the first portion of chat messages;

[0200] Summarize the summary result of the (k - 1)th portion of chat messages and the kth portion of chat messages through a language large model to obtain a summary result of the kth portion of chat messages, update k to k + 1, repeat this step until k is equal to P, and determine the summary result of the kth portion of chat messages as the message summary information, where k is a positive integer less than or equal to P.

[0201] In another optional example, the processor 120 is further configured to:

[0202] Determine the maximum length of a single input and output of the language large model as the first length;

[0203] Determine the second length of the output statement of the language large model;

[0204] Determine the template length of the prompt corresponding to the language large model;

[0205] Determine the first difference obtained by subtracting the second length from the first length and then subtracting the template length;

[0206] Divide the unread chat messages in the first conversation entry into P portions of chat messages so that the message length of each portion of chat message is less than or equal to the first difference.

[0207] In another optional example, the display unit 126 is used to display, for any one of the at least one first conversation entry, a first message card corresponding to the second conversation entry, where the first message card includes the conversation name of the second conversation entry, an event summary in the second conversation entry, and a matter reminder.

[0208] In another optional example, the electronic device further includes:

[0209] A user input unit 127, configured to receive a second input to the first message card;

[0210] The display unit 126 is configured to switch the displayed first message card to a second message card in response to the second input, where the second message card is a message card corresponding to the next first conversation entry of the second conversation entry.

[0211] In another optional example, the chat message summarization device further includes:

[0212] A user input unit 127, configured to receive a third input to the first message card;

[0213] The processor 120 is configured to classify the events in at least one first conversation entry in response to the third input to obtain at least one event type;

[0214] The display unit 126 is configured to switch the displayed first message card to a third message card, where the third message card includes the topic name of an event type, an event summary of the events in the event type, and a matter reminder.

[0215] It should be understood that in the embodiments of the present application, the input unit 124 may include a Graphics Processing Unit (GPU) 1241 and a microphone 1242. The GPU 1241 processes the image data of static pictures or videos obtained by an image capturing device (such as a camera) in a video capturing mode or an image capturing mode. The display unit 126 may include a display panel 1261, and the display panel 1261 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 127 includes at least one of a touch panel 1271 and other input devices 1272. The touch panel 1271 is also referred to as a touch screen. The touch panel 1271 may include two parts: a touch detection device and a touch controller. The other input devices 1272 may include, but are not limited to, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, and a joystick, which will not be elaborated here.

[0216] The memory 129 can be used to store software programs and various data. The memory 129 mainly includes a first storage area for storing programs or instructions and a second storage area for storing data. Among them, the first storage area can store an operating system, applications or instructions required for at least one function (such as a sound playback function, an image playback function, etc.). In addition, the memory 129 may include a volatile memory or a non-volatile memory, or the memory 129 may include both a volatile memory and a non-volatile memory. Among them, the non-volatile memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically EPROM (EEPROM), or a flash memory. The volatile memory may be a Random Access Memory (RAM), a Static RAM (SRAM), a Dynamic RAM (DRAM), a Synchronous DRAM (SDRAM), a Double Data Rate SDRAM (DDR SDRAM), an Enhanced SDRAM (ESDRAM), a Synch link DRAM (SLDRAM), and a Direct Rambus RAM (DRRAM). The memory 129 in the embodiments of the present application includes, but is not limited to, these and any other suitable types of memories.

[0217] The processor 120 may include one or more processing units; optionally, the processor 120 integrates an application processor and a modem processor. Among them, the application processor mainly processes operations related to the operating system, user interface, application programs, etc., and the modem processor mainly processes wireless communication signals, such as a baseband processor. It can be understood that the above-mentioned modem processor may not be integrated into the processor 120 either.

[0218] The embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, it implements each process of the embodiment of the above message summarization method and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0219] Among them, the processor is the processor in the electronic device in the above embodiment. The readable storage medium includes a computer-readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk, or an optical disc, etc.

[0220] The embodiment of the present application further provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement each process of the embodiment of the above message summarization method and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0221] It should be understood that the chip mentioned in the embodiment of the present application may also be referred to as a system-on-chip, system chip, chip system, or system-on-chip, etc.

[0222] The embodiment of the present application provides a computer program product, which is stored in a storage medium. The program product is executed by at least one processor to implement each process of the embodiment of the above message summarization method and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0223] It should be noted that in this text, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the existence of additional identical elements in the process, method, article or device comprising that element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, but may also include performing functions in a substantially simultaneous manner or in a reverse order according to the functions involved. For example, the described methods may be performed in an order different from that described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0224] From the description of the above embodiments, those skilled in the art can clearly understand that the above-described method of the embodiment can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions for causing a terminal (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present application.

[0225] The embodiments of the present application have been described above in conjunction with the accompanying drawings. However, the present application is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present application, those of ordinary skill in the art can also make many forms without departing from the purpose of the present application and the scope protected by the claims, and all of them fall within the protection scope of the present application.

Claims

1. A method for summarizing messages, characterized in that, Including: Displaying an application interface of a social application, where the application interface includes N session entries, and N is a positive integer; Receiving a first input for at least one first session entry among the N session entries; In response to the first input, summarizing the chat messages in the at least one first session entry that are in an unread state to obtain message summary information; Displaying the message summary information corresponding to each of the first session entries.

2. The method according to claim 1, characterized in that, The step of, in response to the first input, summarizing the chat messages in the at least one first session entry that are in an unread state to obtain message summary information includes: Obtaining input information, where the input information is used to indicate summarizing the unread content in the session entry; Displaying a reply statement generated according to the input information, where the reply statement is used to guide the user to perform the first input on the session entry to be summarized; In the case of receiving the first input for the at least one first session entry, in response to the first input, summarizing the chat messages in the at least one first session entry that are in an unread state according to the input information to obtain message summary information.

3. The method according to claim 2, wherein The message summary information includes an event summary. The step of, according to the input information, summarizing the chat messages in the at least one first session entry that are in an unread state to obtain message summary information includes: Generating first description information according to the input information, where the first description information is used to indicate summarizing the events in the chat messages; Inputting the first description information and the chat messages in the unread state into a language large model, and the language large model summarizes the events in the chat messages according to the first description information to obtain an event summary of at least one event.

4. The method according to claim 2, wherein The message summary information includes a matter reminder. The step of, according to the input information, summarizing the chat messages in the at least one first session entry that are in an unread state to obtain message summary information includes: Generating second description information according to the input information, where the second description information is used to indicate summarizing the matter reminders in the chat messages; Determining at least one reminder identifier in the chat messages in the first session entry that are in an unread state, where the reminder identifier is used to remind a specific user to view the chat messages; Determining the chat messages associated with the at least one reminder identifier as reminder messages; Inputting the second description information and the reminder messages into a language large model, and the language large model summarizes the reminder messages according to the second description information to obtain a matter reminder corresponding to each reminder identifier in the first session entry.

5. The method according to any one of claims 1 to 4, characterized in that The step of summarizing the chat messages in the at least one first session entry that are in an unread state to obtain message summary information includes: Dividing the chat messages in the first session entry that are in an unread state into P portions of chat messages according to time sequence, and P is a positive integer; Summarizing the first portion of chat messages through a language large model to obtain a summary result of the first portion of chat messages; Summarize the summary result of the (k - 1)-th chat message and the k-th chat message through a language model to obtain the summary result of the k-th chat message. Update k to k + 1, and repeat this step until k is equal to P. Determine the summary result of the k-th chat message as the message summary information, where k is a positive integer less than or equal to P.

6. The method according to claim 5, wherein The dividing the chat messages in the unread state in the first session entry into P chat messages includes: Determine the maximum length of a single input and output of the language model as the first length; Determine the second length of the output statement of the language model; Determine the template length of the prompt word corresponding to the language model; Determine the first difference obtained by subtracting the second length and the template length from the first length; Divide the chat messages in the unread state in the first session entry into P chat messages so that the message length of each chat message is less than or equal to the first difference.

7. The method according to claim 1, characterized in that, The displaying the message summary information corresponding to each of the first session entries includes: For any second session entry in the at least one first session entry, display a first message card corresponding to the second session entry, where the first message card includes the session name of the second session entry, the event summary and matter reminder in the second session entry.

8. The method according to claim 7, characterized in that After displaying the first message card corresponding to the second session entry, the method further includes: Receiving a second input to the first message card; In response to the second input, switching the displayed first message card to a second message card, where the second message card is the message card corresponding to the next first session entry of the second session entry.

9. The method according to claim 7, wherein After displaying the first message card corresponding to the second session entry, the method further includes: Receiving a third input to the first message card; In response to the third input, classify the events in the at least one first session entry to obtain at least one event type; Switch the displayed first message card to a third message card, where the third message card includes the topic name of an event type, the event summary and matter reminder of the events in the event type.

10. A summary device for chat messages, characterized in that including: A first display module for displaying an application interface of a social application, where the application interface includes N session entries, and N is a positive integer; A first receiving module for receiving a first input to at least one first session entry among the N session entries; A first summarizing module for, in response to the first input, summarizing the chat messages in the unread state in the at least one first session entry to obtain message summary information; A second display module for displaying the message summary information corresponding to each of the first session entries.

Images