Content recommendation method, system, device, and medium

Abstract

The present disclosure provides a content recommendation method, a system, a device, and a medium. The content recommendation method comprises: displaying an instant messaging page, the instant messaging page being used for performing content interaction between a local user and at least one first user; in response to receipt of a first message sent by the at least one first user and / or an editing operation by the local user on a second message, presenting at least one item of recommended content in the instant messaging page, the at least one item of recommended content being generated on the basis of the first message and / or the second message, and the at least one item of recommended content being used for replying to the first message or executing an operation associated with the first message and / or the second message. In the content recommendation method, a user can conveniently reply to a message or perform a related operation by using the recommended content, so that interaction efficiency in instant messaging is improved.

Description

Content recommendation methods, systems, devices and media

[0001] This application claims priority to Chinese Patent Application No. 202410669009.5, filed on May 27, 2024, the disclosure of which is incorporated herein by reference in its entirety. Technical Field

[0002] This disclosure relates to a content recommendation method, system, electronic device, and computer-readable storage medium. Background Technology

[0003] With the continuous development of computer technology, instant messaging (IM) systems have emerged, allowing users to communicate with each other. Specifically, users can have one-on-one chats or create groups to chat with multiple users within those groups.

[0004] Typically, users need to manually type content into input boxes using the keyboard or via voice input. However, these methods are inefficient for both message input and response. Summary of the Invention

[0005] This disclosure provides a content recommendation method. This method can improve the interaction efficiency in instant messaging. This disclosure also provides systems, electronic devices, computer-readable storage media, and computer program products corresponding to the above method.

[0006] Firstly, this disclosure provides a content recommendation method, the method comprising:

[0007] Display an instant messaging page, which is used for content interaction between the local user and at least one first user;

[0008] In response to receiving a first message sent by at least one first user and / or an editing operation by the local user on a second message, at least one recommended content is presented on the instant messaging page. The at least one recommended content is generated based on the first message and / or the second message, and the at least one recommended content is used to reply to the first message or perform an operation associated with the first message and / or the second message.

[0009] In some possible implementations, the method further includes:

[0010] In response to a triggering operation targeting a specific recommended content among the at least one recommended content, the target recommended content is sent; or,

[0011] In response to a triggering operation for a target recommended content among the at least one recommended content, the target recommended content is displayed in the input box of the instant messaging page.

[0012] In some possible implementations, the at least one recommended content is generated through the following steps:

[0013] Extract key information from the first message and / or the second message;

[0014] Identify at least one recommended content that matches the key information.

[0015] In some possible implementations, the at least one recommended content is generated through the following steps:

[0016] A prompt message is generated based at least on the first message and / or the second message;

[0017] The prompt information is sent to the language model, and at least one recommended content is received from the language model. The prompt information is used to instruct the language model to generate recommended content based on the first message and / or the second message.

[0018] In some possible implementations, sending the prompt information to the language model and receiving at least one recommended content returned by the language model includes:

[0019] The prompt information is sent to the language model so that the language model can determine whether the content recommendation conditions for the first message and / or the second message are met. In response to meeting the content recommendation conditions for the first message and / or the second message, at least one recommended content is generated based on the first message and / or the second message.

[0020] Receive at least one recommended content returned by the language model.

[0021] In some possible implementations, generating the prompt information based at least on the first message and / or the second message includes:

[0022] Based on the first message and / or the second message, and at least one of the following information: the identity type information of the first user and / or the local user, the context information of the first message, and the user group information of the first user and / or the local user, a prompt message is generated.

[0023] In some possible implementations, presenting at least one recommended piece of content on the instant messaging page includes:

[0024] At least one recommended piece of content is displayed in the area associated with the input box on the instant messaging page.

[0025] In some possible implementations, the recommended content includes at least one of the following: text-type recommended content, emoticon-type recommended content, document-type recommended content, recommended content indicating the entry point of a function module, and recommended content indicating text processing functions.

[0026] Secondly, this disclosure provides a content recommendation system, the system comprising:

[0027] The display module is used to display the instant messaging page, which is used for content interaction between the local user and at least one first user;

[0028] The presentation module is configured to, in response to receiving a first message sent by at least one first user and / or an editing operation by the local user on a second message, present at least one recommended content on the instant messaging page, wherein the at least one recommended content is generated based on the first message and / or the second message, and the at least one recommended content is used to reply to the first message or perform an operation associated with the first message and / or the second message.

[0029] In some possible implementations, the system further includes a sending module, which is used to:

[0030] In response to a triggering operation targeting a specific recommended content among the at least one recommended content, the target recommended content is sent.

[0031] The presentation module is also used for:

[0032] In response to a triggering operation for a target recommended content among the at least one recommended content, the target recommended content is displayed in the input box of the instant messaging page.

[0033] In some possible implementations, the system further includes a generation module, which is used to:

[0034] Extract key information from the first message and / or the second message;

[0035] Identify at least one recommended content that matches the key information.

[0036] In some possible implementations, the generation module is used to:

[0037] A prompt message is generated based at least on the first message and / or the second message;

[0038] The prompt information is sent to the language model, and at least one recommended content is received from the language model. The prompt information is used to instruct the language model to generate recommended content based on the first message and / or the second message.

[0039] In some possible implementations, the generation module is specifically used for:

[0040] The prompt information is sent to the language model so that the language model can determine whether the content recommendation conditions for the first message and / or the second message are met. In response to meeting the content recommendation conditions for the first message and / or the second message, at least one recommended content is generated based on the first message and / or the second message.

[0041] Receive at least one recommended content returned by the language model.

[0042] In some possible implementations, the generation module is specifically used for:

[0043] Based on the first message and / or the second message, and at least one of the following information: the identity type information of the first user and / or the local user, the context information of the first message, and the user group information of the first user and / or the local user, a prompt message is generated.

[0044] In some possible implementations, the presentation module is specifically used for:

[0045] At least one recommended piece of content is displayed in the area associated with the input box on the instant messaging page.

[0046] In some possible implementations, the recommended content includes at least one of the following: text-type recommended content, emoticon-type recommended content, document-type recommended content, recommended content indicating the entry point of a function module, and recommended content indicating text processing functions.

[0047] Thirdly, this disclosure provides an electronic device including a processor and a memory. The processor and the memory communicate with each other. The processor is configured to execute instructions stored in the memory to cause the electronic device to perform a content recommendation method as described in the first aspect or any implementation thereof.

[0048] Fourthly, this disclosure provides a computer-readable storage medium storing instructions that instruct an electronic device to perform the content recommendation method described in the first aspect or any implementation thereof.

[0049] Fifthly, this disclosure provides a computer program product containing instructions that, when run on an electronic device, causes the electronic device to execute the content recommendation method described in the first aspect or any implementation thereof.

[0050] Based on the implementation methods provided in the above aspects, this disclosure can be further combined to provide more implementation methods. Attached Figure Description

[0051] To more clearly illustrate the technical methods of the embodiments of this disclosure, the accompanying drawings used in the embodiments will be briefly described below.

[0052] Figure 1 is a flowchart illustrating a content recommendation method provided in an embodiment of this disclosure;

[0053] Figures 2A to 2D are schematic diagrams of an instant messaging page provided in an embodiment of this disclosure;

[0054] Figure 3 is a schematic diagram of the structure of a content recommendation system provided in an embodiment of this disclosure; and

[0055] Figure 4 is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0056] The terms "first" and "second" used in the embodiments of this disclosure are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature.

[0057] First, some technical terms involved in the embodiments of this disclosure will be introduced.

[0058] Instant messaging (IM) systems, also known as IM software or IM tools, can be understood as internet-based clients that enable real-time voice and text transmission. Users can interact with other users through IM systems.

[0059] Typically, IM systems provide input fields. Users can enter messages in these fields to send or reply to messages during content interaction with other users.

[0060] However, the above-mentioned content interaction methods have the following problems: users need to manually enter content in the input box using the keyboard, or enter content through voice input, which is slow and has low interaction efficiency.

[0061] In view of this, the present disclosure provides a content recommendation method. The method first displays an instant messaging page, wherein the instant messaging page is used for content interaction between the local user and at least one first user. In response to receiving a first message sent by at least one first user, the local user interacts with at least one first user and presents at least one recommended content on the instant messaging page. The at least one recommended content is generated based on the first message and / or a second message, and the at least one recommended content is used to reply to the first message or perform an operation associated with the first message and / or the second message.

[0062] This method targets scenarios where users interact with content on instant messaging pages. Based on messages sent by other users or messages to be sent by the current user, it generates and presents recommended content. Users can then conveniently reply to messages or perform related actions using the recommended content, improving the efficiency of instant messaging interactions.

[0063] To facilitate understanding of the technical solutions provided in the embodiments of this disclosure, the following description will be provided in conjunction with the accompanying drawings.

[0064] Referring to Figure 1, which shows a flowchart of a content recommendation method provided in an embodiment of this disclosure, the method specifically includes:

[0065] S101: Displays the instant messaging page.

[0066] The instant messaging page can be provided by the server of the instant messaging system and displayed on the client side of the instant messaging system. In some embodiments, the instant messaging system can be a standalone software system, such as standalone instant messaging software or instant messaging tools. In other embodiments, the instant messaging system can also be deployed in other systems. For example, the instant messaging system can be deployed in an office automation (OA) system as a functional module of the OA system, providing instant messaging functionality.

[0067] In this context, an OA system can be understood as a collaborative office system. An OA system can include multiple functional modules, each providing different functions. For example, in addition to the instant messaging module mentioned above, it can also include a schedule module for calendar management, a video conferencing module for video conferencing, and a cloud document module for document management.

[0068] For ease of description, in this embodiment of the disclosure, the user using the client of the instant messaging system is referred to as the local user. That is, in this embodiment of the disclosure, the instant messaging page can be displayed in the client of the local user's instant messaging system.

[0069] Furthermore, the instant messaging page can be used for content interaction with at least one primary user. In other words, the primary user can be understood as the communication or chat partner of the current user.

[0070] This disclosure does not limit the content interaction method between the local user and the first user. In some embodiments, the content interaction method between the local user and the first user can be one-on-one chat, in which case the instant messaging page is used to interact with a specific first user. In other embodiments, the content interaction method between the local user and the first user can be group chat; in other words, the local user and multiple first users are located in the same group, in which case the instant messaging page is used to interact with multiple first users in the group.

[0071] S102: In response to receiving a first message sent by at least one first user and / or an editing operation by the local user on a second message, at least one recommended content is displayed on the instant messaging page.

[0072] The first message can be understood as a chat message sent by at least one first user. For example, when a user on this end is having a one-on-one chat with the first user, the first message could be a chat message sent by the first user to the user on this end. As another example, when a user on this end is having a group chat with multiple first users, the first message could be a chat message sent by the multiple first users within the group.

[0073] The second message can be understood as a message edited by the user on the instant messaging page. For example, when the user needs to reply to or send a message on the instant messaging page, they can edit the content in the input box (such as entering, modifying, or deleting content). In this case, the content edited by the user in the input box can be understood as the second message.

[0074] In this embodiment, at least one recommended content can be generated based on a first message and / or a second message, and the recommended content can be used to reply to the first message or perform operations associated with the first message and / or the second message. That is, when the local user receives a message from another user (i.e., the first user), the local user can quickly reply to the message using the recommended content. When the local user edits a message on the instant messaging page, the local user can use the recommended content to perform operations associated with the first message and / or the second message, without needing to select the required functional modules layer by layer, thus reducing the length of the operation chain.

[0075] In some embodiments, at least one recommended piece of content may be displayed in the area associated with the input box on the instant messaging page. The area associated with the input box on the instant messaging page can be understood as an area that provides functionality related to the input function. For example, instant messaging systems typically provide screenshot functionality, emoji selection functionality, file selection functionality, etc., in the area associated with the input box.

[0076] In practice, at least one recommended content can be displayed in the area above and / or below the input box on the instant messaging page. By displaying recommended content in the area associated with the input box, users on this end can quickly find the recommended content when replying to the first message or editing the second message through the input box. This allows them to quickly generate a reply to the first message or perform operations associated with the first and / or second messages using the recommended content.

[0077] This disclosure supports different types of recommended content. Specifically, the recommended content may include at least one of the following: text-based recommended content, emoticon-based recommended content, document-based recommended content, recommended content indicating the entry point of a function module, and recommended content indicating text processing functions.

[0078] Specifically, text-based recommendations can be a short text, while emoticon-based recommendations can be a single emoticon. Document-based recommendations can point to a document; for example, when the instant messaging system is a standalone software system, the recommended document could be a local document, or when the instant messaging system is a functional module within an OA system, the recommended document could be a cloud document link. When the instant messaging system is a functional module within an OA system, recommendations indicating the module's entry point can be an entry control for that module, such as an entry control for a scheduling module or a video conferencing module. Recommendations indicating text processing functions can be controls for text processing functions, such as translation, text correction, or editing functions.

[0079] By providing recommended content indicating entry points to functional modules, users on this end can quickly access other functional modules while interacting with at least one primary user, eliminating the need to manually switch between modules and improving the efficiency of collaborative work using the OA system. For example, when the first message is "Let's chat sometime," the recommended content could include an entry point to the video conferencing module. When the second message edited by the user on this end is "Let me see when I'm free," the recommended content could include an entry point to the scheduling module.

[0080] By providing recommended content that indicates text processing functions, users on this end can quickly invoke the text processing capabilities existing in the OA system during content interaction with at least one primary user, thereby realizing text processing during message reply.

[0081] In this way, different types of recommended content are presented in the associated area of ​​the input box, allowing users on this end to quickly reply to messages or enter other functional modules to perform corresponding operations without a long operation process, effectively solving the problem of deep functional entry points in related technologies.

[0082] In embodiments of this disclosure, recommended content can be generated in different ways. In some embodiments, key information can be extracted from a first message and / or a second message, and at least one piece of recommended content matching the key information can be determined.

[0083] In other words, the server of an instant messaging system can store pre-configured correspondences between key information and recommended content. These correspondences can be manually configured by users of the instant messaging system or provided by the server. Thus, by identifying key information in the first and / or second messages, if a key piece of information is found in the first and / or second message, at least one piece of recommended content corresponding to that key information can be obtained, thereby determining the recommended content.

[0084] For example, when the first message is "Let's have a meeting to discuss this," the key information "meeting" is present in the first message. In this case, the recommended content can be content that matches the key information "meeting," such as "When are you free?" or "I'll schedule a meeting."

[0085] By identifying key information in the first message, the server of the instant messaging system can determine the conversation context or topic between the current user and at least one first user, and then present recommended content that matches the conversation context to the current user.

[0086] In other embodiments, recommended content can be determined using a language model. Specifically, based at least on the first message and / or the second message, a prompt message can be generated and sent to the language model, and at least one recommended content returned by the language model can be received.

[0087] The language model can be a model with natural language processing capabilities, capable of handling different types of natural language tasks. For example, the language model can be a deep learning model trained on text data.

[0088] A prompt message can be used to instruct the language model to generate recommended content based on a first message and / or a second message. In other words, after the prompt message is sent to the language model, the language model can generate at least one corresponding recommended content based on the prompt message's suggestive capabilities and the first and / or second message. Thus, by leveraging the language model and prompt learning technology, the automatic generation and determination of recommended content can be achieved.

[0089] In some possible implementations, fine-tuning models can be used to optimize language models, making the recommendations generated by the optimized language model more accurate and more in line with the current dialogue context. For example, the fine-tuning model can be a low-rank adaptation of large language models (LoRA). LoRA models freeze the weight matrix of the language model and inject the trainable rank decomposition matrix into each layer of the encoder (transformer) architecture, thereby reducing the number of training parameters for downstream tasks and achieving optimization of the language model.

[0090] In addition to the above-described process of generating prompt information, this embodiment of the disclosure may also generate prompt information using other information related to the current dialogue. Specifically, prompt information is generated based on the first message and / or the second message, and at least one of the following: the identity type information of the first user and / or the local user, the context information of the first message, and the user group information of the first user and / or the local user.

[0091] The identity type information of the first user and / or the local user can be understood as the classification result after classifying the first user based on at least one attribute. For example, after classifying users based on technical attributes, the identity type information of the first user and / or the local user can be technical personnel, managers, administrative personnel, etc. As another example, after classifying users based on their department, the identity type information of the first user and / or the local user can be employees of department A, employees of department B, etc.

[0092] The context information of the first message can be the content of the conversation between the local user and at least one first user in the current dialogue. For example, when the local user is having a one-on-one chat with a first user, the context information can be the content of that one-on-one chat in the current dialogue. As another example, when the local user is having a group chat with multiple first users, the context information can be the content of the group chat in the current dialogue within the group.

[0093] The user group information of the first user and / or the local user can be understood as the user's organizational identity information when using the instant messaging system. For example, the first user's user group information could be organization A, and the local user's user group information could be organization B. By using the user group information of the first user and / or the local user, it can be determined whether the local user and the first user are members of the same user group.

[0094] By combining the contextual information of the first message, the recommended content generated by the language model is more in line with the current dialogue context and better meets the message reply needs of the user on this end.

[0095] By combining the identity type information of the first user and / or the local user, as well as the user group information of the first user and / or the local user, the recommended content generated by the language model is more closely aligned with the user's identity. For example, when the identity type information of the first user and / or the local user is a technical person, the recommended content generated by the language model can include technical terms. As another example, when the first user's organization information differs from the local user's user group information—that is, when the first user is an external member—the tone of the recommended content generated by the language model can be more gentle.

[0096] In this way, by combining relevant information from the current conversation to generate prompts, the language model can better understand the context and user identity of the current conversation, and generate more relevant recommended content.

[0097] Furthermore, the prompt message can also include information to guide the reasoning process of the language model. For example, it could be "Should content recommendation be performed for the current first message?" or "Does the current first message meet the content recommendation criteria?" Therefore, after the prompt message is sent to the language model, the language model can determine whether the content recommendation criteria for the first message and / or the second message are met based on the information indicating the reasoning process in the prompt message. In response to meeting the content recommendation criteria for the first message and / or the second message, the language model generates at least one recommended piece of content based on the first message and / or the second message.

[0098] The content recommendation criteria for the first message and / or the second message can be understood as the conditions for content recommendation after receiving the first message and / or performing an editing operation on the second message. In some embodiments, the content recommendation criteria for the first message can be the ability to generate an accurate response to the first message. In other words, when the language model determines that it can generate an accurate response to the first message, the content recommendation criteria for the first message are met, and the language model can generate recommended content. For example, when the first message includes judgment questions such as "is it," "does it exist," or "is it right or wrong," the language model can determine that it can generate an accurate response to the first message; when the first message includes open-ended questions, the language model can determine that it cannot generate an accurate response to the first message.

[0099] In practical implementation, by acquiring and analyzing the language model's inference logs, we can understand the language model's inference process for the first and / or second messages, given the indication capabilities of the prompts. In other words, the language model's inference logs reveal whether the content recommendation criteria for the first and / or second messages are met. Thus, by leveraging the language model to automatically determine the timing of content recommendations, we can avoid excessive information load on the instant messaging page due to frequent presentations of recommended content, thereby improving the user experience.

[0100] After the recommended content is displayed on the instant messaging page, the user on this device can also perform actions on the recommended content. In some embodiments, in response to a triggered action targeting a specific recommended content among at least one recommended content, the target recommended content is sent.

[0101] In other words, users on this platform can select from at least one recommended content that matches their response needs and can be used as the first message or can be sent directly. By triggering the target recommended content, users can send the target recommended content directly, thus achieving a quick response to the first message and a quick sending of the second message.

[0102] In other embodiments, in response to a triggering operation for a target recommended content among at least one recommended content, the target recommended content is displayed in an input box on the instant messaging page.

[0103] In other words, at least one of the presented recommended content items may have certain defects or flaws, failing to fully meet the content interaction needs of the user on this end, and making it difficult to send directly. In this case, the user on this end can trigger a target recommended content item (e.g., the recommended content item that is closest to the reply needs among at least one recommended content item), causing the target recommended content to appear in the input box. In this way, the user on this end can further modify the target recommended content in the input box and send the modified target recommended content.

[0104] In this way, whether the target recommended content is sent directly or presented in the input box and then modified, the user on this end does not need to enter all the content in the input box, thus improving the efficiency of content interaction and operation for the user on this end.

[0105] Based on the above description, this disclosure provides a content recommendation method. The method first displays an instant messaging page, whereby a local user interacts with at least one first user. In response to receiving a first message from at least one first user and / or an editing operation by the local user on a second message, at least one recommended piece of content is presented on the instant messaging page. This recommended content is generated based on the first message and / or the second message, and is used to reply to the first message or perform an operation associated with the first message and / or the second message.

[0106] This method targets scenarios where users interact with content on instant messaging pages. Based on messages sent by other users or messages to be sent by the current user, it generates and presents recommended content. Users can then conveniently reply to messages or perform related actions using the recommended content, improving the efficiency of instant messaging interactions.

[0107] The preceding text introduced the content recommendation method provided in this publication. The following text will explain it in the context of specific scenarios.

[0108] Figures 2A to 2D are schematic diagrams of an instant messaging page provided in an embodiment of the present disclosure. As shown in Figure 2A, the instant messaging page 20 includes a dialogue information display area 201, a dialogue content display area 202, an input box 203, and an area 204 associated with the input box.

[0109] The dialogue information display area 201 is used to display information related to the dialogue. For example, when the current dialogue is a one-on-one chat between the current user and a first user, the first user's information can be displayed. Or, when the current dialogue is a group chat between the current user and multiple first users, group information can be displayed. The dialogue content display area 202 is used to display messages sent by the current user or at least one first user. The input box 203 is used for the current user to input content. The area 204 associated with the input box is used to display at least one recommended piece of content.

[0110] In Figure 2A, the local user and the first user are having a one-on-one chat. The first message 205 sent by the first user is "Will today's meeting continue? If there's a topic, could you please schedule a time? I'll be at the office around 2 PM." Based on the first message 205, at least one piece of recommended content 206 can be generated and displayed in the area 204 associated with the input box. For example, recommended content 206 could be the text-type recommended content "I'll schedule a time." Alternatively, recommended content 206 could be the text-type recommended content "Today's topic is XXXXXX." The local user can reply to the message by directly sending recommended content 206, or by displaying recommended content 206 in the input box 203, allowing for modification and adjustment of recommended content 206.

[0111] In Figure 2B, the local user and multiple first users are having a group chat in the group "Department Team Building Group". The first message 207 sent by the first user in the group is "Is there any team building allowance left? Let's make arrangements." Based on the first message 207, at least one recommended content 208 can be generated. For example, recommended content 208 can be a text-type recommended content "Department team building allowance balance is xxxx yuan". Alternatively, recommended content 208 can also be recommended content indicating the entry point to a functional module, such as "Reimbursement module entry". This allows the local user to quickly reply to the first message or quickly enter other functional modules to perform corresponding operations.

[0112] In Figure 2C, the local user and the first user are having a one-on-one chat. The first message 209 sent by the first user is in a language that the local user does not use. For example, if the local user's usual language is Chinese, the first message 209 sent by the first user is in English. Based on the first message 209, at least one piece of recommended content 210 can be generated. For example, the recommended content 210 could be a recommendation to enable text processing functions, such as "Enable the write-and-translate function." Thus, when the current conversation involves a language that the local user does not use, text processing functions related to translation are recommended to the local user. The local user does not need to manually search for and enable the translation function, reducing the number of operations the local user needs to perform during content interaction.

[0113] In Figure 2D, the local user and the first user are having a one-on-one chat. The first message 209 sent by the first user uses language that the local user doesn't use often. The local user then inputs content into an input box, which includes a second message 211. Based on the second message 211, at least one recommended message 212 can be generated. For example, recommended message 212 could be a text processing function such as "check grammar function," or "edit text function." In this way, by recommending content to the local user, the creation cost of replying to messages is reduced, and the quality of message replies is improved.

[0114] The content recommendation method provided by the embodiments of this disclosure has been described in detail above with reference to Figure 1. The system and device provided by the embodiments of this disclosure will be described below with reference to the accompanying drawings.

[0115] Referring to the structural diagram of the content recommendation system shown in Figure 3, the system 30 includes:

[0116] The display module 301 is used to display an instant messaging page, which is used for content interaction between the local user and at least one first user.

[0117] The presentation module 302 is configured to, in response to receiving a first message sent by the at least one first user and / or an editing operation by the local user on a second message, present at least one recommended content on the instant messaging page, wherein the at least one recommended content is generated based on the first message and / or the second message, and the at least one recommended content is used to reply to the first message or perform an operation associated with the first message and / or the second message.

[0118] In some possible implementations, the system further includes a sending module, which is used to:

[0119] In response to a triggering operation targeting a specific recommended content among the at least one recommended content, the target recommended content is sent.

[0120] The presentation module 302 is also used for:

[0121] In response to a triggering operation for a target recommended content among the at least one recommended content, the target recommended content is displayed in the input box of the instant messaging page.

[0122] In some possible implementations, the system further includes a generation module, which is used to:

[0123] Extract key information from the first message and / or the second message;

[0124] Identify at least one recommended content that matches the key information.

[0125] In some possible implementations, the generation module is used to:

[0126] A prompt message is generated based at least on the first message and / or the second message;

[0127] The prompt information is sent to the language model, and at least one recommended content is received from the language model. The prompt information is used to instruct the language model to generate recommended content based on the first message and / or the second message.

[0128] In some possible implementations, the generation module is specifically used for:

[0129] The prompt information is sent to the language model so that the language model can determine whether the content recommendation conditions for the first message and / or the second message are met. In response to meeting the content recommendation conditions for the first message and / or the second message, at least one recommended content is generated based on the first message and / or the second message.

[0130] Receive at least one recommended content returned by the language model.

[0131] In some possible implementations, the generation module is specifically used for:

[0132] Based on the first message and / or the second message, and at least one of the following information: the identity type information of the first user and / or the local user, the context information of the first message, and the user group information of the first user and / or the local user, a prompt message is generated.

[0133] In some possible implementations, the presentation module 302 is specifically used for:

[0134] At least one recommended piece of content is displayed in the area associated with the input box on the instant messaging page.

[0135] In some possible implementations, the recommended content includes at least one of the following: text-type recommended content, emoticon-type recommended content, document-type recommended content, recommended content indicating the entry point of a function module, and recommended content indicating text processing functions.

[0136] The content recommendation system 30 according to the embodiments of this disclosure can correspond to the execution of the methods described in the embodiments of this disclosure, and the above and other operations and / or functions of each module / unit of the content recommendation system 30 are respectively for implementing the corresponding processes of each method in the embodiment shown in FIG1. ​​For the sake of brevity, they will not be described again here.

[0137] This disclosure also provides an electronic device. Specifically, this electronic device is used to implement the functions of the content recommendation system 30 shown in the embodiment of FIG3.

[0138] Figure 4 provides a schematic diagram of the structure of an electronic device 400. As shown in Figure 4, the electronic device 400 includes a bus 401, a processor 402, a communication interface 403, and a memory 404. The processor 402, the memory 404, and the communication interface 403 communicate with each other via the bus 401.

[0139] Bus 401 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, only one thick line is used in Figure 4, but this does not indicate that there is only one bus or one type of bus.

[0140] The processor 402 can be any one or more of the following processors: central processing unit (CPU), graphics processing unit (GPU), microprocessor (MP), or digital signal processor (DSP).

[0141] Communication interface 403 is used for communication with external devices. For example, communication interface 403 can be used to communicate with a terminal.

[0142] Memory 404 may include volatile memory, such as random access memory (RAM). Memory 404 may also include non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid state drive (SSD).

[0143] The memory 404 stores executable code, and the processor 402 executes the executable code to perform the aforementioned recommended method.

[0144] Specifically, in the implementation of the embodiment shown in FIG3, and where each module or unit of the content recommendation system 30 described in FIG3 is implemented by software, the software or program code required to execute the functions of each module / unit in FIG3 can be partially or wholly stored in the memory 404. The processor 402 executes the program code corresponding to each unit stored in the memory 404 to execute the aforementioned content recommendation method.

[0145] This disclosure also provides a computer-readable storage medium. The computer-readable storage medium can be any available medium that a computing device can store, or a data storage device such as a data center containing one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive). The computer-readable storage medium includes instructions that instruct the computing device to perform the file processing method described above for the content recommendation system 30.

[0146] This disclosure also provides a computer program product comprising one or more computer instructions. When the computer instructions are loaded and executed on a computing device, all or part of the processes or functions described in this disclosure are generated.

[0147] The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, or data center to another website, computer, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0148] When the computer program product is executed by a computer, the computer performs any of the aforementioned content recommendation methods. The computer program product can be a software installation package; when any of the aforementioned content recommendation methods needs to be used, the computer program product can be downloaded and executed on the computer.

[0149] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0150] The units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the units / modules do not necessarily limit the specific unit itself.

[0151] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0152] In the context of embodiments of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0153] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems or apparatus disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple, and relevant parts can be referred to the method section.

[0154] It should be understood that in this disclosure, "at least one item" means one or more, and "more than one" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0155] It should also be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0156] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0157] The above description of the disclosed embodiments enables those skilled in the art to make or use this disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A content recommendation method, comprising: displaying an instant messaging page, the instant messaging page being used for content interaction between a local user and at least one first user; in response to receiving a first message sent by the at least one first user and / or an editing operation of a second message by the local user, presenting at least one recommendation content in the instant messaging page, the at least one recommendation content being generated based on the first message and / or the second message, the at least one recommendation content being used for replying to the first message or performing an operation associated with the first message and / or the second message.

2. The method of claim 1, further comprising: in response to a triggering operation on a target recommendation content in the at least one recommendation content, sending the target recommendation content; or in response to a triggering operation on a target recommendation content in the at least one recommendation content, presenting the target recommendation content in an input box of the instant messaging page. The at least one recommendation content is generated by:

3. The method of claim 1 or 2, wherein, extracting key information from the first message and / or the second message; determining at least one recommendation content matching the key information. The at least one recommendation content is generated by:

4. The method of claim 1 or 2, wherein, generating prompt information based on at least the first message and / or the second message; sending the prompt information to a language model, and receiving at least one recommendation content returned by the language model, the prompt information being used to instruct the language model to generate a recommendation content based on the first message and / or the second message. The sending the prompt information to the language model, and receiving at least one recommendation content returned by the language model, comprises:

5. The method of claim 4, wherein, sending the prompt information to the language model, so that the language model determines whether a content recommendation condition for the first message and / or the second message is met, and in response to the content recommendation condition for the first message and / or the second message being met, generates at least one recommendation content based on the first message and / or the second message; receiving the at least one recommendation content returned by the language model. The generating prompt information based on at least the first message and / or the second message, comprises:

6. The method of claim 4 or 5, wherein, generating prompt information based on the first message and / or the second message, and at least one of the following information: identity type information of the first user and the local user, context information of the first message, user group information of the first user and the local user. The presenting at least one recommendation content in the instant messaging page, comprises:

7. The method according to any one of claims 1 to 6, wherein, presenting at least one recommendation content in a region associated with an input box in the instant messaging page. The recommendation content comprises at least one of the following: a text type recommendation content, an expression type recommendation content, a document type recommendation content, a recommendation content indicating an entry of a function module, and a recommendation content indicating a text processing function.

8. The method according to any one of claims 1 to 7, wherein, 9. A content recommendation system, comprising: a display module configured to display an instant messaging page, the instant messaging page being used for content interaction between a local user and at least one first user; ​ The presentation module is configured to present at least one recommended content in the instant messaging page in response to receiving the first message sent by the at least one first user and / or the editing operation of the second message by the local user, the at least one recommended content being generated based on the first message and / or the second message, the at least one recommended content being used for replying to the first message or performing an operation associated with the first message and / or the second message. 10.An electronic device comprising a processor and a memory, wherein The processor is configured to execute instructions stored in the memory, causing the electronic device to perform the content recommendation method according to any one of claims 1-8.

11. A computer-readable storage medium comprising instructions, wherein, The instructions instruct the electronic device to perform the content recommendation method according to any one of claims 1-8.

Images