Content recommendation method, system, equipment and medium

Abstract

The invention provides a content recommendation method, system and device and a medium, and the method comprises the steps: displaying an instant messaging page which is used for the content interaction between a home terminal user and at least one first user; in response to a received first message sent by at least one first user and / or an editing operation of a home terminal user for a second message, 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 recommended content is used for replying the first message or executing an operation associated with the first message and / or the second message. According to the method, the user can conveniently perform message reply or execute related operation by utilizing the recommended content, so that the interaction efficiency in instant messaging is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, and particularly relates to a content recommendation method and system, an electronic device and a computer readable storage medium. BACKGROUND

[0002] With the continuous development of computer technology, instant messaging (IM) systems emerge as the times require. Users can communicate with other users through the instant messaging system. Specifically, users can chat with other users in the instant messaging system, or establish a group in the instant messaging system and chat with multiple users in the group.

[0003] Generally, users need to manually input content in the input box through the keyboard, or input content in the input box through voice input and the like. However, the message input and reply efficiency of the above-mentioned manner is low. SUMMARY

[0004] The present application provides a content recommendation method. The method can improve the interaction efficiency in instant messaging. The present application also provides a system, an electronic device, a computer readable storage medium and a computer program product corresponding to the above-mentioned method.

[0005] In a first aspect, the present application provides a content recommendation method, which comprises:

[0006] displaying an instant messaging page, the instant messaging page being used for content interaction between a local user and at least one first user;

[0007] 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.

[0008] In some possible implementation manners, the method further comprises:

[0009] in response to a triggering operation on a target recommendation content in the at least one recommendation content, sending the target recommendation content; or

[0010] 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.

[0011] In some possible implementation manners, the at least one recommendation content is generated through the following steps:

[0012] extracting key information from the first message and / or the second message;

[0013] determining at least one recommended content matched with the key information.

[0014] In some possible implementation manners, the at least one recommended content is generated by the following steps:

[0015] generating prompt information based at least on the first message and / or the second message;

[0016] sending the prompt information to a language model, and receiving at least one recommended content returned by the language model, the prompt information being used to instruct the language model to generate recommended content based on the first message and / or the second message.

[0017] In some possible implementation manners, the sending the prompt information to the language model, and receiving the at least one recommended content returned by the language model, includes:

[0018] 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 recommended content based on the first message and / or the second message;

[0019] receiving the at least one recommended content returned by the language model.

[0020] In some possible implementation manners, the generating prompt information based at least on the first message and / or the second message includes:

[0021] 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.

[0022] In some possible implementation manners, the presenting at least one recommended content in the instant messaging page includes:

[0023] presenting at least one recommended content in a region associated with the input box in the instant messaging page.

[0024] In some possible implementation manners, the recommended content includes at least one of the following: recommended content of a text type, recommended content of an expression type, recommended content of a document type, recommended content indicating an entrance of a function module, and recommended content indicating a text processing function.

[0025] In a second aspect, the present application provides a content recommendation system, the system comprising:

[0026] a display module configured to display an instant messaging page, the instant messaging page being configured to enable a local user and at least one first user to interact with content;

[0027] a presentation module configured to present at least one recommended content in the instant messaging page in response to receiving a first message sent by the at least one first user and / or an editing operation on a 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 configured to reply to the first message or perform an operation associated with the first message and / or the second message.

[0028] In some possible implementation manners, the system further comprises a sending module configured to:

[0029] send a target recommended content in the at least one recommended content in response to a triggering operation on the target recommended content;

[0030] The presentation module is further configured to:

[0031] present the target recommended content in the input box of the instant messaging page in response to the triggering operation on the target recommended content in the at least one recommended content.

[0032] In some possible implementation manners, the system further comprises a generation module configured to:

[0033] extract key information from the first message and / or the second message;

[0034] determine at least one recommended content matching the key information.

[0035] In some possible implementation manners, the generation module is configured to:

[0036] generate prompt information based on at least the first message and / or the second message;

[0037] send the prompt information to a language model, and receive at least one recommended content returned by the language model, the prompt information being configured to instruct the language model to generate recommended content based on the first message and / or the second message.

[0038] In some possible implementation manners, the generation module is specifically configured to:

[0039] send the prompt information to the language model, so that the language model judges 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 recommended content based on the first message and / or the second message;

[0040] receive the at least one recommended content returned by the language model.

[0041] In some possible implementation manners, the generating module is specifically configured to:

[0042] generate 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 / or the local user, context information of the first message, user group information of the first user and / or the local user.

[0043] In some possible implementation manners, the presenting module is specifically configured to:

[0044] present the at least one recommended content in a region associated with the input box in the instant messaging page.

[0045] In some possible implementation manners, the recommended content includes at least one of the following: a recommended content of a text type, a recommended content of an expression type, a recommended content of a document type, a recommended content indicating an entrance of a function module, and a recommended content indicating a text processing function.

[0046] In a third aspect, the present application provides an electronic device, which includes a processor and a memory. The processor and the memory are in communication with each other. The processor is configured to execute instructions stored in the memory, so that the electronic device performs the content recommendation method in the first aspect or any implementation manner of the first aspect.

[0047] In a fourth aspect, the present application provides a computer-readable storage medium, which stores instructions. The instructions instruct an electronic device to perform the content recommendation method in the first aspect or any implementation manner of the first aspect.

[0048] In a fifth aspect, the present application provides a computer program product including instructions, which, when executed on an electronic device, cause the electronic device to perform the content recommendation method in the first aspect or any implementation manner of the first aspect.

[0049] On the basis of the implementation manners of the aspects described above, the present application can be further combined to provide more implementation manners.

[0050] From the above technical solution, the present application has the following advantages:

[0051] The present application provides a content recommendation method, which first displays an instant messaging page, wherein the instant messaging page is used for content interaction between a local user and at least one first user, and at least one recommended content is presented in the instant messaging page 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, 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 for replying to the first message or performing an operation associated with the first message and / or the second message.

[0052] The method generates and presents recommended content based on messages sent by other users or messages to be sent by the local user in the scenario of content interaction of the user in the instant messaging page. In this way, the user can conveniently reply to messages or perform related operations by using the recommended content, thereby improving the interaction efficiency in instant messaging. BRIEF DESCRIPTION OF DRAWINGS

[0053] In order to more clearly illustrate the technical method of the embodiments of the present application, the drawings required to be used in the embodiments will be briefly introduced as follows.

[0054] Figure 1 A flowchart of a content recommendation method provided by the embodiments of the present application;

[0055] Figures 2A to 2D A schematic diagram of an instant messaging page provided by the embodiments of the present application;

[0056] Figure 3 A structural schematic diagram of a content recommendation system provided by the embodiments of the present application;

[0057] Figure 4 A structural schematic diagram of an electronic device provided by the embodiments of the present application. DETAILED DESCRIPTION

[0058] The terms "first", "second" in the embodiments of the present application are only for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include one or more of the features.

[0059] First, some technical terms involved in the embodiments of the present application are introduced.

[0060] An instant message (IM) system, which can also be referred to as IM software or IM tool, can be understood as a tool for real-time voice and text transmission based on an Internet client. A user can interact with other users through the IM system.

[0061] Generally, the IM system can provide an input box. During the content interaction between the user and the other user, a message can be input in the input box for message sending or message replying.

[0062] However, the above content interaction mode has the following problems: the user needs to manually input content in the input box through a keyboard or input content through voice input, etc., which is slow in input efficiency and low in interaction efficiency.

[0063] Therefore, the present application provides a content recommendation method. The method first displays an instant message page, wherein the instant message page is used for content interaction between a local user and at least one first user, the local user and the at least one first user perform content interaction in response to receiving a first message sent by the at least one first user, and at least one recommended content is presented in the instant message page, wherein 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 for replying to the first message or performing an operation associated with the first message and / or the second message.

[0064] The method generates and presents recommended content based on messages sent by other users or messages to be sent by the local user in the scenario of content interaction of the user in the instant message page. In this way, the user can conveniently reply to a message or perform a related operation by using the recommended content, thereby improving the interaction efficiency in instant messaging.

[0065] In order to facilitate understanding of the technical solutions provided by the embodiments of the present application, the following will be described with reference to the accompanying drawings.

[0066] Referring to Figure 1 The flowchart of the content recommendation method provided by the embodiments of the present application is shown in FIG. 1, and the method specifically includes the following steps.

[0067] S101: Display an instant message page.

[0068] The instant messaging page can be a page provided by a server of an instant messaging system and displayed in a client of the instant messaging system. In some embodiments, the instant messaging system can be a standalone software system, for example, a standalone instant messaging software or tool. 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 to provide instant messaging functions.

[0069] The OA system can be understood as a collaborative office system, and the OA system can include multiple functional modules, and different functional modules can provide different functions. For example, in addition to the instant messaging module described above that provides instant messaging functions, the OA system can also include a schedule module that provides schedule management functions, a video conference module that provides video conference functions, a cloud document module that provides document management functions, and the like.

[0070] For ease of description, the user of the client of the instant messaging system will be referred to as a local user in the embodiments of the present application. That is, in the embodiments of the present application, the instant messaging page can be displayed in the client of the instant messaging system of the local user.

[0071] Further, the instant messaging page can be used for content interaction with at least one first user. In other words, the first user can be understood as a communication object or chat object of the local user.

[0072] The embodiments of the present application do not limit the content interaction mode of the local user and the first user. In some embodiments, the content interaction mode of the local user and the first user can be single chat, and at this time, the instant messaging page is used for content interaction with a certain first user. In other embodiments, the content interaction mode of the local user and the first user can be group chat, in other words, the local user and multiple first users are in the same group, and at this time, the instant messaging page is used for content interaction with multiple first users in the group.

[0073] S102: In response to receiving the first message sent by the at least one first user and / or the editing operation of the local user on the second message, at least one recommended content is presented in the instant messaging page.

[0074] The first message can be understood as a chat message sent by the at least one first user. For example, when the local user and the first user are in single chat, the first message can be a chat message sent by the first user to the local user. For another example, when the local user and multiple first users are in group chat, the first message can be a chat message sent by the multiple first users in the group.

[0075] The second message can be understood as a message edited by the local user in the instant messaging page. For example, when the local user needs to reply to a message or send a message in the instant messaging page, the local user can edit the content (such as content input, content modification, content deletion, etc.) in the input box of the instant messaging page. At this time, the content edited by the local user in the input box can be understood as the second message.

[0076] In the embodiments of the present application, the at least one recommended content can be generated based on the first message and / or the second message, and the at least one recommended content can be used to reply to the first message or perform an operation associated with the first message and / or the second message. That is, when the local user receives a message sent by another user (i.e., the first user), the local user can quickly reply to the message by means of the recommended content. When the local user edits a message in the instant messaging page, the local user can perform an operation associated with the first message and / or the second message by means of the recommended content, without layer-by-layer selecting a functional module required to perform the operation, thereby reducing the length of the operation link.

[0077] In some embodiments, the at least one recommended content can be presented in a region associated with the input box in the instant messaging page. The region associated with the input box in the instant messaging page can be understood as a region providing functions associated with the input function. For example, the instant messaging system can usually provide a screenshot function, an expression selection function, a file selection function, etc. in the region associated with the input box.

[0078] In specific implementation, the at least one recommended content can be presented in a region above the input box and / or a region below the input box in the instant messaging page. By presenting the recommended content in the region associated with the input box, the local user can quickly find the recommended content when replying to the first message through the input box or editing the second message through the input box, thereby being able to quickly generate a reply message to the first message by means of the recommended content or quickly perform an operation associated with the first message and / or the second message.

[0079] The embodiments of the present application support different types of recommended content. Specifically, the recommended content can include at least one of the following: text type recommended content, expression type recommended content, document type recommended content, recommended content indicating a functional module entrance, and recommended content indicating a text processing function.

[0080] The recommended content of the text type can be a piece of text, the recommended content of the expression type can be an expression. The recommended content of the document type can indicate a document, for example, when the instant messaging system is an independent software system, the recommended content of the document type can be a local document, and for another example, when the instant messaging system is a functional module in an OA system, the recommended content of the document type can be a cloud document link. When the instant messaging system is a functional module in an OA system, the recommended content indicating the entrance of the functional module can be an entrance control of a functional module, for example, an entrance control of a schedule module, an entrance control of a video conference module, and the like. The recommended content indicating the text processing function can be a control of a text processing function, for example, a translation function, a text correction function, a polishing function, and the like.

[0081] By providing the recommended content indicating the entrance of the functional module, the local user can quickly enter other functional modules in the process of content interaction with the at least one first user, without manually switching between the functional modules, thereby improving the efficiency of collaborative office work using the OA system. For example, when the first message is "Let's chat sometime", the recommended content can include an entrance indicating the video conference module. When the second message edited by the local user is "I'll check my schedule", the recommended content can include an entrance indicating the schedule module.

[0082] By providing the recommended content indicating the text processing function, the local user can quickly call the text processing capability existing in the OA system in the process of content interaction with the at least one first user, thereby realizing text processing in the message reply process.

[0083] In this way, different types of recommended content are presented in the input box association area, so that the local user can quickly realize message reply or enter other functional modules to perform corresponding operations without a long operation link, thereby effectively solving the problem of deep functional entrance in related technologies.

[0084] In the embodiments of the present application, the recommended content can be generated in different ways. In some embodiments, key information can be extracted from the first message and / or the second message, and at least one recommended content matching the key information can be determined.

[0085] That is, the server of the instant messaging system can store a pre-configured corresponding relationship between the key information and the recommended content, which can be manually configured by the user using the instant messaging system, or provided by the server of the instant messaging system. In this way, by identifying the key information from the first message and / or the second message, if the first message and / or the second message hits a certain key information, at least one recommended content having a corresponding relationship with the key information can be further obtained, thereby realizing the determination of the recommended content.

[0086] For example, when the first message is "Let's have a meeting to discuss it", there is a key information "meeting" in the first message, and at this time, the recommended content can be the recommended content "When are you free?" and "I will make an appointment for a meeting" matched with the key information "meeting".

[0087] By identifying the key information in the first message, the server of the instant messaging system can determine the dialogue context or dialogue topic between the local user and at least one first user according to the key information, and then present the recommended content matched with the dialogue context to the local user.

[0088] In some embodiments, the recommended content can be determined by means of a language model. In specific implementation, prompt information can be generated based on at least the first message and / or the second message, and the prompt information can be sent to the language model, and at least one recommended content returned by the language model can be received.

[0089] The language model can be a model with natural language processing capability and capable of processing different types of natural language tasks. For example, the language model can be a deep learning model trained based on text data.

[0090] The prompt information can be used to instruct the language model to generate the recommended content based on the first message and / or the second message. In other words, after the prompt information is sent to the language model, the language model can generate at least one recommended content corresponding to the first message and / or the second message based on the prompting capability of the prompt information. In this way, by means of the language model and the prompt learning technology, the automatic generation and determination of the recommended content are realized.

[0091] In some possible implementations, a fine-tuning model can also be used to optimize the language model, so that the recommended content generated by the optimized language model is more accurate and more consistent with the current dialogue context. For example, the fine-tuning model can be a low-rank adaptive model (low-rank adaptation of large language models, LoRA). The LoRA model injects a trainable rank decomposition matrix into each layer in the transformer architecture by freezing the weight matrix of the language model, thereby reducing the number of training parameters for downstream tasks and optimizing the language model.

[0092] For the above process of generating prompt information, the prompt information can also be generated by means of other information related to the current dialogue in the embodiment of the application. Specifically, the prompt information is generated 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 / or the local user, context information of the first message, user group information of the first user and / or the local user.

[0093] The identity type information of the first user and / or the local user can be understood as a classification result of classifying the first user according to at least one attribute. For example, after classifying the user according to a technical attribute, the identity type information of the first user and / or the local user can be a technical personnel, a management personnel, an administrative personnel, and the like. For another example, after classifying the user according to a department to which the user belongs, the identity type information of the first user and / or the local user can be an A department employee, a B department employee, and the like.

[0094] The context information of the first message can be a conversation content of the local user and the at least one first user in a current conversation. For example, when the local user and the first user are in one-on-one chatting, the context information can be one-on-one chatting content in the current conversation. For another example, when the local user and a plurality of first users are in group chatting, the context information can be group chatting content of the current conversation in the group.

[0095] The user group information of the first user and / or the local user can be understood as organizational identity information of the user when using the instant messaging system. For example, the user group information of the first user can be an A organization, and the user group information of the local user can be a B organization. Through 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 under the same user group.

[0096] By combining the context information of the first message, the recommended content generated by the language model is more in line with the conversation context of the current conversation and better meets the message reply needs of the local user.

[0097] By combining the identity type information of the first user and / or the local user and the user group information of the first user and / or the local user, the recommended content generated by the language model is more in line with the user identity. For example, when the identity type information of the first user and / or the local user is a technical personnel, technical terms can be included in the recommended content generated by the language model. For another example, when the organization information of the first user is different from the user group information of the local user, that is, the first user is an external member, the tone of the recommended content generated by the language model can be softer.

[0098] In this way, by combining the information related to the current conversation to generate the prompt information, the language model can better understand the conversation context and the user identity of the current conversation, and generate recommended content that is more in line with actual needs.

[0099] Further, the prompt information can further include information indicating the inference process of the language model. For example, "Do you need to make content recommendation for the current first message?", or "Does the current first message meet the content recommendation condition?", etc. Therefore, after sending the prompt information to the language model, the language model can determine whether the content recommendation condition for the first message and / or the second message is met according to the information indicating the inference process in the prompt information, and generate at least one recommended content based on the first message and / or the second message in response to meeting the content recommendation condition for the first message and / or the second message.

[0100] In some embodiments, the content recommendation condition for the first message can be that an accurate reply for the first message can be generated, in other words, when the language model determines that an accurate reply for the first message can be made, the content recommendation condition for the first message is met, and the language model can generate the recommended content. For example, when the first message includes a judgment question such as "Is it", "Have you", "Is it correct", the language model can determine that an accurate reply for the first message can be made, and when the first message includes an open question, the language model can determine that an accurate reply for the first message cannot be made.

[0101] In specific implementation, by obtaining and analyzing the inference log of the language model, the inference process of the language model for the first message and / or the second message under the indication of the prompt information can be understood. That is, through the inference log of the language model, it can be known whether the language model determines that the content recommendation condition for the first message and / or the second message is met. In this way, by means of the language model, the automatic determination of the content recommendation opportunity is realized, which avoids the excessive information amount in the instant messaging page caused by frequent presentation of the recommended content, and improves the user experience.

[0102] After presenting the recommended content in the instant messaging page, the local user can also operate the recommended content. In some embodiments, in response to a trigger operation on a target recommended content in the at least one recommended content, the target recommended content is sent.

[0103] In other words, the local user can select a target recommended content in the at least one recommended content that meets the reply demand of the local user and can be used as a reply message of the first message or can be directly sent, and directly send the target recommended content by triggering the target recommended content, so as to realize the quick reply to the first message and the quick sending of the second message.

[0104] In some embodiments, the target recommended content is presented in the input box of the instant messaging page in response to a trigger operation on the target recommended content in the at least one recommended content.

[0105] In other words, the at least one recommended content presented may all have defects or flaws and cannot fully meet the content interaction needs of the local user, and it is difficult to be directly sent. At this time, the local user can trigger a target recommended content (for example, a recommended content closest to the reply needs in the at least one recommended content), so that the target recommended content is presented in the input box. In this way, the local user can further modify the target recommended content in the input box and send the modified target recommended content.

[0106] In this way, whether the target recommended content is directly sent or presented in the input box and then modified based on the target recommended content, the local user does not need to completely input all the content in the input box, which improves the content interaction efficiency and operation efficiency of the local user.

[0107] Based on the above content description, the embodiments of the present application provide a content recommendation method. The method first displays an instant messaging page, wherein the instant messaging page is 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 the local user on a second message, at least one recommended content is presented in 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 for replying to the first message or performing an operation associated with the first message and / or the second message.

[0108] The method generates and presents recommended content based on messages sent by other users or messages to be sent by the local user in the scenario of content interaction of the user in the instant messaging page. In this way, the user can use the recommended content to conveniently reply to the message or perform the related operation, which improves the interaction efficiency in instant messaging.

[0109] The foregoing describes the content recommendation method provided by the present application, and the following will be described in combination with specific scenarios.

[0110] Figures 2A to 2D A schematic diagram of an instant messaging page provided by the embodiments of the present application is shown in FIG. 2. Figure 2A As shown in FIG. 2, the instant messaging page 20 includes a conversation information presentation area 201, a conversation content presentation area 202, an input box 203, and an area 204 associated with the input box.

[0111] The conversation information presents the rest 201 for presenting information related to the conversation. For example, when the current conversation is a single chat between the local user and the first user, the information of the first user can be presented. For another example, when the current conversation is a group chat between the local user and a plurality of first users, the group information can be presented. The conversation content presentation area 202 is used for presenting the messages sent by the local user or at least one first user. The input box 203 is used for the local user to input content. The area 204 associated with the input box is used for presenting at least one recommended content.

[0112] In Figure 2A , the local user has a single chat with the first user. The first message 205 sent by the first user is "Will today's meeting continue? If there is a topic, help me arrange a time, I will be at the company at about 2 pm", based on the first message 205, at least one recommended content 206 can be generated and presented in the area 204 associated with the input box. For example, the recommended content 206 can be a text type recommended content "I will arrange a time". For another example, the recommended content 206 can also be a text type recommended content "The topic of today is XXXXXX". The local user can directly send the recommended content 206 for message reply by triggering the recommended content 206, or present the recommended content 206 in the input box 203 so as to modify and adjust the recommended content 206.

[0113] In Figure 2B , the local user has a group chat with a plurality of first users in the group "department team building group". The first message 207 sent by the first user in the group is "Is there still team building fee? Arrange it", based on the first message 207, at least one recommended content 208 can be generated. For example, the recommended content 208 can be a text type recommended content "The balance of the department team building fee is xxxx yuan". For another example, the recommended content 208 can also be a recommended content indicating the entrance of the expense reporting module. In this way, the local user can quickly reply to the first message or quickly enter other functional modules for corresponding operation.

[0114] In Figure 2C , the local user has a single chat with the first user. The first message 209 sent by the first user is an uncommon language of the local user, for example, the commonly used language of the local user is Chinese, and the first message 209 sent by the first user is English. Based on the first message 209, at least one recommended content 210 can be generated, for example, the recommended content 210 can be a recommended content indicating the text processing function "Turn on the write-as-you-translate function". In this way, when the current conversation involves the uncommon language of the local user, the text processing function related to translation is recommended for the local user, and the local user does not need to manually find and turn on the translation function, reducing the number of operations of the local user in the content interaction process.

[0115] In Figure 2D , the local user chats with the first user. The first message 209 sent by the first user is in a non-native language of the local user, and the local user inputs content in an input box, and the input box includes the second message 211. At least one recommended content 212 can be generated based on the second message 211. For example, the recommended content 212 can be a recommended content “check grammar function” indicating a text processing function, or for another example, the recommended content 212 can be a recommended content “polish text function” indicating a text processing function. In this way, by recommending content to the local user, the creation cost of the local user replying to the message is reduced, and the quality of the message reply is improved.

[0116] The above describes Figure 1 The content recommendation method provided by the embodiments of the present application is described in detail, and the system and device provided by the embodiments of the present application will be described below with reference to the drawings.

[0117] Referring to Figure 3 the structural schematic diagram of the content recommendation system, the system 30 includes:

[0118] The display module 301 is configured to display an instant messaging page, and the instant messaging page is used for content interaction between the local user and at least one first user.

[0119] The presentation module 302 is configured to present at least one recommended content in the instant messaging page in response to receiving a first message sent by the at least one first user and / or an editing operation of the local user on a second message, 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 for replying to the first message or performing an operation associated with the first message and / or the second message.

[0120] In some possible implementation manners, the system further includes a sending module, and the sending module is configured to:

[0121] In response to a triggering operation on a target recommended content in the at least one recommended content, the target recommended content is sent.

[0122] The presentation module 302 is further configured to:

[0123] In response to a triggering operation on a target recommended content in the at least one recommended content, the target recommended content is presented in an input box of the instant messaging page.

[0124] In some possible implementation manners, the system further includes a generation module, and the generation module is configured to:

[0125] Extract key information from the first message and / or the second message.

[0126] determining at least one recommended content matching the key information.

[0127] In some possible implementation manners, the generating module is configured to:

[0128] generating prompt information based on at least the first message and / or the second message;

[0129] sending the prompt information to a language model, and receiving at least one recommended content returned by the language model, the prompt information being used to instruct the language model to generate recommended content based on the first message and / or the second message.

[0130] In some possible implementation manners, the generating module is specifically configured to:

[0131] sending the prompt information to a 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, generating at least one recommended content based on the first message and / or the second message;

[0132] receiving the at least one recommended content returned by the language model.

[0133] In some possible implementation manners, the generating module is specifically configured to:

[0134] generating prompt information based on the first message and / or the second message, and at least one of the following: 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.

[0135] In some possible implementation manners, the presenting module 302 is specifically configured to:

[0136] presenting, in a region associated with the input box in the instant messaging page, at least one recommended content.

[0137] In some possible implementation manners, the recommended content includes at least one of the following: a recommended content of a text type, a recommended content of an expression type, a recommended content of a document type, a recommended content indicating an entry of a function module, and a recommended content indicating a text processing function.

[0138] The content recommendation system 30 according to the embodiments of the present application can correspond to performing the methods described in the embodiments of the present application, and the above and other operations and / or functions of each module / unit of the content recommendation system 30 are respectively implemented to achieve the purposes of Figure 1The corresponding flow of each method in the illustrated embodiment will not be described here in detail for the sake of brevity.

[0139] The embodiments of the present application also provide an electronic device. The electronic device is specifically used to implement the functions of the content recommendation system 30 in the embodiments. Figure 3 The functions of the content recommendation system 30 in the embodiments.

[0140] Figure 4 A structural schematic diagram of an electronic device 400 is provided, as shown in the figure. Figure 4 As shown, 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 through the bus 401.

[0141] The bus 401 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience, Figure 4 In the figure, only one thick line is used to represent the bus, but it does not mean that there is only one bus or only one type of bus.

[0142] The processor 402 can be any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP) processor, etc.

[0143] The communication interface 403 is used for external communication. For example, the communication interface 403 can be used for communication with a terminal.

[0144] The memory 404 can include a volatile memory (volatile memory), such as a random access memory (RAM). The memory 404 can also include a non-volatile memory (non-volatile memory), such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD), or a solid state drive (SSD).

[0145] The executable code is stored in the memory 404, and the processor 402 executes the executable code to perform the aforementioned content recommendation method.

[0146] Specifically, in the case of the embodiment shown in the figure, and Figure 3 In the case of the embodiment shown in the figure, and Figure 3 In the case of the embodiment shown in the figure, and Figure 3 In the case of the embodiment shown in the figure, and

[0147] The embodiments of the present application also provide a computer readable storage medium. The computer readable storage medium can be any available medium or data storage device that can store the instructions of the computer device. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk), etc. The computer readable storage medium includes instructions indicating the computer device to execute the file processing method applied to the content recommendation system 30 described above.

[0148] The embodiments of the present application also provide a computer program product, which includes one or more computer instructions. When the computer instructions are loaded and executed on the computer device, the flow or function described in the embodiments of the present application is generated in whole or in part.

[0149] The computer instructions can be stored in a computer readable storage medium, or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions can be transmitted from one website, computer or data center to another website, computer or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode.

[0150] When the computer program product is executed by the computer, the computer executes any of the aforementioned content recommendation methods. The computer program product can be a software installation package, and when any of the aforementioned content recommendation methods is needed, the computer program product can be downloaded and executed on the computer.

[0151] The computer program product of the present application can be a computer program product comprising a computer readable storage medium and a computer program mechanism embedded in the computer readable storage medium. The computer program mechanism comprises parts which when loaded into the processing unit of the computer causes the processing unit to carry out the steps of the present application. These steps are carried out in the order disclosed herein, but other sequences are possible. The computer readable storage medium can be a tangible or physical computer readable storage medium.

[0152] The units described in the embodiments of the present application can be implemented by software, or by hardware. In some cases, they can be implemented by a combination of software and hardware.

[0153] The functions described in this specification can be implemented in hardware, software, or any combination thereof. In some embodiments, the functionality described can be provided as a service or software that can be used on a computer system, e.g., that is implemented in software, or that is provided by a service that is executed on a computer system. In some embodiments, the functions described can be implemented in software such as as part of an operating system, or as any other type of computer program. As used herein, the term "software" encompasses any type of computer instruction, code, or data that can be read by a computer processor, including, without limitation, machine code, object code, and source code. The functions described can be implemented in software as executable instructions stored on a non-transitory computer-readable medium (e.g., on a magnetic disk, a floppy disk, a hard disk, a magnetic tape, a magnetic cassette, an optical disk, a CD-ROM, a ROM, a flash memory, a memory stick, a memory card, a memory chip, a RAM, a ROM, or any other type of non-transitory computer-readable medium that can be read by a computer processor).

[0154] In the context of the present application, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium will include one or more lines of a computer program code, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0155] It should be noted that the various embodiments described herein are described with reference to a plurality of distinct embodiments; however, persons of ordinary skill in the art will understand that each of these embodiments represents but a single exemplification of the various embodiments disclosed herein. Accordingly, any particular stated implementation of an embodiment should not be treated as a limitation to the embodiments described herein. Additionally, it is contemplated that individuals skilled in the art will be able to devise their own implementation of embodiments combining aspects of the various embodiments described herein without the need for undue experimentation.

[0156] It should be understood that, in this specification, "at least one", "one or more" means one or more or more than one. "And / or" is used to describe the association between associated objects, which means that there can be three relationships, for example, "A and / or B" can mean: only A, only B, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the front and rear associated objects. "At least one of the following" or similar expressions means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b or c, can mean: 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.

[0157] It should also be noted that the relationship terms such as first and second, etc. used in this text are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between the entities or operations. Moreover, the terms "include", "contain" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or device. Without more limitations, the element defined by the statement "including a" does not exclude the presence of another identical element in the process, method, article or device including the element.

[0158] The steps of the method or algorithm described in connection with the embodiments disclosed herein can be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software module can be located in random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0159] The foregoing description of the disclosed embodiments enables a person skilled in the art to make or use the application. Modifications of these embodiments will occur to persons of skill in the art, and that the generic principles defined herein can be applied to other embodiments without departing from the spirit or scope of the application. Therefore, the present application is not intended 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, characterized in that, The method includes: Display an instant messaging page, which 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 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.

2. The method according to claim 1, characterized in that, The method further includes: 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, 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.

3. The method according to claim 1, characterized in that, The at least one recommended content is generated through the following steps: Extract key information from the first message and / or the second message; Identify at least one recommended content that matches the key information.

4. The method according to claim 1, characterized in that, The at least one recommended content is generated through the following steps: A prompt message is generated based at least on the first message and / or the second message; 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.

5. The method according to claim 4, characterized in that, The step of sending the prompt information to the language model and receiving at least one recommended content returned by the language model includes: 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. Receive at least one recommended content returned by the language model.

6. The method according to claim 4, characterized in that, The step of generating a prompt message based at least on the first message and / or the second message includes: 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.

7. The method according to claim 1, characterized in that, The presentation of at least one recommended item on the instant messaging page includes: At least one recommended piece of content is displayed in the area associated with the input box on the instant messaging page.

8. The method according to any one of claims 1 to 7, characterized in that, 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.

9. A content recommendation system, characterized in that, The system includes: 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; 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.

10. An electronic device, characterized in that, The electronic device includes a processor and a memory; The processor is configured to execute instructions stored in the memory, causing the electronic device to perform the method as described in any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that, Includes instructions that instruct an electronic device to perform the method as described in any one of claims 1 to 8.

Images