Information reminding method and system

Abstract

The invention provides an information reminding method and system. The information reminding method comprises the steps of generating target reminding according to first information; the first information represents historical situation information related to the user; the target reminding at least comprises target reminding content and a target triggering situation; acquiring second information; the second information represents current situation information related to the user; and under the condition that the current situation information is matched with the target triggering situation, outputting the target reminding content.

Description

Technical Field

[0001] This disclosure relates to, but is not limited to, the field of computer technology, and in particular to an information reminder method and system. Background Technology

[0002] Currently, many commonly used applications have information reminder functions, such as calendars, project management, or smart agents. Information delivery functions can use visual, auditory, or tactile signals to push important pre-set schedules to users at specified times or locations to help users manage tasks. Summary of the Invention

[0003] In view of this, this disclosure provides at least one information notification method and system.

[0004] The technical solution disclosed herein is implemented as follows:

[0005] On the one hand, this disclosure provides an information reminder method, which includes:

[0006] Based on the first information, a target reminder is generated; the first information represents historical contextual information related to the user; the target reminder includes at least the target reminder content and the target triggering context.

[0007] Obtain the second information; the second information represents current contextual information relevant to the user;

[0008] If the current contextual information matches the target triggering context, output the target reminder content.

[0009] In some implementations, a target reminder is generated based on the first information, including:

[0010] Based on historical context information, determine user intent and candidate content;

[0011] Given that the user intent represents the user's expectation to be reminded of the selected content in the first candidate context, a target reminder is generated; wherein, the candidate content is used as the target reminder content, and the first candidate context is used as the target trigger context.

[0012] In some implementations, a target reminder is generated based on the first information, including:

[0013] Based on historical context information, determine user intent and candidate content;

[0014] When the user intent represents the user's expectation to be reminded of the alternative content, and the first alternative scenario cannot be determined through the user intent, the user is interacted with based on the alternative content to obtain the second alternative scenario;

[0015] Generate a target reminder; wherein, the candidate content is used as the target reminder content, and the second candidate scenario is used as the target trigger scenario.

[0016] In some implementations, user intent and candidate content are determined based on historical context information, including at least one of the following:

[0017] Based on user behavior information from historical context, user intent and candidate content are generated using a target model.

[0018] Based on user behavior information and the objects of behavior in historical context information, user intent and candidate content are generated using the target model;

[0019] Based on historical context information and user profile information, user intent and candidate content are generated using the target model.

[0020] In some implementations, after generating the target reminder based on the first information, the method further includes:

[0021] Update the context listening list based on the context type of the target triggering context;

[0022] The context monitoring list includes various context types to be monitored; each context type corresponds to at least one alert.

[0023] In some implementations, obtaining the second information includes:

[0024] Based on the user's current situation, determine the target situation type from multiple types of situations to be monitored;

[0025] Based on the target context type, second information is obtained using at least one application; each application represents an application running on an electronic device associated with the user.

[0026] In some implementations, the second information includes at least one of the following: the user's current geographical location, the current time, the user's current physiological or emotional state, and the task the user is currently performing.

[0027] In some implementations, the method further includes:

[0028] The third information is obtained using at least one application; the third information represents current contextual information related to the user, and the context type corresponding to the third information is different from the target context type; the third information includes at least one of the following: the user's current activity information, cognitive state information, and emotional state information;

[0029] Based on third-party information, determine the target reminder time;

[0030] Output target reminder content, including: output target reminder content at the target reminder time.

[0031] In some implementations, the output of the target reminder content also includes:

[0032] Based on the third information, determine the target output device and the target output mode corresponding to the target reminder content from at least one electronic device currently used by the user;

[0033] Utilize the target output device to output the target reminder content in the target output mode.

[0034] On the other hand, this disclosure also provides an information reminder system, including a reminder generation device, an information acquisition device, and a reminder output device; wherein,

[0035] The reminder generation device generates a target reminder based on the first information; the first information represents historical context information related to the user; the target reminder includes at least the target reminder content and the target triggering context;

[0036] An information acquisition device acquires second information; the second information represents current contextual information relevant to the user.

[0037] The reminder output device outputs the target reminder content when the current context information matches the target trigger context.

[0038] It should be understood that the above general description and the following detailed description are merely exemplary and explanatory, and are not intended to limit the technical solutions of this disclosure. Attached Figure Description

[0039] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the specification, serve to illustrate the technical solutions of this disclosure.

[0040] Figure 1 A schematic diagram illustrating the implementation process of an information notification method provided in this disclosure;

[0041] Figure 2 This is a schematic diagram of the reminder generation process in one embodiment of the present disclosure;

[0042] Figure 3 A schematic diagram of the reminder triggering process in one embodiment provided in this disclosure.

[0043] Figure 4 This is a system architecture diagram of an information reminder system provided in this disclosure;

[0044] Figure 5 This is a schematic diagram of the hardware entity of an electronic device provided in this disclosure. Detailed Implementation

[0045] To make the objectives, technical solutions, and advantages of this disclosure clearer, the technical solutions of this disclosure are further described in detail below with reference to the accompanying drawings and embodiments. The described embodiments should not be regarded as limitations on this disclosure. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0046] In the following description, references are made to “some embodiments,” which describe a subset of all possible embodiments. However, it is understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0047] The terms “first / second / third” are used merely to distinguish similar objects and do not represent a specific ordering of objects. It is understood that “first / second / third” may be interchanged in a specific order or sequence where permitted, so that the embodiments of this disclosure described herein can be implemented in an order other than that illustrated or described herein.

[0048] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure pertains. The terminology used herein is for descriptive purposes only and is not intended to limit the scope of this disclosure.

[0049] In existing technologies, common reminder solutions trigger information pushes based on time or location. For example, users can set reminders to be received "when arriving at a certain location" or "at a specific time." These methods typically require users to actively set specific trigger conditions, and then the reminder logic is executed based on these conditions. However, users' actual situations are often complex and variable, and cannot be covered by simple preset conditions.

[0050] For example, some tasks need to be handled at an uncertain future time. When setting reminders, users often cannot accurately set a specific trigger condition (such as trigger time or trigger location). For instance, after a friend recommends a restaurant, a user may not want to go there specifically, but only want to be reminded when they are nearby and need to eat; or, for example, users may want to be reminded to view tools, links, or materials recommended by friends only when they are handling related tasks.

[0051] It is evident that the reminder solutions in related technologies rely excessively on users' accurate predictions of the future, placing a significant cognitive burden on users when setting reminders. Furthermore, the specific reminder conditions set by users after careful consideration may not be truly suitable for future users, and may even cause them disturbance.

[0052] In view of this, this disclosure provides an information reminder method. First, a target reminder is generated based on first information, wherein the first information represents historical contextual information related to the user, and the target reminder includes at least target reminder content and a target triggering context. Then, second information is obtained, wherein the second information represents current contextual information related to the user. Finally, if the current contextual information matches the target triggering context, the target reminder content is output. In this way, on the one hand, compared to related technologies that rely on users actively setting reminder conditions to establish reminders, this solution actively senses contextual information and actively generates and triggers reminders, achieving a quick and seamless reminder generation and triggering mechanism, improving the flexibility and intelligence of reminder setting and triggering. On the other hand, compared to specific and clear triggering conditions such as time and location, the target triggering context has uncertainty and ambiguity. Therefore, using the target triggering context as the condition for triggering the target reminder content allows users to set reminders even without knowing the specific triggering conditions (e.g., time, location), without having to worry about specific triggering conditions. This improves the reminder hit rate, reduces the cognitive burden of setting reminders, and ultimately improves the user experience.

[0053] The method provided in this disclosure can be executed by an electronic device, which can be a laptop, tablet, desktop computer, set-top box, mobile device (e.g., mobile phone, portable music player, personal digital assistant, dedicated messaging device, portable gaming device), or a server. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0054] The technical solutions in this disclosure will now be clearly and completely described with reference to the accompanying drawings.

[0055] Figure 1 This is a schematic diagram illustrating the implementation process of an information reminder method provided in this disclosure, such as... Figure 1 As shown, the method includes the following steps S11 to S13:

[0056] Step S11: Generate a target reminder based on the first information; the first information represents historical context information related to the user; the target reminder includes at least the target reminder content and the target triggering context.

[0057] Here, the first information represents the historical contextual information related to the user; that is, the first information is the contextual information related to the user obtained at a certain point in time or during a certain period in the past.

[0058] Contextual information refers to any information that can describe the user's own state and / or the surrounding environment.

[0059] In some implementations, contextual information related to the user's own state may include the user's location information, emotional state (e.g., anxious, tense, relaxed, etc.), cognitive state (e.g., focused, silent, etc.), and task processing state (e.g., the task currently being processed).

[0060] In some implementations, contextual information related to the user's surrounding environment may include information about the physical environment around the user, information collected or received by electronic devices related to the user, etc. In some implementations, this may include temperature, light levels, noise levels, etc., of the user's surrounding environment. In some implementations, this may include information input by the user into the electronic device, information received by the electronic device through a communication network, sensor information collected by the electronic device through at least one sensor, etc. Information input by the user into the electronic device may include, for example, text information, image information, voice information, video information, or multimodal information input by the user into the application running on the electronic device, or user operation information on the electronic device. Information received by the electronic device through a communication network may include, for example, email information, system notification messages, interactive information sent to the user by others, etc., received by applications on the electronic device through a communication network. Sensor information collected by the electronic device through at least one sensor may include, for example, image or video information collected by a camera, voice information collected by a microphone, fingerprint information collected using a fingerprint sensor, etc.

[0061] It is evident that contextual information related to users is multidimensional data, which can change over time, and different dimensions are correlated.

[0062] A target reminder refers to information that needs to be reminded to the user in the future (relative to the historical time point corresponding to the first piece of information). This target reminder includes the target reminder content and the target triggering context.

[0063] Targeted reminder content refers to specific information that needs to be reminded to the user in the future. Targeted reminder content can be of any type. In some implementations, targeted reminder content can be a task that the user needs to perform in the future, such as organizing a meeting, writing meeting minutes, or making purchases. In other implementations, targeted reminder content can be information that the user has saved or follows, such as restaurant posts, news articles, emails, applications, tools, or links.

[0064] A target triggering context refers to the situation in which a target reminder is issued to the user. In some implementations, the target triggering context can be a context related to the user's own state, such as location, emotional state, cognitive state, task processing state, etc. In some implementations, the target triggering context can be a context related to the user's surrounding environment, such as time, people, specific scenes, etc. In some implementations, the target triggering context can be a single context, or a combination of multiple contexts (e.g., a combination of a specific scene and cognitive state, a combination of a person and the user's task state, etc.).

[0065] In some implementations, the target model can be used to extract information and / or understand semantics from the historical context information to determine whether the historical context information contains matters that need to be reminded in the future.

[0066] Thus, a target reminder is generated based on the first information. Specifically, information extraction and / or semantic understanding are performed on the first information to determine the content and triggering context of the target reminder, thereby generating the target reminder. Here, the target model can be any model, such as a large language model, speech model, image processing model, video processing model, multimodal model, etc. In some implementations, since the first information is multi-dimensional information of various types, the target model can include multiple types of models, or the target model can be a multimodal model.

[0067] In some implementations, a target model can be used to perform semantic understanding of the first information, thereby generating target reminder content and target triggering context. For example, if the first information is the user's operation information about collecting classical music and the user's voice input, the target model can be used to perform semantic recognition on the voice information to determine that the semantics of the voice information is "Remind me to listen to this piece when I am anxious." The target model can use the user's collected classical music as the target content and the user's anxious state as the target triggering context.

[0068] In some implementations, after generating the target reminder, the target reminder content and the target triggering context are stored in a designated database. In some implementations, this designated data can be of any type, such as a graph database, a relational database, etc.

[0069] Step S12: Obtain second information; the second information represents current context information related to the user.

[0070] Here, the second information refers to the current contextual information obtained after collecting or acquiring contextual information about the user's current situation. Similarly, the second information can include any type of contextual information related to the user's current state and / or surrounding environment.

[0071] In some implementations, at least one electronic device associated with the user can be used to collect contextual information related to the user in real time, thereby obtaining the second information.

[0072] In some implementations, contextual information related to the user can be collected within a user-specified time period according to user settings, thereby obtaining second information.

[0073] Step S13: If the current context information matches the target triggering context, output the target reminder content.

[0074] Matching current contextual information with the target triggering context means determining, based on information extraction and / or semantic understanding of the current contextual information, whether the current context corresponds to the target triggering context. For example, if the target triggering context is "the user is in an anxious state," and by collecting current contextual information, such as the user's current physiological signals, language signals, and body signals, it is determined that the user is currently in an anxious state, then the current contextual information is considered to match the target triggering context.

[0075] In some implementations, a target model can be used to perform semantic understanding and analysis of the current context information, thereby determining the current context corresponding to the current context information.

[0076] The information reminder method provided in this application first generates a target reminder based on first information, wherein the first information represents historical contextual information related to the user, and the target reminder includes at least target reminder content and a target triggering context; then, second information is obtained, wherein the second information represents current contextual information related to the user; finally, if the current contextual information matches the target triggering context, the target reminder content is output. In this way, on the one hand, compared to related technologies that rely on users actively setting reminder conditions to establish reminders, this solution actively senses contextual information and actively generates and triggers reminders, achieving a quick and seamless reminder generation and triggering mechanism, improving the flexibility and intelligence of reminder setting and triggering; on the other hand, compared to specific and clear triggering conditions such as time and location, the target triggering context has a high degree of abstract compatibility. Therefore, using the target triggering context as the condition for triggering the target reminder content allows users to set reminders even without knowing the specific triggering conditions (e.g., time, location), without having to worry about specific triggering conditions, thereby improving the reminder hit rate, reducing the cognitive burden of setting reminders, and ultimately improving the user experience.

[0077] In some implementations, generating the target reminder based on the first information, i.e., step S11 above, can be implemented as steps S111 to S112:

[0078] Step S111: Determine the user intent and candidate content based on the historical context information;

[0079] Step S112: When the user intent represents the user's expectation to be reminded of the candidate content in the first candidate scenario, the target reminder is generated; wherein the candidate content is used as the target reminder content, and the first candidate scenario is used as the target trigger scenario.

[0080] Here, "selectable content" refers to any content from the historical context that can serve as a reminder. Examples include tasks to be completed, information that can be referenced, and tools that can be used.

[0081] User intent refers to the goals or needs that a user hopes to achieve within the context of that historical information.

[0082] In some implementations, user intent can be determined in multiple ways.

[0083] In some implementations, the user's intent can be directly determined based on the semantic information of the historical context. For example, the user may directly express their desire to set a reminder through text, voice, or gestures.

[0084] In some implementations, the user's intent can be determined by analyzing or inferring the semantic information of the historical context information in conjunction with the user's user profile information. For example, if the historical context information shows that the user has saved a post about a restaurant, combined with user profile information, such as the user being a food enthusiast, it can be inferred that the user wants to be reminded of that post in a future context.

[0085] In some implementations, the content of the user's intent can be any content related to setting reminders.

[0086] In some implementations, the user's intent can be a clearly defined reminder setting. This allows for direct determination of the need to create a target reminder based on the user's intent.

[0087] In some implementations, the user's intent may express interest in or liking of the selected content. Based on this intent, it can be inferred that the user may wish to set a reminder.

[0088] Determining user intent and candidate content based on historical context information refers to extracting information and / or semantically understanding historical context information to determine the candidate content and user intent contained therein.

[0089] The first candidate scenario refers to the scenario determined from historical context information in which the user hopes to be reminded of candidate content in the future (relative to the time when the historical context information was collected).

[0090] In some implementations, the first candidate scenario can be directly determined based on the historical context information, that is, the historical context information specifies the triggering scenario for the candidate content. For example, in the above embodiment, the user specifies via voice that he should be reminded to listen to his favorite classical music in an anxious state; therefore, the "anxious state" is the first candidate scenario directly included in the historical context information.

[0091] In some implementations, the first candidate scenario can be determined directly based on the historical context information by combining user profile information. That is, the historical context information does not directly indicate the first candidate scenario, but the first candidate scenario can be inferred from the user profile information.

[0092] In some implementations, target models can be used to extract information and / or understand semantics from historical contextual information to determine user intent and candidate content.

[0093] In this way, when the user's intent represents the user's expectation to be reminded of the selected content in the first candidate context, a target reminder can be proactively generated, and the candidate content can be used as the target reminder content, with the first candidate context as the target trigger context.

[0094] In the embodiments provided in this application, on the one hand, by actively detecting user intent and candidate content in historical context information, it is determined whether to generate a target reminder, thereby enabling intelligent generation of reminders based on the user's true intent or needs, avoiding the generation of reminders that do not conform to the user's intent and thus causing interference to the user; on the other hand, when the user's intent is only to pay attention or like, actively generating a reminder can help the user avoid missing important matters or things of interest due to forgetting to set a reminder; furthermore, by actively analyzing user intent and candidate content to generate a target reminder, the user's operational and cognitive burden in setting reminders can be reduced.

[0095] In some implementations, generating the target reminder based on the first information, i.e., step S11 above, can be implemented as steps S113 to S115:

[0096] Step S113: Determine the user intent and candidate content based on the historical context information;

[0097] Step S114: If the user intent indicates that the user expects to be reminded of the candidate content, and the first candidate scenario cannot be determined by the user intent, then the user is interacted with based on the candidate content to obtain a second candidate scenario.

[0098] Step S115: Generate the target reminder; wherein the candidate content is used as the target reminder content, and the second candidate scenario is used as the target trigger scenario.

[0099] Here, the specific implementation method of determining the user's intent and the candidate content based on historical context information in step S113 is the same as the specific implementation method of step S111 above, and will not be repeated here.

[0100] User intent represents a user's expectation to be reminded of alternative content, but the first alternative scenario cannot be determined through this user intent. It also represents a scenario in which the user's desired alternative content cannot be inferred from the historical context information.

[0101] However, since it can be determined from the user's intent that the user expects to be reminded of the candidate content, the interaction with the user is based on the candidate content in order to determine the second candidate scenario corresponding to the candidate content from the user's feedback information.

[0102] In some implementations, when interacting with a user, firstly, a prompt message is generated based on the candidate content and a preset prompt word template; then, the generated prompt message is input into a language model to generate a query message; subsequently, the query message is sent to the user; finally, a second candidate scenario is determined based on the user's feedback on the query message.

[0103] In some implementations, interaction with the user can be conducted in any suitable manner. For example, interaction can be conducted via text, voice, or animation.

[0104] In some implementations, the second candidate scenario can be determined through multiple rounds of interaction with the user.

[0105] In this way, after determining the second candidate scenario, a target reminder is generated, and the candidate content is used as the target reminder content, while the second candidate scenario is used as the target trigger scenario.

[0106] In the embodiments provided in this disclosure, when the first candidate scenario corresponding to the candidate content cannot be determined based on historical context information, the second candidate scenario corresponding to the candidate content can be determined by actively interacting with the user, which can improve the accuracy of the determined trigger scenario.

[0107] In some implementations, determining the user intent and candidate content based on the historical context information, i.e., instead of step S111 or S113, can be implemented as at least one of the following steps S1111 to S1113:

[0108] Step S1111: Based on the user behavior information in the historical context information, generate the user intent and the candidate content using the target model.

[0109] Here, by using the target model to analyze and understand user behavior information in historical context information, the user's intent and the candidate content can be determined.

[0110] In some implementations, user behavior information can be a user's interactions with others in the real world, such as a user's conversations with others in the real world.

[0111] In this context, semantic analysis of the voice or video content during user interactions with others can be performed using a target model to determine user intent and potential content. For example, by detecting the content of a user's conversation with another person, it can be determined that the user wants to visit a friend in their free time. Here, "visiting a friend" can be considered as potential content, "free time" as the triggering context, and "wanting to visit a friend in their free time" as the user intent.

[0112] In some implementations, user behavior information can be the behavior of a user interacting with others in the virtual world or through instant messaging applications on electronic devices, such as the behavior of a user interacting with others in a game world, or interacting with them through applications such as calling applications or WeChat.

[0113] In this context, semantic analysis of text, voice, images, videos, or multimodal content during user interactions with others can be performed using a target model to determine user intent and potential content. For example, by detecting user interactions and determining that the other party recommended a delicious restaurant to the user, and the user expressed their liking for it, the restaurant mentioned in the interaction can be considered as potential content, and the user's desire to try it can be considered as user intent.

[0114] Step S1112: Based on the user behavior information and the object of the behavior in the historical context information, generate the user intent and the candidate content using the target model.

[0115] Here, by using the target model to analyze and understand user behavior information in historical context information, the user's intent can be determined. At the same time, by combining the target of the user's behavior, the candidate content can be determined.

[0116] In some implementations, the user behavior information can be the user's interaction with applications running on the electronic device. For example, the user's actions such as liking, saving, or browsing posts displayed in the application for extended periods or multiple times.

[0117] In this scenario, analyzing the user behavior information using a target model can generate the user's intent regarding the objects of their actions (such as following or liking posts), with the candidate content representing those objects. For example, based on the user behavior in the example above, "posts" could be considered candidate content, and "following viewed posts" could be considered the user intent.

[0118] In some implementations, user behavior information can be the user's actions on the electronic device. For example, the user's actions of taking pictures of road signs or recording audio using the electronic device.

[0119] In this scenario, analyzing the user's behavior information using a target model can generate the user's intent regarding the object of their attention or liking behavior, with the candidate content representing the object of that behavior. For example, based on the user behavior in the example above, "the location corresponding to the road sign" can be considered as candidate content, and "follow the location corresponding to the road sign" as the user's intent.

[0120] Step S1113: Based on the historical context information and the user profile information, generate the user intent and the candidate content using the target model.

[0121] Here, the target model cannot determine the user's intent and the candidate content through isolated analysis of historical context information. Therefore, the user's profile information is used as a reference to determine the user's intent and the candidate content.

[0122] For example, if the historical context information indicates that a user's electronic device received an advertising email, the target model cannot determine the user's intent based solely on the context of receiving the email. Therefore, the target model uses user profile information as contextual information to further determine the user's intent. For instance, if the advertising email is related to a sports event, and the user profile information indicates that the user is a sports enthusiast, the target model can infer that the user's intent is "to be reminded of this advertising email," and that the advertising email is the candidate content. As another example, if the advertising email is an investment information ad, and the user profile information indicates that the user is not interested in investing, the target model can infer that the user's intent is "to ignore this advertising email."

[0123] For example, if the historical context information indicates that a user's electronic device received an email, the user's intent can be determined using a target model based on the sender and user profile information. For instance, if the sender of the email is a colleague of the user, the target model can determine that the user's intent is "to be reminded that they received this email."

[0124] In some implementations, user profile information may include a user's long-term habits, preferences, social identity, etc.

[0125] In the embodiments provided in this disclosure, user intent and candidate content are determined based on user behavior information, or by combining user behavior information with the object of the behavior, or by combining user behavior information with user profile information. This can make the determination result of user intent interpretable and improve the matching degree between the generated user intent and the user's true intent, thereby improving the generation effect of target reminders.

[0126] In some implementations, after generating the target reminder based on the first information, that is, after step S11 above, the following step S14 is also included:

[0127] Step S14: Update the context listening list based on the context type of the target triggering context;

[0128] The scenario monitoring list includes various scenarios to be monitored; each scenario type corresponds to at least one alert.

[0129] Here, the type of context to be monitored refers to the type of context information to be monitored, such as geographical location, time, person, or user's emotional state.

[0130] A context listener list is a list of context types to be listened to that are associated with at least one notification for the current user. The context listener list includes various context types, and each context type corresponds to at least one notification.

[0131] For example, when the monitored context type is the user's emotional state type, this emotional state type could correspond to reminders such as "reminding the user to listen to soothing music in an anxious situation" or "reminding the user to call a friend in a happy situation." Similarly, when the monitored context type is time-related, this time type could correspond to reminders such as "reminding me to pack up old clothes to donate on the weekend" or "reminding me to bring coffee to work."

[0132] This context monitoring list can be used to dynamically manage user reminders. That is, based on this context monitoring list, context information corresponding to the context types to be monitored can be continuously monitored, and the corresponding reminder can be triggered when a matching context is detected.

[0133] In this way, after generating the target reminder, the context type of the target triggering context is updated to the context listening list, which can automatically detect whether context information matching the target triggering context appears during subsequent operation.

[0134] In the embodiments provided in this disclosure, by dynamically maintaining the scenario monitoring list, it is possible to centrally manage and automatically monitor the triggering scenarios of multiple reminders, thereby proactively triggering the corresponding reminders and improving the flexibility and intelligence of the reminder triggering method.

[0135] In some implementations, obtaining the second information, i.e., step S12 above, can be implemented as the following steps S121 to S122:

[0136] Step S121: Determine the target context type from the multiple context types to be monitored based on the current context of the user.

[0137] When monitoring user context information, the context monitoring list may contain a large number of context types to be monitored. If all the information corresponding to these context types is monitored simultaneously, it may lead to excessive device load. At the same time, some types of context information will not appear or are not important in different contexts (for example, task-type context information does not need to be monitored in a sleep context, and location-type context information does not need to be monitored in a work context), and therefore do not need to be monitored.

[0138] Therefore, the context type that matches the user's current context among the various context types in the context monitoring list is taken as the target context type, and context information related to the target context type is monitored.

[0139] Here, the target context type refers to the context type with the highest probability of triggering the current situation. For example, when the user is currently chatting on WeChat, the content of the WeChat chat is monitored. Another example is when the user is walking, contextual information such as location, time, and physical state is monitored.

[0140] Step S122: Based on the target context type, obtain the second information using at least one application; each application represents an application running in an electronic device associated with the user.

[0141] Here, after determining the target context type, at least one application running on the user's associated electronic device is used to obtain the second information.

[0142] In some implementations, the at least one application may acquire second information that matches the target context type in a variety of ways.

[0143] In some implementations, the at least one application can obtain the second information by reading the user's application interaction information. For example, in a WeChat chat context, the WeChat application reads interaction information such as text, images, voice, video, and / or multimodal inputs and received during the user's interaction. As another example, in an e-shopping context, the shopping application reads various operational information from the user's shopping process, such as product filtering information, hardware operation information such as mouse or keyboard inputs, and browsing duration information.

[0144] In some implementations, the at least one application can obtain information sent to the current device by other electronic devices and use that information as secondary information. For example, an email application obtains email information, and a system application obtains notification messages.

[0145] In some implementations, when the at least one application is a driver program for a sensor installed in an electronic device, the at least one application can acquire sensor information collected by the corresponding sensor. For example, a camera application can acquire image information collected by an image sensor.

[0146] In the embodiments provided in this application, determining the target context type based on the user's current context and performing monitoring of the target context type can reduce the monitoring burden on electronic devices and improve the intelligence level of context monitoring. At the same time, focusing the context monitoring task on the target context type can also improve the accuracy of context information monitoring.

[0147] In some implementations, the second information includes at least one of the following: the user's current geographical location, current time, the user's current physiological or emotional state, and the task the user is currently performing.

[0148] Here, while listening to the contextual information in the user's current situation, the system listens for the second information that matches the target triggering context in the target reminder.

[0149] Geographic location can refer to any type of location-related information, such as the world coordinates of a user's current location, the user's current distance or position relative to a specified location, etc. In some implementations, a variety of methods can be used to determine the user's current geographic location information. For example, the user's current location can be determined using Global Positioning System (GPS), Wireless Fidelity (WiFi) signals, Near Field Communication (NFC) signals, etc.

[0150] Current time information refers to vague time information rather than precise time, such as weekend, end of month, year-end, summer vacation, etc. In some implementations, current time information can be obtained through time and calendar applications in electronic devices.

[0151] A user's current physiological or emotional state information is information related to the user's own condition. For example, the user may be currently in a state of anxiety, excitement, or depression. In some implementations, physiological signals of the user can be collected through sensors such as blood pressure sensors, respiration sensors, heart rate sensors, and body temperature sensors in smart wearable devices. In some implementations, facial images, motion information, and voice information of the user can be collected through cameras, microphones, etc., to infer the user's physiological or emotional state. In some implementations, the user's physiological or emotional state information can be determined by combining multiple physiological signals and analyzing the user's facial expressions, speech rate, heart rate, etc.

[0152] The user's currently executing task information refers to the task the user is currently processing. In some implementations, this information can be determined by acquiring information from the application, webpage, or device the user is currently using. For example, if the WeChat application is currently active, it can be determined that the user is currently chatting. Similarly, if the user's computer is booting up, it can be determined that the user is currently powering on. In some implementations, real-time task identification can be achieved by collecting the user's real-time status information through a camera or microphone.

[0153] In some implementations, the second information can also be information about people in the user's current situation. For example, if the target reminder is "When you meet Xiao Wang, ask him something," the second information is information about the person. In some implementations, the target person can be identified by recognizing images captured by a camera, or the device user's identity can be identified by device information.

[0154] In some implementations, the method further includes the following steps S15 to S16:

[0155] Step S15: Obtain third information using at least one application; the third information represents current context information related to the user, and the context type corresponding to the third information is different from the target context type; the third information includes at least one of the following: the user's current activity information, cognitive state information, and emotional state information.

[0156] The third piece of information refers to current contextual information relevant to the user, which is used to help determine the timing of outputting the target reminder content.

[0157] In some implementations, the third information can be information of any contextual type. In some implementations, the third information may include the user's current activity information, such as walking, driving, working, or resting. In some implementations, the third information may include the user's current cognitive state information, such as focused or silent state. In some implementations, the third information may also include the user's current emotional state information, such as anxiety, tension, or excitement.

[0158] Here, since the third information is information that helps determine the output time of the target reminder content, rather than triggering context information, the context type corresponding to the third information is different from the target context type. For example, if the target context type is location type, then the third information could be information about the user's current cognitive state type or emotional state type, etc.

[0159] In some implementations, the method of obtaining the third information is the same as the method of obtaining the first and / or second information, which will not be described again here.

[0160] Step S16: Determine the target reminder time based on the third information.

[0161] Here, the target reminder time refers to the appropriate time to output the target reminder content after understanding and analyzing the third-party information. It is clear that the target reminder time is not a fixed point in time, but rather dynamically determined based on contextual information such as the user's current activity, cognitive state, and / or emotional state. For example, if the user is focused on working, the target reminder time can be postponed until the user finishes their current task; conversely, if the user's current emotional state is relatively stable, the target reminder content can be output immediately to increase the user's acceptance of the target content.

[0162] In some implementations, a designated model can be used to perform comprehensive semantic understanding and / or information extraction on the third information to determine the target reminder time. Here, the designated model can be of various types, such as a large language model, a speech model, a video model, or a multimodal model.

[0163] In some implementations, the designated model includes at least a large language model with world knowledge. World knowledge refers to the set of factual information, logical relationships, common-sense rules, and cross-domain knowledge about the real world acquired through training by the large language model. Thus, when determining the target reminder time, the designated model can comprehensively analyze third-party information based on the learned world knowledge to determine the target reminder time. For example, if the designated model determines, based on the third-party information, that the user is currently at a busy intersection, and combined with world knowledge, the designated model can infer that outputting the target reminder content at this time might distract the user and potentially lead to a traffic accident. Based on this, the designated model will generate a reasoning result that postpones the target reminder time.

[0164] Thus, the output of the target reminder content, i.e., the above step S13, can be implemented as the following step S131:

[0165] Step S131: Output the target reminder content at the target reminder time.

[0166] Here, after determining the target reminder time, the target reminder content is output at that time.

[0167] In the embodiments provided in this disclosure, by collecting third-party information about the user's current situation, the user's current state and environment can be understood more comprehensively, the appropriate time to output the target reminder content can be determined, and reminders can be output at inappropriate times to avoid disturbing the user, thereby improving the intelligence of the information reminder method and increasing the user's acceptance of the information.

[0168] In some implementations, the output of the target reminder content, i.e., step S13 above, is further implemented as steps S132 to S133:

[0169] Step S132: Based on the third information, determine the target output device and the target output mode corresponding to the target reminder content from at least one electronic device currently used by the user.

[0170] Here, the third piece of information is used to help determine the output device and output mode of the target reminder content.

[0171] A target output device refers to at least one electronic device currently in use by the user that is suitable for outputting the target reminder content. Common output devices currently include smartphones, smartwatches, car stereos, headphones, smart glasses, and computer monitors. In some implementations, the target reminder device can be determined based on the user's attention state, current activity, and / or whether the device is active or in a state conducive to receiving the target reminder content. For example, when the user is wearing wireless headphones, audio reminders are preferred; if the user is using a mobile phone but not wearing headphones, a pop-up window on the screen may be used.

[0172] The target output modality refers to the information mode that is easy for the user to receive in the current context; that is, the information interaction method that is easy for the user to accept. For example, in a noisy environment, vibration or screen pop-ups are preferred over voice when outputting the target reminder content. Similarly, in a driving scenario, voice prompts, which are considered safer and more effective, are preferred. In some implementations, the target output modality can be dynamically adjusted based on the urgency of the target reminder content and user preferences. For example, a combination of multiple modalities (e.g., sound plus vibration) can be used to output higher-priority reminders.

[0173] In this way, a designated model can be used to comprehensively analyze and understand the third information to determine, in the context corresponding to the third information, which modality and on which device the target reminder content should be output to be more suitable for the user to receive, without affecting the user's current task or state. In some implementations, the designated large model can be based on learned world knowledge to comprehensively understand and analyze the third information to determine the target output device and target output modality.

[0174] Step S133: Using the target output device, output the target reminder content in the target output mode.

[0175] After determining the target output device and the target output mode, the target reminder content is output in the target output mode using the target output device.

[0176] In some implementations, after determining the target output modality, the target reminder content can be regenerated based on the target output modality to obtain the output information of the target output modality. For example, if the target modality is speech, the target reminder content is converted into speech information. As another example, if the target modality is a notification message, the target reminder content is converted into text information.

[0177] In some implementations, after determining the target output device, the target reminder content can be regenerated according to the communication format and / or receivable data format of the target output device to meet the information processing capabilities of the target output device.

[0178] In some implementations, after determining the target output device and target output mode, the information content of the target reminder is adjusted according to the target output device and target output mode. For example, when the target output device is a smartwatch, since the display area of ​​a smartwatch is small, in order to facilitate users to quickly obtain the target reminder content, the target reminder content can be regenerated using a language model, or a summary of the target reminder content can be generated, thereby reducing the information content of the target reminder. As another example, when the target output mode is speech, since long speech information is not easy to remember, the information content of the target reminder can also be reduced.

[0179] In some implementations, third-party information can be used to determine the content that the user is interested in in the current context, and content extraction can be performed on the target reminder content accordingly. The extracted content can then be used as the output content for the user. For example, if a user has saved a long article about a European town and set a reminder, and the user is traveling in that town, if it is detected that it is lunchtime, the section about the town's food from the saved article can be used as the reminder content for the user.

[0180] In the embodiments provided in this disclosure, the target output device and target output mode are dynamically selected based on third information, thereby realizing a more intelligent and context-aware reminder mechanism.

[0181] Below, in conjunction with Figure 2 The process of generating a first reminder in one embodiment provided in this disclosure will be described. For example... Figure 2 As shown, this embodiment includes the following steps S201 to S205:

[0182] Step S201: Obtain the fourth information; then, proceed to step S202.

[0183] Here, the fourth piece of information could be a post that a user liked, an email they received, a photo they took, a message they received, etc.

[0184] Step S202: Use a multimodal large model to perform semantic understanding on the fourth information to generate candidate reminder information; then, execute step S203.

[0185] Here, the multimodal big model detects the user intent and candidate content in the fourth information; when it is determined that the user wants to be reminded of the candidate content in the candidate context, candidate reminder information is generated, wherein the candidate content is used as candidate reminder content and the candidate context is used as candidate trigger context.

[0186] Step S203: Based on the candidate reminder information, generate reminder suggestions and output them to the user; in response to the user's confirmation information, use the candidate reminder information as the first reminder information; then, execute step S204;

[0187] Step S204: Store the first reminder in the global reminder database; then, proceed to step S205.

[0188] Here, the global alert database can be implemented as a graph database.

[0189] Step S205: Update the context information list according to the context type of the triggering context in the first reminder.

[0190] Below, in conjunction with Figure 3 The process of triggering the second reminder in one embodiment provided in this disclosure will be described. For example... Figure 3 As shown, this embodiment includes the following steps S301 to S306:

[0191] Step S301: Determine the target context type from the context listening list based on the user's current context; then, proceed to step S302.

[0192] Step S302: Obtain the fifth context information corresponding to the target context type and the sixth context information related to the reminder time judgment; then, execute step S303.

[0193] Step S303: Using the specified model, perform semantic understanding on the fifth and sixth contextual information; then, proceed to step S304.

[0194] Using a specified model, semantic understanding of the fifth and sixth contextual information is performed based on the world knowledge learned from the model, so as to obtain the semantic understanding results corresponding to the fifth and sixth contextual information.

[0195] Step S304: When the fifth context information matches the triggering context of the second reminder, and the sixth context information indicates that it is currently appropriate to output a reminder, obtain the seventh context information related to the reminder strategy; then, execute step S305.

[0196] Here, the seventh contextual information may include the user's current task, emotional state, cognitive state, surrounding environment, or the status of the device being used.

[0197] Step S305: Using the specified model, perform semantic understanding on the seventh context information to determine the target output device and target output modality; then, execute step S306.

[0198] Here, the world knowledge learned from the model is used to perform semantic understanding of the seventh context information, so as to determine the most suitable target output device and target output modality for presenting the reminder based on information such as the user's current task, emotional state, cognitive state, surrounding environment or the status of the device being used.

[0199] Step S306: Using the target output device, output the reminder content of the second reminder in the target output mode.

[0200] As can be seen from the above embodiments, the information reminder method provided by this disclosure, on the one hand, extracts and semantically understands perceived contextual information based on world knowledge learned by a large model, thereby automatically generating and triggering reminders, achieving quick and seamless reminder generation and triggering; on the other hand, it drives reminder generation based on context, replacing the reminder setting driven by explicit triggering conditions in related technologies, which can improve the reminder hit rate and reduce the cognitive and operational burden on users setting reminders; furthermore, based on world knowledge and user profile information, it performs comprehensive semantic understanding of the current contextual information to determine whether the user expects to set a reminder, thus supporting fuzzy reminder generation functions, such as "Remind me when I need it" or "Do it casually," etc.; finally, it automatically determines whether there is a triggering context for the reminder and the appropriate device and information modality for outputting the reminder content through contextual awareness, thereby making the reminder output mechanism more flexible and accurate, thus avoiding disturbing the user and improving user acceptance.

[0201] Based on the foregoing embodiments, this disclosure provides an information reminder system. For example... Figure 4 As shown, the information reminder system 400 includes: a reminder generation device 410, an information acquisition device 420, and a reminder output device 430; wherein,

[0202] The reminder generation device 410 generates a target reminder based on the first information; the first information represents historical context information related to the user; the target reminder includes at least the target reminder content and the target triggering context.

[0203] The information acquisition device 420 acquires second information; the second information represents current context information related to the user.

[0204] The reminder output device 430 outputs the target reminder content when the current context information matches the target triggering context.

[0205] In some embodiments, the reminder generating device 410 is used for:

[0206] Based on the historical context information, determine the user's intent and the content to be selected;

[0207] When the user intent represents the user's expectation to be reminded of the candidate content in the first candidate context, the target reminder is generated; wherein the candidate content is used as the target reminder content, and the first candidate context is used as the target trigger context.

[0208] In some embodiments, the reminder generating device 410 is used for:

[0209] Based on the historical context information, determine the user's intent and the content to be selected;

[0210] If the user intent indicates that the user expects to be reminded of the candidate content, and the first candidate scenario cannot be determined through the user intent, the user is interacted with based on the candidate content to obtain a second candidate scenario;

[0211] Generate the target reminder; wherein the candidate content is used as the target reminder content, and the second candidate scenario is used as the target trigger scenario.

[0212] In some embodiments, the reminder generating device 410 is configured to perform at least one of the following:

[0213] Based on the user behavior information in the historical context information, the target model is used to generate the user intent and the candidate content;

[0214] Based on the user behavior information and the object of the behavior in the historical context information, the user intent and the candidate content are generated using the target model;

[0215] Based on the historical context information and the user profile information, the target model is used to generate the user intent and the candidate content.

[0216] In some embodiments, the reminder generating device 410 is further configured to:

[0217] Update the context listening list based on the context type of the target triggering context;

[0218] The scenario monitoring list includes various scenarios to be monitored; each scenario type corresponds to at least one alert.

[0219] In some embodiments, the information acquisition device 420 is used for:

[0220] Based on the user's current situation, determine the target situation type from the multiple types of situations to be monitored;

[0221] Based on the target context type, the second information is obtained using at least one application; each application represents an application running on an electronic device associated with the user.

[0222] In some implementations, the second information includes at least one of the following: the user's current geographical location, current time, the user's current physiological or emotional state, and the task the user is currently performing.

[0223] In some embodiments, the information alerting system 400 further includes an output decision device;

[0224] The output decision device is used for:

[0225] The third information is obtained using at least one application; the third information represents current contextual information related to the user, and the context type corresponding to the third information is different from the target context type; the third information includes at least one of the following: the user's current activity information, cognitive state information, and emotional state information;

[0226] Based on the aforementioned third information, the target reminder time is determined;

[0227] The step of outputting the target reminder content includes: outputting the target reminder content at the target reminder time.

[0228] In some embodiments, the output decision device is used for:

[0229] Based on the third information, determine the target output device and the target output mode corresponding to the target reminder content from at least one electronic device currently used by the user;

[0230] The target reminder content is output in the target output mode using the target output device.

[0231] The descriptions of the system embodiments above are similar to those of the method embodiments above, and have similar beneficial effects. In some embodiments, the functions or modules included in the system provided by this disclosure can be used to execute the methods described in the method embodiments above. For technical details not disclosed in the system embodiments of this disclosure, please refer to the descriptions of the method embodiments of this disclosure for understanding.

[0232] If the technical solution disclosed herein involves personal information, the product using this technical solution has clearly informed the user of the personal information processing rules and obtained the user's voluntary consent before processing the personal information. If the technical solution disclosed herein involves sensitive personal information, the product using this technical solution has obtained the user's separate consent before processing the sensitive personal information, and also meets the requirement of "express consent". For example, at personal information collection devices such as cameras, clear and prominent signs are set up to inform users that they have entered the scope of personal information collection and that personal information will be collected. If an individual voluntarily enters the collection scope, it is deemed that they have agreed to the collection of their personal information; or on the personal information processing device, with clear signs / information informing users of the personal information processing rules, authorization is obtained from the individual through pop-up information or by asking the individual to upload their personal information; wherein, the personal information processing rules may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the types of personal information processed.

[0233] It should be noted that, in the embodiments of this disclosure, if the above-described information reminder method is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiments of this disclosure, or the part that contributes to related technologies, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this disclosure. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), magnetic disks, or optical disks. Thus, the embodiments of this disclosure are not limited to any specific hardware, software, or firmware, or any combination of hardware, software, and firmware.

[0234] This disclosure provides a computer device including a memory and a processor. The memory stores a computer program that can run on the processor. When the processor executes the program, it implements some or all of the steps in the above-described method.

[0235] This disclosure provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements some or all of the steps in the above-described method. The computer-readable storage medium may be transient or non-transient.

[0236] This disclosure provides a computer program including computer-readable code, wherein when the computer-readable code is executed in a computer device, a processor in the computer device performs some or all of the steps in the above-described method.

[0237] This disclosure provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program. When the computer program is read and executed by a computer, it implements some or all of the steps in the above-described method. This computer program product can be implemented specifically through hardware, software, or a combination thereof. In some embodiments, the computer program product is specifically embodied as a computer storage medium; in other embodiments, the computer program product is specifically embodied as a software product, such as a software development kit (SDK), etc.

[0238] It should be noted that the descriptions of the various embodiments above tend to emphasize the differences between them, while their similarities or commonalities can be referenced interchangeably. The descriptions of the above embodiments of the device, storage medium, computer program, and computer program product are similar to the descriptions of the above method embodiments and have similar beneficial effects. For technical details not disclosed in the embodiments of the device, storage medium, computer program, and computer program product of this disclosure, please refer to the descriptions of the method embodiments of this disclosure for understanding.

[0239] It should be noted that, Figure 5 This is a schematic diagram of a hardware entity of the electronic device in this disclosure, such as... Figure 5 As shown, the hardware entity of the electronic device 500 includes: a processor 501, a communication interface 502, and a memory 503, wherein:

[0240] Processor 501 typically controls the overall operation of electronic device 500.

[0241] Communication interface 502 enables electronic devices to communicate with other terminals or servers via a network.

[0242] The memory 503 is configured to store instructions and applications executable by the processor 501, and can also cache data to be processed or already processed (e.g., image data, audio data, voice communication data, and video communication data) in the processor 501 and various modules in the electronic device 500. It can be implemented using flash memory or random access memory (RAM). Data transfer between the processor 501, the communication interface 502, and the memory 503 can be performed via bus 504.

[0243] It should be understood that the phrase "an embodiment" or "one embodiment" throughout the specification means that a specific feature, structure, or characteristic related to the embodiment is included in at least one embodiment of this disclosure. Therefore, "in one embodiment" or "one embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. It should be understood that in the various embodiments of this disclosure, the sequence numbers of the above steps / processes do not imply a sequential order of execution; the execution order of each step / process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this disclosure. The sequence numbers of the above embodiments of this disclosure are merely descriptive and do not represent the superiority or inferiority of the embodiments.

[0244] It should be noted that, in this document, 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. Unless otherwise specified, 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 that element.

[0245] In the several embodiments provided in this disclosure, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components may be combined, or integrated into another system, or some features may be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0246] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0247] In addition, each functional unit in the various embodiments of this disclosure can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0248] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as mobile storage devices, read-only memory (ROM), magnetic disks, or optical disks.

[0249] Alternatively, if the integrated units described above are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this disclosure, or the part that contributes to related technologies, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this disclosure. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, magnetic disks, or optical disks.

[0250] The above description is merely an embodiment of this disclosure, but the scope of protection of this disclosure is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this disclosure should be included within the scope of protection of this disclosure.

Claims

1. An information reminder method, comprising: Based on the initial information, generate a target reminder; The first information represents historical contextual information related to the user; The target reminder includes at least the target reminder content and the target triggering context; Obtain the second information; The second information represents current contextual information related to the user; If the current context information matches the target triggering context, the target reminder content is output.

2. The method according to claim 1, wherein generating the target reminder based on the first information includes: Based on the historical context information, determine the user's intent and the content to be selected; When the user intent represents the user's expectation to be reminded of the candidate content in the first candidate context, the target reminder is generated; wherein the candidate content is used as the target reminder content, and the first candidate context is used as the target trigger context.

3. The method according to claim 1, wherein generating the target reminder based on the first information includes: Based on the historical context information, determine the user's intent and the content to be selected; If the user intent indicates that the user expects to be reminded of the candidate content, and the first candidate scenario cannot be determined through the user intent, the user is interacted with based on the candidate content to obtain a second candidate scenario; Generate the target reminder; wherein the candidate content is used as the target reminder content, and the second candidate scenario is used as the target trigger scenario.

4. The method according to claim 2 or 3, wherein determining the user intent and candidate content based on the historical context information includes at least one of the following: Based on the user behavior information in the historical context information, the target model is used to generate the user intent and the candidate content; Based on the user behavior information and the object of the behavior in the historical context information, the user intent and the candidate content are generated using the target model; Based on the historical context information and the user profile information, the target model is used to generate the user intent and the candidate content.

5. The method according to claim 1, further comprising, after generating the target reminder based on the first information: Update the context listening list based on the context type of the target triggering context; The scenario monitoring list includes various scenarios to be monitored; each scenario type corresponds to at least one alert.

6. The method according to claim 5, wherein obtaining the second information includes: Based on the user's current situation, determine the target situation type from the multiple types of situations to be monitored; Based on the target context type, the second information is obtained using at least one application; Each of the aforementioned applications represents an application running in an electronic device associated with the user.

7. The method according to claim 5 or 6, wherein the second information includes at least one of the following: the user's current geographical location information, current time information, the user's current physiological or emotional state information, and the user's current task information.

8. The method according to claim 6, further comprising: Use at least one application to obtain third-party information; The third information represents current contextual information related to the user, and the context type corresponding to the third information is different from the target context type; the third information includes at least one of the following: the user's current activity information, cognitive state information, and emotional state information; Based on the aforementioned third information, the target reminder time is determined; The step of outputting the target reminder content includes: outputting the target reminder content at the target reminder time.

9. The method according to claim 8, wherein outputting the target reminder content further includes: Based on the third information, determine the target output device and the target output mode corresponding to the target reminder content from at least one electronic device currently used by the user; The target reminder content is output in the target output mode using the target output device.

10. An information reminder system, comprising a reminder generation device, an information acquisition device, and a reminder output device; wherein, The reminder generating device generates a target reminder based on the first information; The first information represents historical contextual information related to the user; the target reminder includes at least the target reminder content and the target triggering context; The information acquisition device acquires the second information; The second information represents current contextual information related to the user; The reminder output device outputs the target reminder content when the current context information matches the target triggering context.

Images