Message pushing method, device and equipment and readable storage medium

Abstract

The invention relates to a message pushing method, device and equipment and a readable storage medium, and the method comprises the steps: judging whether the current time is suitable for message pushing or not when a user event is recognized to meet a learned triggering condition of a user habit; according to the embodiment of the invention, the push message of the user habit is not sent under the condition that the current time does not belong to the message push opportunity, the target user event used for representing the delayed push time period is subscribed, and the push message is generated and sent to the display interface to be displayed after the target user event is received, so that the user is prevented from being disturbed at an improper opportunity, and the user experience is improved. The push message can be sent in the time period in which the user is more likely to pay attention, and the acceptability of the user to the automatic execution function of the user habits and the user experience are improved.

Description

Technical Field

[0001] This disclosure relates to the field of communication technology, and in particular to a message push method, apparatus, device, and readable storage medium. Background Technology

[0002] Currently, some smart home systems can provide more personalized services by learning users' daily behavioral patterns, or user habits. For example, if a user is accustomed to turning on the humidifier first thing after getting home from get off work, the system can learn this habit to also turn on the humidifier when getting home.

[0003] The learned user habits are typically stored as automated data, which includes trigger conditions and device operations. The trigger conditions indicate when the device operation will be executed. Currently, after learning a user habit, when a received user event meets the trigger condition for that habit, the system sends a push message to the user asking if they want the system to remember and enable the automated execution function for that habit. This automated execution function allows the system to automatically execute the corresponding device operation without user intervention when the trigger condition for the habit is met.

[0004] However, practical results show that the above-mentioned message push method suffers from low user acceptance and decreased user participation in the smart home system. Therefore, a new method is needed to optimize the push message sending mechanism to better suit user habits. Summary of the Invention

[0005] In view of this, in order to solve the above-mentioned technical problems, this disclosure provides a message push method, apparatus, device and storage medium.

[0006] According to a first aspect of the present disclosure, a message push method is provided, the method comprising:

[0007] In response to a received first user event that satisfies a triggering condition of user habits, the system identifies whether the timing of the fulfillment of the triggering condition falls within a message push timing context; the triggering condition is used to trigger device operations within the user habits.

[0008] In response to the fact that the timing of the triggering condition being met does not fall within the message push timing, the subscription indicates a target user event for which the push timing is delayed;

[0009] In response to receiving the target user event, a push message based on the user's habits is generated and sent to the display interface for display; the push message is used to ask the user whether to enable the automated execution function of the user's habits.

[0010] Optionally, identifying whether the timing of the fulfillment of the triggering condition belongs to the message push timing includes:

[0011] Obtain a pre-defined dataset for storing non-push events;

[0012] If the timing of the triggering condition being met exists within the dataset, it is determined that the timing of the triggering condition being met does not belong to the message push timing.

[0013] Optionally, the method further includes:

[0014] Based on a preset delayed push correspondence, a preset user event that matches the timing when the triggering condition is met is determined as the target user event;

[0015] The delayed push correspondence includes at least one predefined non-push time and a preset user event corresponding to each non-push time that indicates a delayed push time.

[0016] Optionally, the method further includes:

[0017] Obtain the user behavior represented by the first user event;

[0018] A pre-trained neural network predicts an ending event that characterizes the end of the user behavior, which is then used as the target user event; wherein the output layer of the neural network classifies different types of user events that support subscription.

[0019] Optionally, the method further includes:

[0020] The push message identifier of the user habit is obtained from the first data storage; the first data storage also includes the triggering conditions of the user habit, device operation, and the user identifier of the user to whom the user habit belongs;

[0021] After subscribing to the target user event, a push record is constructed and stored in the second data storage based on the target user event and the push message identifier; the push record is deleted after the push message according to the user's habits is generated and sent to the display interface.

[0022] Optionally, the step of generating a push message based on the user's habits and sending it to the display interface for display in response to receiving the target user event includes:

[0023] Based on the target user event, the record to be pushed is retrieved from the second data storage;

[0024] Based on the push message identifier in the record to be recommended, the triggering conditions of matching user habits, device operations and user identifiers are determined from the first data storage;

[0025] The push message is generated based on the triggering conditions and device operation;

[0026] The push message is sent to the display interface on the device associated with the user identifier.

[0027] Optionally, the record to be pushed further includes the occurrence time of the first user event satisfying the triggering condition of the user habit; the step of generating a push message for the user habit in response to receiving the target user event includes:

[0028] Obtain the reception time of the target user event, and determine the time interval between the reception time and the occurrence time;

[0029] If the time interval does not exceed a preset duration threshold, a push message based on the user's habits is generated.

[0030] Optionally, the method further includes:

[0031] In response to receiving the target user event, unsubscribe from the target user event.

[0032] Optionally, the method is applied to a target device, which has a device event subscription service built into it; the device event subscription service is used to receive various user events reported by different devices managed by the target device, and to publish the various user events according to the subscription relationship;

[0033] The subscription refers to target user events where the push timing is delayed, including:

[0034] The device event subscription service is requested to subscribe to the target user event; the subscription also includes instructing the device event subscription service to publish the target user event to a set data queue.

[0035] Optionally, the method further includes:

[0036] If an update to the specified data queue is detected, read the pending events from the data queue;

[0037] If the event to be processed is determined to be the target user event, the push message is generated.

[0038] Optionally, the target device further includes at least a first push service and a second push service; the method also includes:

[0039] Through the first push service, when the timing of the triggering condition being met falls within the message push timing period, a push message tailored to the user's habits is generated and sent to the display interface.

[0040] The subscription refers to the target user event for which the push timing is delayed, including: requesting to subscribe to the target user event from the device event subscription service through the first push service;

[0041] The second push service retrieves the target user event from the designated data queue and generates the push message in response to the target user event, which is then sent to the display interface.

[0042] According to a second aspect of the present disclosure, a message push device is provided, the device comprising:

[0043] The push timing identification module is used to identify whether the timing when the first user event received meets the triggering condition of the user's habit is a message push timing; the triggering condition is used to trigger the device operation in the user's habit.

[0044] The user event subscription module is used to subscribe to the target user event indicating a delayed push timing when the timing of the triggering condition being met does not belong to the message push timing.

[0045] The message push module is used to respond to the received target user event, generate a push message based on the user's habits, and send it to the display interface for display; the push message is used to ask the user whether to enable the automated execution function of the user's habits.

[0046] In some embodiments, the push timing identification module is specifically used for:

[0047] Obtain a pre-defined dataset for storing non-push events;

[0048] If the timing of the triggering condition being met exists within the dataset, it is determined that the timing of the triggering condition being met does not belong to the message push timing.

[0049] In some embodiments, the apparatus further includes:

[0050] Based on a preset delayed push correspondence, a preset user event that matches the timing when the triggering condition is met is determined as the target user event;

[0051] The delayed push correspondence includes at least one predefined non-push time and a preset user event corresponding to each non-push time that indicates a delayed push time.

[0052] In some embodiments, the apparatus further includes:

[0053] Obtain the user behavior represented by the first user event;

[0054] A pre-trained neural network predicts an ending event that characterizes the end of the user behavior, which is then used as the target user event; wherein the output layer of the neural network classifies different types of user events that support subscription.

[0055] In some embodiments, the apparatus further includes:

[0056] The push message identifier of the user habit is obtained from the first data storage; the first data storage also includes the triggering conditions of the user habit, device operation, and the user identifier of the user to whom the user habit belongs;

[0057] After subscribing to the target user event, a push record is constructed and stored in the second data storage based on the target user event and the push message identifier; the push record is deleted after the push message according to the user's habits is generated and sent to the display interface.

[0058] In some embodiments, the message push module is specifically used for:

[0059] Based on the target user event, the record to be pushed is retrieved from the second data storage;

[0060] Based on the push message identifier in the record to be recommended, the triggering conditions of matching user habits, device operations and user identifiers are determined from the first data storage;

[0061] The push message is generated based on the triggering conditions and device operation;

[0062] The push message is sent to the display interface on the device associated with the user identifier.

[0063] In some embodiments, the record to be pushed further includes the occurrence time of the first user event satisfying the triggering condition of the user habit; the message push module is specifically used for:

[0064] Obtain the reception time of the target user event, and determine the time interval between the reception time and the occurrence time;

[0065] If the time interval does not exceed a preset duration threshold, a push message based on the user's habits is generated.

[0066] In some embodiments, the apparatus further includes:

[0067] In response to receiving the target user event, unsubscribe from the target user event.

[0068] In some embodiments, the apparatus is applied to a target device, which has a device event subscription service configured therein; the device event subscription service is used to receive various user events reported by different devices managed by the target device, and to publish the various user events according to the subscription relationship;

[0069] The user event subscription module is specifically used to: request the device event subscription service to subscribe to the target user event; the subscription also includes instructing the device event subscription service to publish the target user event to a set data queue.

[0070] In some embodiments, the apparatus further includes:

[0071] If an update to the specified data queue is detected, read the pending events from the data queue;

[0072] If the event to be processed is determined to be the target user event, the push message is generated.

[0073] In some embodiments, the target device further includes at least a first push service and a second push service; the apparatus further includes:

[0074] Through the first push service, when the timing of the triggering condition being met falls within the message push timing period, a push message tailored to the user's habits is generated and sent to the display interface.

[0075] The subscription refers to the target user event for which the push timing is delayed, including: requesting to subscribe to the target user event from the device event subscription service through the first push service;

[0076] The second push service retrieves the target user event from the designated data queue and generates the push message in response to the target user event, which is then sent to the display interface.

[0077] According to a third aspect of the present disclosure, an electronic device is provided, comprising: a processor and a memory; the memory being used to store a computer program; and the processor being used to invoke the computer program to implement the above-described message push method.

[0078] According to a fourth aspect of the present disclosure, a readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the above-described message push method.

[0079] The technical solutions provided by the embodiments of this disclosure may include the following beneficial effects:

[0080] This disclosure provides a more flexible habit-based message push experience by determining whether the current time is suitable for pushing messages when a user event is identified as meeting the triggering conditions of learned user habits. If the current time is not a suitable time for pushing messages, the push message based on the user habit is not sent. Furthermore, it subscribes to target user events that represent delayed push periods. Upon receiving the target user event, a push message is generated and sent to the display interface. Through push timing judgment and delayed push, this provides a more flexible habit-based message push experience, avoiding disturbing users at inappropriate times and reducing user aversion to untimely pushes. Without changing the structure of existing automated user habit data, it achieves push message delivery during periods when users are more likely to pay attention, conforming to the user's daily life rhythm and improving user acceptance of the automatic execution function of user habits and the user experience.

[0081] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Furthermore, no embodiment in this disclosure is required to achieve all the effects described above. Attached Figure Description

[0082] Figure 1 This is a flowchart illustrating a message push method according to an exemplary embodiment;

[0083] Figure 2 This is an example diagram illustrating a delayed push correspondence according to an exemplary embodiment;

[0084] Figure 3A This is an example of a first data storage—a user habit database—illustrated according to an exemplary embodiment;

[0085] Figure 3B This is an example of a second data storage—a delayed push record database—illustrated according to an exemplary embodiment;

[0086] Figure 4 This is an example diagram illustrating the generation and sending of push messages based on a first data storage and a second data storage, according to an exemplary embodiment.

[0087] Figure 5 This is a schematic diagram illustrating a scenario structure for introducing a device event subscription service, according to an exemplary embodiment.

[0088] Figure 6 This is a schematic diagram illustrating another scenario structure for introducing a first push service and a second push service, according to an exemplary embodiment.

[0089] Figure 7 This is a schematic diagram of the structure of a message push device according to an exemplary embodiment;

[0090] Figure 8 This is a block diagram illustrating a terminal device according to an exemplary embodiment. Detailed Implementation

[0091] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0092] The terminology used in this disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The singular forms “a,” “the,” and “the” as used in this disclosure and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

[0093] It should be understood that although the terms first, second, third, etc., may be used in this disclosure to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this disclosure, a first user event may also be referred to as a second user event, and similarly, a second user event may also be referred to as a first user event. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0094] Currently, some smart home systems can provide more personalized services by learning users' daily behavioral patterns, i.e., user habits. For example, Xiaomi's HyperMind smart function, which spans multiple devices and learns user habits, can analyze the working data of its associated devices to learn these habits. For instance, if a user habitually turns on the humidifier after getting home from get off work, the system can learn this habit. The system typically stores these learned user habits as automated data, which includes trigger conditions and device operations. The trigger conditions indicate when the device operation is performed. For example, the automated data for the user habit "turn on the humidifier after getting home from get off work" can be represented as: trigger condition: "get home from get off work" + device operation: "turn on the humidifier".

[0095] Currently, after learning user habits, for each user habit in the pending recommendation state, when the received user event meets the triggering conditions of the user habit, the system is triggered to construct a push message for that user habit and send it to the display interface, such as the user terminal interface, to ask the user whether they want the system to remember and enable the automatic execution function of the user habit. This automatic execution function is used to automatically execute the corresponding device operation without user operation when the triggering conditions of the user habit are met.

[0096] However, practical results show that the above-mentioned message push method suffers from low user acceptance and decreased user participation in the smart home system. Therefore, a new method is needed to optimize the push message sending mechanism to better suit user habits.

[0097] The inventors of this disclosure analyzed historical data regarding the timing of push notifications for various user habits sent to the display interface, whether users viewed the push notifications, and user selections related to the push notifications. They discovered that the aforementioned push notification methods tend to send push notifications about user habits during times when users do not wish to be disturbed, thus disrupting their state and causing annoyance. For example, for user habit A, "turning on the speakers when starting to study," sending a push notification about habit A after the user has started studying will cause the notification's ringtone or vibration to interfere with the user's study. Similarly, for user habit B, "adjusting the air conditioner to sleep mode when the user falls asleep," sending a push notification about habit A after the user has fallen asleep will cause the notification's ringtone or vibration to interfere with the user's sleep, and the push notification cannot be effectively viewed.

[0098] The inappropriate timing of push notifications in the above-mentioned methods not only directly annoys users, making it difficult for them to effectively receive and pay attention to the content, but also results in low user acceptance of the push message, which in turn affects the user experience and the acceptance and practicality of habit-based recommendation functions.

[0099] Therefore, based on the above findings, the inventors propose the message push method of this disclosure, which optimizes the timing of push messages based on user habits. This message push method can be applied to target devices, including servers such as Xiaomi Cloud or clients capable of learning user habits. The target device can collect usage data from different smart devices it manages, such as smart wearables, door locks, lights, air conditioners, smart mattresses, humidifiers, speakers, refrigerators, washing machines, treadmills, etc., and automatically learn user habits based on this usage data. Different types of user events can be predefined in the target device, enabling it to analyze and report specific user events based on the collected smart device usage data. For example, it can report user sleep / wake-up events based on smart wearable device and / or smart mattress data, and user indoor exercise events based on treadmill data.

[0100] The message push method provided in this disclosure uses a predefined set of message push timings to determine whether the time when the triggering condition of the user habit to be recommended is a message push timing. If the time when the triggering condition is met is not a message push timing, a delayed push strategy is adopted to redetermine the delayed push timing for the user habit and postpone the push, thereby reducing the interference of push messages for the user habit and improving the exposure and acceptance of push messages.

[0101] See Figure 1 The flowchart illustrating an exemplary message push method shows the steps of the message push method provided in this disclosure, which may include at least the following steps:

[0102] S101, in response to the received first user event satisfying the triggering condition of the user's habit, identify whether the timing of ...

[0103] The user habits described in this disclosure are triggered by user events or situations and involve device operations related to a specific device. That is, the user habit includes a triggering condition and a specific device operation, where the triggering condition is used to activate the device operation within the user habit. For example, the user habit "adjusting the air conditioner to sleep mode when the user is asleep" has the triggering condition of the user being asleep, and the device operation is adjusting the air conditioner to sleep mode. When the condition of the user being asleep is met, the device operation on the air conditioner is triggered, i.e., adjusting it to sleep mode.

[0104] These user habits can be obtained by the target device learning user behavior patterns. This involves analyzing a large amount of data, such as user operation records, usage time, preference settings, and interaction frequency on the smart devices managed by the target device, and using machine learning or deep learning algorithms to identify the user's regular behaviors and preferences. Alternatively, these user habits can be quickly matched and recommended based on preset habit templates. These habit templates can cover common habits of different user groups in specific scenarios. By matching user information with these habit templates, settings and services that match the user's potential habits can be quickly recommended or configured, which is especially suitable for new users or situations where there is a lack of sufficient behavioral data.

[0105] The first user event refers to a user's behavior or operation at a specific point in time or under specific circumstances. This can be determined by analyzing real-time usage data from various smart devices, such as a user waking up, a user's movement, or a user returning home. It's understood that the "first" in this first user event is only used to distinguish user events of the same type and does not have any specific indicative meaning in itself.

[0106] The learned user habits refer to user behavior patterns learned by analyzing the historical usage data of different smart devices. In this step, the learned user habits are in a state of pending recommendation, that is, the automatic execution function is not enabled for this user habit, and a push message needs to be sent to prompt the user whether to enable the automatic execution function.

[0107] The message push timing is used to indicate the appropriate time to send notifications or messages to users, ensuring that push messages tailored to user habits are seen and noticed by users in a timely manner. Identifying whether the timing of the triggering condition being met constitutes a push notification timing can be achieved by pre-defining a dataset storing various non-push timings. This dataset can store various non-push timings that are not suitable for sending push messages to users, such as when the user is asleep, when the user starts studying, or when the user starts exercising.

[0108] Regarding this step, upon receiving the first user event, it can be compared with the triggering conditions of each learned user habit that is in a pending recommendation state to determine whether the first user event meets the triggering condition of at least one user habit. When the first user event meets the triggering condition of at least one user habit, for each user habit whose triggering condition is met, it is determined whether the timing of the fulfillment of the triggering condition is suitable for message push, i.e., whether it is a suitable time for message push.

[0109] For example, taking the learned user habit "adjusting the air conditioner to sleep mode when the user is asleep" as an example, the trigger condition for this user habit is "the user is asleep." When the first user event is received, if the first user event represents the user's sleeping behavior, such as the "user is asleep" event, then it is determined that the first user event meets the trigger condition for the user habit. Further, it is determined whether the timing of this trigger condition being met—the user falling asleep—belongs to the message push timing. Similarly, taking the user habit "turning on the humidifier when the user starts indoor exercise" as an example, when the trigger condition "the user starts indoor exercise" is met, it is determined whether the timing of this trigger condition being met—"the user starts indoor exercise"—belongs to the message push timing.

[0110] S102, in response to the fact that the timing when the triggering condition is met does not belong to the message push timing, subscribe to the target user event indicating the delayed push timing;

[0111] The delayed push notification timing refers to not sending a push notification based on a user's habit when the trigger condition for that habit is met is not a typical push notification timing. Instead, a new push notification timing is selected, which can reduce the disruption to users at inappropriate times. For example, if a user's habit is "adjusting the air conditioner to sleep mode when the user is asleep," and the trigger condition "the user is asleep" is not a typical push notification timing, then a delayed push notification timing could be, for example, when the user wakes up.

[0112] The target user event is closely related to the delayed push timing. The target user event is the basis for determining the delayed push timing, which is the point in time or period during which the target user event occurs. In the example of the user habit "adjusting the air conditioner to sleep mode when the user is asleep," if the user waking up is taken as the delayed push timing, then the target user event representing this delayed push timing could be the user waking up event.

[0113] Subscription is a means of enabling the attention or monitoring of specific events. In this embodiment, subscription is used to enable the attention of target user events so as to receive target user events in a timely manner and trigger the sending of push messages based on user habits.

[0114] Regarding the target user event representing the delayed push timing, it can be implemented in any of the following ways: it can be determined based on a predefined non-recommended timing-target user event correspondence; it can also be implemented through scheduled push, i.e., automatically setting a reasonable first time period as the delayed push timing and selecting a target user event or a first scheduled event for that time period; or it can be implemented based on user preference settings to determine a second time period as the delayed push timing, and then selecting a target user event or a scheduled event for that time period. That is, when users are allowed to set the time when they prefer to receive push information, such as when users set to receive push information only during the day or specify a certain time period, the determined delayed push timing can be flexibly adjusted according to the user's personal preferences and lifestyle, thereby improving user satisfaction.

[0115] If the timing of the user's habit triggering condition falls within the message push timing, then the push message for that user habit can be directly generated and sent to the display interface for display.

[0116] S103, in response to receiving the target user event, generate a push message for the user's habit and send it to the display interface for display; the push message is used to ask the user whether to enable the automated execution function of the user's habit.

[0117] This push notification asks the user whether to enable the automated execution function of the user's habit, that is, whether to allow the server to automatically execute the device operation in the user's habit when the trigger condition of the user's habit is met. This device operation can be achieved without manual operation by the user. For example, taking "adjusting the air conditioner to sleep mode when the user is asleep" as an example, the push notification for this user habit could be: "Hello, we have learned your user habit 'automatically adjust the air conditioner to sleep mode at 11 pm,' do you want to enable the automated execution function?". For this push notification, users can provide options such as "enable," "ignore," and "don't remind again for 7 days," allowing users to flexibly choose according to their needs.

[0118] The display interface can include the display interface on various devices used by the user to receive push information, such as smartphones, tablets, or computers. This display interface can be the system interface or application interface that carries the push notification. Taking Xiaomi Cloud as an example, the display interface can be the interface of the configured HyperOS system, the user interface of the Xiao Ai APP, or the Mi Home APP.

[0119] In some embodiments, to avoid repeatedly sending push messages and unnecessary resource consumption, in response to receiving the target user event, while generating the push message according to the user's habits and sending it to the display interface for display, it is necessary to unsubscribe from the target user event. This ensures that after the push message has been successfully triggered and sent according to the target user event, no additional response is required for that target user event, thereby avoiding repeatedly sending the same push message to the user, improving user experience and system efficiency.

[0120] In this step, when a subscribed target user event is received, a push message is automatically constructed based on the user's habitual trigger conditions and device operation, following a pre-defined push message format. The message asks the user if they wish to enable automated execution functions based on that user habit. This push message is then sent to the user's device for display, allowing the user to decide whether to enable the function. If the user chooses to enable the automated execution function for that user habit, the habit's status will change from pending recommendation to recommended, and no further push messages will be sent for that user habit.

[0121] Taking "adjusting the air conditioner to sleep mode when the user is asleep" as an example, since the triggering condition for this user habit, "the user is asleep," is not a push notification timing, the aforementioned embodiment determines the delayed push timing as "the user wakes up" and subscribes to the target user event "the user wakes up event." Therefore, in this step, in response to receiving the user wakes up event, a push message for this user habit is generated and sent to the display interface. From the user's perspective, taking the user's mobile phone as an example, when the user wakes up, the user's mobile phone will receive a push message. This push message asks the user whether to activate the automated execution function of the user habit "adjusting the air conditioner to sleep mode when the user is asleep."

[0122] The above embodiments use the example of a first user event satisfying a trigger condition for a user habit in a pending recommendation state to explain and illustrate the method. It can be understood that if the first user event simultaneously satisfies multiple trigger conditions for user habits in a pending recommendation state, then each user habit whose trigger condition is satisfied can be processed in accordance with the message push method provided in the above embodiments.

[0123] In this embodiment of the disclosure, by judging the timing of push notifications and delaying push notifications, when a user event is identified as meeting the triggering conditions of the learned user habits, it is determined whether the current time is suitable for pushing messages. If the current time is not a suitable time for pushing messages, the system subscribes to a target user event that represents a delayed push period. After receiving the target user event, a push message is generated and sent to the display interface. This reduces the occurrence of sending push messages at inappropriate times and disturbing users, reduces user aversion to untimely push notifications, and ensures that push messages are delivered during the time when users are more likely to pay attention, thereby improving user acceptance of push notification habits.

[0124] In some embodiments, identifying whether the timing of the fulfillment of the triggering condition belongs to a message push timing can be achieved by pre-defining a dataset that stores various non-push timings. Based on this, this embodiment provides a method for identifying whether the timing of the fulfillment of the triggering condition belongs to a message push timing. This method can be implemented through the following steps: obtaining a preset dataset for storing non-push timings; and determining that the timing of the fulfillment of the triggering condition does not belong to a message push timing when the timing of the fulfillment of the triggering condition exists in the dataset.

[0125] Non-push events refer to times or periods when it is not appropriate to push messages, such as when the user is asleep, studying, or doing housework. The dataset used to store non-push events can be a predefined and stored collection of data containing various unsuitable times for message pushes. This data can be set based on users' general behavioral patterns and can be analyzed and updated based on user data related to push messages. Furthermore, this dataset can also store non-push events learned based on individual user preferences.

[0126] When a user's preferred trigger condition is met, the system checks whether the timing of this trigger condition's fulfillment exists in the dataset. This involves matching the timing of the trigger condition's fulfillment with each non-push event in the dataset. If the two events represent the same event or the semantic similarity is greater than a set threshold, then the timing of the trigger condition's fulfillment is determined to exist in the dataset, meaning it is not a push event. Conversely, if the timing of the trigger condition's fulfillment does not match any of the non-push events in the dataset, then the timing of the trigger condition's fulfillment is determined to not exist in the dataset, meaning it is a push event.

[0127] In this embodiment of the disclosure, by using a predefined dataset for storing non-push events, it is possible to accurately identify whether the timing of the user's habitual triggering conditions being met belongs to the push event, thereby providing a data basis for subsequent precise control of the push event timing and avoiding sending push messages at unnecessary times.

[0128] In some embodiments, the target user event representing the delayed push timing based on the subscription can be determined according to a predefined non-recommended timing-target user event correspondence. This embodiment provides an implementation method for determining the target user event representing the delayed push timing, which can be achieved through the following steps: determining a preset user event that matches the timing when the triggering condition is met, based on the preset delayed push correspondence, as the target user event; wherein, the delayed push correspondence includes at least one predefined non-push timing and a preset user event corresponding to each non-push timing that indicates the delayed push timing.

[0129] The delayed push correspondence is a mechanism for determining whether to delay message pushes during specific non-push events until a target user event occurs. This delayed push correspondence is based on understanding and predicting user behavior patterns, ensuring that push messages about user habits are delivered at the most suitable time for the user to receive them, thus avoiding inconvenience and improving message effectiveness and user satisfaction. The delayed push correspondence defines at least one non-push event, including time periods or scenarios where the user may not want to be disturbed, such as when the user is resting, studying, or working. For each non-push event, one or more corresponding preset user events are specified, indicating that the user is transitioning from a non-push event state to a state more suitable for receiving push messages.

[0130] For example, see Figure 2 An example diagram illustrating the correspondence between delayed push notifications is provided. Examples of non-push notification times include when the user is asleep, when the user starts exercising, when the user is studying, when the user is driving, and when the user is playing a game. Examples of corresponding delayed push notification events are also given.

[0131] If the timing when the user's habitual triggering condition is met does not fall within the message push timing, then a target correspondence record matching the timing when the triggering condition is met can be found through a matching query based on a preset delayed push correspondence, and the preset user event in the target correspondence record can be used as the target user event.

[0132] In this embodiment of the disclosure, based on a predefined delayed push correspondence, the target user event for delayed push timing is quickly determined, improving the timeliness and efficiency of processing.

[0133] In some embodiments, as user behavior patterns diversify and personalized needs increase, static correspondences may not fully meet the needs of all users. Therefore, for the target user event described in step S102 above, this embodiment provides another implementation method based on a neural network. In this embodiment, for the received first user event, the user behavior represented by the first user event is obtained; an end event representing the end of the user behavior is predicted by a pre-trained neural network as the target user event; wherein, the output layer classification of the neural network includes different types of user events that support subscription.

[0134] In this embodiment, when a first user event is received, the user behavior represented by the event is first obtained; for example, if the first user event is a user falling asleep event, then the user behavior represented by it is that the user is asleep; if the first user event is a user starting to learn, then the user behavior represented by it is that the user is learning.

[0135] Based on the user behavior represented by the first user event, the pre-trained neural network can extract deep features of the user behavior through multi-layer nonlinear transformations, learn the complex relationship between the generated features and the behavior termination event, and predict the termination event representing the end of the user behavior in the output layer. The output layer of the neural network can be a probability distribution, representing the likelihood of different user events as target user events, and can select the user event with the highest probability as the predicted termination event, i.e., the target user event. The output layer of the pre-trained neural network includes various types of user events defined in the server, which support the subscription described in step S102 above.

[0136] In this embodiment of the disclosure, a target user event is used to represent the user's state transition from a non-push time to a suitable time for push notification. By utilizing big data and machine learning technologies, user behavior is analyzed in depth, and the timing of the end of user behavior is predicted. This determines the target user event representing the delayed push timing, realizing the dynamic prediction of the suitable time for message push, and improving the accuracy and flexibility of prediction.

[0137] In some embodiments, to facilitate data storage and management, a first data storage device can be set up specifically for storing learned user habits, and a second data storage device can be set up specifically for storing each delayed push message and its subscribed target user events. The first and second data storage devices can be databases or other data structures, and this disclosure does not limit their use. Based on the first and second data storage devices, the aforementioned message push method may further include the following implementation process:

[0138] The push message identifier of the user habit is obtained from the first data storage; the first data storage also includes the triggering conditions of the user habit, device operation, and the user identifier of the user to whom the user habit belongs;

[0139] After subscribing to the target user event, a push record is constructed and stored in the second data storage based on the target user event and the push message identifier; the push record is deleted after the push message according to the user's habits is generated and sent to the display interface.

[0140] In other words, the first data storage can record data items related to user habits, such as trigger conditions, device operations, and the user ID of the user to whom the habit belongs. This information together constitutes a complete description of the user habit. Furthermore, a unique push message ID can be assigned to each user habit for reference in subsequent message push processes. For example, ... Figure 3A The first data storage example shown is a user habit database, which also includes the recommended status of user habits. When a push message is sent to the display interface and the user selects "Enable / Remember" or other functions that indicate the activation of the user habit's automated execution function, the user's status in the first data storage is synchronously updated from "Pending Recommendation" to "Recommended / Remembered".

[0141] For the secondary data storage, after a user subscribes to a target user event, a pending push record can be automatically generated. This record may include, but is not limited to, information such as a push message identifier, the identifier or content of the target user event, and the user identifier. This pending push record is temporarily stored in the secondary data storage, awaiting the occurrence of the target user event. After the target user event occurs and is received, the corresponding pending push record is retrieved from the secondary data storage, and a final push message is generated and sent to the display interface. After the push message is successfully sent, the pending push record is deleted from the secondary data storage to free up storage space and avoid duplicate pushes.

[0142] See Figure 3B The exemplified second data storage—a delayed push record database—takes the user habit represented by the push message identifier "aaa" as an example. When the received first user event meets the trigger condition "user falls asleep," after subscribing to the user's wake-up event, it constructs... Figure 3B The push record shown is used to temporarily cache individual push message records that need to be delayed.

[0143] Based on the aforementioned first data storage and second data storage, in some embodiments, combined with Figure 4 The example diagram illustrating the generation and sending of push messages, regarding the aforementioned step S103, which involves generating a push message tailored to the user's habits in response to receiving the target user event and sending it to the display interface for display, can be implemented by querying the recommended record in the second data storage and then querying the first data storage to generate a push message tailored to the user's habits before sending it. This can include the following implementation steps:

[0144] S401, based on the target user event, find the record to be pushed from the second data storage;

[0145] The target user event for a subscription can include one or more events. That is, there may be one or more user habits that result in delayed push notifications. If the triggering condition for each user habit is met at a time when it is not a push notification time, a target user event will be subscribed for that user habit, and a record for that user habit awaiting push notification will be added to the second data storage. Regarding the subscription of target user events, if multiple user habits correspond to the same target user event, a single subscription to that target user event or repeated subscriptions can be performed. During repeated subscriptions, the latest subscription operation will overwrite the previous subscription.

[0146] Based on this, upon receiving a target user event, all recommended records in the second data store can be matched against that target user event, and at least one record to be pushed can be found from the second data store. See also Figure 4 As shown, for the target user event "user wake-up event", a record to be pushed was found, marked by the gray box in the figure.

[0147] S402, based on the push message identifier in the record to be recommended, determine the triggering conditions of matching user habits, device operation and user identifier from the first data storage;

[0148] Continue to refer to Figure 4 As shown, based on the push message identifier in the found push record, the user habit record matching the push message identifier can be found in the first data storage, as shown in the record marked by the gray box in the figure. The trigger conditions of the user habit "user asleep", the device operation "turn off the light" and the user identifier "111" can be extracted from the user habit record.

[0149] S403, Generate the push message based on the triggering conditions and device operation;

[0150] Since push messages are used to ask users whether to activate automated functions based on user habits, the push message needs to include complete information about user habits, namely the triggering conditions and device operations. The push message can be obtained by combining and encapsulating messages according to a pre-defined push message format.

[0151] S404, the push message is sent to the display interface on the device associated with the user identifier.

[0152] The user identifier can uniquely determine the display interface to receive the push message. For example, if a unique correspondence between the display interface address and the user identifier is stored in advance, the display interface address corresponding to the user identifier can be retrieved based on this unique correspondence, and then the constructed push message can be sent to that display interface.

[0153] In this embodiment of the disclosure, by storing user habits and push message-related information in the first data storage and the second data storage respectively, data classification management and efficient retrieval are achieved. When a push message needs to be generated, the record to be pushed can be quickly found in the second data storage, and complete user habit information can be obtained in the first data storage according to the push message identifier, thereby generating a push message, which improves the efficiency and accuracy of message push.

[0154] The foregoing embodiments focused on how to generate and send push messages related to user habits based on target user events. However, in practical applications, the impact of time factors on message pushes also needs to be considered. To ensure the timeliness and accuracy of push messages and avoid sending unnecessary messages to users in outdated situations, the occurrence time of the triggering condition is introduced when constructing the push record.

[0155] In this embodiment, based on the need to improve the timeliness and accuracy of message push, and to avoid sending push messages to users in outdated or irrelevant situations, when constructing the push record based on the first data storage and subscribed target user events, the push record may further include the occurrence time of the first user event satisfying the triggering condition of the user's habit, for example... Figure 3B The time at which the triggering condition shown is met. Based on the occurrence time in the record to be recommended, the aforementioned step S103, which involves generating the push message based on the user's habits in response to receiving the target user event, can be implemented through the following steps:

[0156] Obtain the reception time of the target user event and determine the time interval between the reception time and the occurrence time; if the time interval does not exceed a preset duration threshold, generate a push message according to the user's habits.

[0157] That is, in response to receiving the target user event, the receiving time of the target user is recorded as the starting point for judging the timeliness of message push, and for each push notification matching the target user event, the occurrence time when the triggering condition corresponding to the target user event is met is retrieved from the push notification record, for example... Figure 3B The timeframe shown is 2024-10-13 22:00. Next, the time interval between the occurrence time and the reception time is calculated. This time interval reflects the length of time between the fulfillment of the triggering condition and the receipt of the subscribed target user event. Finally, it is determined whether the message push exceeds the preset duration threshold to determine whether the message push still has timeliness. Taking 12 hours as the preset duration threshold as an example, if the reception time is within 12 hours after the occurrence time, then the time interval does not exceed the preset duration threshold, thus determining that the message push still has timeliness.

[0158] For example, with Figure 3B Taking 2024-10-13 22:00 as an example, if the preset duration threshold is 12 hours, the time interval will not exceed the preset duration threshold if the receiving time is 2024-10-14 10:00 or earlier (i.e., within 12 hours after the occurrence time); if the receiving time is after 2024-10-14 10:00, such as 2024-10-14 14:00, the time interval will exceed the preset duration threshold.

[0159] If the time interval does not exceed the preset duration threshold, a push message according to the user's habits is generated and sent to the display interface for display; if the time interval exceeds the preset duration threshold, fault feedback can be provided, which is at least used to indicate that the reporting time of the target user event is abnormal.

[0160] In this embodiment of the disclosure, by introducing a judgment mechanism for the occurrence time of the triggering condition and a preset duration threshold, the timing of message push can be controlled more intelligently, avoiding sending unnecessary messages to users in outdated or irrelevant situations, thereby improving the timeliness and accuracy of message push.

[0161] In some embodiments, to achieve precise push notifications based on user habits by subscribing to target user events and to improve the timeliness and accuracy of message pushes, this embodiment introduces a device event subscription service set up internally within the target device. This device event subscription service can receive and process various user events reported from different devices associated with the target device. Based on the reported user events and subscription relationships, the device event subscription service can intelligently publish relevant events to subscribers who have subscribed to the user event, thereby meeting the need for delayed push notifications. The device event subscription service can adopt a publish-subscribe messaging model, allowing decoupling between the publisher (device event subscription service) and the receiver (subscriber). In this messaging model, the publisher sends messages to blocks specified by each subscriber, and the subscriber receives messages by accessing one or more blocks, such as the data queues defined in this disclosure.

[0162] like Figure 5As shown, based on the aforementioned device event subscription service, when the message push method provided in this disclosure is applied to a target device, the device event subscription service set up inside the target device can be used to receive various user events reported by different devices associated with the target device, and publish the various user events according to the subscription relationship; based on this, the subscription of the target user event indicating the delayed push timing in the aforementioned step S102 can be implemented in the following way, namely: requesting to subscribe to the target user event from the device event subscription service; the subscription also includes instructing the device event subscription service to publish the target user event to a set data queue.

[0163] This data queue is a pre-set queue for the target device to perform delayed push processing of push messages based on user habits. This data queue is used to ensure that target user events can be captured in a timely and accurate manner.

[0164] In this embodiment, the target device first initiates a subscription request to the device event subscription service, which explicitly specifies the target user events to be subscribed to. Simultaneously, the target device also instructs the device event subscription service to publish the target user event to a designated data queue, i.e., the set data queue, when it detects the occurrence of the target user event.

[0165] For example, taking the user habit of "adjusting the air conditioner to sleep mode when the user is asleep" as an example, the target user event is the user waking up event. The target device can subscribe to a target user event named "user waking up event" from a device event subscription service and instruct the device event subscription service to publish it to a data queue Q upon receiving the user waking up event. For the device event subscription service, after receiving the user waking up event, it publishes the user waking up event to a data queue Q according to the target device's subscription request, for the target device to read and consume.

[0166] The subscription also includes instructing the device event subscription service to publish the target user event to a designated data queue. Therefore, when the device time subscription service receives a user event reported by the device that is the target user event, it publishes the target user event to the designated data queue according to the subscription relationship. After subscribing to the target user event indicating a delayed push timing, the designated data queue can be monitored to obtain the target user event in a timely manner. For example, this can be achieved by continuously monitoring whether the designated data queue is updated; that is, if an update is detected in the designated data queue, the event to be processed is read from the data queue; if it is determined that the event to be processed is the target user event, the push message is generated.

[0167] In this embodiment of the disclosure, the target user's event is published to a set data queue through the device event subscription service and subscription request, so that the target device can consume the target user's event efficiently and in a timely manner, thereby improving the accuracy and timeliness of message push.

[0168] In some embodiments, the target device not only integrates a device event subscription service to receive and process user events from different devices, but also further extends the functionality of the push service to support more complex and flexible message push strategies. For example, the target device can also integrate a target push service that supports handling different situations, which can be used to implement the message push method provided in the foregoing embodiments. This embodiment aims to decouple the processing procedures under different message push timings, such as... Figure 6 The schematic diagram of the scenario structure shown indicates that the target device can also be equipped with at least a first push service and a second push service. The second push service is dedicated to handling push messages that users are accustomed to delaying. The two work together to achieve accurate response to user events and intelligent delivery of push messages.

[0169] Based on the first and second push services, the target device can identify whether the timing of the user's habit triggering condition being met belongs to a message push timing through the first push service: if the timing of the triggering condition being met belongs to a message push timing, the target device can trigger the generation of a push message for the user's habit through the first push service and send it to the display interface; in response to the timing of the triggering condition being met not belonging to a message push timing, it subscribes to the target user event, as shown in the figure, that is, it can request to subscribe to the target user event through the first push service to the device event subscription service, and instruct the device event subscription service to publish the target user event to a set data queue; through the second push service, it retrieves the target user event from the set data queue, and in response to the target user event, generates the push message and sends it to the display interface.

[0170] In this embodiment, by setting up a first push service and a second push service, the first push service is responsible for scenarios with immediate push notifications, while the second push service focuses on scenarios with delayed push notifications, sending push messages at a more appropriate time. This decouples the push message sending process under different circumstances, allowing the target device to better utilize system resources, avoid resource conflicts and waste, and improve the processing efficiency of push messages. Furthermore, through the combination of the device event subscription service, the first push service, and the second push service, the target device can adapt to different business needs and user scenarios, enabling dynamic adjustment and optimization of the push strategy. When new push strategies or functions need to be introduced, only extensions or modifications need to be made within the existing framework, without the need to refactor the entire system, thus reducing development and maintenance costs.

[0171] It is understood that the steps described in the above embodiments are not necessarily a specific execution order or timing. In some embodiments, they can be executed in different orders or at different times and still achieve the desired effect.

[0172] Corresponding to the aforementioned embodiments of the message push method, Figure 7 This is a schematic diagram illustrating the structure of a message push device according to an exemplary embodiment, such as... Figure 7 As shown, the device includes a push timing identification module 701, a user event subscription module 702, and a message push module 703.

[0173] The push timing identification module 701 is used to identify whether the timing when the first user event received meets the triggering condition of the user's habit is a message push timing; the triggering condition is used to trigger the device operation in the user's habit.

[0174] User event subscription module 702 is used to subscribe to target user events indicating delayed push timing in response to the fact that the timing when the triggering condition is met does not belong to the message push timing.

[0175] The message push module 703 is used to generate a push message based on the user's habits in response to receiving the target user event and send it to the display interface for display; the push message is used to ask the user whether to enable the automated execution function of the user's habits.

[0176] In some embodiments, the push timing identification module is specifically used for:

[0177] Obtain a pre-defined dataset for storing non-push events;

[0178] If the timing of the triggering condition being met exists within the dataset, it is determined that the timing of the triggering condition being met does not belong to the message push timing.

[0179] In some embodiments, the apparatus further includes:

[0180] Based on a preset delayed push correspondence, a preset user event that matches the timing when the triggering condition is met is determined as the target user event;

[0181] The delayed push correspondence includes at least one predefined non-push time and a preset user event corresponding to each non-push time that indicates a delayed push time.

[0182] In some embodiments, the apparatus further includes:

[0183] Obtain the user behavior represented by the first user event;

[0184] A pre-trained neural network predicts an ending event that characterizes the end of the user behavior, which is then used as the target user event; wherein the output layer of the neural network classifies different types of user events that support subscription.

[0185] In some embodiments, the apparatus further includes:

[0186] The push message identifier of the user habit is obtained from the first data storage; the first data storage also includes the triggering conditions of the user habit, device operation, and the user identifier of the user to whom the user habit belongs;

[0187] After subscribing to the target user event, a push record is constructed and stored in the second data storage based on the target user event and the push message identifier; the push record is deleted after the push message according to the user's habits is generated and sent to the display interface.

[0188] In some embodiments, the message push module is specifically used for:

[0189] Based on the target user event, the record to be pushed is retrieved from the second data storage;

[0190] Based on the push message identifier in the record to be recommended, the triggering conditions of matching user habits, device operations and user identifiers are determined from the first data storage;

[0191] The push message is generated based on the triggering conditions and device operation;

[0192] The push message is sent to the display interface on the device associated with the user identifier.

[0193] In some embodiments, the record to be pushed further includes the occurrence time of the first user event satisfying the triggering condition of the user habit; the message push module is specifically used for:

[0194] Obtain the reception time of the target user event, and determine the time interval between the reception time and the occurrence time;

[0195] If the time interval does not exceed a preset duration threshold, a push message based on the user's habits is generated.

[0196] In some embodiments, the apparatus further includes:

[0197] In response to receiving the target user event, unsubscribe from the target user event.

[0198] In some embodiments, the apparatus is applied to a target device, which has a device event subscription service configured therein; the device event subscription service is used to receive various user events reported by different devices managed by the target device, and to publish the various user events according to the subscription relationship;

[0199] The user event subscription module is specifically used to: request the device event subscription service to subscribe to the target user event; the subscription also includes instructing the device event subscription service to publish the target user event to a set data queue.

[0200] In some embodiments, the apparatus further includes:

[0201] If an update to the specified data queue is detected, read the pending events from the data queue;

[0202] If the event to be processed is determined to be the target user event, the push message is generated.

[0203] In some embodiments, the target device further includes at least a first push service and a second push service; the apparatus further includes:

[0204] Through the first push service, when the timing of the triggering condition being met falls within the message push timing period, a push message tailored to the user's habits is generated and sent to the display interface.

[0205] The subscription refers to the target user event for which the push timing is delayed, including: requesting to subscribe to the target user event from the device event subscription service through the first push service;

[0206] The second push service retrieves the target user event from the designated data queue and generates the push message in response to the target user event, which is then sent to the display interface.

[0207] The specific implementation process of the functions and roles of each unit in the above device can be found in the implementation process of the corresponding steps in the above method, and will not be repeated here.

[0208] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this disclosure according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0209] This disclosure also provides an electronic device. The electronic device includes a memory and a processor. The memory stores processor-executable instructions, and the processor is configured to execute the executable instructions in the memory to implement the message push steps described above.

[0210] Figure 8 This is a block diagram of an electronic device provided according to an exemplary embodiment. (e.g.) Figure 8 As shown, the electronic device 800 may include one or more of the following components: a processing component 802, a memory 804, a power supply component 806, a multimedia component 808, an audio component 810, an input / output (I / O) interface 812, a sensor component 814, a communication component 816, and an image acquisition component.

[0211] Processing component 802 typically handles the overall operation of electronic device 800, such as operations associated with display, telephone calls, data communication, camera operation, and recording. Processing component 802 may include one or more processors 820 to execute instructions. Furthermore, processing component 802 may include one or more units to facilitate interaction between processing component 802 and other components. For example, processing component 802 may include a multimedia unit to facilitate interaction between multimedia component 808 and processing component 802.

[0212] Memory 804 is configured to store various types of data to support the operation of electronic device 800. Examples of this data include instructions for any application or method operating on electronic device 800, contact data, phonebook data, messages, pictures, videos, etc. Memory 804 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0213] Power supply component 806 provides power to various components of electronic device 800. Power supply component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to electronic device 800.

[0214] Multimedia component 808 includes a screen that provides an output interface between electronic device 800 and target object. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touchscreen to receive input signals from the target object. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors may sense not only the boundaries of a touch or swipe action but also the duration and pressure associated with the touch or swipe operation.

[0215] Audio component 810 is configured to output and / or input audio signals. For example, audio component 810 includes a microphone (MIC) configured to receive external audio signals when electronic device 800 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 804 or transmitted via communication component 816. In some embodiments, audio component 810 also includes a speaker for outputting audio signals.

[0216] I / O interface 812 provides an interface between processing component 802 and peripheral interface units, such as keyboards, click wheels, buttons, etc.

[0217] Sensor assembly 814 includes one or more sensors for providing status assessments of various aspects of electronic device 800. For example, sensor assembly 814 can detect the on / off state of electronic device 800, the relative positioning of components such as the display screen and keypad of electronic device 800, changes in the position of electronic device 800 or a component, the presence or absence of contact between a target object and electronic device 800, the orientation or acceleration / deceleration of electronic device 800, and temperature changes of electronic device 800. As another example, sensor assembly 814 also includes a light sensor disposed below the OLED display screen.

[0218] Communication component 816 is configured to facilitate wired or wireless communication between electronic device 800 and other devices. Electronic device 800 can access wireless networks based on communication standards, such as WiFi, 2G, or 3G, or combinations thereof. In one exemplary embodiment, communication component 816 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 816 also includes a near-field communication (NFC) unit to facilitate short-range communication. For example, the NFC unit may be implemented based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0219] In an exemplary embodiment, the electronic device 800 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components.

[0220] In one exemplary embodiment, this disclosure also provides a readable storage medium storing executable instructions. These executable instructions can be executed by a processor of an electronic device to implement the steps of the message push method provided above. The readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, or optical data storage device, etc.

[0221] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the disclosure herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the foregoing claims.

[0222] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A message push method, characterized in that, The method includes: In response to a received first user event that satisfies a triggering condition of user habits, the system identifies whether the timing of the fulfillment of the triggering condition falls within a message push timing context; the triggering condition is used to trigger device operations within the user habits. In response to the fact that the timing of the triggering condition being met does not fall within the message push timing, the subscription indicates a target user event for which the push timing is delayed; In response to receiving the target user event, a push message based on the user's habits is generated and sent to the display interface for display; the push message is used to ask the user whether to enable the automated execution function of the user's habits.

2. The method according to claim 1, characterized in that, The step of identifying whether the timing of the fulfillment of the triggering condition falls within the message push timing includes: Obtain a pre-defined dataset for storing non-push events; If the timing of the triggering condition being met exists within the dataset, it is determined that the timing of the triggering condition being met does not belong to the message push timing.

3. The method according to claim 1 or 2, characterized in that, The method further includes: Based on a preset delayed push correspondence, a preset user event that matches the timing when the triggering condition is met is determined as the target user event; The delayed push correspondence includes at least one predefined non-push time and a preset user event corresponding to each non-push time that indicates a delayed push time.

4. The method according to claim 1, characterized in that, The method further includes: Obtain the user behavior represented by the first user event; A pre-trained neural network predicts an ending event that characterizes the end of the user behavior, which is then used as the target user event; wherein the output layer of the neural network classifies different types of user events that support subscription.

5. The method according to claim 1, characterized in that, The method further includes: The push message identifier of the user habit is obtained from the first data storage; the first data storage also includes the triggering conditions of the user habit, device operation, and the user identifier of the user to whom the user habit belongs; After subscribing to the target user event, a push record is constructed and stored in the second data storage based on the target user event and the push message identifier; the push record is deleted after the push message according to the user's habits is generated and sent to the display interface.

6. The method according to claim 5, characterized in that, The step of responding to receiving the target user event, generating the push message according to the user's habits, and sending it to the display interface for display includes: Based on the target user event, the record to be pushed is retrieved from the second data storage; Based on the push message identifier in the record to be recommended, the triggering conditions of matching user habits, device operations and user identifiers are determined from the first data storage; The push message is generated based on the triggering conditions and device operation; The push message is sent to the display interface on the device associated with the user identifier.

7. The method according to claim 5, characterized in that, The record to be pushed also includes the occurrence time of the first user event satisfying the triggering condition of the user habit; The step of generating the push message based on the user's habits in response to receiving the target user event includes: Obtain the reception time of the target user event, and determine the time interval between the reception time and the occurrence time; If the time interval does not exceed a preset duration threshold, a push message based on the user's habits is generated.

8. The method according to claim 1, characterized in that, The method further includes: In response to receiving the target user event, unsubscribe from the target user event.

9. The method according to claim 1, characterized in that, The method is applied to a target device, which has a device event subscription service built into it. The device event subscription service is used to receive user events reported by different devices managed by the target device, and to publish the user events according to the subscription relationship. The subscription refers to target user events where the push timing is delayed, including: Request to subscribe to the target user's event from the device event subscription service; The subscription also includes instructing the device event subscription service to publish the target user event to a designated data queue.

10. The method according to claim 9, characterized in that, The method further includes: If an update to the specified data queue is detected, read the pending events from the data queue; If the event to be processed is determined to be the target user event, the push message is generated.

11. The method according to claim 9, characterized in that, The target device is also equipped with at least a first push service and a second push service; the method further includes: Through the first push service, when the timing of the triggering condition being met falls within the message push timing period, a push message tailored to the user's habits is generated and sent to the display interface. The subscription refers to the target user event for which the push timing is delayed, including: requesting to subscribe to the target user event from the device event subscription service through the first push service; The second push service retrieves the target user event from the designated data queue and generates the push message in response to the target user event, which is then sent to the display interface.

12. A message push device, characterized in that, The device includes: The push timing identification module is used to identify whether the timing when the first user event received meets the triggering condition of the user's habit is a message push timing; the triggering condition is used to trigger the device operation in the user's habit. The user event subscription module is used to subscribe to the target user event indicating a delayed push timing when the timing of the triggering condition being met does not belong to the message push timing. The message push module is used to respond to the received target user event, generate a push message based on the user's habits, and send it to the display interface for display; the push message is used to ask the user whether to enable the automated execution function of the user's habits.

13. An electronic device, characterized in that, include: Memory, processor; The memory is used to store computer programs; The processor is configured to invoke the computer program to implement the method as described in any one of claims 1-11.

14. A readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-11.

Images