Water drinking reminding method and device, intelligent water cup and program product

Abstract

The invention is suitable for the technical field of smart home, and provides a water drinking reminding method and device, a smart water cup and a program product, and the method comprises the steps: obtaining water cup data of the smart water cup, the water cup data being used for reflecting the use condition of the smart water cup; obtaining user data of target users, wherein the target users comprise users having a binding relationship with the intelligent water cup; determining fine-grained scene information according to the water cup data and the user data, wherein the fine-grained scene information is used for reflecting the state of the target user; determining a water drinking reminding strategy based on the fine-grained scene information, wherein the water drinking reminding strategy comprises target triggering time of water drinking reminding; and carrying out water drinking reminding on the target user based on the water drinking reminding strategy. The accuracy and effectiveness of water drinking reminding can be improved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of smart home, and particularly relates to a drinking water reminding method and device, a smart water cup and a program product. BACKGROUND

[0002] With the development of sensor technology, various smart home devices are increasingly widely applied. Among them, the smart water cup is a representative and practical product in the field of smart home, which integrates various sensors to provide users with more convenient and healthy drinking water experience. Drinking water reminding is one of the core functions of the smart water cup, aiming to help users overcome the problem of insufficient drinking water caused by factors such as forgetfulness and busyness, and develop a regular drinking water habit.

[0003] At present, the smart water cup usually reminds drinking water in a timing reminding manner, which ignores the current actual situation of the user, easily disturbs the user, and affects the user experience and reduces the effectiveness of drinking water reminding. SUMMARY

[0004] The embodiments of the application provide a drinking water reminding method, device, smart water cup and program product, which can improve the accuracy and effectiveness of drinking water reminding.

[0005] In a first aspect, the embodiments of the application provide a drinking water reminding method, comprising:

[0006] obtaining water cup data of a smart water cup, the water cup data being used to reflect a usage status of the smart water cup;

[0007] obtaining user data of a target user, the target user including a user having a binding relationship with the smart water cup;

[0008] determining fine-grained scene information according to the water cup data and the user data, the fine-grained scene information being used to reflect a state of the target user;

[0009] determining a drinking water reminding strategy based on the fine-grained scene information, the drinking water reminding strategy including a target triggering time of drinking water reminding;

[0010] performing drinking water reminding on the target user based on the drinking water reminding strategy.

[0011] In a second aspect, the embodiments of the application provide a drinking water reminding device, comprising:

[0012] a water cup data obtaining module, configured to obtain water cup data of a smart water cup, the water cup data being used to reflect a usage status of the smart water cup;

[0013] a user data obtaining module, configured to obtain user data of a target user, the target user including a user having a binding relationship with the smart water cup;

[0014] a fine-grained scene information determination module configured to determine fine-grained scene information according to the cup data and the user data, the fine-grained scene information being used to reflect a state of the target user;

[0015] a strategy determination module configured to determine a water drinking reminding strategy based on the fine-grained scene information, the water drinking reminding strategy including a target triggering time of water drinking reminding;

[0016] a reminding module configured to remind the target user to drink water based on the water drinking reminding strategy.

[0017] In a third aspect, an embodiment of the present application provides an intelligent cup, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements steps of the water drinking reminding method in the first aspect when executing the computer program.

[0018] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, and the computer readable storage medium stores a computer program, and the computer program implements steps of the water drinking reminding method in the first aspect when executed by a processor.

[0019] In a fifth aspect, an embodiment of the present application provides a computer program product, and when the computer program product is executed on an intelligent cup, the intelligent cup executes the water drinking reminding method in the first aspect.

[0020] Compared with the prior art, the embodiment of the present application has the following beneficial effects:

[0021] In the embodiment of the present application, the cup data can reflect the use condition of the intelligent cup, and the user data can reflect the information of the target user bound to the intelligent cup, so that the state of the target user can be accurately analyzed according to the cup data and the user data, the fine-grained scene information with high accuracy is obtained, the target triggering time of water drinking reminding is determined according to the fine-grained scene information, the water drinking reminding strategy is obtained, and the target user is reminded to drink water based on the water drinking reminding strategy, so that the actual state of the target user can be fully considered, the water drinking reminding is performed at the target triggering time matched with the actual state of the user, instead of simple timing reminding, thereby effectively reducing the interference on the target user, improving the user experience, and improving the effectiveness of water drinking reminding. BRIEF DESCRIPTION OF DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiments or the prior art description will be briefly introduced.

[0023] Figure 1 is a flowchart of a drinking water reminding method according to an embodiment of the present application;

[0024] Figure 2 is a flowchart of another drinking water reminding method according to an embodiment of the present application;

[0025] Figure 3 is a structural diagram of a drinking water reminding device according to an embodiment of the present application;

[0026] Figure 4 is a structural diagram of a smart water cup according to an embodiment of the present application. DETAILED DESCRIPTION

[0027] In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular sequences of steps, techniques, etc., in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application can be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known methods, devices, and circuits are omitted so as not to obscure the description of the present application with unnecessary detail.

[0028] It should be understood that the term "comprises" when used in this specification and the appended claims, specifies the presence of stated features, integers, steps, operations, elements, and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0029] It should also be understood that the term "and / or" when used in this specification and the appended claims, means any one of the associated listed items, or a combination of any combination of at least one of the associated listed items.

[0030] In addition, in the description of the specification and the appended claims of the present application, the terms "first", "second", "third", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0031] In the present specification, the reference "one embodiment" or "some embodiments" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present application. Thus, the statements "in one embodiment", "in some embodiments", "in other some embodiments", "in yet some embodiments", etc. appearing in various places in the specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments" unless otherwise specifically stated.

[0032] Embodiment One:

[0033] Figure 1 A flowchart of a water drinking reminding method provided by an embodiment of the present application is shown. The water drinking reminding method provided by the embodiment of the present application can be applied to a smart water cup, a processor or a water drinking reminding system, and can be set according to actual application requirements. The above method is described in detail as follows.

[0034] S101, cup data of a smart water cup is acquired, the cup data being used to reflect a usage status of the smart water cup.

[0035] Optionally, the cup data includes, but is not limited to, movement data of a base, movement data of a cup body, water drinking data, water temperature data, water level data and location data and other related data of the smart water cup.

[0036] It should be understood that when the cup data of the smart water cup is acquired, the data included in the cup data can be determined according to actual application requirements; when the data is acquired, the required data can be acquired based on various sensors arranged on the smart water cup.

[0037] For example, when the movement data of the base is required to be acquired, the movement status (such as being stationary, the frequency of being picked up and put down or whether being used in movement, etc.) of the base can be detected by a motion sensor arranged on the base to obtain the movement data of the base.

[0038] For another example, when the water drinking data of the smart water cup is required to be acquired, the water drinking status (such as the amount of water drinking, the frequency of water drinking or the speed of water drinking, etc.) of the user can be detected by a weight sensor arranged on the base or the cup body to obtain the water drinking data.

[0039] In some embodiments, the cup data further includes sound data, which can be acquired by a microphone array arranged on the smart water cup, and can reflect the sound in the current scene of the smart water cup, so as to subsequently analyze the scene information such as the current scene of the smart water cup, the sound volume, the sound density, the type to which the smart water cup belongs, the noise type and the noise level according to the sound data, and help better analyze the state of the target user and other information.

[0040] In the embodiment of the present application, the cup data reflecting the usage status of the smart water cup is acquired, so that the analysis of the state of the target user can be subsequently combined with the actual usage status of the smart water cup, and the accuracy of the data obtained by the analysis can be improved.

[0041] S102, user data of a target user is acquired, the target user including a user having a binding relationship with the smart water cup.

[0042] It should be understood that the user data generally refers to the data related to the user, and mainly reflects one or more of the information such as the characteristics, behaviors, preferences and needs of the user.

[0043] Optionally, the user data includes, but is not limited to, user-related data such as location data of the user, motion data (e.g., motion type, motion intensity, step count, or energy consumption), physiological data (e.g., heart rate, sleep state, or blood pressure), calendar data (e.g., activity schedule, activity type, or activity location), network connection data (e.g., type and name of the connected network or device), and terminal device state data (e.g., do-not-disturb state or normal state).

[0044] It should be understood that when obtaining the user data of the target user, the user data of the target user can be obtained through a terminal device (e.g., a mobile phone) or a wearable device corresponding to the target user, or can be obtained through a third-party service such as a health data platform bound to the user.

[0045] As an example, the smart water cup can send an acquisition request (used to instruct a terminal device corresponding to the target user to send user data to the smart water cup) to the terminal device when it needs to obtain the user data of the target user; after receiving the acquisition request sent by the smart water cup, the terminal device sends the user data of the target user to the smart water cup in response to the acquisition request.

[0046] As another example, the smart water cup can obtain authorization of the terminal device of the target user in advance, and set the acquisition frequency of the target data by sending the acquisition frequency or user settings to the terminal device, so as to obtain the user data of the target user from the terminal device at the set acquisition frequency (e.g., once every minute).

[0047] In the embodiments of the present application, the user of the smart water cup is usually the target user with which there is a binding relationship, and the user data of the user can better reflect the behavior state and other information of the user, so that obtaining the user data of the target user for subsequent state analysis can help improve the accuracy of subsequent analysis.

[0048] S103, determining fine-grained scene information according to the water cup data and the user data, the fine-grained scene information being used to reflect the state of the target user.

[0049] It should be understood that the state of the user usually refers to the specific situation or characteristics of the user, specifically, the physiological characteristics, behavior patterns, environmental conditions, or other dynamic information related to the user.

[0050] Optionally, the state of the user can be at least one of behavior, physical condition, scene, and concentration level.

[0051] In some embodiments, the fine-grained scene information can be used to reflect a current state of the target user (supposedly referred to as a current state) and / or a state of the target user in a set future time period (such as in the next one hour) (supposedly referred to as a future state).

[0052] The future time period is usually determined according to the current time and a first preset time length. For example, assuming that the preset time length is two hours, the future time period can be two hours after the current time. The preset time length (i.e., the future time period) can be obtained by user setting or input, or can be automatically calculated by a smart algorithm.

[0053] Optionally, when determining the fine-grained scene information according to the cup data and the user data, the required fine-grained scene information can be inferred based on a predetermined rule (supposedly referred to as a first rule, which can reflect a mapping relationship between the cup data, the user data and the fine-grained scene information), can be inferred by a classifier or a clustering algorithm, or can be inferred by a combination of the predetermined rule and the smart algorithm. The embodiments of the present application do not make specific limitations on the implementation manner of determining the fine-grained scene information according to the cup data and the user data.

[0054] For example, part of the rules in the predetermined rule can include: if the location is an office, the mobile phone motion is static, the base is static for a long time, the state of the terminal device is unused, and the keyboard sound is detected (if audio analysis is available), the target user can be in an office-concentrating work state, and the disturbability is low.

[0055] In the embodiments of the present application, since the cup data can better reflect the condition of the target user using the smart cup, and the user data of the target user can reflect the dynamic information such as the specific situation of the target user, therefore, according to the cup data and the user data, multi-source heterogeneous data can be integrated, the complex and dynamic scene in which the target user is located can be more accurately analyzed, and thus the state of the target user can be more accurately analyzed, and the fine-grained scene information with high accuracy can be obtained.

[0056] S104, determining a drinking water reminding strategy based on the fine-grained scene information, the drinking water reminding strategy including a target triggering time of the drinking water reminding.

[0057] Since the user can currently be in a state that does not want to be disturbed or temporarily does not need to drink water, etc., when determining the strategy of the water drinking reminder, the strategy of the water drinking reminder can be determined in combination with the fine-grained scene information, so as to fully consider the actual state of the target user, obtain a water drinking reminder strategy that matches the actual state of the user, and make the subsequent water drinking reminder to the target user based on the water drinking reminder strategy, which can better reduce the interference to the target user, and at the same time can better improve the probability of the target user drinking water after receiving the water drinking reminder, that is, improve the effectiveness of the water drinking reminder.

[0058] Optionally, when determining the water drinking reminder strategy based on the fine-grained scene information, the water drinking reminder strategy corresponding to the fine-grained scene information can be inferred based on a predetermined rule (supposedly called a second rule, which can reflect the mapping relationship between the fine-grained scene information and the water drinking reminder strategy), or the water drinking reminder strategy required can be determined by an intelligent algorithm such as a large model according to the fine-grained scene information. The embodiments of the present application do not make specific limitations on the way of determining the water drinking reminder strategy based on the fine-grained scene information.

[0059] In some embodiments, the water drinking reminder strategy can be determined based on the fine-grained scene information and a predetermined water drinking reminder suggestion; when the target user is reminded to drink water based on the water drinking reminder strategy, the water drinking reminder suggestion can be displayed through the terminal device of the target user or other ways. The water drinking reminder suggestion can include the amount of water drinking and the reason for drinking water, which can be calculated by an intelligent algorithm or obtained by user setting or input.

[0060] Optionally, the amount of water drinking in the water drinking reminder suggestion can be adjusted in combination with the fine-grained scene information, so that the final amount of water drinking is matched with the actual state of the target user, and the accuracy and effect of the water drinking reminder are improved.

[0061] In other embodiments, the water drinking reminder strategy can also include the reminding mode and / or the reminding intensity of the water drinking reminder. Optionally, the reminding mode can include one or more of visual, auditory, and tactile modes.

[0062] For example, assuming that the visual reminding is performed through light (such as an LED on a smart cup or a flashlight of the terminal device of the target user, etc.), at this time, different reminding intensities can be represented by different attributes of the light, such as the flicker frequency, color, or brightness; assuming that the auditory reminding is performed through a buzzer, at this time, different reminding intensities can be represented by different attributes of the buzzer, such as the frequency or volume; assuming that the tactile reminding is performed through the terminal device of the target user, at this time, different reminding intensities can be represented by different vibration intensities.

[0063] In some embodiments, the trigger duration difference value can be determined according to the noise level of the scene where the target user is located, the importance of the water drinking reminder, and the target trigger time in the water drinking reminder strategy and the expected trigger time set, and the reminding manner and / or reminding intensity of the water drinking reminder can be determined according to one or more of the noise level, the importance, and the trigger duration threshold.

[0064] As an example, the importance of the water drinking reminder can be analyzed according to the fine-grained scene information, and the reminding manner and / or reminding intensity of the water drinking reminder can be determined according to the importance and the trigger duration difference value.

[0065] As another example, the reminding manner and / or reminding intensity of the water drinking reminder can be determined according to the noise level and the ambient light level of the scene where the user is currently located. For example, in a dim scene, a soft breathing light reminder (such as a light reminder with a lower flicker frequency and a lower light brightness) can be used; in a noisy gym, a vibration reminder with a higher intensity (such as a higher vibration intensity or a higher vibration frequency) can be used.

[0066] S105, reminding the target user of drinking water based on the water drinking reminder strategy.

[0067] It should be understood that when reminding the target user of drinking water based on the water drinking reminder strategy, the water drinking reminder can be triggered to remind the target user to drink water when the target trigger time in the water drinking reminder strategy is reached.

[0068] In the embodiments of the present application, since the obtained cup data can reflect the usage status of the intelligent cup, and the obtained user data can reflect the information of the target user bound to the intelligent cup, the state of the target user can be accurately analyzed according to the cup data and the user data, fine-grained scene information with high accuracy can be obtained, and then the target trigger time of the water drinking reminder can be determined according to the fine-grained scene information, the water drinking reminder strategy can be obtained, and the target user can be reminded of drinking water based on the water drinking reminder strategy. The actual state of the target user can be fully considered, the water drinking reminder can be performed at the target trigger time that matches the actual state of the user, instead of a simple timing reminder, so that the interference on the target user can be effectively reduced, and the probability of the target user drinking water after receiving the water drinking reminder can be improved, that is, the user experience can be improved and the effectiveness of the water drinking reminder can be improved.

[0069] In some embodiments, the step S103 comprises:

[0070] The cup data and the user data are input into a trained prediction model to obtain fine-grained scene information output by the prediction model, the prediction model being trained according to samples including cup data and user data and fine-grained scene information labels, and being configured to analyze a state of the target user according to the cup data, an influence degree of the cup data on the state of the user, the user data, and an influence degree of the user data on the state of the user.

[0071] It should be understood that the influence degree of the cup data on the state of the user and the influence degree of the user data on the state of the user can be represented as a weight, which is a fixed weight learned in a training process of the prediction model or input by a user, or a weight dynamically determined by the prediction model based on a rule learned in the training process, or a weight dynamically adjusted by the prediction model according to the cup data and the user data input at present.

[0072] In some embodiments, weights corresponding to respective sub-data in the cup data and weights corresponding to respective sub-data in the user data are set, that is, the influence degrees of specific sub-data in each data on the state of the user are considered, so as to improve the accuracy of the state of the target user analyzed by more fine-grained analysis.

[0073] For example, when the prediction model detects that the user data contains "running" related data and the environmental data contains "high temperature" related data, the attention mechanism will automatically increase the weights corresponding to "heart rate" and "sweating rate estimation" in the user data, and decrease the weight corresponding to "static cup body" in the cup data. Conversely, when the user data indicates that the target user is in a "working" scene, the prediction model can increase the weights corresponding to "calendar events" in the user data and "cup body movement frequency" in the environmental data.

[0074] Optionally, the prediction model can be constructed based on a network structure of a recurrent neural network (RNN), a convolutional neural network (CNN), a long short-term memory (LSTM), or a Transformer.

[0075] It should be understood that when training the prediction model, the samples including the cup data and the user data can be input to the constructed prediction model, and after the prediction model analyzes the corresponding predicted fine-grained scene information according to the input cup data and user data, the model parameters of the prediction model can be optimized according to the difference between the predicted fine-grained scene information and the fine-grained scene information label, so as to obtain the trained prediction model.

[0076] In some embodiments, the prediction model can be deployed in the cloud; after the smart cup obtains the cup data and the user data, the cup data and the user data can be sent to the cloud, the cup data and the user data are input to the prediction model by the cloud, and the fine-grained scene information output by the prediction model is obtained and then sent to the smart cup. Alternatively, the cloud can determine the drinking water reminding strategy according to the fine-grained scene information, and directly send the drinking water reminding strategy to the smart cup, so that the smart cup only needs to remind the target user to drink water according to the received drinking water reminding strategy, without the need for data analysis and calculation, thereby effectively reducing the requirement for the computing power of the smart cup.

[0077] In some embodiments, the input of the prediction model can also include environmental data, which can be the environmental data of the scene where the smart cup is located and / or the environmental data of the scene where the user is located. Correspondingly, the prediction model is used to analyze the state of the target user according to the cup data, the user data, the environmental data, and the influence degree of each data on the state of the user.

[0078] In some embodiments, the prediction model can be a model based on an attention mechanism, which can include a hierarchical encoder, a cross-modal attention network, and an output network.

[0079] The hierarchical encoder can include a time series data encoder for encoding time series related data (such as smart cup usage data or user heart rate data, etc.), which can use a long short-term memory network or a gated recurrent unit to capture dynamic change patterns in time series; the hierarchical encoder can also include a static encoder for encoding static data or category data and other data.

[0080] It should be understood that the feature vectors obtained by each encoder can be used as the input of the cross-modal attention network, which can dynamically learn the influence degree (i.e., the weight) of each data on the state of the user based on the attention mechanism, so as to weight and fuse the feature vectors corresponding to each data according to the obtained weights, and obtain a multi-modal feature vector.

[0081] The output network is used to analyze the state of the target user and other required information according to the multi-modal feature vector output by the cross-modal attention network, and obtain the required fine-grained scene information.

[0082] In the embodiments of the present application, since the prediction model can learn the linear or nonlinear complex relationship between the cup data, the user data and the fine-grained scene information in the training process, the fine-grained scene information corresponding to the input cup data and user data can be quickly and accurately analyzed by the trained prediction model, which helps to improve the calculation efficiency and accuracy of the drinking water reminding.

[0083] In some embodiments, the fine-grained scene information is also used to reflect the fine-grained information of the scene where the target user is located. The cup data and the user data are input into the trained prediction model to obtain the fine-grained scene information output by the prediction model, which includes:

[0084] The cup data, the user data and the environment data are input into the prediction model to obtain the fine-grained scene information output by the prediction model. The environment data is used to reflect the environmental conditions of the scene where the target user is located. The prediction model is used to analyze the state of the target user according to the cup data, the user data, the environment data and the influence degree of each data on the state of the user, and analyze the fine-grained information of the scene where the target user is located.

[0085] It should be understood that the environment data includes but is not limited to indoor temperature, indoor humidity, outdoor temperature, outdoor humidity, ultraviolet index and weather data.

[0086] It should be understood that the environment data can be obtained by the corresponding sensors in the intelligent cup or the terminal device corresponding to the target user, or can be obtained by calling third-party services such as weather services, or can be obtained by the Internet of Things ecosystem (such as smart home system or smart building system) of the scene where the target user is located. The specific setting can be made according to the actual application requirements.

[0087] Fine-grained information generally refers to more detailed and accurate division and description of data or information, which can provide more specific and accurate details, distinguish subtle differences in data, and provide more semantic content, etc. For example, the fine-grained information of the scene where the target user is located includes but is not limited to the detailed information of the scene elements (such as the objects contained in the scene, the attributes of the objects, the states of the objects and the positional relationship between the objects, etc.), the detailed information of the scene behavior, the detailed information of the scene environment and the dynamic changes of the scene, etc.

[0088] In some embodiments, the fine-grained scene information can reflect fine-grained information of a current scene where the target user is located, and / or reflect fine-grained information of a future scene where the target user is located. It should be understood that when the fine-grained scene information is used to reflect the fine-grained information of the current scene where the target user is located, it is usually also used to reflect the current state of the target user; when the fine-grained scene information is used to reflect the fine-grained information of the future scene where the target user is located, it is usually also used to reflect the future state of the target user (i.e., the state of the target user in a future time period).

[0089] For example, assuming that the determined fine-grained scene information includes fine-grained information of a current scene and a current state of the target user, the fine-grained information of the current scene is that the office is less than 50 square meters, the space is compact, the noise level is lower than 40 decibels, and the target user is coding; the current state of the user is that the concentration level is high, the degree of disturbance is low, and the predicted fatigue level is medium.

[0090] For another example, assuming that the determined fine-grained scene information includes fine-grained information of a current scene and a current state of the target user, the fine-grained information of the current scene is that the conference room is less than 100 square meters and greater than 60 square meters, the noise level is between 40 decibels and 60 decibels, and the target user is making a presentation; the current state of the user is that the concentration level is high, the degree of disturbance is low, and the predicted fatigue level is low.

[0091] Optionally, when the fine-grained scene information is used to reflect fine-grained information of a future scene (i.e., a scene where the target user is located in a future time period) of the target user, the prediction model can predict the future scene of the target user according to the user data, analyze the fine-grained information of the future scene in combination with the features of the user data and the future scene, and analyze the state of the target user in the future scene in combination with the cup data and the user data.

[0092] It should be noted that when the prediction model analyzes the fine-grained information of the scene where the target user is located according to the cup data, the user data, and the environment data, the prediction model can analyze the fine-grained information in combination with the influence degree of each data on the state of the user (i.e., the weight corresponding to each data), or directly analyze the fine-grained information according to each data, which can be set according to actual application requirements.

[0093] In the embodiments of the present application, the prediction model analyzes the fine-grained information of the scene where the user is located and the state of the user according to the cup data, the user data, and the environment data, and the prediction model can learn the linear or nonlinear complex relationship between the cup data, the user data, the environment data, and the fine-grained information of the scene where the user is located and the state of the user in the training process. Therefore, through the trained prediction model, the required fine-grained scene information can be quickly and accurately analyzed, which helps to improve the calculation efficiency and accuracy of the water drinking reminder.

[0094] In some embodiments, before step S104, the method further comprises:

[0095] obtaining response data, the response data being used to reflect a response of the target user to the historical water drinking reminders;

[0096] constructing a fine-tuning sample based on the response data, a water drinking reminder strategy corresponding to the response data, and the fine-grained scene information;

[0097] fine-tuning the strategy model using the fine-tuning sample to obtain a fine-tuned strategy model, the strategy model being trained according to fine-grained scene information samples and water drinking reminder strategy labels.

[0098] Correspondingly, step S104 comprises:

[0099] inputting the fine-grained scene information into the fine-tuned strategy model to obtain the water drinking reminder strategy output by the strategy model

[0100] In some embodiments, the response data is also used to reflect feedback (i.e. evaluation) of the target user to the water drinking reminders.

[0101] In some embodiments, the response data of the target user can be obtained and the fine-tuning sample can be constructed based on a set fine-tuning frequency (e.g. every day) to fine-tune the strategy model in the smart water cup. It should be understood that the response data obtained at this time is usually the response data after the previous fine-tuning of the strategy model.

[0102] In the embodiments of the present application, the fine-tuning sample is constructed based on the response data of the target user, the water drinking reminder strategy corresponding to the response data, and the fine-grained scene information, and the strategy model is fine-tuned, so that the target user can gradually optimize the strategy model in the process of using the smart water cup, so that the water drinking reminder strategy obtained by the smart water cup according to the fine-grained scene information corresponding to the target user when determining the water drinking reminder strategy is more and more close to the preference of the target user, and the personalized water drinking reminder is realized while reducing the interference of the water drinking reminder on the user and improving the reliability of the water drinking reminder.

[0103] In some embodiments, the strategy model comprises a strategy network and a selection network, and step S104 comprises:

[0104] inputting the fine-grained scene information into the strategy network to obtain an executable strategy output by the strategy network and selection information, the selection information comprising a value and / or a probability of the executable strategy, the strategy network being used to determine a corresponding executable strategy according to the fine-grained scene information and analyze the value and / or the probability of the executable strategy.

[0105] The executable strategy and the selection information are input into the selection network, and the drinking water reminding strategy output by the selection network is obtained, and the selection network is used to determine the drinking water reminding strategy from the executable strategy according to the selection information.

[0106] The executable strategy generally refers to an executable drinking water reminding strategy (that is, a feasible drinking water reminding strategy), and the value of the executable strategy generally refers to an expected reward after the executable strategy is taken; and the probability of the executable strategy generally refers to the probability that the executable strategy is selected.

[0107] It should be understood that the selection information of the executable strategy can be used to guide the selection of the drinking water reminding strategy, and the information included in the selection information can be set according to actual application requirements.

[0108] It should be understood that when the selection network determines the drinking water reminding strategy from the executable strategies output by the strategy network according to the selection information, the executable strategy with the highest probability can be determined as the drinking water reminding strategy, or the executable strategy with the highest value can be determined as the drinking water reminding strategy, or the drinking water reminding strategy can be determined from the executable strategies in combination with user demand and selection information, and the specific implementation can be set according to actual application requirements, which is not limited in the embodiments of the present application.

[0109] Optionally, the strategy network can be constructed based on a network structure such as a recurrent neural network, a convolutional neural network or a Transformer, and the network structure of the strategy network is not limited in the embodiments of the present application.

[0110] In some embodiments, the strategy network can be trained based on a reinforcement learning algorithm (RL). The reinforcement learning algorithm is a machine learning method for learning an optimal decision strategy through interaction between an agent and an environment. Training the strategy network based on the reinforcement learning algorithm can enable the strategy network to directly learn, under given information (that is, fine-grained scene information), which reminding strategy (when to trigger a reminder and which reminding method, etc.) can maximize long-term user goals (such as drinking water compliance rate, user satisfaction or low neglect rate, etc.), thereby helping to make an optimal drinking water reminding strategy.

[0111] Among them, the reward function can be designed to reflect the expected water reminder strategy. For example, if the target user drinks water within a short time (such as 1 minute) after the water reminder, a higher reward (such as +100) can be given; if the target user ignores (does not drink water for a long time, such as 30 minutes) after the water reminder, a medium penalty (such as -50) can be given; if the target user gives a positive evaluation (such as a high score) to the water reminder, an additional reward (such as +50) can be given; if the target user gives a negative evaluation (such as a low score) to the water reminder, an additional penalty (such as -50) can be given; if the target user achieves the water target for the day, a periodic reward (such as +20) can be given; if the target trigger time of the water reminder is the time when the target user does not want to be disturbed (such as the time when the target user is in high concentration), a fixed penalty (such as -20) can be given regardless of whether the target user drinks water or not, so as to avoid disturbing the target user as much as possible when determining the water reminder strategy, and determine a water reminder strategy with lower interference to the target user. In the above processing, the decision is continuously optimized through interaction with the target user and the reward signal obtained, so as to better adapt to the preferences and behavior patterns of the target user, and effectively improve the accuracy and effectiveness of the water reminder.

[0112] In the embodiments of the present application, the executable strategy and the corresponding selection information are first determined through the strategy network, and then the final adopted water reminder strategy is determined from the executable strategy based on the selection information through the selection network, so that when determining the final water reminder strategy, the water reminder strategy matched with the target user can be determined by fully combining the actual demand, which helps to improve the accuracy and effectiveness of the determined water reminder strategy.

[0113] In some embodiments, the above fine-grained scene information is used to reflect the state of the above target user in a set future time period, and the determination of the water reminder strategy based on the above fine-grained scene information comprises:

[0114] In the case where it is determined according to the above fine-grained scene information that the target user cannot receive the water reminder at the set expected trigger time, the water reminder strategy is determined based on the expected trigger time and the fine-grained scene information, and the expected trigger time is a time within the future time period.

[0115] In the embodiments of the present application, the intelligent water cup has a predetermined water reminder suggestion, which can include an expected trigger time. Generally, the intelligent water cup will remind the target user to drink water based on the water reminder suggestion when the expected trigger time is reached.

[0116] In other embodiments, the expected trigger time can be any time within a set expected trigger time period.

[0117] For example, the predetermined drinking water reminding suggestion can be: expected triggering time period: 14:00-14:15, recommended amount: 150 ml, and recommended reason: maintaining afternoon energy.

[0118] However, to avoid directly reminding the target user to drink water at the expected triggering time and causing disturbance to the target user, the smart cup can obtain the cup data and the user data of the target user before a second preset time length (e.g., 30 minutes) to the expected triggering time, analyze the state of the target user in a future time period including the expected triggering time, and obtain fine-grained scene information reflecting the state of the target user in the future time period.

[0119] If it is determined according to the fine-grained scene information that the target user cannot receive the drinking water reminding at the expected triggering time, a time earlier than the expected triggering time and at which the target user can receive the drinking water reminding can be determined as the target triggering time, or a time later than the expected triggering time and at which the target user can receive the drinking water reminding can be determined as the target triggering time, so as to ensure that the target user is reminded to drink water on the basis of avoiding causing disturbance to the target user and improve the effectiveness of the drinking water reminding.

[0120] It should be understood that if it is determined according to the fine-grained scene information that the target user can receive the drinking water reminding at the expected triggering time, the expected triggering time can be taken as the target triggering time, and other information in the drinking water reminding strategy can be determined based on the fine-grained scene information.

[0121] In the embodiments of the present application, since the fine-grained scene information can reflect the state of the target user in a future time period including the expected triggering time, it can be better determined according to the fine-grained scene information whether the target user will be disturbed by the drinking water reminding at the expected triggering time, so that in the case where it is determined that the target user cannot be reminded to drink water at the expected triggering time, the triggering time is advanced or delayed in combination with the expected triggering time and the fine-grained scene information to obtain a drinking water reminding strategy including the target triggering time, so that the target user will not be disturbed when the target user is reminded to drink water based on the drinking water reminding strategy, and the user experience is ensured and the effectiveness of the drinking water reminding is improved.

[0122] Figure 2 A flowchart of another drinking water reminding method provided by some embodiments is shown. Referring to FIG. 6, the method includes the following steps. Figure 2 The step S105 includes:

[0123] In the case where the target triggering time is reached and the target user meets the predetermined triggering condition, the target user is reminded to drink water based on the drinking water reminding strategy.

[0124] The aforementioned triggering conditions can be obtained through user input or settings, or they can be calculated by intelligent algorithms such as large models based on information such as the target user's drinking preferences.

[0125] As an example, the trigger condition could be that the target user's real-time level of focus meets the focus requirement. For example, the trigger condition could be that the target user's current level of focus is low or medium.

[0126] As another example, the trigger condition could be that the target user's rest time after engaging in a set high-intensity activity reaches a time threshold (such as 2 minutes).

[0127] If the target user meets the triggering conditions, a drinking reminder can be triggered directly to remind the target user to drink water.

[0128] Reference Figure 2 If the target user does not meet the set trigger conditions, the water drinking reminder can be triggered only when the target user meets the trigger conditions.

[0129] In other embodiments, if the target user does not meet the triggering conditions, the current water cup data of the smart water cup and the user data of the target user can be obtained to redetermine the fine-grained scene information, redetermine the drinking reminder strategy based on the latest fine-grained scene information, and make drinking reminders based on the latest drinking reminder strategy.

[0130] In some embodiments, when the target trigger time is reached and the target user meets the predetermined trigger conditions, it can be determined whether the reminder method and / or reminder intensity need to be adjusted based on whether the target user's real-time status matches the reminder method and / or reminder intensity in the drinking water reminder strategy; if it is determined that the reminder method and / or reminder intensity need to be adjusted, the reminder method and / or reminder intensity are adjusted in conjunction with the target user's real-time status to obtain the adjusted reminder method and / or reminder intensity; and the target user is reminded to drink water based on the adjusted reminder method and / or reminder intensity.

[0131] In other embodiments, it can also be determined whether the reminder method and / or reminder intensity need to be adjusted based on whether the target data (which may include one or more data such as the light level, noise level, and real-time status of the target user's current environment) matches the reminder method and / or reminder intensity in the drinking water reminder strategy. If it is determined that the reminder method and / or reminder intensity need to be adjusted, the reminder method and / or reminder intensity can be adjusted in combination with the light level and noise level of the target user's current environment to obtain the adjusted reminder method and / or reminder intensity. The target user is then reminded to drink water based on the adjusted reminder method and / or reminder intensity.

[0132] In this embodiment, when the target trigger time for the water drinking reminder is reached, it is first determined whether the target user meets the set trigger conditions. When the target user meets the trigger conditions, the water drinking reminder is then given to the target user. This avoids giving a water drinking reminder directly when the target user does not want to be disturbed or is not able to drink water immediately, thereby reducing the disturbance to the target user or avoiding adverse effects on the target user's health, improving the user experience, and enhancing the effectiveness and reliability of the water drinking reminder.

[0133] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each 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 application.

[0134] Example 2:

[0135] Corresponding to the drinking water reminder method described in the above embodiments, Figure 3 A structural block diagram of the drinking water reminder device provided in the embodiments of this application is shown. For ease of explanation, only the parts related to the embodiments of this application are shown.

[0136] Reference Figure 3 The device includes: a water cup data acquisition module 31, a user data acquisition module 32, a fine-grained scene information determination module 33, a strategy determination module 34, and a reminder module 35. Among them,

[0137] The water cup data acquisition module 31 is used to acquire water cup data from the smart water cup, which reflects the usage status of the smart water cup.

[0138] User data acquisition module 32 is used to acquire user data of target users, including users who have a binding relationship with the smart water cup.

[0139] The fine-grained scene information determination module 33 is used to determine fine-grained scene information based on the water cup data and the user data, and the fine-grained scene information is used to reflect the status of the target user.

[0140] The strategy determination module 34 is used to determine a drinking water reminder strategy based on the above-mentioned fine-grained scenario information. The drinking water reminder strategy includes the target trigger time for the drinking water reminder.

[0141] The reminder module 35 is used to remind the target user to drink water based on the above-mentioned drinking water reminder strategy.

[0142] In this embodiment, since the acquired water cup data reflects the usage status of the smart water cup and the acquired user data reflects the information of the target user bound to the smart water cup, the target user's status can be analyzed more accurately based on the water cup data and user data, resulting in highly accurate fine-grained scene information. Furthermore, the target trigger time for the drinking reminder is determined based on this fine-grained scene information, resulting in a drinking reminder strategy. Then, the drinking reminder strategy is used to remind the target user to drink water. This approach fully considers the target user's actual status, providing a drinking reminder at a target trigger time that matches the user's actual status, rather than a simple timed reminder. This effectively reduces interference with the target user and increases the probability of the target user drinking water after receiving the reminder, thus improving the user experience and the effectiveness of the drinking reminder.

[0143] In some embodiments, the fine-grained scene information determination module 33 includes:

[0144] The first model processing unit is used to input the water cup data and the user data into the trained prediction model to obtain the fine-grained scene information output by the prediction model. The prediction model is trained based on samples including water cup data and user data and fine-grained scene information labels. It is used to analyze the state of the target user based on the water cup data, the degree of influence of the water cup data on the user's state, the user data, and the degree of influence of the user data on the user's state.

[0145] In some embodiments, the fine-grained scene information is further used to reflect fine-grained information about the scene in which the target user is located, and the fine-grained scene information determination module 33 further includes:

[0146] The second model processing unit is used to input the water cup data, user data, and environmental data into the prediction model to obtain the fine-grained scene information output by the prediction model. The environmental data is used to reflect the environmental conditions of the scene in which the target user is located. The prediction model is used to analyze the state of the target user based on the water cup data, user data, environmental data, and the degree of influence of each data on the user's state, and to analyze the fine-grained information of the scene in which the target user is located.

[0147] In some embodiments, the above-mentioned drinking water reminder device further includes:

[0148] The response data acquisition module is used to acquire response data, which reflects the target user's response to historical drinking water reminders.

[0149] The sample construction module is used to construct fine-tuned samples based on the above response data, the above drinking water reminder strategy corresponding to the above response data, and the above fine-grained scenario information.

[0150] The fine-tuning module is used to fine-tune the strategy model using the aforementioned fine-tuning samples to obtain the fine-tuned strategy model. The strategy model is trained based on fine-grained scene information samples and drinking reminder strategy labels.

[0151] In some embodiments, the policy model described above includes a policy network and a selection network, and the policy determination module 34 includes:

[0152] An executable strategy determination unit is used to input the fine-grained scene information into the policy network to obtain the executable strategy and selection information output by the policy network. The selection information includes the value and / or probability of the executable strategy. The policy network is used to determine the corresponding executable strategy based on the fine-grained scene information and to analyze the value and / or probability of the executable strategy.

[0153] The strategy filtering unit is used to input the executable strategy and the selection information into the selection network to obtain the drinking water reminder strategy output by the selection network. The selection network is used to determine the drinking water reminder strategy from the executable strategy based on the selection information.

[0154] In some embodiments, the fine-grained scene information is used to reflect the state of the target user in a set future time period, and the strategy determination module 34 includes:

[0155] The strategy determination unit is used to determine the water reminder strategy based on the expected trigger time and the fine-grained scenario information when it is determined that the target user will not receive the water reminder at the set expected trigger time. The expected trigger time is the time within the future time period.

[0156] In some embodiments, the above-mentioned reminder module 35 includes:

[0157] The reminder unit is used to remind the target user to drink water based on the aforementioned water reminder strategy when the target trigger time is reached and the target user meets the predetermined trigger conditions.

[0158] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0159] Example 3:

[0160] Figure 4 This is a schematic diagram of the structure of a smart water cup provided in one embodiment of this application. Figure 4 As shown, the smart water cup 4 of this embodiment includes: at least one processor 40 ( Figure 4 The diagram shows only one processor, a memory 41, and a computer program 42 stored in the memory 41 and executable on the at least one processor 40, which, when executing the computer program 42, performs the steps in any of the above method embodiments.

[0161] Those skilled in the art will understand that Figure 4 This is merely an example of the structure of the smart water bottle 4 and does not constitute a limitation on the smart water bottle 4. It may include more or fewer parts than shown in the figure, or combine certain parts, or different parts, such as including a base and a cup body.

[0162] The processor 40 may be a Central Processing Unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0163] In some embodiments, the memory 41 may be an internal storage unit of the smart water cup 4, such as a hard drive or memory. In other embodiments, the memory 41 may be an external storage device of the smart water cup 4, such as a plug-in hard drive, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the smart water cup 4. Furthermore, the memory 41 may include both internal and external storage units of the smart water cup 4. The memory 41 is used to store the operating system, applications, bootloader, data, and other programs, such as the program code of the computer program. The memory 41 can also be used to temporarily store data that has been output or will be output.

[0164] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0165] This application also provides a network device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the steps in any of the above method embodiments.

[0166] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, can implement the steps in the above-described method embodiments.

[0167] This application provides a computer program product that, when run on a smart water bottle, enables the smart water bottle to implement the steps described in the above-described method embodiments.

[0168] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying the computer program code to a camera / smart water bottle, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunication signals.

[0169] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0170] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0171] In the embodiments provided in this application, it should be understood that the disclosed apparatus / network devices and methods can be implemented in other ways. For example, the apparatus / network device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0172] The units described as separate components may or may not be physically separate. 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 embodiment according to actual needs.

[0173] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for reminding people to drink water, characterized in that, include: Acquire water cup data from the smart water cup, the water cup data being used to reflect the usage status of the smart water cup; Acquire user data of target users, including users who have a binding relationship with the smart water bottle; Fine-grained scene information is determined based on the water cup data and the user data, and the fine-grained scene information is used to reflect the state of the target user; A drinking water reminder strategy is determined based on the fine-grained scene information, and the drinking water reminder strategy includes the target trigger time for the drinking water reminder; The target user is reminded to drink water based on the aforementioned water reminder strategy.

2. The drinking water reminder method as described in claim 1, characterized in that, The step of determining fine-grained scene information based on the water cup data and the user data includes: The water cup data and the user data are input into a trained prediction model to obtain the fine-grained scene information output by the prediction model. The prediction model is trained based on samples including water cup data and user data, as well as fine-grained scene information labels. It is used to analyze the state of the target user based on the water cup data, the degree of influence of the water cup data on the user's state, the user data, and the degree of influence of the user data on the user's state.

3. The drinking water reminder method as described in claim 2, characterized in that, The fine-grained scene information is also used to reflect the fine-grained information of the scene in which the target user is located. The step of inputting the water cup data and the user data into a trained prediction model to obtain the fine-grained scene information output by the prediction model includes: The water cup data, user data, and environmental data are input into the prediction model to obtain the fine-grained scene information output by the prediction model. The environmental data is used to reflect the environmental conditions of the scene in which the target user is located. The prediction model is used to analyze the state of the target user based on the water cup data, user data, environmental data, and the degree of influence of each data on the user's state, and to analyze the fine-grained information of the scene in which the target user is located.

4. The drinking water reminder method as described in claim 1, characterized in that, The fine-grained scene information is used to reflect the state of the target user in a set future time period. The step of determining a hydration reminder strategy based on the fine-grained scene information includes: If it is determined, based on the fine-grained scene information, that the target user cannot receive a water reminder at the set expected trigger time, the water reminder strategy is determined based on the expected trigger time and the fine-grained scene information, wherein the expected trigger time is a time within the future time period.

5. The drinking water reminder method as described in claim 1, characterized in that, Before determining the drinking water reminder strategy based on the fine-grained scene information, the method further includes: Acquire response data, which is used to reflect the target user's response status to historical drinking water reminders; A fine-tuning sample is constructed based on the response data, the drinking water reminder strategy corresponding to the response data, and the fine-grained scene information; The strategy model is fine-tuned using the fine-tuning samples to obtain the fine-tuned strategy model, which is trained based on fine-grained scene information samples and drinking reminder strategy labels. Correspondingly, determining the drinking water reminder strategy based on the fine-grained scene information includes: The fine-grained scene information is input into the finely tuned strategy model to obtain the drinking water reminder strategy output by the strategy model.

6. The drinking water reminder method as described in claim 5, characterized in that, The strategy model includes a strategy network and a selection network. The step of inputting the fine-grained scene information into the finely tuned strategy model to obtain the drinking reminder strategy output by the strategy model includes: The fine-grained scene information is input into the policy network to obtain the executable policy and selection information output by the policy network. The selection information includes the value and / or probability of the executable policy. The policy network is used to determine the corresponding executable policy based on the fine-grained scene information and to analyze the value and / or probability of the executable policy. The executable strategy and the selection information are input into the selection network to obtain the drinking water reminder strategy output by the selection network. The selection network is used to determine the drinking water reminder strategy from the executable strategy based on the selection information.

7. The drinking water reminder method according to any one of claims 1 to 6, characterized in that, The step of reminding the target user to drink water based on the water drinking reminder strategy includes: When the target trigger time is reached and the target user meets the predetermined trigger conditions, the target user is reminded to drink water based on the water drinking reminder strategy.

8. A drinking water reminder device, characterized in that, include: A water cup data acquisition module is used to acquire water cup data from a smart water cup, which reflects the usage status of the smart water cup. The user data acquisition module is used to acquire user data of target users, including users who have a binding relationship with the smart water cup. The fine-grained scene information determination module is used to determine fine-grained scene information based on the water cup data and the user data, wherein the fine-grained scene information is used to reflect the state of the target user; The strategy determination module is used to determine a drinking water reminder strategy based on the fine-grained scene information, wherein the drinking water reminder strategy includes the target trigger time for the drinking water reminder; The reminder module is used to remind the target user to drink water based on the water drinking reminder strategy.

9. A smart water cup, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method as described in any one of claims 1 to 7.

10. A computer program product, characterized in that, When the computer program product is run on the smart water bottle, it causes the smart water bottle to perform the method as described in any one of claims 1 to 7.

Images