Automatic reminder method, device and terminal based on behavior statistics

Abstract

The present invention discloses an automatic reminder method, device and terminal based on behavior statistics, including: based on the behavior monitoring function of a smart terminal such as a television, some behaviors can be preset in advance, such as the user's action of taking medicine, the user's action of feeding, etc. When the user is watching a movie on the smart terminal, such as in front of the TV, the action is captured and the time is recorded. When the user performs the same behavior in a certain period of time for a cumulative number of n days, the behavior is marked as an automatic reminder, and then the user is reminded to perform the behavior in the same period of time every subsequent day. The present invention uses a smart terminal to add a new function: it has the function of automatically setting reminders according to user behavior, realizes statistics based on user behavior recognition, and automatically generates timed reminders without the user having to set them by themselves, which provides convenience for users.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent terminals, and in particular to an automatic reminder method, device, intelligent terminal and storage medium based on behavior statistics. Background Art

[0002] With the development of science and technology and the continuous improvement of people's living standards, the use of various smart terminals such as smart TVs and smart phones is becoming more and more popular, and smart terminals have become an indispensable tool for people.

[0003] Smart terminals in the prior art, such as smart TVs, have more and more functions, for example, an alarm reminder function is also one of the functions; however, the reminder function of smart terminals in the prior art requires users to actively set a specific reminder time, and sometimes users forget to set it, which easily leads to forgetfulness and is not easy to help users.

[0004] Therefore, the existing technology still needs to be improved and developed. Summary of the invention

[0005] The technical problem to be solved by the present invention is that, in view of the problems and defects of the above-mentioned prior art, an automatic reminder method, device, intelligent terminal and storage medium based on behavior statistics are provided. The present invention provides friendly reminders for some daily necessary matters, such as taking medicine every day, which is sometimes easy to forget. At this time, the present invention can automatically generate reminders to remind the user that it is time to take the medicine, which provides convenience for the user.

[0006] The technical solution adopted by the present invention to solve the problem is as follows: An automatic reminder method based on behavior statistics, comprising: Through the camera installed on the smart terminal, the user's daily behavior actions are captured and the time when the daily behavior actions occur is recorded; Automatically conduct statistical analysis on the captured daily behaviors of users and the time when the recorded daily behaviors occur, and analyze whether the same user performs the same behavior operation continuously in the same period of time in a certain cycle; When statistics show that the same user performs the same action continuously in the same period of time, the corresponding action and its corresponding occurrence time are automatically marked as automatic reminder events; Automatic control automatically reminds the corresponding user to perform the corresponding action during the same period of the subsequent cycle time.

[0007] The automatic reminder method based on behavior statistics, wherein the step of capturing the user's daily behavior actions and recording the time when the daily behavior actions occur by means of a camera installed on the smart terminal, comprises: Behavior actions are preset in the smart terminal in advance, wherein the preset behavior actions include user aerobics actions, user medicine taking actions, user breastfeeding actions, user reading actions and / or user sleeping actions.

[0008] The automatic reminder method based on behavior statistics, wherein before the step of capturing the user's daily behavior actions through a camera installed on the smart terminal and recording the time when the daily behavior actions occur, it also includes: Establishing a neural network model in advance; The preset behavior actions of the user's aerobics movements, the user's medicine-taking movements, the user's breastfeeding movements, the user's reading movements and / or the user's sleeping movements are respectively input into the neural network model for training and recognition, so as to obtain a trained user behavior action recognition network model.

[0009] The automatic reminder method based on behavior statistics, wherein the step of automatically performing statistical analysis on the captured daily behavior actions of the user and the time when the recorded daily behavior actions occur, and analyzing whether the same user continuously performs the same behavior operation in the same period of a certain cycle time, includes: Automatically conduct statistical analysis on the captured daily behaviors of users and the time when the recorded daily behaviors occur, and identify the action names corresponding to the daily behaviors of users; Determine whether the action name corresponding to the recognized daily action of the user includes the preset action; When the action name corresponding to the recognized daily action of the user includes the preset action, further analyzing whether the daily action of the current user that meets the preset action occurs in the same period for N days cumulatively; wherein N is greater than or equal to 3; When the daily behavior actions of the current user that meet the preset behavior actions occur in the same time period for N consecutive days, it is determined that the same user has continuously performed the same behavior operation in the same time period of a certain period of time.

[0010] The automatic reminder method based on behavior statistics, wherein the step of automatically marking the corresponding behavior action and its corresponding occurrence time as an automatic reminder event when statistics show that the same user continuously performs the same behavior operation in the same period of a certain cycle time includes: When it is determined that the same user continuously performs the same behavioral operation at the same time period in a certain cycle time, the corresponding behavioral action and its corresponding occurrence time are automatically marked as automatic reminder events; and the action name and corresponding occurrence time of the corresponding behavioral action are obtained, and a timing instruction is automatically generated. The automatic reminder method based on behavior statistics, wherein the step of automatically controlling the corresponding user to perform the corresponding behavior action in the same period of the subsequent cycle time includes: According to the generated timing instruction, the automatic control automatically reminds the corresponding user to perform the corresponding action in the same period of the subsequent cycle time.

[0011] The automatic reminder method based on behavior statistics, wherein the step of automatically performing statistical analysis on the captured daily behavior actions of the user and the time when the recorded daily behavior actions occur, and analyzing whether the same user continuously performs the same behavior operation in the same period of a certain cycle time, further includes: Obtain the captured daily behaviors of users and the time when the daily behaviors occur; The captured daily behaviors of users are input into the trained user behavior recognition network model; The trained user behavior action recognition network model is used to identify the action names corresponding to the user's daily behavior actions, and whether there are preset behavior actions such as user aerobics actions, user medicine taking actions, user breastfeeding actions, user reading actions and / or user sleeping actions.

[0012] An automatic reminder device based on behavior statistics, wherein the device comprises: A preset action module, used to preset action in the smart terminal, wherein the preset action includes an action of a user doing aerobics, an action of a user taking medicine, an action of a user feeding a baby, an action of a user reading a book and / or an action of a user sleeping; The daily behavior capture module is used to capture the user's daily behavior through the camera installed on the smart terminal and record the time when the daily behavior occurs; The behavior action statistical analysis module is used to automatically perform statistical analysis on the captured daily behavior actions of users and the time when the recorded daily behavior actions occur, and analyze whether the same user performs the same behavior operation continuously in the same period of a certain cycle time; The automatic reminder setting module is used to automatically mark the corresponding behavior and its corresponding occurrence time as an automatic reminder event when statistics show that the same user performs the same behavior operation continuously in the same period of a certain period of time; The automatic reminder module is used to automatically control the corresponding user to perform the corresponding behavior action in the same period of the subsequent cycle time.

[0013] An intelligent terminal includes a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors, including the method for executing any one of the methods described above.

[0014] A computer-readable storage medium, wherein when instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute any one of the methods described above.

[0015] Beneficial effects of the present invention: The present invention provides an automatic reminder method, device, smart terminal and storage medium based on behavior statistics. The present invention is based on the behavior monitoring function of smart terminals such as televisions, and can preset some behaviors in advance, such as the user's action of taking medicine, the user's action of feeding, etc. When the user is watching a movie on the smart terminal, such as in front of the TV, the action is captured and the time is recorded. When the user performs the same behavior in a certain period of time for a cumulative n days, the behavior is marked as an automatic reminder, and then the user is reminded to perform the behavior in the same period of time every subsequent day. The present invention uses a smart terminal to add a new function: it has the function of automatically setting reminders according to user behavior, realizes statistics based on user behavior recognition, and automatically generates timed reminders without the user having to set it himself, which provides convenience for users. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 It is a flowchart of the automatic reminder method based on behavior statistics provided in Example 1 of the present invention.

[0018] Figure 2 It is a flowchart of the automatic reminder method based on behavior statistics provided in Example 2 of the present invention.

[0019] Figure 3 It is a flowchart of the automatic reminder method based on behavior statistics provided in Example 3 of the present invention.

[0020] Figure 4 A principle block diagram of an embodiment of an automatic reminder device based on behavior statistics provided by the present invention.

[0021] Figure 5 It is a block diagram of the internal structure principle of the intelligent terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solution and advantages of the present invention clearer and more specific, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0023] It should be noted that if the embodiments of the present invention involve directional indications (such as up, down, left, right, front, back, etc.), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0024] Smart terminals in the prior art, such as smart TVs, have more and more functions, for example, an alarm reminder function is also one of the functions; however, the reminder function of smart terminals in the prior art requires users to actively set the specific time of the reminder. Sometimes users forget to set it, which is easy to cause forgetfulness and is not easy to help users.

[0025] like Figure 1 As shown, an automatic reminder method based on behavior statistics in embodiment 1 of the present invention includes the following steps: Step S100: Capture the user's daily behavior and actions through a camera installed on the smart terminal and record the time when the daily behavior and actions occur; In the embodiment of the present invention, the smart terminal is described by taking a smart TV as an example, and a camera is integrated or attached to the smart TV, which can effectively capture various behaviors of the user when watching TV. This camera can be built-in or external.

[0026] When the user is in front of the smart TV, the camera is controlled to monitor the user's daily behavior through image recognition technology, such as capturing the user's aerobics movements, the user's medication movements, the user's breastfeeding movements, the user's reading movements and / or the user's sleeping movements.

[0027] In the embodiment of the present invention, after capturing the daily behavior of the user, the system will automatically record the specific time when each daily behavior occurs. These timestamps can help analyze whether the specific time of occurrence of each daily behavior of the user is regular in the following steps.

[0028] Step S200: Automatically perform statistical analysis on the captured daily behaviors of the user and the time when the recorded daily behaviors occur, and analyze whether the same user continuously performs the same behavior operation in the same period of a certain cycle time; In this step, the captured user behavior data is obtained, including each user's behavior action and its corresponding timestamp. These data may include the user's specific behavior action data and the time when the specific action data occurs; The present invention then processes the collected data using statistical analysis methods to calculate the frequency of the user performing the same behavior within a specific time period (e.g., daily, weekly, or monthly). By analyzing this data, the system can identify whether the user repeats the same behavior within the same time period.

[0029] Through analysis, the present invention can identify the user's behavior pattern. For example, if a user always likes to do aerobics at 8 o'clock every evening, the present invention will record this behavior pattern.

[0030] For example, a user's smart TV system records the following behavior data: Behavior Record: Monday to Friday: Record user A taking medicine from 8 to 9 pm every day.

[0031] Saturday: From 8 to 10 pm, the user A’s aerobics behavior was captured.

[0032] Sunday: Capture user A doing reading activity from 3pm to 5pm.

[0033] After statistical analysis, it was found that user A took medicine between 8 and 9 pm every day, and did aerobics between 8 and 10 pm on Saturdays.

[0034] It can be seen that the present invention facilitates the provision of more intelligent reminders in the following steps by identifying the user's behavior pattern. In addition, by capturing user behavior data, it is possible to understand the user's behavior habits and help the system optimize the user experience. For example, the system can automatically adjust the settings before the user's usual viewing time to ensure the best viewing environment (such as adjusting brightness, volume, etc.).

[0035] In addition, statistical analysis can help identify whether the user's lifestyle is healthy. If the system finds that the user sits still for a long time in certain time periods, it can issue a reminder to encourage the user to take appropriate rest and activities. And by analyzing the user's behavior pattern, the present invention can predict the user's future behavior. This predictive ability can help the system proactively provide services or information when the user needs it.

[0036] Step S300: when it is counted that the same user continuously performs the same action operation in the same period of a certain cycle time, the corresponding action and its corresponding occurrence time are automatically marked as automatic reminder events; In the embodiment of the present invention, the user's behavior data is continuously monitored by the smart TV system, and the time and type of each behavior are recorded. When the user repeats the same behavior in the same time period of a certain cycle time, the system of the present invention will record the behavior action data and the specific time of occurrence.

[0037] In the embodiment of the present invention, the system identifies the user's repeated behavior in the same time period of a certain period of time through statistical analysis. For example, if the user always takes medicine between 8 and 9 pm for several consecutive days, the system of the embodiment of the present invention will regard this behavior as a behavior that the user often takes.

[0038] Once such a repeated behavior is identified, the embodiment of the present invention will automatically mark the behavior and the time when it occurs as an "automatic reminder event". For example, it will automatically set as a reminder alarm, so that the next time the same time period comes, the user will be actively reminded to perform the behavior or provide relevant suggestions.

[0039] For example, a user's smart TV system detects the following behavior: User Conduct: Monday-Friday: Watch the news every night from 8 to 9 p.m.

[0040] Saturday: Movies from 8 to 10 p.m.

[0041] After statistical analysis, the present invention finds that the user always watches the news between 8 and 9 p.m. from Monday to Friday. Therefore, the television system of the embodiment of the present invention marks this behavior as an automatic reminder event.

[0042] The result of automatic reminder: At 7:50 p.m. from Monday to Friday, the system will automatically send a reminder: "You will watch the news at 8 o'clock, please be ready." In this way, users can prepare in advance to ensure that they will not miss the show.

[0043] If the system detects the user's habit of watching movies between 8 and 10 p.m. on Saturdays, the system can also send a reminder at 7:50 p.m. on Saturdays: "Your favorite movie is about to start at 8 p.m. tonight, get ready to watch it!".

[0044] In this way, smart TVs not only help users manage their time and improve the regularity of their lives, but also provide additional support in health management and personalized services.

[0045] In this way, in the embodiment of the present invention, through automatic reminders, users can better manage their time and avoid missing important activities or programs. For example, users can be reminded to watch their favorite programs on time, improving the regularity of life.

[0046] Embodiments of the present invention can also promote healthy habits. For example, if the system recognizes that the user has been sitting still for a long time within a certain period of time, the behavior can be marked as a reminder event to encourage the user to take regular breaks and activities, thereby promoting health.

[0047] The automatic reminder of the present invention can make the user experience more personalized and intelligent. For example, users can arrange their daily activities more conveniently by receiving reminders during their usual time periods. In addition, through the automatic reminders of the present invention, users do not need to think about what to do next all the time. The system will help them make decisions, thereby reducing decision fatigue.

[0048] Step S400: Automatically control to automatically remind the corresponding user to perform the corresponding action during the same period of the subsequent cycle time.

[0049] In the embodiment of the present invention, the system continuously monitors the user's behavior and identifies the same user's behavior actions of performing the same behavior operation continuously in the same period of a certain period of time. For example, the user takes medicine at 8 pm every Monday to Sunday.

[0050] Once the system recognizes this behavior pattern, it will automatically set a reminder in the same subsequent time period. The present invention will select a suitable reminder method according to the user's preference, such as a pop-up notification, a sound prompt or a mobile phone push notification, or an alarm reminder.

[0051] When the scheduled time arrives, the smart TV system of the embodiment of the present invention will actively send a reminder to the user to prompt them to perform the action. This reminder can be a simple text message or more interactive content, such as recommending related programs or activities.

[0052] For example, a user's smart TV system detects that user A takes medicine at 8 pm every Monday to Sunday. After analysis, the system sets the action of taking medicine at 8 pm every day as an automatic reminder event.

[0053] Thus, through the embodiment of the present invention, the smart TV system will send a reminder at 7:50 every evening: "Dear user A, don't forget to take medicine on time at 8 o'clock tonight, I wish you good health." This not only helps users prepare in advance, but also ensures that they will not forget to take medicine.

[0054] In addition, in the embodiment of the present invention, when user A watches a movie between 8 and 10 p.m. on the weekend, the system will also send a similar reminder at 7:50 p.m. on Saturday: "There is a movie you like at 8 p.m. tonight, please don't miss it!".

[0055] In this way, smart TVs not only help users maintain regular viewing habits, but also improve their quality of life, promote health management, reduce decision-making burdens, and make daily life more convenient and intelligent.

[0056] And the present invention also has the following benefits: 1) Enhance behavioral consistency: Through regular reminders, users can more easily maintain consistent behavioral habits. For example, regularly reminding users to exercise or watch their favorite shows can help them form a regular lifestyle. 2) Improve the quality of life: Automatic reminders can help users better arrange their daily activities, ensure that they do not miss important things, and improve the overall quality of life. 3) Promote health management: If the user's behavior involves health-related activities (such as exercise, taking medicine, etc.), the system's automatic reminders can effectively promote users to follow health plans and help them maintain good health. 4) Reduce the burden of decision-making: Users do not have to remember what they need to do all the time. The system's automatic reminders reduce their decision-making burden and make life easier and more efficient.

[0057] Furthermore, if Figure 2 As shown, an automatic reminder method based on behavior statistics in embodiment 2 of the present invention includes the following steps: S111. Preset behavioral actions in the smart terminal, wherein the preset behavioral actions include a user's aerobics action, a user's medicine-taking action, a user's breastfeeding action, a user's reading action, and / or a user's sleeping action.

[0058] In this specific embodiment, some preset behavior actions are set for the user in advance on the smart terminal, such as a smart TV, wherein the preset behavior actions include the user's aerobics action, the user's medicine-taking action, the user's breastfeeding action, the user's reading action and / or the user's sleeping action. The preset behavior actions can be used to further identify the user's daily behavior actions.

[0059] S112, automatically performing statistical analysis on the captured daily behaviors of the user and the time when the recorded daily behaviors occur, and identifying the action names corresponding to the daily behaviors of the user; In the embodiment of this step, a statistical analysis will be automatically performed on the captured daily behavior actions of the user and the time when the recorded daily behavior actions occur, and the action names corresponding to the user's daily behavior actions will be identified. For example, when the captured daily behavior actions of the user include jumping movements of the user, the action name that can be identified is aerobics action; when the captured daily behavior actions of the user include opening a medicine bottle or a medicine box to take medicine, the action name that can be identified is aerobics action as the user taking medicine action, etc.

[0060] S113, determining whether the action name corresponding to the identified daily action of the user includes the preset action; In this step, it is determined whether the action names corresponding to the identified daily actions of the user include the preset action, such as the user's aerobics action, the user's medicine-taking action, the user's breastfeeding action, the user's reading action and / or the user's sleeping action.

[0061] S114, when the action name corresponding to the recognized daily action of the user includes the preset action, further analyzing whether the daily action of the current user that meets the preset action occurs in the same period for N cumulative days; wherein N is greater than or equal to 3; For example, if the action name corresponding to the user's daily action is identified, such as the user's action of taking medicine, the user's action of feeding milk, etc., the user's daily action that meets the preset action is further analyzed to see whether the current user's daily action that meets the preset action occurs in the same period for N consecutive days (for example, 3 consecutive days). When the user is watching a movie in front of the TV, the action is captured and the time is recorded. When the user performs the same action for 3 consecutive days or more in a certain period, step S115 is entered.

[0062] S115. When the daily behavior of the current user that meets the preset behavior occurs in the same time period for N consecutive days, it is determined that the same user performs the same behavior operation continuously in the same time period of a certain period of time.

[0063] In this step, when the system monitors the daily behavior of the current user, it accumulates and observes the specific behavior actions of the user in the same period. If the user performs the same behavior (such as taking medicine) in the same time period (for example, from 8 to 9 pm every day) for N consecutive days, the system will determine that the behavior is a repeated behavior of the user and an automatic reminder needs to be set.

[0064] This step embodiment can identify the user's behavior habits through continuous monitoring and help the user understand his or her daily life pattern. In addition, the present invention makes judgments based on data to ensure that reminders and suggestions are targeted at the user's actual behavior, thereby increasing the effectiveness of intelligent services.

[0065] For example, if user A takes medicine between 8 and 9 pm every day in the past 7 days, the system will record this behavior and determine it as a repetitive behavior of the user and an automatic reminder needs to be set.

[0066] S116. When it is determined that the same user continuously performs the same action operation in the same period of a certain cycle time, the corresponding action and its corresponding occurrence time are automatically marked as automatic reminder events; and the action name and corresponding occurrence time of the corresponding action are obtained, and a timing instruction is automatically generated. In this step embodiment, once the system determines that the user has repeated behavior within a specific period, it will automatically mark the behavior and its occurrence time as an automatic reminder event. At the same time, it will obtain the name and occurrence time of the behavior and generate a corresponding timing instruction. That is, the present invention will create a reminder mechanism for the user's behavior at this time.

[0067] For example, if the system finds that the user takes medicine at 8 o'clock every night, it will mark this behavior as an automatic reminder event and record the action name and time of "taking medicine". Then, the system will generate a timer instruction to automatically remind the user at the corresponding time in the future.

[0068] In this way, the present invention can achieve automatic reminders, and users do not need to manually set reminders. The system will automatically generate reminders for them, thereby improving user experience. In addition, the present invention can provide personalized reminders based on the user's behavioral habits to help users maintain a regular lifestyle.

[0069] S117. According to the generated timing instruction, automatically control to automatically remind the corresponding user to perform the corresponding action in the same period of the subsequent cycle time.

[0070] In this step, according to the generated timing instruction, a reminder is automatically sent to the user in the same period of the subsequent cycle to prompt them to perform the previously recorded behavior. For example, the smart TV system of the present invention will send a notification at the user's usual time to remind them to perform the behavior.

[0071] The invention provides the advantage that the timed reminder helps the user maintain consistent behavior habits and promotes a healthy lifestyle. Moreover, through the automatic reminder, the user can better arrange his time and ensure that he will not miss important activities or programs.

[0072] For example, when the user's behavior is recorded as taking medicine at 8 o'clock every night, the present invention will automatically send a reminder at 7:50 p.m. on every weekday: "Take medicine on time at 8 o'clock tonight, please pay attention to health and wellness." In this way, the user can prepare in advance and will not miss the time to take medicine.

[0073] It can be seen that the smart TV system of the embodiment of the present invention can effectively identify the user's behavior pattern, automatically generate reminder events, and send reminders to the user at an appropriate time. This not only improves the user experience, but also helps them develop good living habits, optimize time management, and enhance the regularity of life.

[0074] In another embodiment, the automatic reminder method based on behavior statistics described in the embodiment of the present invention, wherein, before the step of capturing the user's daily behavior actions through a camera installed on the smart terminal and recording the time when the daily behavior actions occur, it also includes: S211, pre-establishing a neural network model; That is, in the specific implementation of the present invention, a neural network model can be created as the basis for user behavior recognition. This model will be used to analyze and identify various user behaviors. A neural network is a computational model that simulates the connection of neurons in the human brain and can perform pattern recognition by learning a large amount of data.

[0075] Neural networks are able to process complex data patterns and are suitable for behavior recognition tasks. Once established, the model can be adjusted and optimized based on new data to improve recognition accuracy.

[0076] S212, inputting preset behavior actions of a user's aerobics, a user's medicine-taking, a user's breastfeeding, a user's reading, and / or a user's sleeping into the neural network model for training and recognition, to obtain a trained user behavior action recognition network model; In this step, the preset user behavior actions (such as aerobics, taking medicine, feeding, reading, and sleeping) are input into the neural network model for training. By providing a large amount of labeled data, the model can learn to recognize the characteristics of these specific actions.

[0077] For example, there is a data set that contains video clips of users doing exercises, taking medicine, etc. This data can be input into a neural network for training, and the model optimizes recognition capabilities by continuously adjusting weights.

[0078] Through training in this step, the model can accurately identify different user behaviors and reduce the possibility of misjudgment. In addition, the model can adapt to the behavioral differences of different users and enhance its versatility.

[0079] S213, obtaining the captured daily behavior of the user and the time when the recorded daily behavior occurs; In this step, when the smart TV system is turned on, it will capture the user's daily behavior and record the specific time when these behaviors occur. This step is the process of data collection, which provides raw data for subsequent behavior identification.

[0080] For example, a smart TV system monitors the user's activities through a camera or sensor, and records the user's behavior data on a certain day, including the time of taking medicine, the length of time reading, etc. In this way, the present invention can capture the user's behavior in real time and ensure the timeliness of the data. It can also collect diverse behavior data to provide a more comprehensive training basis for the model.

[0081] S214, inputting the captured daily behavior of the user into the trained user behavior recognition network model; In this step embodiment, at this stage, the captured user daily behavior actions are input into the trained user behavior action recognition network model. The present invention uses the previously trained model to analyze new data.

[0082] For example, when user A has just finished aerobics, the smart TV system of the present invention will input this behavior data (e.g., time, action features) into the neural network model for recognition.

[0083] In this way, the present invention can realize automatic recognition and automatically process user behavior data without manual intervention. Moreover, through real-time recognition of the model, users can quickly obtain feedback and enhance the interactive experience.

[0084] S215, identifying the action names corresponding to the user's daily behavior actions through the trained user behavior action recognition network model, and whether there are preset behavior actions such as user aerobics actions, user medicine taking actions, user breastfeeding actions, user reading actions and / or user sleeping actions.

[0085] In the embodiment of this step, the trained user behavior action recognition network model analyzes the input daily behavior data, identifies the user's behavior action name, and determines whether it belongs to a preset behavior action (such as aerobics, taking medicine, feeding, reading, and sleeping).

[0086] For example, when a user sits down to read a book at 9 o'clock in the evening, the system recognizes this behavior as "reading a book" through the model and can provide the user with relevant reading suggestions or reminders based on this recognition result.

[0087] It can be seen that the present invention can accurately identify user behavior and reduce misjudgment through the deep learning ability of the model, and the recognition results can be used to provide personalized suggestions or reminders to improve user experience.

[0088] Through the above five steps, the smart TV system of this specific embodiment can effectively build and train a neural network model to capture the user's daily behavior and accurately identify the names of these behaviors. This not only improves the user experience, but also provides data support for personalized services and promotes health management and lifestyle improvements.

[0089] The present invention is further described in detail below through another specific application embodiment: like Figure 3 As shown, an automatic reminder method based on behavior statistics according to a specific application embodiment 3 of the present invention comprises the following steps: S31, start, and enter S32.

[0090] S32, pre-set preset behaviors in the smart TV, such as setting the user's medicine-taking action, the user's breastfeeding action, etc., and proceed to step S33 respectively.

[0091] S33. When the user is watching a movie in front of the TV, the user's behavior is captured and the time is recorded, and it is determined whether the captured user behavior has a preset behavior. If not, continue to capture the user's behavior. If yes, proceed to step S34.

[0092] S34: Whether the cumulative number of times is greater than N, if not, return to step S33, if yes, proceed to step S35.

[0093] That is, whether it is counted that the user has performed the same behavior in a certain period of time for a cumulative n days, if not, return to step S33, if yes, go to step S35.

[0094] S35, generate a timing instruction; and proceed to step S36.

[0095] S36, remind the user at the appointed time, and proceed to step S37.

[0096] S37, end the current process.

[0097] As can be seen from the above, the embodiment of the present invention provides an automatic reminder method based on behavior statistics, which uses a behavior monitoring function based on a television set, and can preset some behaviors in advance, such as the user's action of taking medicine, the user's action of feeding, etc. When the user is watching a movie in front of the TV, the action is captured and the time is recorded. When the user performs the same behavior in a certain period of time for a cumulative n days, the behavior is marked as an automatic reminder, and then the user is reminded to perform the behavior in the same period of time every subsequent day. The present invention can provide friendly reminders for some daily necessities, such as taking medicine every day, which is sometimes easy to forget to take. At this time, the present invention can automatically generate reminders to remind the user that it is time to take medicine. The present invention uses a smart terminal to add a new function: it has the function of automatically setting reminders according to user behavior, realizes statistics based on user behavior recognition, and automatically generates timed reminders without the user having to set it himself, which provides convenience for users.

[0098] Exemplary Devices like Figure 4 As shown, an embodiment of the present invention provides an automatic reminder device based on behavior statistics, the device comprising: A preset action module 310 is used to preset action in the smart terminal in advance, wherein the preset action includes an action of a user doing exercises, an action of a user taking medicine, an action of a user feeding a baby, an action of a user reading a book and / or an action of a user sleeping; The daily behavior capture module 320 is used to capture the user's daily behavior through a camera installed on the smart terminal and record the time when the daily behavior occurs; The behavior action statistical analysis module 330 is used to automatically perform statistical analysis on the captured daily behavior actions of the user and the time when the recorded daily behavior actions occur, and analyze whether the same user continuously performs the same behavior operation in the same period of a certain cycle time; The automatic reminder setting module 340 is used to automatically mark the corresponding behavior action and its corresponding occurrence time as an automatic reminder event when statistics show that the same user performs the same behavior operation continuously in the same period of a certain period of time; The automatic reminder module 350 is used to automatically control the automatic reminder of the corresponding user to perform the corresponding action in the same period of the subsequent cycle time, as described above.

[0099] Based on the above embodiments, the present invention further provides an intelligent terminal, whose principle block diagram can be shown as follows: Figure 5 As shown. The intelligent terminal includes a processor, a memory, a network interface, a display screen, and a database connected through a system bus. Among them, the processor of the intelligent terminal is used to provide computing and control capabilities. The memory of the intelligent terminal includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the intelligent terminal is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an automatic reminder method based on behavior statistics is implemented. The database of the intelligent terminal is used to store an automatic reminder program based on behavior statistics.

[0100] Those skilled in the art will understand that Figure 5 The principle block diagram shown in the figure is only a block diagram of a partial structure related to the scheme of the present invention, and does not constitute a limitation on the smart terminal to which the scheme of the present invention is applied. The specific smart terminal may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0101] In one embodiment, a smart terminal is provided, comprising a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors, and the one or more programs include instructions for performing the following operations: Through the camera installed on the smart terminal, the user's daily behavior actions are captured and the time when the daily behavior actions occur is recorded; Automatically conduct statistical analysis on the captured daily behaviors of users and the time when the recorded daily behaviors occur, and analyze whether the same user performs the same behavior operation continuously in the same period of time in a certain cycle; When statistics show that the same user performs the same action continuously in the same period of time, the corresponding action and its corresponding occurrence time are automatically marked as automatic reminder events; The automatic control automatically reminds the corresponding user to perform the corresponding action during the same period of the subsequent cycle time, as described above.

[0102] The step of capturing the user's daily actions and recording the time when the daily actions occur by using a camera installed on the smart terminal includes: Behavior actions are preset in the smart terminal in advance, wherein the preset behavior actions include user aerobics actions, user medicine taking actions, user breastfeeding actions, user reading actions and / or user sleeping actions.

[0103] Wherein, before the step of capturing the user's daily behavior actions and recording the time when the daily behavior actions occur through a camera installed on the smart terminal, the step further includes: Establishing a neural network model in advance; The preset behavior actions of the user's aerobics movements, the user's medicine-taking movements, the user's breastfeeding movements, the user's reading movements and / or the user's sleeping movements are respectively input into the neural network model for training and recognition, so as to obtain a trained user behavior action recognition network model.

[0104] The step of automatically performing statistical analysis on the captured daily behaviors of the user and the time when the recorded daily behaviors occur, and analyzing whether the same user continuously performs the same behavior operation in the same period of a certain cycle time includes: Automatically conduct statistical analysis on the captured daily behaviors of users and the time when the recorded daily behaviors occur, and identify the action names corresponding to the daily behaviors of users; Determine whether the action name corresponding to the recognized daily action of the user includes the preset action; When the action name corresponding to the recognized daily action of the user includes the preset action, further analyzing whether the daily action of the current user that meets the preset action occurs in the same period for N days cumulatively; wherein N is greater than or equal to 3; When the daily behavior actions of the current user that meet the preset behavior actions occur in the same time period for N consecutive days, it is determined that the same user has continuously performed the same behavior operation in the same time period of a certain period of time.

[0105] Wherein, when statistics show that the same user continuously performs the same action operation in the same period of a certain cycle time, the step of automatically marking the corresponding action and its corresponding occurrence time as an automatic reminder event includes: When it is determined that the same user continuously performs the same behavioral operation at the same time period in a certain cycle time, the corresponding behavioral action and its corresponding occurrence time are automatically marked as automatic reminder events; and the action name and corresponding occurrence time of the corresponding behavioral action are obtained, and a timing instruction is automatically generated. The step of automatically reminding the corresponding user to perform the corresponding action in the same period of the subsequent cycle time includes: According to the generated timing instruction, the automatic control automatically reminds the corresponding user to perform the corresponding action in the same period of the subsequent cycle time.

[0106] The step of automatically performing statistical analysis on the captured daily behaviors of the user and the time when the recorded daily behaviors occur, and analyzing whether the same user continuously performs the same behavior operation in the same period of a certain cycle time, further includes: Obtain the captured daily behaviors of users and the time when the daily behaviors occur; The captured daily behaviors of users are input into the trained user behavior recognition network model; The trained user behavior action recognition network model is used to identify the action names corresponding to the user's daily behavior actions, and whether there are preset behavior actions such as user aerobics actions, user medicine taking actions, user breastfeeding actions, user reading actions and / or user sleeping actions, as described above.

[0107] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0108] In summary, the present invention provides an automatic reminder method, device, smart terminal and storage medium based on behavior statistics. The present invention is based on the behavior monitoring function of smart terminals such as televisions, and can preset some behaviors in advance, such as the user's action of taking medicine, the user's action of feeding, etc. When the user is watching a movie on the smart terminal, such as in front of the TV, the action is captured and the time is recorded. When the user performs the same behavior in a certain period of time for n days, the behavior is marked as an automatic reminder, and then the user is reminded to perform the behavior in the same period of time every day. The present invention uses smart terminals to add new functions: it has the function of automatically setting reminders according to user behavior, realizes statistics based on user behavior recognition, and automatically generates timed reminders without the user having to set them by themselves, which provides convenience for users.

Claims

1. An automatic reminder method based on behavior statistics, characterized in that: include: Through the camera installed on the smart terminal, the user's daily behavior actions are captured and the time when the daily behavior actions occur is recorded; Automatically conduct statistical analysis on the captured daily behaviors of users and the time when the daily behaviors occur, and analyze whether the same user performs the same behavior operation continuously in the same period of time in a certain cycle; When statistics show that the same user performs the same action continuously in the same period of time, the corresponding action and its corresponding occurrence time are automatically marked as automatic reminder events; Automatic control automatically reminds the corresponding user to perform the corresponding action during the same period of the subsequent cycle time.

2. The automatic reminder method based on behavior statistics according to claim 1, characterized in that: The step of capturing the user's daily actions and recording the time when the daily actions occur by using a camera installed on the smart terminal includes: Behavior actions are preset in the smart terminal in advance, wherein the preset behavior actions include user aerobics actions, user medicine taking actions, user breastfeeding actions, user reading actions and / or user sleeping actions.

3. The automatic reminder method based on behavior statistics according to claim 1, characterized in that: The step of capturing the user's daily actions and recording the time when the daily actions occur by using a camera installed on the smart terminal also includes: Establishing a neural network model in advance; The preset behavior actions of the user's aerobics movements, the user's medicine-taking movements, the user's breastfeeding movements, the user's reading movements and / or the user's sleeping movements are respectively input into the neural network model for training and recognition, so as to obtain a trained user behavior action recognition network model.

4. The automatic reminder method based on behavior statistics according to claim 2, characterized in that: The step of automatically performing statistical analysis on the captured daily behaviors of the user and the time when the recorded daily behaviors occur, and analyzing whether the same user continuously performs the same behavior operation in the same period of a certain cycle time includes: Automatically conduct statistical analysis on the captured daily behaviors of users and the time when the recorded daily behaviors occur, and identify the action names corresponding to the daily behaviors of users; Determine whether the action name corresponding to the recognized daily action of the user includes the preset action; When the action name corresponding to the recognized daily action of the user includes the preset action, further analyzing whether the daily action of the current user that meets the preset action occurs in the same period for N days in total; wherein N is greater than or equal to 3; When the daily behavior actions of the current user that meet the preset behavior actions occur in the same time period for N cumulative days, it is determined that the same user has continuously performed the same behavior operation in the same time period of a certain cycle time.

5. The automatic reminder method based on behavior statistics according to claim 4 is characterized in that: When it is counted that the same user continuously performs the same action operation in the same period of a certain cycle time, the step of automatically marking the corresponding action and its corresponding occurrence time as an automatic reminder event includes: When it is determined that the same user continuously performs the same behavioral operation at the same time period in a certain cycle time, the corresponding behavioral action and its corresponding occurrence time are automatically marked as automatic reminder events; and the action name and corresponding occurrence time of the corresponding behavioral action are obtained, and a timing instruction is automatically generated.

6. The automatic reminder method based on behavior statistics according to claim 5, characterized in that: The step of automatically controlling the corresponding user to perform the corresponding action in the same period of the subsequent cycle time includes: According to the generated timing instruction, the automatic control automatically reminds the corresponding user to perform the corresponding action in the same period of the subsequent cycle time.

7. The automatic reminder method based on behavior statistics according to claim 3, characterized in that: After the step of automatically performing statistical analysis on the captured daily behaviors of the user and the time when the recorded daily behaviors occur, and analyzing whether the same user continuously performs the same behavior operation in the same period of a certain cycle time, the step further includes: Obtain the captured daily behaviors of users and the time when the daily behaviors occur; The captured daily behaviors of users are input into the trained user behavior recognition network model; The trained user behavior action recognition network model is used to identify the action names corresponding to the user's daily behavior actions, and whether there are preset behavior actions such as user aerobics actions, user medicine taking actions, user breastfeeding actions, user reading actions and / or user sleeping actions.

8. An automatic reminder device based on behavior statistics, characterized in that: The device comprises: A preset action module, used to preset action in the smart terminal in advance, wherein the preset action includes an action of a user doing aerobics, an action of a user taking medicine, an action of a user feeding a baby, an action of a user reading a book and / or an action of a user sleeping; The daily behavior capture module is used to capture the user's daily behavior through the camera installed on the smart terminal and record the time when the daily behavior occurs; The behavior action statistical analysis module is used to automatically perform statistical analysis on the captured daily behavior actions of users and the time when the recorded daily behavior actions occur, and analyze whether the same user performs the same behavior operation continuously in the same period of a certain cycle time; The automatic reminder setting module is used to automatically mark the corresponding behavior and its corresponding occurrence time as an automatic reminder event when statistics show that the same user performs the same behavior operation continuously in the same period of a certain period of time; The automatic reminder module is used to automatically control the corresponding user to perform the corresponding behavior action in the same period of the subsequent cycle time.

9. An intelligent terminal, characterized in that: The device comprises a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors, and the one or more programs include being used to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the method as described in any one of claims 1 to 7.

Images