CN113796717A

CN113796717A - Intelligent tea set based on reinforcement learning

Info

Publication number: CN113796717A
Application number: CN202111180414.3A
Authority: CN
Inventors: 熊作芒
Original assignee: Individual
Current assignee: Individual
Priority date: 2021-10-11
Filing date: 2021-10-11
Publication date: 2021-12-17

Abstract

The invention provides an intelligent tea set based on reinforcement Learning, wherein a tea bin cover, a tea bin, a tea storage cup and a base module form a conducting circuit through an electric contact to connect a sensor of the tea bin cover, an electric control valve of the tea bin and an electric heater of the tea storage cup to a power supply module and a circuit of a chip, the base module communicates with an APP end of an intelligent mobile phone through a Bluetooth protocol, a corresponding configuration file is selected according to the name of tea leaves, a two-dimensional code, a one-dimensional code and a number parameter on a tea bag, the configuration file stores the optimal soaking time of the tea leaves before each soup outlet, the chip communicates with the intelligent mobile phone through the Bluetooth to obtain the soaking time parameter corresponding to the current tea bag, the App on the intelligent mobile phone can mark the taste of the tea soup, the App is configured with a reinforcement Learning Q-Learning algorithm to calculate the next soaking time parameter after adjustment, and the number of marking is increased, the closer to the taste preference of the user, and the memory storage is performed. This intelligence tea set can carry out intelligent regulation and dash the bubble time, satisfies user's demand.

Description

Intelligent tea set based on reinforcement learning

Technical Field

The invention relates to the technical field of tea making appliances, in particular to an intelligent tea set based on reinforcement learning.

Background

Some tea sets capable of outputting soup by one key are available in the market, and most of the tea sets are realized based on mechanical structures. The user needs to press the key properly to realize the separation of the tea leaves and the tea water (commonly called soup).

The prior art has the following disadvantages:

1. the tea soaking time needs to be controlled manually, and the situation that a button is forgotten to be pressed easily occurs.

2. Insufficient precision in manual timing can lead to undesirable tea soup taste.

3. The optimal brewing parameters of each type of tea are different, and the tea cannot be accurately shared and spread.

Therefore, it is desirable to design an intelligent tea set based on reinforcement learning to solve the above-mentioned problems.

Disclosure of Invention

The invention aims to provide an intelligent tea set based on reinforcement learning, which can intelligently adjust brewing time and meet the requirements of users.

In order to achieve the purpose, the invention is realized by the following technical scheme: an intelligent tea set based on reinforcement learning comprises a tea bin cover, a tea bin, a tea storage cup, a base module, a sensor, an electric control valve, an electric heater, an electric contact, a filter screen, a tea outlet, a cup handle, a chip and a power supply module, wherein the tea bin cover is provided with the sensor for detecting whether the tea bin cover is closed, the detachable filter screen is arranged inside the tea bin, the bottom end of the tea bin is provided with a water outlet, the electric control valve is arranged on the water outlet, one side of the tea storage cup is fixedly provided with the cup handle, the tea bin is lapped at the opening at the top of the tea storage cup, the tea bin cover is matched and covered with the tea bin in a matching manner, the chip and the power supply module are arranged inside the base module, the bottom end of the tea bin cover, the top end of the tea bin, the top end of the cup handle, the bottom end of the cup handle and the top end of the base module are respectively provided with the electric contact to form a conduction circuit for connecting the sensor of the tea bin cover, the electric control valve of the tea bin cover and the electric control valve, The electric heater of the tea storage cup is connected to a circuit of the power supply module and the chip, the base module communicates with an APP end of the smart phone through a Bluetooth protocol to receive and send signals, meanwhile, a corresponding configuration file is selected according to tea names, two-dimensional codes, one-dimensional codes and digital number parameters on a tea bag, the optimal soaking time of tea before soup is discharged each time is stored in the configuration file, the chip communicates with the smart phone through Bluetooth to obtain the soaking time parameter corresponding to the current tea bag, the flavor of the tea soup each time can be marked in the App on the smart phone, the depth is too thick or too light, the App is configured with a reinforcement Learning Q-Learning algorithm to calculate the next soaking time parameter after adjustment, the more times of marking of a user are, the soaking time parameter is closer to the flavor of the user, and the memory parameter is stored in a preferential mode.

Preferably, a tea outlet is formed in one side of the tea storage cup.

Preferably, the electric heater is installed at the bottom end of the inner cavity of the tea storage cup.

Preferably, the tea bin cover, the tea bin, the tea storage cup and the base module are fixed together through a strong magnet or a buckle.

The invention provides an intelligent tea set based on reinforcement learning. The method has the following beneficial effects:

1. the soaking time control is more accurate and stable than manual work, and due to the time delay of human eye visual signal transmission (hundreds of milliseconds level) and muscle movement (hundreds of milliseconds level), the manual control is accurate to seconds at most. The soaking time is calculated by adopting a computer algorithm, the mechanical structure is controlled by an electric signal to realize the separation of tea and water, and the soaking time can be accurate to 10 milliseconds;

2. the digitalized brewing parameters can be conveniently transmitted and shared through the internet, a tea seller can configure preset brewing parameters for each type of tea, consumers can conveniently taste tea soup with the optimal flavor, different users can use the internet to quickly share and exchange brewing configuration, and the transmission and development of tea culture are promoted;

3. according to the invention, the intelligent tea set is controlled by the intelligent mobile phone, the feedback of the user on the tea soup is collected, the brewing time is automatically adjusted based on the reinforcement learning algorithm in artificial intelligence, and the personalized tea soup taste adjustment is realized.

Drawings

Fig. 1 is a schematic structural diagram of an intelligent tea set based on reinforcement learning.

In the figure: the tea cup comprises a tea bin cover 1, a tea bin 2, a tea storage cup 3, a base module 4, a sensor 5, an electric control valve 6, an electric heater 7, an electric contact 8, a filter screen 9, a tea outlet 10, a cup handle 11, a chip 12 and a power supply module 13.

Detailed Description

The invention is further described with reference to the following drawings and detailed description:

in the description of the present invention, it should be noted that the terms "top", "bottom", "one side", "the other side", "front", "back", "middle part", "inside", "top", "bottom", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of describing the present invention and simplifying the description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation, and be operated, and thus, should not be construed as limiting the present invention; the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance; furthermore, unless expressly stated or limited otherwise, the terms "mounted," "connected," and "connected" are to be construed broadly, as they may be fixedly connected, detachably connected, or integrally connected, for example; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.

As shown in figure 1, an intelligent tea set based on reinforcement learning comprises a tea bin cover 1, a tea bin 2, a tea storage cup 3, a base module 4, a sensor 5, an electric control valve 6, an electric heater 7, an electric contact 8, a filter screen 9, a tea outlet 10, a cup handle 11, a chip 12 and a power supply module 13, wherein the sensor 5 for detecting whether the tea bin cover is closed or not is installed on the tea bin cover 1, the detachable filter screen 9 is arranged inside the tea bin 2 to ensure that tea leaves and fragments cannot block a water outlet, the bottom end of the tea bin 2 is provided with the water outlet, the electric control valve 6 is installed on the water outlet, the cup handle 11 is fixed on one side of the tea storage cup 3, the tea storage cup 3 and the upper tea bin 2 can be taken up together through the cup handle 11, tea soup is poured out through the tea outlet 10 for drinking, the tea bin 2 is overlapped at the top opening of the tea storage cup 3, the tea bin cover 1 is covered with the tea bin 2 in a matched manner, the tea processing device is characterized in that a chip 12 and a power supply module 13 are arranged in the base module 4, the bottom end of the tea bin cover 1, the top end of the tea bin 2, the top end of the cup handle 11, the bottom end of the cup handle 11 and the top end of the base module 4 are respectively provided with an electric contact 8 to form a conducting circuit, the sensor 5 of the tea bin cover 1, the electric control valve 6 of the tea bin 2 and the electric heater 7 of the tea storage cup 3 are connected into the circuits of the power supply module 13 and the chip 12, the base module 4 is communicated with an APP end of the smart phone through a Bluetooth protocol to receive and send signals, corresponding configuration files are selected according to tea names, two-dimensional codes, one-dimensional codes and digital number parameters on tea bags, the optimal soaking time of tea before each time of soup is made is stored in the configuration files, the chip 12 is communicated with the smart phone through the Bluetooth to obtain the soaking time parameters corresponding to the current tea bags, the flavors of the tea soup can be marked in the App on the smart phone, if the concentration is too high or too low, the App is configured with a reinforcement Learning Q-Learning algorithm to calculate the next soaking time parameter after adjustment, and the more times the user marks, the closer the soaking time parameter is to the taste preference of the user and the memory parameter is stored.

Through the scheme of the invention, one side of the tea storage cup 3 is provided with the tea outlet 10.

Through the scheme of the invention, the electric heater 7 is arranged at the bottom end of the inner cavity of the tea storage cup 3 for heating and heat preservation.

Through the scheme of the invention, the tea bin cover 1, the tea bin 2, the tea storage cup 3 and the base module 4 are fixed together through a strong magnet or a fastener.

During the use, the user is connected in App (application program) configuration bluetooth on the smart mobile phone, link to this smart machine, simultaneously according to the tealeaves name, the two-dimensional code on the tea bag, the configuration file that corresponds is selected to one-dimensional code, parameter such as digit serial number, the configuration file preserves the best soak time of tealeaves before the hot water of every time, base module 4 chip 12 is through the bluetooth with smart mobile phone communication, acquire the soak time parameter that current tea bag corresponds, chip 12 passes through electric signal control electric control valve 6, electric control valve 6 also can be the steering wheel, realize mechanical structure switching control, accurate control tealeaves soak time, open behind the mechanical structure, then tea hot water flows into in the teacup 3 from tea storehouse 2 under the action of gravity. The user can drink the tea soup by pouring the tea soup into a cup. After the mechanical structure is closed, a user can open the tea bin cover 1 to inject hot water into the tea bin 2 and cover the tea bin cover 1. When the tea bin cover 1 is covered, the electric signal of the sensor 5 can be transmitted to the chip, the soaking time is timed, the timer is used for timing, and a user can mark the taste of tea soup every time in App on the smart phone, and the tea soup is too thick or too thin. After the user marks, the App can calculate the next adjusted soaking time parameter by using a Q-Learning algorithm in reinforcement Learning, and the more times the user marks, the closer the intelligent tea set is to the taste preference of the user.

Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art will understand that various changes, modifications and substitutions can be made without departing from the spirit and scope of the invention as defined by the appended claims. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent tea set based on reinforcement learning is characterized by comprising a tea bin cover (1), a tea bin (2), a tea storage cup (3), a base module (4), a sensor (5), an electric control valve (6), an electric heater (7), an electric contact (8), a filter screen (9), a tea outlet (10), a cup handle (11), a chip (12) and a power supply module (13), wherein the sensor (5) for detecting whether the tea bin cover is closed or not is installed on the tea bin cover (1), the detachable filter screen (9) is arranged inside the tea bin (2), a water outlet is formed in the bottom end of the tea bin (2), the electric control valve (6) is installed on the water outlet, the cup handle (11) is fixed on one side of the tea storage cup (3), the tea bin (2) is overlapped at the opening at the top of the tea storage cup (3), the tea bin cover (1) is matched and covered with the tea bin (2), the tea bag is characterized in that a chip (12) and a power supply module (13) are arranged inside the base module (4), the bottom end of the tea bin cover (1), the top end of the tea bin (2), the top end of the cup handle (11), the bottom end of the cup handle (11) and the top end of the base module (4) are respectively provided with an electric contact (8) to form a conducting circuit, the sensor (5) of the tea bin cover (1), the electric control valve (6) of the tea bin (2) and the electric heater (7) of the tea storage cup (3) are connected into the circuit of the power supply module (13) and the chip (12), the base module (4) is communicated with an intelligent mobile phone APP end through a Bluetooth protocol to receive and send signals, and simultaneously selects and stores corresponding configuration files according to tea names, two-dimensional codes, one-dimensional codes and digital number parameters on the tea bags, the configuration files have the optimal tea soaking time before each soup outlet, and the chip (12) is communicated with the intelligent mobile phone through Bluetooth, the method comprises the steps of obtaining a soaking time parameter corresponding to a current tea bag, enabling an App on the smart phone to mark the taste of tea soup each time, wherein the App is too thick or too thin, and is configured with a reinforcement Learning Q-Learning algorithm to calculate the next soaking time parameter after adjustment, wherein the more times the user marks, the more the soaking time parameter is close to the taste preference of the user, and the memory parameter is stored.

2. The intelligent tea set based on reinforcement learning as claimed in claim 1, wherein: a tea outlet (10) is arranged on one side of the tea storage cup (3).

3. The intelligent tea set based on reinforcement learning as claimed in claim 1, wherein: the electric heater (7) is arranged at the bottom end of the inner cavity of the tea storage cup (3).

4. The intelligent tea set based on reinforcement learning as claimed in claim 1, wherein: the tea bin cover (1), the tea bin (2), the tea storage cup (3) and the base module (4) are fixed together through a strong magnet or a buckle.