Intelligent coffee machine manufacturing method and device

Abstract

The invention relates to the technical field of intelligent equipment, in particular to an intelligent coffee machine manufacturing method and device. The making method of the intelligent coffee machine comprises the steps that a face image of a user is collected, the face image is recognized to obtain user recognition data, and the recognition data comprises identity data and expression state data of the user; and generating a corresponding user label according to the user identification data of the user, generating coffee parameters needing to be configured according to the user label, and making coffee based on the coffee parameters. According to the method, the identity and the expression of the user are recognized to obtain the identity and the current state of the user, so that coffee recommendation can be accurately performed for each user, then coffee making is performed to meet the requirements of each user, and the method is higher in practicability and more intelligent.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent devices, and in particular to an intelligent coffee making method and device. Background Art

[0002] Coffee is a beverage made from roasted and ground coffee beans. As one of the three major beverages in the world, it is a major beverage popular in the world along with cocoa and tea.

[0003] The coffee tree is a perennial evergreen shrub or small tree belonging to the Rubiaceae family. The coffee we drink daily is made from coffee beans and various cooking utensils. Coffee beans refer to the kernels inside the coffee tree fruit, which are then roasted using appropriate methods. A standard cup of coffee should not taste just bitter. A qualified barista will rigorously perform each step when making coffee, and the coffee served to the guests will have different degrees of sweetness, sourness, aroma or cleanliness in taste.

[0004] A coffee machine is a machine that automatically brews coffee. People applied electronic technology to coffee machines, realizing automatic control of the entire process of brewing coffee, including grinding, pressing, filling, brewing, and removing residues, thus creating the coffee machine.

[0005] The existing coffee machines are not very intelligent. There are many parameters that need to be controlled when making coffee, and each person has different tastes. The existing coffee machines require users to manually control them according to their needs, which is troublesome to operate. In order to solve this problem, an intelligent coffee machine making method and device are proposed. Summary of the invention

[0006] In order to solve the technical problems existing in the above-mentioned prior art, the present invention provides a smart coffee making method and device.

[0007] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions: In a first aspect, in an embodiment provided by the present invention, a smart coffee machine making device is provided, and the smart coffee machine making method includes: Collecting user face images and identifying the face images to obtain user identification data, wherein the identification data includes the user's identity data and expression state data; According to the user identification data of the user, a corresponding user tag is generated, the coffee parameters that need to be configured are generated according to the user tag, and coffee is made based on the coffee parameters.

[0008] As a further solution of the present invention, the user's facial image is collected and the facial image is recognized to obtain user recognition data, wherein the recognition data includes the user's identity data and expression state data, including: Collecting a user's face image and preprocessing the face image to obtain a preprocessed image with face features; Recognize the pre-processed image to obtain the user's identity data; The pre-processed image is recognized to obtain the user's expression state data.

[0009] As a further solution of the present invention, the step of collecting a facial image of a user and preprocessing the facial image to obtain a preprocessed image having facial features includes: Use the Dlib face detector to extract face data from the face image to obtain a preprocessed image.

[0010] As a further solution of the present invention, the step of identifying the pre-processed image to obtain the user's identity data includes: Recognize the preprocessed image to obtain the key points of the face; Align the key points to obtain aligned face data; Use the deep learning model to extract features from the aligned face data to obtain feature vectors; The feature vector is compared with the pre-stored data in the pre-stored face database to obtain the user's identity data.

[0011] As a further solution of the present invention, the step of identifying the pre-processed image to obtain the user's expression state data includes: Cropping the preprocessed image to obtain a cropped image; Perform feature extraction on the cropped image to obtain feature data; The feature data is identified to obtain the user's expression state data.

[0012] As a further solution of the present invention, the step of extracting features from the cropped image to obtain feature data includes: The cropped image is subjected to feature map extraction to obtain a feature map; the feature map is then subjected to global average pooling to obtain a first feature vector; a dimension convolution is selected according to the number of channels of the feature map to extract local feature information and obtain the weight of each channel of the feature map; the weight is normalized; the normalized weight is multiplied by each channel of the feature map to obtain an enhanced feature map, and a weighted feature map dimension is obtained based on the feature map and the weight of each channel; feature data is obtained based on the enhanced feature map and the feature map dimension.

[0013] As a further solution of the present invention, the coffee parameters include water temperature, water volume, powder weight, grinding degree, sugar addition amount and milk addition amount.

[0014] As a further solution of the present invention, the method of generating a corresponding user tag according to the user identification data of the user, generating coffee parameters to be configured according to the user tag, and making coffee based on the coffee parameters also includes: Pre-store user history data, which includes user identity data and coffee preference data, and is also used to receive user evaluation data so as to update the user history data according to the user evaluation data.

[0015] As a further solution of the present invention, the method of generating a corresponding user tag according to the user identification data of the user, generating coffee parameters to be configured according to the user tag, and making coffee based on the coffee parameters also includes: Based on the user identification data, determine whether the user is a new user. If the user is a new user, obtain the current user status data based on the user identification data, and generate recommended coffee data based on the status data for the current user to choose.

[0016] In a second aspect, in an embodiment provided by the present invention, a smart coffee machine making device is provided, the smart coffee machine making device comprising: a face recognition module and a coffee machine body; The face recognition module is configured to collect a user's face image and recognize the face image to obtain user recognition data, wherein the recognition data includes the user's identity data and expression state data; The coffee machine body is configured to generate a corresponding user tag according to the user identification data of the user, generate coffee parameters to be configured according to the user tag, and make coffee based on the coffee parameters. The face recognition module is configured to collect a user's face image and recognize the face image to obtain user recognition data, wherein the recognition data includes the user's identity data and expression state data; The coffee machine body is configured to generate a corresponding user tag according to the user identification data of the user, generate coffee parameters to be configured according to the user tag, and make coffee based on the coffee parameters.

[0017] The present invention recognizes the user's identity and expression through a face recognition module to obtain the user's identity and the user's current status, so that coffee recommendations can be made accurately for each user, and then coffee is made through the coffee machine body to meet the needs of each user, which is more practical and more intelligent.

[0018] As a further solution of the present invention, the image preprocessing unit, the identity recognition unit and the expression recognition unit are included; The image preprocessing unit is configured to collect a facial image of a user and preprocess the facial image to obtain a preprocessed image with facial features; The identity recognition unit is configured to recognize the pre-processed image to obtain the user's identity data; The expression recognition unit is configured to recognize the pre-processed image to obtain the user's expression state data.

[0019] As a further solution of the present invention, the image preprocessing unit is configured to use a Dlib face detector to extract face data in the face image to obtain a preprocessed image.

[0020] As a further solution of the present invention, the identity recognition unit includes a key point processing subunit, an alignment subunit, a first feature extraction subunit and a first recognition subunit; The key point processing subunit is used to identify the pre-processed image to obtain the key points of the face; The alignment subunit is used to align key points to obtain aligned face data; The first feature extraction subunit is used to extract features from the aligned face data using a deep learning model to obtain a feature vector; The first recognition subunit is used to compare the feature vector with pre-stored data in a pre-stored face database to obtain the user's identity data.

[0021] As a further solution of the present invention, the expression recognition unit includes a cropping subunit, a second feature extraction subunit and a second recognition subunit; The cropping subunit is used to crop the preprocessed image to obtain a cropped image; The second feature extraction subunit is used to extract features from the cropped image to obtain feature data; The second recognition subunit is used for recognizing feature data to obtain the user's expression state data.

[0022] As a further solution of the present invention, the second feature extraction subunit is used to perform feature map extraction on the cropped image to obtain a feature map; then perform global average pooling on the feature map to obtain a first feature vector; select a dimension convolution according to the number of channels of the feature map to extract local feature information and obtain the weight of each channel of the feature map; normalize the weight; multiply the normalized weight by the channel-by-channel of the feature map to obtain an enhanced feature map, and obtain a weighted feature map dimension based on the feature map and the weight of each channel; and obtain feature data based on the enhanced feature map and the feature map dimension.

[0023] As a further solution of the present invention, the coffee machine body includes a control unit and a coffee making device; The control unit is used to generate a corresponding user tag according to the user identification data of the user, and generate coffee parameters to be configured according to the user tag; The coffee making device is used to make coffee according to coffee parameters.

[0024] As a further embodiment of the present invention, the coffee parameters include water temperature, water volume, powder weight, grinding degree, sugar addition amount and milk addition amount.

[0025] As a further solution of the present invention, the control unit is used to pre-store user history data, which includes user identity data and coffee preference data, and is also used to receive user evaluation data so as to update its user history data according to the user evaluation data.

[0026] As a further solution of the present invention, the control unit is also used to determine whether the user is a new user based on the user identification data. If the user is a new user, the control unit is used to obtain the current user status data based on the user identification data, and generate recommended coffee data based on the status data for the current user to select.

[0027] The technical solution provided by the present invention has the following beneficial effects: The face recognition module of the present invention collects the user's face image and recognizes the face image to obtain user recognition data, wherein the recognition data includes the user's identity data and expression state data; the coffee machine body generates a corresponding user tag according to the user's user recognition data, generates coffee parameters that need to be configured according to the user tag, and makes coffee based on the coffee parameters. The present invention recognizes the user's identity and expression through the face recognition module to obtain the user's identity and the user's current state, so that coffee recommendations can be made accurately for each user, and then coffee is made through the coffee machine body to meet the needs of each user, which is more practical and more intelligent.

[0028] These and other aspects of the present invention will be more clearly understood in the following description of the embodiments. It should be understood that the above general description and the following detailed description are only exemplary and explanatory and cannot limit the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] 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 in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other embodiments can be obtained based on these drawings without paying creative work.

[0030] Figure 1 The present invention is a flowchart of a smart coffee making method according to an embodiment of the present invention.

[0031] Figure 2 This is a structural block diagram of an intelligent coffee making device according to an embodiment of the present invention.

[0032] Figure 3 This is a structural block diagram of a face recognition module in an intelligent coffee machine making device according to an embodiment of the present invention.

[0033] Figure 4 This is a structural block diagram of an identity recognition unit in an intelligent coffee machine making device according to an embodiment of the present invention.

[0034] Figure 5 This is a structural block diagram of an expression recognition unit in an intelligent coffee machine making device according to an embodiment of the present invention.

[0035] Figure 6 This is a structural block diagram of a coffee machine main body in an intelligent coffee machine making device according to an embodiment of the present invention.

[0036] In the figure: 100-face recognition module, 200-coffee machine body, 101-image preprocessing unit, 102-identity recognition unit, 103-expression recognition unit, 201-control unit, 202-coffee making device, 1021-key point processing subunit, 1022-alignment subunit, 1023-first feature extraction subunit, 1024-first recognition subunit, 1031-cropping subunit, 1032-second feature extraction subunit, 1033-second recognition subunit. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0038] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0039] It should be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0040] In the following description and drawings, specific examples of more than one form will be described in detail. However, these forms are only examples, and some of the various methods in the principles of various forms can be used, and the descriptions set forth are intended to include all forms and their equivalents. Specifically, the terms "embodiment", "example", "form", "illustration", etc. used in this specification can be interpreted as any form or design described can be better or have advantages over other forms or designs.

[0041] In addition, various forms and features may be embodied by a system including more than one device, terminal, server, equipment, component and / or module, etc. It should be understood and recognized that various systems may include additional multiple devices, terminals, servers, equipment, components and / or modules, and / or may not include all of the multiple devices, terminals, servers, equipment, components, modules, etc. shown in the figure.

[0042] The terms "computer program", "component", "module", "system", etc. used in this specification are used interchangeably and refer to computer-related entities, hardware, firmware, software, a combination of software and hardware, or the execution of software. For example, a component can be a process executed on a processor, a processor, an object, an execution thread, a program and / or a computer, but is not limited to this. For example, it can be an application program executed on a computer device and / or all components of a computing device. More than one component can be installed in a processor and / or execution thread. A component can be localized in one computer. A component can also be distributed between two or more computers.

[0043] The existing coffee machine has a low intelligence level. There are many parameters that need to be controlled when making coffee. However, each person has different tastes. The existing coffee machine requires the user to manually control the operation according to the needs, which is troublesome to operate. In order to solve this problem, an intelligent coffee machine making device is proposed. The intelligent coffee machine making device provided by the present invention recognizes the user's identity and expression through the face recognition module 100 to obtain the user's identity and the user's current state, so that coffee recommendations can be made accurately for each user, and then coffee is made through the coffee machine body 200 to meet the needs of each user, which is more practical and more intelligent.

[0044] Specifically, the embodiments of the present invention are further described below in conjunction with the accompanying drawings.

[0045] See also Figure 1 , Figure 1 is a flow chart of a method for making coffee using an intelligent coffee machine provided by an embodiment of the present invention. Figure 1 As shown, the smart coffee machine making method includes steps S10 to S30.

[0046] S10, collecting a user's facial image and identifying the facial image to obtain user identification data, wherein the identification data includes the user's identity data and expression state data; In an embodiment of the present invention, the step S10 collects a user's facial image and identifies the facial image to obtain user identification data, wherein the identification data includes the user's identity data and expression state data, including: S101, collecting a user's facial image, and preprocessing the facial image to obtain a preprocessed image with facial features; In an embodiment of the present invention, the step of collecting a facial image of a user and preprocessing the facial image to obtain a preprocessed image having facial features includes: Use the Dlib face detector to extract face data from the face image to obtain a preprocessed image.

[0047] S102, identifying the pre-processed image to obtain user identity data; In an embodiment of the present invention, the step of identifying the pre-processed image to obtain the user's identity data includes: S1021, identifying the preprocessed image to obtain key points of the face; S1022, aligning key points to obtain aligned face data; S1023, extracting features from the aligned face data using a deep learning model to obtain a feature vector; S1024. Compare the feature vector with pre-stored data in a pre-stored face database to obtain the user's identity data.

[0048] S103: Recognize the pre-processed image to obtain the user's expression state data.

[0049] In an embodiment of the present invention, the step S103 of recognizing the pre-processed image to obtain the user's expression state data includes: S1031, cropping the preprocessed image to obtain a cropped image; S1032, extracting features from the cropped image to obtain feature data; In an embodiment of the present invention, the step S1032 of extracting features from the cropped image to obtain feature data includes: The cropped image is subjected to feature map extraction to obtain a feature map; the feature map is then subjected to global average pooling to obtain a first feature vector; a dimension convolution is selected according to the number of channels of the feature map to extract local feature information and obtain the weight of each channel of the feature map; the weight is normalized; the normalized weight is multiplied by each channel of the feature map to obtain an enhanced feature map, and a weighted feature map dimension is obtained based on the feature map and the weight of each channel; feature data is obtained based on the enhanced feature map and the feature map dimension.

[0050] S1033. Identify the feature data to obtain the user's expression state data.

[0051] S20. Generate a corresponding user tag according to the user identification data of the user, generate coffee parameters that need to be configured according to the user tag, and make coffee based on the coffee parameters.

[0052] In an embodiment of the present invention, the coffee parameters include water temperature, water volume, powder weight, grinding degree, sugar addition amount and milk addition amount.

[0053] The method of generating a corresponding user tag according to the user identification data of the user, generating coffee parameters to be configured according to the user tag, and making coffee based on the coffee parameters also includes: Pre-store user history data, which includes user identity data and coffee preference data, and is also used to receive user evaluation data so as to update the user history data according to the user evaluation data.

[0054] The method of generating a corresponding user tag according to the user identification data of the user, generating coffee parameters to be configured according to the user tag, and making coffee based on the coffee parameters also includes: Based on the user identification data, determine whether the user is a new user. If the user is a new user, obtain the current user status data based on the user identification data, and generate recommended coffee data based on the status data for the current user to choose.

[0055] The present invention obtains the user identity and the user's current status by recognizing the user's identity and expression, so as to accurately recommend coffee to each user, and then make coffee to meet the needs of each user, which is more practical and more intelligent.

[0056] In one embodiment, see Figure 2 As shown, a structural block diagram of an intelligent coffee machine making device is provided. In an embodiment of the present invention, an intelligent coffee machine making device is also provided, and the intelligent coffee machine making device includes a face recognition module 100 and a coffee machine body 200.

[0057] The face recognition module 100 is configured to collect user face images and recognize the face images to obtain user recognition data, wherein the recognition data includes the user's identity data and expression status data.

[0058] See also Figure 3 As shown, Figure 3 A structural block diagram of a face recognition module in an intelligent coffee machine making device is provided. In an embodiment of the present invention, the face recognition module 100 includes an image preprocessing unit 101, an identity recognition unit 102 and an expression recognition unit 103.

[0059] The image preprocessing unit 101 is configured to collect a facial image of a user and preprocess the facial image to obtain a preprocessed image with facial features.

[0060] In an embodiment of the present invention, the image preprocessing unit 101 is configured to extract face data from a face image using a Dlib face detector to obtain a preprocessed image. The image preprocessing unit 101 uses a pretrained face detector to read and detect the face image, which can enhance the accuracy of the detection and can quickly and accurately process and analyze the face image.

[0061] In an embodiment of the present invention, the Dlib face detector can extract the position and bounding box of the face accurately detected in the image or video, and provide the image for subsequent operations.

[0062] The identity recognition unit 102 is configured to recognize the pre-processed image to obtain the user's identity data.

[0063] In an embodiment of the present invention, the identity recognition unit 102 is configured to identify the preprocessed image to obtain the key points of the face, then align the key points to obtain aligned face data, use a deep learning model to extract features of the aligned face data to obtain a feature vector; compare the feature vector with pre-stored data in a pre-stored face database to obtain the user's identity data.

[0064] See also Figure 4 As shown, Figure 4 A structural block diagram of an identity recognition unit in an intelligent coffee machine making device is provided. In an embodiment of the present invention, the identity recognition unit 102 includes a key point processing subunit 1021, an alignment subunit 1022, a first feature extraction subunit 1023 and a first recognition subunit 1024.

[0065] The key point processing subunit 1021 is used to identify the pre-processed image to obtain the key points of the face, including eyes, mouth, nose, etc.

[0066] The alignment subunit 1022 is used to align key points to obtain aligned face data.

[0067] The first feature extraction subunit 1023 is used to extract features from the aligned face data using a deep learning model to obtain a feature vector; The first recognition subunit 1024 is used to compare the feature vector with pre-stored data in a pre-stored face database to obtain the user's identity data.

[0068] The expression recognition unit 103 is configured to recognize the pre-processed image to obtain the user's expression state data.

[0069] In the embodiment of the present invention, the expression recognition unit 103 is configured to crop the pre-processed image and then perform feature extraction to obtain the user's expression state data.

[0070] Face recognition is a biometric technology that identifies people based on their facial features. It uses a camera or camcorder to collect images or video streams containing faces, automatically detects and tracks faces in images, and then performs facial recognition on the detected faces. It is also commonly called portrait recognition or facial recognition.

[0071] See also Figure 5 As shown, Figure 5 A structural block diagram of an expression recognition unit in an intelligent coffee machine making device is provided. In an embodiment of the present invention, the expression recognition unit 103 includes a cropping subunit 1031 , a second feature extraction subunit 1032 and a second recognition subunit 1033 .

[0072] The cropping subunit 1031 is used to crop the pre-processed image to obtain a cropped image; The second feature extraction subunit 1032 is used to extract features from the cropped image to obtain feature data.

[0073] In an embodiment of the present invention, the second feature extraction subunit 1032 is used to extract a feature map from the cropped image to obtain a feature map; then perform global average pooling on the feature map to obtain a first feature vector; select a dimension convolution according to the number of channels of the feature map to extract local feature information and obtain the weight of each channel of the feature map; normalize the weight; multiply the normalized weight by the channel-by-channel of the feature map to obtain an enhanced feature map, and obtain a weighted feature map dimension based on the feature map and the weight of each channel; obtain feature data based on the enhanced feature map and the feature map dimension. The second feature extraction subunit 1032 enhances the global information of the feature map and suppresses useless information to improve the accuracy of feature extraction.

[0074] In an embodiment of the present invention, the second feature extraction subunit 1032 uses a feature attention module to enhance the feature map. The feature attention module FAM can use global information to enhance the expression of important information while suppressing useless information.

[0075] The second recognition subunit 1033 is used for recognizing feature data to obtain the user's expression state data.

[0076] The coffee machine body 200 is configured to generate a corresponding user tag according to the user identification data of the user, generate coffee parameters to be configured according to the user tag, and make coffee based on the coffee parameters.

[0077] See also Figure 6 As shown, Figure 6 A structural block diagram of a coffee machine body in an intelligent coffee making device is provided. In an embodiment of the present invention, the coffee machine body 200 includes a control unit 201 and a coffee making device 202.

[0078] The control unit 201 is used to generate a corresponding user tag according to the user identification data of the user, and generate coffee parameters that need to be configured according to the user tag.

[0079] In an embodiment of the present invention, the coffee parameters include water temperature, water volume, powder weight, grinding degree, sugar addition amount and milk addition amount.

[0080] In an embodiment of the present invention, the control unit 201 is used to pre-store user history data, and the user history data includes user identity data and coffee preference data.

[0081] In the embodiment of the present invention, the control unit 201 is further configured to receive user evaluation data so as to update the user history data according to the user evaluation data.

[0082] The user evaluation data may include coffee alcohol content, coffee aroma, astringency, sweetness, bitterness, etc.

[0083] Specifically, based on the user evaluation data, the generated recommendation parameters are evaluated, and then the coffee preference data in the user's historical data is updated to provide a better experience for the user.

[0084] In the embodiment of the present invention, the control unit 201 is further used to determine whether the user is a new user based on the user identification data, and if the user is a new user, obtain the current user status data based on the user identification data, and generate recommended coffee data based on the status data for the current user to choose; after the user makes a choice, the coffee making device 202 makes coffee. In this way, suitable coffee can be automatically recommended to meet the needs of various users.

[0085] In the embodiment of the present invention, the user status data includes data such as facial expression status, physical status and age, so as to be able to fully understand the user status data and comprehensively judge the user's needs.

[0086] The coffee making device 202 is used to make coffee according to coffee parameters.

[0087] The present invention recognizes the user's identity and expression through the face recognition module 100 to obtain the user's identity and the user's current status, so that coffee recommendations can be made accurately for each user, and then coffee is made through the coffee machine body 200 to meet the needs of each user, which is more practical and more intelligent.

[0088] It should be understood that, as used herein, the singular form "a" or "an" is intended to include the plural form as well, unless the context clearly supports an exception. It should also be understood that, as used herein, "and / or" refers to any and all possible combinations of one or more of the items listed in association. The serial numbers of the embodiments disclosed in the above embodiments of the present invention are for description only and do not represent the advantages and disadvantages of the embodiments.

[0089] A person skilled in the art should understand that the discussion of any of the above embodiments is only exemplary and is not intended to imply that the scope of the disclosure of the embodiments of the present invention (including the claims) is limited to these examples; under the concept of the embodiments of the present invention, the technical features in the above embodiments or different embodiments can also be combined, and there are many other changes in different aspects of the above embodiments of the present invention, which are not provided in detail for the sake of simplicity. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present invention should be included in the protection scope of the embodiments of the present invention.

Claims

1. A method for making a smart coffee machine, characterized in that: The smart coffee machine making method comprises: Collecting user face images and identifying the face images to obtain user identification data, wherein the identification data includes the user's identity data and expression state data; According to the user identification data of the user, a corresponding user tag is generated, the coffee parameters that need to be configured are generated according to the user tag, and coffee is made based on the coffee parameters.

2. The smart coffee making method according to claim 1, characterized in that: The user's facial image is collected and recognized to obtain user recognition data, wherein the recognition data includes the user's identity data and expression state data, including: Collecting a user's face image and preprocessing the face image to obtain a preprocessed image with face features; Recognize the pre-processed image to obtain the user's identity data; The pre-processed image is recognized to obtain the user's expression state data.

3. The intelligent coffee making method according to claim 2, characterized in that: The step of collecting the user's facial image and preprocessing the facial image to obtain a preprocessed image with facial features includes: Use the Dlib face detector to extract face data from the face image to obtain a preprocessed image.

4. The intelligent coffee making method according to claim 2, characterized in that: The step of identifying the pre-processed image to obtain the user's identity data includes: Recognize the preprocessed image to obtain the key points of the face; Align the key points to obtain aligned face data; Use the deep learning model to extract features from the aligned face data to obtain feature vectors; The feature vector is compared with the pre-stored data in the pre-stored face database to obtain the user's identity data.

5. The intelligent coffee making method according to claim 2, characterized in that: The step of identifying the pre-processed image to obtain the user's expression state data includes: Cropping the preprocessed image to obtain a cropped image; Perform feature extraction on the cropped image to obtain feature data; The feature data is identified to obtain the user's expression state data.

6. The intelligent coffee making method according to claim 5, characterized in that: The step of extracting features from the cropped image to obtain feature data includes: The cropped image is subjected to feature map extraction to obtain a feature map; the feature map is then subjected to global average pooling to obtain a first feature vector; a dimension convolution is selected according to the number of channels of the feature map to extract local feature information and obtain the weight of each channel of the feature map; the weight is normalized; the normalized weight is multiplied by each channel of the feature map to obtain an enhanced feature map, and a weighted feature map dimension is obtained based on the feature map and the weight of each channel; feature data is obtained based on the enhanced feature map and the feature map dimension.

7. The intelligent coffee making method according to claim 1, characterized in that: The coffee parameters include water temperature, water volume, powder weight, grinding degree, sugar addition amount and milk addition amount.

8. The intelligent coffee making method according to claim 7, characterized in that: The method of generating a corresponding user tag according to the user identification data of the user, generating coffee parameters to be configured according to the user tag, and making coffee based on the coffee parameters also includes: Pre-store user history data, which includes user identity data and coffee preference data, and is also used to receive user evaluation data so as to update the user history data according to the user evaluation data.

9. The intelligent coffee making method according to claim 7, characterized in that: The method of generating a corresponding user tag according to the user identification data of the user, generating coffee parameters to be configured according to the user tag, and making coffee based on the coffee parameters also includes: Based on the user identification data, determine whether the user is a new user. If the user is a new user, obtain the current user status data based on the user identification data, and generate recommended coffee data based on the status data for the current user to choose.

10. An intelligent coffee making device, characterized in that: The smart coffee machine making method comprises: a face recognition module and a coffee machine body; The face recognition module is configured to collect a user's face image and recognize the face image to obtain user recognition data, wherein the recognition data includes the user's identity data and expression state data; The coffee machine body is configured to generate a corresponding user tag according to the user identification data of the user, generate coffee parameters to be configured according to the user tag, and make coffee based on the coffee parameters.

Images