Plant recommendation method, readable storage medium and electronic device

Abstract

The present invention provides a plant recommendation method, a readable storage medium, and an electronic device, comprising: obtaining a plant image taken by a current user and identifying attribute information of the plant in the plant image; assigning different tags to the plant photographed by the current user based on the identified different attribute information; and recommending plants to the current user based on the assigned tags. Specifically, by identifying the attribute information of the plant in the plant image taken by the user, assigning tags corresponding to the different attributes of the plant, and then aggregating all the tags, the user's preferences can be understood, allowing for effective recommendations of plants that meet the user's preferences for maintenance, thereby improving the user experience.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a plant recommendation method. Background Art

[0002] Plant recommendations need to be considered based on user preferences and user convenience. Randomly recommending completely irrelevant plants will cause trouble to users, or ineffective recommendations will not achieve the desired effect. Summary of the Invention

[0003] The purpose of the present invention is to provide a plant recommendation method to effectively recommend plants that meet user preferences for maintenance and improve user experience.

[0004] Based on the above ideas, the present invention provides a plant recommendation method, comprising:

[0005] Obtaining a plant picture taken by the current user and identifying attribute information of the plant in the plant picture;

[0006] Setting different labels for the plants photographed by the current user according to the different identified attribute information; and

[0007] According to the set tags, plants are recommended to the current user.

[0008] Optionally, in the plant recommendation method, the attribute information includes species information, and setting different labels for the plants photographed by the current user according to the identified different attribute information includes:

[0009] For the identified species information, a similar image with multiple different labels closest to the plant image is obtained from a pre-established plant image library;

[0010] The obtained label of the similar image is used as the label of the plant image.

[0011] Optionally, in the plant recommendation method, the multiple different labels include: one or more of maintenance information labels, ornamental information labels and color labels.

[0012] Optionally, in the plant recommendation method, the closest similar image is obtained by calculating the color similarity distance between the plant image and multiple similar images in the plant image library.

[0013] Optionally, in the plant recommendation method, the attribute information includes species information, and setting different labels for the plants photographed by the current user according to the identified different attribute information includes:

[0014] confirming characteristic information of the plant photographed by the current user based on the identified species information, wherein the characteristic information includes at least one of maintenance information and viewing information; and

[0015] A corresponding label is set for the confirmed characteristic information.

[0016] Optionally, in the plant recommendation method, setting corresponding labels for the confirmed characteristic information includes:

[0017] Set corresponding maintenance labels according to the maintenance method classification standards of the pre-classified classification.

[0018] Optionally, in the plant recommendation method, the attribute information includes color information of the ornamental parts of the plant; setting different labels for the plants photographed by the current user according to the different identified attribute information includes: setting corresponding color labels according to the different identified color information.

[0019] Optionally, in the plant recommendation method, the color information is obtained by directly identifying the color of the ornamental part of the plant in the plant picture, or the color information is obtained by identifying the species information of the plant in the plant picture and judging based on the species information.

[0020] Optionally, in the plant recommendation method, the method of directly identifying the color information of the ornamental part of the plant in the plant picture includes:

[0021] Using a pre-trained color recognition model to perform color recognition and classification on the ornamental parts of the plant in the plant picture to obtain the color information of the plant; or,

[0022] The color similarity between the color of the ornamental part of the plant in the plant picture and a plurality of standard colors is determined to perform color recognition and classification on the plant to obtain the color information of the plant.

[0023] Optionally, in the plant recommendation method, the method of directly identifying the color information of the ornamental part in the plant picture further includes:

[0024] Identifying the ornamental parts of the plant in the plant image using a pre-trained plant part recognition model or attention model, and,

[0025] The identified ornamental parts are divided out for use in identifying color information of the ornamental parts of the plant.

[0026] Optionally, in the plant recommendation method, the plant type information is identified using a pre-trained plant recognition model. Optionally, in the plant recommendation method, recommending plants to the current user based on the set label includes:

[0027] When multiple plant pictures taken by the current user are set with multiple categories of tags, and tags of the same category reach a set number or a set ratio, plants are recommended to the current user based on the tags that reach the set number or the set ratio.

[0028] Optionally, in the plant recommendation method, when multiple categories of labels reach a set number or a set proportion, plants are recommended to the current user based on the plants recommended by each of the labels that reach the set number or the set proportion, or plants are recommended to the current user based on the same plants among the plants recommended by each of the labels that reach the set number or the set proportion.

[0029] Optionally, in the plant recommendation method, the plant recommendation method further includes:

[0030] When there are relatively many plants of a certain type in the multiple plant images taken by the current user, plants of the same type that do not appear in the plant images taken by the current user are recommended. Optionally, in the plant recommendation method, when there are multiple plants to recommend, the plants are recommended in order of the number of plants that are planted more frequently by other users.

[0031] The present invention also provides a readable storage medium storing a computer program, wherein when the computer program is executed, the plant recommendation method described above is implemented. The present invention also provides an electronic device comprising a processor and a memory, wherein the memory stores the computer program, wherein when the computer program is executed, the plant recommendation method described above is implemented.

[0032] The plant recommendation method, readable storage medium, and electronic device provided by the present invention include: obtaining plant images taken by the current user and identifying attribute information of the plants in the plant images; assigning different tags to the plants photographed by the current user based on the identified different attribute information; and recommending plants to the current user based on the assigned tags. Specifically, by identifying the attribute information of the plants in the plant images taken by the user, assigning tags corresponding to the different attributes of the plants, and then aggregating all the tags, the user's preferences can be understood, allowing for effective recommendations of plants that meet the user's preferences for maintenance, thereby improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1This is a flow chart of the plant recommendation method provided by an embodiment of the present invention.

[0034] Figure 2 This is a flowchart of a label setting method according to an embodiment of the present invention;

[0035] Figure 3 The figure is a flowchart of another label setting method in an embodiment of the present invention. DETAILED DESCRIPTION

[0036] In order to make the objects, advantages and features of the present invention clearer, the present invention is described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that the drawings are all in a very simplified form and are not drawn to scale, and are only used to conveniently and clearly assist in explaining the purpose of the embodiments of the present invention. In addition, the structure shown in the drawings is often a part of the actual structure. In particular, the emphasis required to be shown in each drawing is different, and sometimes different proportions are used. It should also be understood that, unless otherwise specified or indicated, the terms "first", "second", "third" and the like in the specification are only used to distinguish between the various components, elements, steps, etc. in the specification, and are not used to represent the logical relationship or sequential relationship between the various components, elements, steps, etc.

[0037] like Figure 1 As shown, an embodiment of the present invention provides a plant recommendation method, comprising the following steps:

[0038] S11, obtaining a plant picture taken by the current user, and identifying attribute information of the plant in the plant picture;

[0039] S12, setting different labels for the plants photographed by the current user according to the different identified attribute information;

[0040] S13, recommending plants to the current user according to the set tags.

[0041] The plant recommendation method provided in the embodiment of the present invention identifies the attribute information of plants in plant pictures taken by users, sets corresponding labels for different attributes of plants, and then summarizes all labels, so as to understand the user's preferences, so that plants that meet the user's preferences can be effectively recommended for maintenance, thereby improving the user experience.

[0042] The above steps S11 to S13 are described in further detail below.

[0043] In step S11, the number of plant images captured by the current user can be one or more. In this embodiment, preferably, multiple plant images captured by the user are captured, and plant attribute information is identified in each of the images. Retrieving multiple plant images allows for a more comprehensive understanding of the user's preferences, thereby ensuring that the final recommended plants better meet the user's expectations.

[0044] In this embodiment, the attribute information includes category information. Figure 2 In step S12, setting different labels for the plants photographed by the current user according to the identified different attribute information includes the following steps:

[0045] S12A, confirming characteristic information of the plant photographed by the current user based on the identified species information, wherein the characteristic information includes at least one of maintenance information and viewing information; and

[0046] S12B: Set a corresponding label for the confirmed feature information.

[0047] For example, plants that are watered every three days can be assigned the same maintenance label based on watering frequency. For example, plants that flower in April and May, or plants that don't flower but are best viewed at night, can be labeled with the specific flowering period or best viewing time.

[0048] Specifically, when users select plants, they generally give priority to the maintenance characteristics and ornamental properties of the plants. Therefore, in this embodiment, preferably, tags are set for the maintenance information and ornamental information, and then plant recommendations are made based on the set tags.

[0049] A plant maintenance plan may include, for example, at least one of watering, spraying, water changes, water addition, fertilizing, pruning, weeding, pot rotation, repotting, sun exposure, shading, temperature adjustment, humidity adjustment, winter protection, and pest and disease control. Plant maintenance plans are related to the plant's habitat and growth cycle, among other factors. Therefore, when confirming tags, corresponding maintenance tags can be set based on pre-classified maintenance method classification standards. Specifically, different maintenance methods are pre-classified for different plant species, and different maintenance methods correspond to different maintenance tags. Once the plant species information is identified, its maintenance information is obtained based on the species information, and the corresponding tag can be associated.

[0050] In this embodiment, the species information includes species information and may also include genus information, family information, etc. The species information can be identified using a pre-trained plant recognition model. Specifically, a plant recognition model can be established based on a neural network (such as a deep convolutional neural network (CNN) or a deep residual network (Resnet), etc.). For example, a certain number of picture samples labeled with the classification name of the plant are obtained for each plant classification, that is, a training sample set, and the neural network is trained using these picture samples until the output accuracy of the neural network meets the requirements. Before performing plant recognition based on the picture, the picture can also be preprocessed. Preprocessing may include normalization, brightness adjustment, or noise reduction. Noise reduction processing can highlight the description of the characteristic parts in the picture, making the features more distinct.

[0051] In addition, it is preferable to determine which attribute category to use for plant species identification based on the part recognition results of the plant image. For example, if it is difficult to obtain more accurate species information from the part photographed by the user, only genus or family information can be output. If the user can obtain more accurate species information from the part photographed, then species information can be output. This can improve recognition accuracy and avoid misleading or confusing the user. Specifically, determining which attribute category to use for plant identification based on the part recognition results of the plant image includes: obtaining the part recognition results of the plant in the plant image, distinguishing the categories of the part recognition results, and obtaining the species information of the plant in the plant image based on the distinguished categories. For example, when the categories of the identified parts are trunk, stem, seedling, etc., it will be more difficult to obtain more accurate species information, so identification can be performed based on genus or family. When the categories of the identified parts are flowers, fruits, leaves, etc., it is easier to obtain accurate species information, so identification can be performed based on species.

[0052] Furthermore, in this embodiment, the attribute information may also include color information of the ornamental parts of the plant. Figure 2 The step of setting different labels for the plants photographed by the current user according to the different attribute information identified may further include: S12C, setting corresponding color labels according to the different color information identified. Figure 2 As shown, while identifying the plant species information to obtain labels such as maintenance and viewing information, the plant color information is identified to obtain its color label, and then the plant is recommended using labels such as maintenance and viewing information, as well as color labels. The more labels there are, the more accurate the recommended plants are. However, it should be understood that in the actual application of this application, it is also possible to only identify the plant species information, obtain labels such as maintenance and viewing information, and recommend plants based on such labels. Alternatively, it is possible to only identify the plant color information and recommend plants based on the color information.

[0053] The color information can be obtained by directly identifying the color of the ornamental part of the plant in the plant image, or by identifying the species information of the ornamental part of the plant in the plant image and determining the color information based on the species information. Therefore, in step S11, identifying the species information and color information of the plant in the plant image can be performed simultaneously, and the species information can be identified first, and then the color information can be identified. Based on this, in step S12, step S12C can be performed simultaneously with steps S12A and S12B.

[0054] When the species of the plant in the picture is in its ornamental period, for example, it has bloomed, the color of the flowers of the plant in the plant picture can be directly identified. Of course, the color of its flowers can also be judged by identifying the species information; when the species in the picture is in its non-ornamental period, that is, it has not bloomed, the color of its flowers that will bloom can be obtained by identifying its species information. For example, if the plant in the picture is Rosa rugosa by identifying the species information, it can be inferred that it will bloom yellow flowers. If the plant in the picture is Prunus guanyonii by identifying the species information, it can be inferred that it will bloom pink flowers, and so on.

[0055] In the above description, although flowers are used as an example of the ornamental parts, it should be understood that the ornamental parts described in this application are not limited to flowers, but can also be leaves, etc. For example, when the plant is a bird of paradise, its color information can directly identify the color of its leaves as green, or, by identifying its species information, it can be judged as green based on the species information.

[0056] Among them, the method of directly identifying the color information of the ornamental parts of the plant in the plant picture includes: using a pre-trained color recognition model to perform color recognition and classification on the ornamental parts of the plant in the plant picture to obtain the color information of the plant; or, judging the color similarity between the color of the ornamental parts of the plant in the plant picture and a plurality of standard colors to perform color recognition and classification on the plant to obtain the color information of the plant.

[0057] The color recognition model can adopt a pre-trained neural network model. For example, based on a deep convolutional neural network (CNN) model, the color recognition model can be obtained by pre-training a neural network on samples in a training set of plant image samples of different colors. Since the present application is to identify the color of the ornamental parts of the plant, before using the color recognition model for color recognition, a pre-trained plant part recognition model or attention model can be used to identify the ornamental parts of the plant in the plant image, and then the identified ornamental parts are divided out and input into the color recognition model for color recognition. The method of dividing the ornamental part here includes but is not limited to slicing, marking, etc.

[0058] The plant part recognition model can be obtained by training a neural network model on complete images of different plants and images of various plant parts. The training steps of the plant part recognition model may include: obtaining a training sample set, wherein each sample in the training sample set is labeled with its part information (including stem, stalk, seedling, flower, fruit, leaf, etc.); obtaining a test sample set, wherein each sample in the test sample set is labeled with its part information, wherein the test sample set is different from the training sample set; training the plant part recognition model based on the training sample set; and testing the plant part recognition model based on the test sample set. If the recognition accuracy does not meet the required accuracy, increasing the number of image samples in the training sample set and retraining the plant part recognition model using the updated training sample set until the trained plant part recognition model meets the required accuracy. If the recognition accuracy meets the required accuracy, training ends. In one embodiment, whether training can be terminated can be determined based on whether the recognition accuracy is less than a preset accuracy. Thus, the trained plant part recognition model with the output accuracy meeting the required accuracy can be used to identify object categories.

[0059] The attention model can be configured to obtain the degree of attention of each image unit in the plant picture, and the thermal value of the image unit increases as the degree of attention increases. Each image unit may include one or more pixels. The area where the ornamental part of the plant is located usually has a higher degree of attention than other areas, and therefore has a higher thermal value, so that the ornamental part can be identified based on the distribution of thermal values ​​in the plant picture. When the color of the identified part of the plant in the plant picture is judged to have a color similarity with a plurality of standard colors to perform color recognition and classification on the plant, before obtaining the color information of the plant, similarly, a pre-trained plant part recognition model or attention model can be used to identify the ornamental part of the plant in the picture, and then perform color comparison.

[0060] The plurality of standard colors can be selected, for example, from images of 12 colors (red, orange, yellow, green, cyan, blue, purple, gray, pink, black, white, and brown) as a judgment benchmark. Of course, other numbers of standard colors can also be selected. The judgment process can be as follows: obtaining a first thermal value of a plant in a plant image; obtaining a second thermal value of each reference image; and determining the reference image with the smallest difference between the second thermal value and the first thermal value as the image with the highest color similarity. Therefore, the color of the reference image is used as the color of the plant in the plant image.

[0061] In other embodiments, when identifying the color of the ornamental parts of a plant, the ornamental parts of the plant may not be divided in advance, but the color of the ornamental parts of the plant in the current image may be directly obtained by comparing the current image with a reference image. Specifically, after the plant species information is identified, labels such as maintenance and ornamental are set according to the plant species information, and multiple reference images with matching labels are obtained based on the set labels. The current image is then compared with the obtained multiple reference images to find the reference image with the smallest color similarity distance, and the color of the ornamental part of the current reference image is confirmed based on the color of the ornamental part of the reference image. For a specific embodiment of comparing the color similarity distance between the current image and the reference image, please refer to the invention application with publication number CN 111881994 A filed by the inventor, the entire content of which is incorporated into this application by reference.

[0062] For example, if the species information identified in the current image is rose, based on the species information, set labels: watering once every two weeks, flowering period in March, etc., and then based on the set multiple labels, obtain pictures of roses with matching labels, including various varieties of red roses, yellow roses, etc. If the color similarity distance between the picture of a certain variety of red rose and the current picture is the smallest, it is confirmed that the color of the ornamental part of the current reference picture is red.

[0063] In some other embodiments, all labels of the plant image can be obtained at one time. Specifically, in step S11, the attribute information includes species information. On this basis, see Figure 3 In step S12, setting different labels for the plants photographed by the current user according to the identified different species information includes the following steps:

[0064] S12a, for the identified species information, obtaining similar images with multiple different labels that are closest to the plant image from a pre-established plant image library;

[0065] S12b: Using the obtained label of the similar image as the label of the plant image.

[0066] In step S12a, the plurality of different labels include one or more of maintenance information labels, ornamental information labels, and color labels.

[0067] Additionally, in step S12a, the closest similar image can be obtained by calculating the color similarity distance between the plant image and multiple similar images in the plant image library. Similarly, for a specific implementation of comparing the color similarity distance between the current image and multiple images in the plant image library, reference can be made to the invention application filed by the present inventor with publication number CN111881994 A.

[0068] It should be noted that the present application can set labels for various attributes of plants. In addition to setting labels for maintenance information, viewing information, color and other aspects that general users are more interested in as mentioned above, labels can also be set for example, plant type (flowers, trees, shrubs, etc.), living environment (soil-based hydroponics, potted plants, outdoor, garden, indoor, etc.), whether it is toxic to special pets or humans, etc. Such labels can be obtained by identifying species information, and the selection of specific label types does not constitute a limitation to the present application.

[0069] In step S13, recommending plants to the current user based on the set labels may specifically include: when multiple plant pictures taken by the current user are set with multiple categories of labels, and the labels of the same category reach a set number or a set proportion, recommending plants to the current user based on the labels that reach the set number or the set proportion.

[0070] Optionally, when multiple categories of tags reach a set number or a set proportion, plants are recommended to the current user based on the plants recommended by each of the tags that reach the set number or the set proportion, or plants are recommended to the current user based on the same plants among the plants recommended by each of the tags that reach the set number or the set proportion.

[0071] For example, when multiple plants with the same maintenance tag (such as watering frequency) are displayed, other plants with the same maintenance method will be recommended. Because there are many types of plants, recommendations can be made in order of the number of plants planted by other users. When matching maintenance methods, the specific maintenance method can be adjusted according to the plant type, planting location, current time, and even the plant's growth stage.

[0072] For example, when the flowering time or best viewing time of the plants owned by the user is missing plants from a certain period, then plants with such labels can be recommended to the user. If all the plants owned by the user are missing plants that bloom or are best viewed between November and December, then plants with labels from this period will be recommended. The recommendations can also be made in order of the number of plants planted by other users.

[0073] For example, when a user has a large number of plants of a certain color, it can be considered that the user prefers plants of this color. In this case, plants with this color label can be recommended to the user, and the recommendations can be made in the order of the number of plants planted by other users.

[0074] In addition, when there are relatively many plants of a certain type in the multiple plant pictures taken by the user, plants of the same type that have not appeared in the plant pictures taken by the current user are recommended.

[0075] For example, if a user has many plants of the same species, they can be recommended plants that have the same species but that the user does not currently have. Because there are many species, they can be recommended in the order of the number of plants that other users have planted.

[0076] For example, if a user owns a large number of plants in the genus Rosaceae, such as various species of Chinese roses or roses, all of which are yellowish in color, and their watering frequencies are roughly consistent or within a day of each other in their care tags, then other plants in the genus Rosaceae with consistent watering frequencies, such as Rosa candida or other yellow roses, can be recommended. There are approximately 317 species in the genus Rosaceae, and recommendations can be made based on the order of the number of plants planted by other users.

[0077] This embodiment further provides a readable storage medium having a computer program stored thereon. When the computer program is executed, the plant recommendation method described in this embodiment is implemented.

[0078] The readable storage medium can be a tangible device that can hold and store instructions used by the instruction execution device, such as, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, and any suitable combination thereof. The computer program described herein can be downloaded from the readable storage medium to various computing / processing devices, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. In addition, the computer program for performing the operations of the present invention can be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages. The computer program may be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In some embodiments, various aspects of the present invention are implemented by utilizing the state information of the computer program to personalize an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), which can execute computer-readable program instructions.

[0079] This embodiment further provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and when the computer program is executed by the processor, the plant recommendation method as described in this embodiment is implemented.

[0080] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Alternatively, the memory may be at least one storage device located away from the processor.

[0081] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor. The processor is the control center of the electronic device, connecting various parts of the entire electronic device using various interfaces and lines.

[0082] The electronic device may include one or more cameras for capturing still images or recording video streams, as well as all components for connecting these elements to each other. Although the electronic device may include a full-size personal computing device, they may alternatively include a mobile computing device capable of wirelessly exchanging data with a server via a network such as the Internet. For example, the electronic device may be a smartphone, or a device such as a PDA with wireless support, a tablet PC, or a netbook capable of obtaining information via the Internet. In another example, the electronic device may be a wearable computing system.

[0083] The electronic device may further include a communication interface and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus. The communication bus may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The communication bus may be divided into an address bus, a data bus, a control bus, and the like. The communication interface is used for communication between the electronic device and other devices.

[0084] In summary, the plant recommendation method, readable storage medium, and electronic device provided by the present invention include: obtaining plant images taken by the current user and identifying attribute information of the plants in the plant images; assigning different tags to the plants photographed by the current user based on the identified different attribute information; and, based on the assigned tags, recommending plants to the current user. Specifically, by identifying the attribute information of the plants in the plant images taken by the user, assigning tags corresponding to the different attributes of the plants, and then aggregating all the tags, the user's preferences can be understood, allowing for effective recommendations for the maintenance of plants that meet the user's preferences, thereby improving the user experience.

[0085] Furthermore, it should be recognized that although the present invention has been disclosed above with reference to preferred embodiments, the above embodiments are not intended to limit the present invention. Any person skilled in the art can utilize the above disclosed technical content to make many possible changes and modifications to the technical solution of the present invention without departing from the scope of the technical solution of the present invention, or modify the technical solution of the present invention into equivalent embodiments with equivalent changes. Therefore, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. A plant recommendation method, characterized in that: include: Obtaining a plant picture taken by the current user and identifying attribute information of the plant in the plant picture, wherein the attribute information includes species information, and identifying the species information using a pre-trained plant recognition model; Setting different labels for the plants photographed by the current user according to the different identified attribute information; and Recommending plants to the current user based on the set tags; The step of setting different labels for the plants photographed by the current user according to the identified different attribute information includes: A plant picture library is pre-established, wherein each plant picture in the plant picture library is annotated with a plurality of different labels. For the identified species information, a plurality of labels of the plant picture are obtained from the pre-established plant picture library, wherein the plurality of labels include one or more of a maintenance information label, an ornamental information label, and a color label; and / or, Different maintenance methods are sorted out in advance for different types of plants. Different maintenance methods correspond to different maintenance labels, so as to obtain a maintenance method classification standard. For the identified type information, a maintenance label is set for the plant image according to the maintenance method classification standard; The step of recommending plants to the current user according to the set tag includes: When multiple plant pictures taken by the current user are set with multiple categories of tags, and the tags of the same category reach a set number or a set ratio, plant recommendations are made to the current user based on the tags that reach the set number or the set ratio; when multiple categories of tags all reach a set number or a set ratio, plant recommendations are made to the current user based on the plants recommended by each of the tags that reach the set number or the set ratio, or plant recommendations are made to the user based on the same plants among the plants recommended by each of the tags that reach the set number or the set ratio; The plant recommendation method further comprises: When there are relatively many plants of a certain type in the multiple plant pictures taken by the current user, recommending plants of the same type that do not appear in the plant pictures taken by the current user; When the recommended plants include multiple types, they are recommended in order of the number of plants that other users have planted more.

2. The plant recommendation method according to claim 1, wherein: The attribute information includes type information, and the step of setting different labels for the plants photographed by the current user according to the identified different attribute information includes: For the identified species information, a similar image with multiple different labels closest to the plant image is obtained from a pre-established plant image library; The obtained label of the similar image is used as the label of the plant image.

3. The plant recommendation method according to claim 2, wherein: The multiple different labels include: one or more of maintenance information labels, viewing information labels and color labels.

4. The plant recommendation method according to claim 2, wherein: The closest similar image is obtained by calculating the color similarity distance between the plant image and multiple similar images in the plant image library.

5. The plant recommendation method according to claim 1, wherein: The attribute information includes type information, and the step of setting different labels for the plants photographed by the current user according to the identified different attribute information includes: confirming characteristic information of the plant photographed by the current user based on the identified species information, wherein the characteristic information includes at least one of maintenance information and viewing information; and A corresponding label is set for the confirmed characteristic information.

6. The plant recommendation method according to claim 5, wherein: Setting corresponding tags for the confirmed characteristic information includes: Set corresponding maintenance labels according to the maintenance method classification standards of the pre-classified classification.

7. The plant recommendation method according to claim 1, wherein: The attribute information includes color information of the ornamental part of the plant; and the step of setting different labels for the plant photographed by the current user according to the identified different attribute information includes: Corresponding color labels are set for the different identified color information.

8. The plant recommendation method according to claim 7, wherein: The color information is obtained by directly identifying the color of the ornamental part of the plant in the plant picture, or the color information is obtained by identifying the species information of the plant in the plant picture and judging based on the species information.

9. The plant recommendation method according to claim 8, wherein: The method for directly identifying the color information of the ornamental part of the plant in the plant picture includes: Using a pre-trained color recognition model to perform color recognition and classification on the ornamental parts of the plant in the plant picture to obtain the color information of the plant; or, The color similarity between the color of the ornamental part of the plant in the plant picture and a plurality of standard colors is determined to perform color recognition and classification on the plant to obtain the color information of the plant.

10. The plant recommendation method according to claim 9, wherein: The method of directly identifying the color information of the ornamental part in the plant picture also includes: Identifying the ornamental parts of the plant in the plant image using a pre-trained plant part recognition model or attention model, and The identified ornamental parts are divided out for use in identifying color information of the ornamental parts of the plant.

11. A readable storage medium storing a computer program, characterized in that: When the computer program is executed, the plant recommendation method according to any one of claims 1 to 10 is implemented.

12. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed, the plant recommendation method according to any one of claims 1 to 10 is implemented.

Images