Plant identification processing method and device

Abstract

The embodiment of the invention provides a plant recognition processing method and device.The plant recognition processing method comprises the steps that in the plant image processing process, recognition cue words are generated for plant images uploaded by a user terminal, and the plant images and the recognition cue words are input into a large language model for shape feature recognition; and according to the obtained shape features, performing graph conversion on the plant contour graph of the plant image to obtain a geometric graph, and finally generating graph knowledge data of the geometric graph and returning the graph knowledge data to the user terminal, thereby performing graph knowledge learning related to the plant shape on the basis of identifying the shape of the plant image.

Description

Technical Field

[0001] This document relates to the technical field of data processing, and in particular, to a plant recognition processing method and apparatus. Background Art

[0002] With the continuous development and popularization of artificial intelligence technologies and hardware devices, the scope of application of various services provided based on artificial intelligence technologies and hardware devices is also becoming wider and wider. In this context, various ways of application interaction through artificial intelligence technologies and hardware devices have emerged, such as application programs for educational learning through artificial intelligence technologies, and services for problem dialogue and knowledge retrieval through artificial intelligence technologies. However, as the number of application programs accessing artificial intelligence technologies increases, the competition among application providers is also intensifying. In this context, how to increase the application frequency of application programs in actual life scenarios has become the focus of attention of all parties. Summary of the Invention

[0003] One or more embodiments of this specification provide a plant recognition processing method, including: obtaining a plant image uploaded by a user terminal, and generating a recognition prompt word for shape recognition of the plant image. Inputting the plant image and the recognition prompt word into a large language model for shape feature recognition to obtain shape features. Based on the shape features, performing graphic transformation on the plant contour graphic of the plant image to obtain a geometric graphic. Generating graphic knowledge data of the geometric graphic and returning it to the user terminal.

[0004] One or more embodiments of this specification provide another plant recognition processing method, including: collecting a plant image and uploading it to a server to perform shape feature recognition on the plant image through a large language model to obtain shape features, and performing graphic transformation on the plant contour graphic of the plant image based on the shape features to obtain a geometric graphic. Receiving and displaying the graphic knowledge data of the geometric graphic returned by the server.

[0005] One or more embodiments of this specification provide a plant recognition processing apparatus, including: a prompt word generation module configured to obtain a plant image uploaded by a user terminal and generate a recognition prompt word for shape recognition of the plant image. A shape recognition module configured to input the plant image and the recognition prompt word into a large language model for shape feature recognition to obtain shape features. A graphic transformation module configured to perform graphic transformation on the plant contour graphic of the plant image based on the shape features to obtain a geometric graphic. A graphic knowledge generation module configured to generate graphic knowledge data of the geometric graphic and return it to the user terminal.

[0006] One or more embodiments of this specification provide another plant recognition processing device, including: an image acquisition and upload module, configured to acquire a plant image and upload it to a server, so as to perform shape feature recognition on the plant image through a large language model to obtain shape features, and perform graphic transformation on the plant contour graph of the plant image based on the shape features to obtain geometric graphs. A graphic knowledge display module, configured to receive and display the graphic knowledge data of the geometric graph returned by the server.

[0007] One or more embodiments of this specification provide a plant recognition processing device, including: a processor; and a memory configured to store computer-executable instructions, the computer-executable instructions, when executed, cause the processor to: acquire a plant image uploaded by a user terminal and generate a recognition prompt for shape recognition of the plant image. Input the plant image and the recognition prompt into a large language model for shape feature recognition to obtain shape features. Perform graphic transformation on the plant contour graph of the plant image based on the shape features to obtain geometric graphs. Generate graphic knowledge data of the geometric graphs and return it to the user terminal.

[0008] One or more embodiments of this specification provide another plant recognition processing device, including: a processor; and a memory configured to store computer-executable instructions, the computer-executable instructions, when executed, cause the processor to: acquire a plant image and upload it to a server, so as to perform shape feature recognition on the plant image through a large language model to obtain shape features, and perform graphic transformation on the plant contour graph of the plant image based on the shape features to obtain geometric graphs. Receive and display the graphic knowledge data of the geometric graph returned by the server.

[0009] One or more embodiments of this specification provide a computer-readable storage medium for storing computer-executable instructions, the computer-executable instructions, when executed, implement the following process: acquire a plant image uploaded by a user terminal and generate a recognition prompt for shape recognition of the plant image. Input the plant image and the recognition prompt into a large language model for shape feature recognition to obtain shape features. Perform graphic transformation on the plant contour graph of the plant image based on the shape features to obtain geometric graphs. Generate graphic knowledge data of the geometric graphs and return it to the user terminal.

[0010] One or more embodiments of this specification provide another computer-readable storage medium for storing computer-executable instructions. When the computer-executable instructions are executed, the following processes are implemented: collecting a plant image and uploading it to a server to perform shape feature recognition on the plant image through a large language model to obtain shape features, and performing graphic transformation on the plant contour graph of the plant image based on the shape features to obtain a geometric graph. Receiving and displaying the graphic knowledge data of the geometric graph returned by the server. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] To more clearly illustrate the technical solutions in one or more embodiments of this specification or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments recorded in this specification. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings. Figure 1 It is a schematic diagram of an implementation environment of a plant recognition processing method provided by one or more embodiments of this specification; Figure 2 It is a processing flow chart of a plant recognition processing method provided by one or more embodiments of this specification; Figure 3 It is a schematic diagram of a plant image acquisition page provided by one or more embodiments of this specification; Figure 4 It is a schematic diagram of a knowledge display page provided by one or more embodiments of this specification; Figure 5 It is a schematic diagram of an image editing page provided by one or more embodiments of this specification; Figure 6 It is a schematic diagram of a virtual badge display page provided by one or more embodiments of this specification; Figure 7 It is a schematic diagram of a virtual badge storage page provided by one or more embodiments of this specification; Figure 8 It is a processing flow chart of a plant recognition processing method applied to a plant recognition scenario provided by one or more embodiments of this specification; Figure 9 It is a processing flow chart of another plant recognition processing method provided by one or more embodiments of this specification; Figure 10 It is a schematic diagram of an embodiment of a plant recognition processing device provided by one or more embodiments of this specification; Figure 11 It is a schematic diagram of another embodiment of a plant recognition processing device provided by one or more embodiments of this specification; Figure 12 Schematic diagram of the structure of a plant recognition processing device provided for one or more embodiments of this specification Figure 13 Schematic diagram of the structure of another plant recognition processing device provided for one or more embodiments of this specification. Detailed implementation manners

[0012] In order to enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings in one or more embodiments of this specification. Obviously, the described embodiments are only some of the embodiments of this specification, rather than all the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of this document.

[0013] The plant recognition processing method provided by one or more embodiments of this specification is applicable to the implementation environment of a plant recognition processing system. Referring to Figure 1 , this implementation environment at least includes: User terminal 101 and server 102; Among them, the user terminal 101 is used to collect plant images and upload them to the server 102, and cooperate with the server 102 to learn graphic knowledge data; the user terminal 101 may specifically be a mobile phone, a personal computer, a tablet computer, an e-book reader, a device for information interaction based on VR (Virtual Reality), AR (Augmented Reality), a vehicle-mounted terminal, an IoT device, a wearable intelligent device, a laptop computer, a desktop computer, and so on; The server 102 is used to perform shape feature recognition and graphic conversion on the plant images uploaded by the user terminal 101 to obtain geometric graphics, and generate graphic knowledge data of the geometric graphics and return it to the user terminal 101. The server 102 may be a single server, or a server cluster composed of several servers, or one or more cloud servers in a cloud computing platform.

[0014] In this implementation environment, during the process of the user terminal 101 and the server 102 cooperating to perform plant recognition processing, the user collects a plant image through the user terminal 101 and uploads it to the server 102. For the uploaded plant image, the server 102 generates an identification prompt word for shape recognition of the plant image. On this basis, by inputting the plant image and the identification prompt word into a large language model for shape feature recognition to obtain shape features, based on the shape features, the plant contour graph of the plant image is graphically transformed to obtain a geometric graph, and finally, the graphic knowledge data of the geometric graph is generated and returned to the user terminal, so as to perform graphic knowledge learning related to the plant shape on the basis of recognizing the shape of the plant image.

[0015] One or more embodiments of a plant recognition processing method provided in this specification are as follows: Refer to Figure 2 In this embodiment, the plant recognition processing method specifically includes steps S202 to S208.

[0016] Step S202: Obtain the plant image uploaded by the user terminal and generate an identification prompt word for shape recognition of the plant image.

[0017] The plant image in this embodiment refers to an image of a plant collected by the user through the user terminal. The plant can specifically be various plants such as arbor plants, shrub plants, or ground cover plants. The plant image can specifically be a plant image collected for the leaves of the plant, such as a leaf image collected for the leaves of a certain tree, or it can also be a plant image collected for the whole or part of the plant, such as a grass image collected for the whole of a certain grass plant, or a fruit image collected for the fruit of a certain plant, or a flower image collected for the flower of a certain plant.

[0018] Specifically in implementation, it is obtained by the user terminal collecting an image of the plant. After the image collection is completed and the plant image is obtained, the user terminal uploads the plant image. Correspondingly, the plant image uploaded by the user terminal is obtained here. Specifically, to collect an image of the plant to obtain the plant image, the image collection can be performed by accessing the application installed on the user terminal. After the image collection is completed, the user terminal can upload the plant image; or, the image collection can also be performed by accessing the service or subroutine provided by the application. After the image collection is completed, the user terminal can upload the plant image.

[0019] Further, after obtaining the plant image uploaded by the user terminal, it is necessary to perform shape recognition on the plant image and conduct relevant knowledge learning based on the shape recognition. The process of performing shape recognition on the plant image can be achieved by calling a large language model. Specifically, before calling the large language model, an identification prompt for performing shape recognition on the plant image is generated. For example, the generated identification prompt contains a task description text for the task of performing shape recognition.

[0020] In the actual scenario, the user who conducts knowledge learning based on plant shape recognition can be a teenage user. In this case, the guardian user of the teenage user can collect a plant image through the user terminal, or, if the teenage user owns a user terminal, the teenage user can also collect a plant image through the user terminal; in addition, the user who conducts knowledge learning during the plant recognition process can be an adult user, and the adult user can collect a plant image through the user terminal.

[0021] In practical applications, during the process of conducting knowledge learning based on plant shape recognition, since the number of common plants is limited and the plant shapes of common plants are also limited, therefore, in order to enhance the richness of knowledge learning, it is possible to start from the user location information and recommend or remind the user terminal to collect plant images based on the user location information and the location information of the plant to be recommended, so as to remind the user to collect plant images and then conduct knowledge learning.

[0022] Specifically, in an optional implementation manner provided in this embodiment, the user location information collected by the user terminal is used to match the user location information with the location information of the plant to be recommended; If the match is successful, an image collection reminder for the plant to be recommended is sent to the user terminal or the connected device of the user terminal; If the match fails, no processing is required.

[0023] During the specific execution process, matching the user location information with the location information of the plant to be recommended can specifically be calculating whether the location distance between the user location information and the location information of the plant to be recommended is less than a preset distance. If it is less, it is determined that the match is successful. If it is greater than or equal to, it is determined that the match fails; the connected device of the user terminal can be a wearable device that establishes a near-field communication or wireless network connection with the user terminal; here, in the case of sending an image collection reminder for the plant to be recommended to the user terminal or the connected device of the user terminal, correspondingly, the plant image uploaded by the above user terminal can be a plant image collected for the plant to be recommended; optionally, the plant to be recommended is determined based on the plant images and plant texts included in the user's social data.

[0024] Step S204: Input the plant image and the recognition prompt into a large language model for shape feature recognition to obtain shape features.

[0025] In this embodiment, shape recognition of a plant image refers to recognizing the specific shape of the plant in the plant image, so that corresponding graphic knowledge learning can be carried out starting from the recognized plant shape. In the specific implementation process, shape features are obtained by inputting the plant image and the recognition prompt into a large language model for shape feature recognition.

[0026] A large language model refers to a shape recognition model that can perform corresponding recognition processing on the input plant image using the input recognition prompt, and this large language model is a multimodal model that supports text and image input. The large language model can adopt a natural language model with a neural network architecture containing a large number of parameters, and can also adopt a pre-trained large language model (Large Language Model, LLM) or an open-source large language model. Or, it can also be a large language model obtained by fine-tuning the base large language model.

[0027] Specifically, in the process of shape feature recognition, in order to improve the recognition success rate and recognition accuracy of shape feature recognition for plant images, shape feature recognition can be carried out from two aspects: the plant contour feature and the number of included angles / corner points in the plant contour. In an optional implementation manner provided in this embodiment, shape feature recognition includes: Extract the plant contour feature of the plant image, and perform graphic fitting on the plant contour feature to obtain a plant contour graph; Perform included angle detection on the plant contour graph to obtain the number of included angles; the shape features include the plant contour graph and / or the number of included angles.

[0028] Among them, in the process of extracting the plant contour feature of the plant image, the plant contour feature of the plant image can be extracted through the contour extraction module or contour extraction algorithm of the large language model. Or, the plant image block can be extracted from the plant image through the image segmentation module or image segmentation algorithm of the large language model, and then the plant contour feature of the plant image block can be extracted through the contour extraction module or contour extraction algorithm of the large language model. Further, the plant contour feature can be subjected to graphic fitting through the graphic fitting module of the large language model to obtain a plant contour graph, and then the number of included angles can be obtained by performing included angle detection on the plant contour graph. The specific method of included angle detection can be to first detect the vertices of the plant contour graph, and then calculate whether the included angle between the adjacent sides of each vertex is greater than a preset angle threshold. If so, it can be determined that the current vertex and the adjacent side form an included angle, and the current vertex is the included angle. The number of included angles represents the number of included angles contained in the plant contour graph.

[0029] It should be noted that the specific method of shape feature recognition provided above can be adjusted according to actual implementation needs during actual execution. For example, shape feature recognition includes extracting the plant contour features of a plant image, and performing graphic fitting on the plant contour features to obtain a plant contour graph, and using the plant contour graph as the shape feature; or, extracting the plant contour graph of the plant image, and performing angle detection on the plant contour graph to obtain the number of angles, and using the number of angles as the shape feature.

[0030] In practical applications, during the process of collecting plant images, the image blocks of plants in the collected plant images may be missing due to improper collection operations, or may also be missing due to the defects of the plants themselves. In view of this, in order to improve the recognition success rate and recognition accuracy of shape feature recognition, the image blocks of plants in the plant images can be repaired, and then shape feature recognition can be performed on the basis of image repair. Here, image repair can be to perform plant species recognition on the plant image blocks to obtain the plant species, and perform image repair on the plant image blocks based on the plant species.

[0031] Specifically, in an optional implementation manner provided in this embodiment, if it is detected that the image blocks of plants in the plant image are missing, plant species recognition is performed on the plant image blocks to obtain the plant species; image repair is performed on the plant image blocks based on the plant species, and the plant image is updated according to the repaired plant image blocks.

[0032] During the specific execution process, image repair can be performed before inputting the plant image and the recognition prompt words into the large language model for shape feature recognition. In this case, after obtaining the plant image uploaded by the user terminal, plant species recognition is performed on the plant image blocks in the plant image to obtain the plant species, and image repair is performed on the plant image blocks based on the plant species, and then recognition prompt words for shape recognition of the repaired plant image are generated, that is: obtaining the plant image uploaded by the user terminal and generating recognition prompt words for shape recognition of the plant image can be replaced by: performing plant species recognition on the plant image blocks in the plant image to obtain the plant species, and performing image repair on the plant image blocks based on the plant species, and then generating recognition prompt words for shape recognition of the repaired plant image (repaired plant image). Correspondingly, in this case, the plant image input into the large language model is the repaired plant image; In addition, after inputting the plant image and the recognition prompt words into the large language model for shape feature recognition, the large language model can perform image restoration on the plant image blocks in the plant image. In this case, recognition prompt words for image restoration and shape recognition of the plant image can be generated. In this case, the recognition prompt words for shape recognition of the plant image can be replaced with recognition prompt words for image restoration and shape recognition of the plant image. Moreover, inputting the plant image and the recognition prompt words into the large language model for shape feature recognition to obtain shape features can be replaced with: inputting the plant image and the recognition prompt words into the large language model for image restoration and shape feature recognition to obtain shape features; among which, image restoration includes obtaining the plant species based on the plant image blocks for plant species recognition, and performing image restoration on the plant image blocks based on the plant species.

[0033] Step S206, perform graphic transformation on the plant contour graph of the plant image based on the shape features to obtain a geometric graph.

[0034] In specific implementation, after obtaining the shape features by performing shape feature recognition on the plant image through the large language model, perform graphic transformation on the plant contour graph of the plant image to obtain a geometric graph. Specifically, it is based on the shape features obtained by performing shape feature recognition, and convert the plant contour graph into a geometric graph, so as to make the matching degree between the converted geometric image and the plant contour graph higher by combining the shape features.

[0035] Specifically, during the process of performing graphic transformation on the plant contour graph of the plant image, a graphic transformation model can be used to perform graphic transformation of the plant contour graph into a geometric graph. In an optional implementation manner provided in this embodiment, performing graphic transformation on the plant contour graph of the plant image based on the shape features to obtain a geometric graph includes: inputting the shape features and the plant contour graph into the graphic transformation model for geometric graph transformation to obtain a geometric graph.

[0036] Optionally, the geometric graph transformation includes: fitting and matching the shape features and the plant contour graph with the regular graphs in the graph library, and using the matched regular graph as the geometric graph.

[0037] For example, the user accesses the service for plant recognition interaction provided by the application installed on the user terminal. The name of this service is "Collect Leaves". After entering the service page, collect an image of a ginkgo leaf (ginkgo leaf image) as the plant image. As Figure 3 shown, after collecting the plant image, the user terminal uploads the plant image; Here, after receiving the plant image uploaded by the user terminal, an identification prompt for shape feature recognition of the plant image is generated. The plant image and the identification prompt are input into a large language model for shape feature recognition to obtain shape features, and based on the shape features, geometric transformation is performed on the plant contour graph of the plant image to obtain a geometric graph. The obtained geometric graph is Figure 4 the sector graph shown in

[0038] It should be noted that obtaining shape features through shape feature recognition of the plant image includes the plant contour graph and / or the number of included angles. Based on this, when the shape features include the plant contour graph and the number of included angles, the above-mentioned geometric transformation of the plant contour graph of the plant image based on the shape features to obtain a geometric graph can be replaced by geometric transformation of the plant contour graph based on the number of included angles; in addition, when the shape features only include the plant contour graph, the above-mentioned geometric transformation of the plant contour graph of the plant image based on the shape features to obtain a geometric graph can be replaced by geometric transformation of the plant contour graph; or, when the shape features only include the number of included angles, the above-mentioned geometric transformation of the plant contour graph of the plant image based on the shape features to obtain a geometric graph can be replaced by geometric transformation of the plant contour graph of the plant image based on the number of included angles. The plant contour graph is obtained by fitting the contour graph of the plant image.

[0039] Step S208: Generate graphic knowledge data of the geometric graph and return it to the user terminal.

[0040] In specific implementation, after converting the plant contour graph of the plant image into a geometric graph, that is, after determining the geometric graph to be used for knowledge learning according to the plant contour graph of the plant image, graphic knowledge data of the geometric graph is generated and returned to the user terminal. In this way, by returning the graphic knowledge data of the geometric graph to the user terminal, the user on the user terminal side can learn knowledge related to geometric graphs.

[0041] In an optional implementation manner provided in this embodiment, the graphic knowledge data of the geometric graph is generated in the following manner: generating a plant knowledge field according to the plant recognition information of the plant image; calling a knowledge retrieval interface to retrieve the graphic knowledge field of the geometric graph, and generating a graphic knowledge text and / or a teaching knowledge text according to the plant knowledge field and the graphic knowledge field. The generated graphic knowledge text and / or teaching knowledge text here is the graphic knowledge data.

[0042] In the process of generating graphic knowledge data of geometric figures, the graphic knowledge data can be generated by calling the corresponding knowledge generation interface. Specifically, the plant species of the plant image can be identified, the plant knowledge fields can be generated according to the plant species, and the knowledge retrieval interface can be called to retrieve the graphic knowledge fields of the geometric figure. The plant knowledge fields and the graphic knowledge fields are used as the graphic knowledge data. Alternatively, the graphic knowledge data can be generated based on these two fields of the plant knowledge fields and the graphic knowledge fields. In addition, in the process of the graphic knowledge data of the geometric figure, the graphic knowledge fields of the geometric figure can also be retrieved through the knowledge retrieval interface, and the retrieved graphic knowledge fields are used as the graphic knowledge data. Among them, the graphic knowledge data can be the graphic knowledge data provided to adolescent users and / or graphic teaching knowledge data.

[0043] Continuing with the above example, after obtaining the sector-shaped geometric figure through geometric figure conversion of the plant contour figure of the ginkgo leaf plant image, based on the recognition that the plant image is a ginkgo leaf image, the generated plant knowledge field is "The ginkgo leaf you found is a natural standard sector", and the graphic knowledge of the sector-shaped figure is retrieved by calling the data retrieval interface or the graphic knowledge retrieval interface. The retrieved graphic knowledge field of the sector-shaped figure is "In the geometric world, this 120° symmetric arc is called a'standard sector', and even Leonardo da Vinci used it to study the golden ratio~". These two parts together form the graphic knowledge data. After the graphic knowledge data is returned to the user terminal, the user terminal displays the returned graphic knowledge data, such as Figure 4 the graphic knowledge data shown on the knowledge display page as shown.

[0044] In this embodiment, after the graphic knowledge data is returned to the user terminal, the returned graphic knowledge data can be displayed on the user terminal. In addition, the graphic knowledge data can also be displayed through the user device connected to the user terminal to improve the adaptability of the graphic knowledge data to the actual scenario where the user is located. Optionally, after the graphic knowledge data is returned to the user terminal, the graphic knowledge data is sent to the wearable device connected to the user terminal, and the graphic knowledge data is rendered and displayed through the wearable device. Among them, the wearable device includes AR (Augmented Reality) glasses.

[0045] In practical applications, when users on the user terminal side participate in the process of plant image recognition and knowledge learning, they may encounter plants with special shapes or plants that users like. In this case, users often want to save the plant images. For this purpose, in order to enhance the user's sense of participation and interactive experience, the plant images can be personalized edited during the process of saving the plant images. Specifically, during the image editing process, the plant images can be edited by editing geometric figures, so as to improve the convenience of the user for image editing. Specifically, after generating the graphic knowledge data of the geometric figure and returning it to the user terminal, in an optional implementation manner provided by this embodiment, according to the editing instruction of the geometric figure submitted by the user terminal, the plant image block in the plant image is edited; the plant image block obtained by the editing process is rendered according to the rendering parameters to obtain a certified image or a virtual voucher image.

[0046] Among them, the geometric figure can be displayed on the upper layer of the plant image; the certified image refers to the image for storage after rendering the edited plant image block; the virtual voucher image refers to the image generated by storing the plant image in the form of a virtual voucher, such as generating a virtual badge image for the edited plant image block.

[0047] Based on this, after the user on the user terminal side completes the editing process of the plant image to obtain a certified image or a virtual voucher image, the certified image or the virtual voucher image obtained by the editing process can be shared. Specifically, in an optional implementation manner provided by this embodiment, after rendering the plant image block obtained by the editing process according to the rendering parameters to obtain a certified image or a virtual voucher image, the following sharing process is adopted: According to the sharing instruction submitted by the user terminal, generate a sharing message of the certified image or the virtual voucher image and send the message; if it is detected that the sharing message is triggered, send the certified image or the virtual voucher image to the user terminal that triggered the sharing message; Or, According to the sharing instruction submitted by the user terminal, generate a sharing message of the certified image or the virtual voucher image and send the message; if an access request submitted by scanning the identification code carried in the sharing message is received, send the certified image or the virtual voucher image to the user terminal that submitted the access request.

[0048] Still taking the recognition of the plant image of ginkgo leaves as an example above, after generating the graphic knowledge data of the fan-shaped figure and returning it to the user terminal, the fan-shaped figure can be displayed on the knowledge display page. The user on the user terminal side can edit the ginkgo leaves by editing the fan-shaped figure. Or, after the display of the graphic knowledge data on the knowledge display page is completed, it can jump from the knowledge display page to the image editing page, such as Figure 5As shown, the image editing page displays a plant image, and a fan-shaped graphic is displayed in the upper layer of the plant image. The user can also edit the ginkgo leaf image by editing the fan-shaped graphic. In addition, a prompt text can be displayed on the image editing page to guide or remind the user to perform graphic editing, such as Figure 5 The prompt text displayed in the image editing page shown.

[0049] In addition, in practical applications, in order to improve the convenience and editing efficiency of users on the user terminal side for plant image editing, the plant image can also be edited according to the user's previous preferences for plant image editing, so as to reduce the editing operations of the user during the plant image editing process, or the image obtained by directly editing according to the user's previous preferences for plant image editing can be stored without the user performing editing operations. Specifically, in an optional implementation manner provided in this embodiment, after generating the graphic knowledge data of the geometric graphic and returning it to the user terminal, the following operations are performed: Read the stored editing preference data, and edit and process the plant image blocks in the plant image according to the editing instruction sequence included in the editing preference data; Render the plant image blocks obtained by the editing process according to the rendering parameters included in the editing preference data to obtain a certified image or a virtual voucher image.

[0050] Among them, the geometric graphic can be displayed in the upper layer of the plant image; the editing preference data refers to the records of the user terminal or the user on the user terminal side for previous plant recognition and graphic knowledge learning. Considering that the editing preference data is to a certain extent the user's privacy, user authorization can be obtained before obtaining the editing preference data.

[0051] In the specific execution process, after obtaining the certified image or the virtual voucher image, the certified image or the virtual voucher image can be stored or archived according to the archiving instruction submitted by the user. After obtaining the certified image or the virtual voucher image, the certified image or the virtual voucher image can also be directly stored or archived. During the storage or archiving process, the certified image or the virtual voucher image can be stored in the user storage space for the user. This user storage space can be the user storage space provided by an application program, the service provided by the application program, or a subroutine.

[0052] For example, in the above scenario of recognizing the plant image of the ginkgo leaf, according to the user's editing instruction for the geometric graphic, the ginkgo leaf image block in the plant image is edited and processed, and the ginkgo leaf image block obtained by the editing process is rendered according to the rendering parameters to obtain a virtual badge image of the ginkgo leaf, such as Figure 6 shown; further, the virtual badge image can be stored in the user storage space, and the virtual badge image stored in the user storage space is asFigure 7 As shown; meanwhile, the user storage space is also configured with a sharing control, and the user can share the virtual badge image in the user storage space by triggering the sharing control.

[0053] In summary, for the plant recognition and processing method provided in this embodiment, during the process of recognizing plant images and learning graphic knowledge, for the plant images uploaded by the user terminal, based on generating recognition prompt words for shape recognition of the plant images, by inputting the plant images and the recognition prompt words into a large language model for shape feature recognition to obtain shape features, thereby realizing graphic recognition of plant images with the help of the multi-modal large language model, and starting from the shape features, combining the shape features to perform graphic conversion on the plant contour graphics of the plant images to obtain geometric graphics, and finally generating graphic knowledge data of the geometric graphics and returning it to the user terminal. In this way, on the basis of shape recognition of plant images, graphic knowledge is generated, enabling the user who collects plant images on the user terminal side to learn graphic knowledge during the image collection process, not only enhancing the interactive interest of plant image collection, but also enhancing the enthusiasm of users for knowledge learning.

[0054] The above steps S202 to S208 provided in this embodiment can be executed by the server. The server can specifically be a server of an application program, a server of a service, or a server of a subroutine; it should be noted that the above steps S202 to S208 executed by the server and the steps S902 to S904 executed by the user terminal in the following embodiment can cooperate with each other during the execution process. Therefore, when reading this embodiment, please refer to the corresponding content of steps S902 to S904 provided in the following method embodiment, and when reading the following method embodiment, please refer to the corresponding content of steps S202 to S208 provided in this embodiment.

[0055] The following takes the application of a plant recognition and processing method provided in this embodiment in a plant recognition scenario as an example, combined with Figure 8 , to further illustrate the plant recognition and processing method provided in this embodiment. See Figure 8 , the plant recognition and processing method applied to a plant recognition scenario specifically includes the following steps.

[0056] Step S804, receive the plant image uploaded by the user terminal.

[0057] Step S806, generate recognition prompt words for shape recognition of the plant image.

[0058] Step S808, input the plant image and the recognition prompt words into a large language model for shape feature recognition to obtain shape features.

[0059] Step S810: Perform graphic transformation on the plant contour graphic of the plant image based on the shape feature to obtain a geometric graphic.

[0060] Step S812: Generate graphic knowledge data of the geometric graphic and return it to the user terminal.

[0061] Step S820: According to the editing instruction submitted by the user terminal, perform editing processing on the plant image blocks in the plant image.

[0062] Step S822: Perform rendering processing on the plant image blocks obtained by the editing processing according to the rendering parameters to obtain a virtual certificate image.

[0063] Step S824: Return the virtual certificate image to the user terminal.

[0064] It should be noted that any one step or any combination of steps from Step S804 to Step S812 and from Step S820 to Step S826 can be combined with any one step or any combination of steps from the above-mentioned Step S202 to Step S208 according to the needs of implementation and deployment to form a new implementation method; in addition, according to the actual deployment needs, any one or any combination of technical features from Step S804 to Step S812 and from Step S820 to Step S826 can be selected and combined with any one or more technical features provided by the above-mentioned Step S202 to Step S208 to form a new implementation method; or, any one or any combination of technical features from Step S804 to Step S812 and from Step S820 to Step S826 can also be replaced by any one or more technical feature combinations provided by the above-mentioned Step S202 to Step S208 according to the actual deployment needs to form a new implementation method, which will not be elaborated here one by one.

[0065] In addition, it should also be noted that the above-mentioned Step S804 to Step S812 and Step S820 to Step S826 provided in this embodiment can be executed by the server. It should be noted that the above-mentioned Step S804 to Step S812 and Step S820 to Step S826 executed by the server can cooperate with the steps S802, S814 to S816, and S826 executed by the user terminal in the following embodiments during the execution process. Therefore, when reading this embodiment, please refer to the corresponding content of the steps S802, S814 to S816, and S826 provided in the following method embodiment, and when reading the following method embodiment, please refer to the corresponding content of the steps S804 to Step S812 and Step S820 to Step S826 provided in this embodiment.

[0066] Another embodiment of the plant recognition processing method provided in this specification is as follows: Refer to Figure 8, the plant recognition processing method provided in this embodiment can be applied to a user terminal, and the method specifically includes steps S902 to S904.

[0067] Step S902, collect a plant image and upload it to the server, so as to perform shape feature recognition on the plant image through a large language model to obtain shape features, and perform graphic conversion on the plant contour graph of the plant image based on the shape features to obtain a geometric graph.

[0068] The plant image in this embodiment refers to an image of a plant collected by a user through a user terminal. The plant can specifically be various plants such as arbor plants, shrub plants, or ground cover plants. The plant image can specifically be a plant image collected for the leaves of the plant, such as a leaf image collected for the leaves of a certain tree, or it can also be a plant image collected for the whole or part of the plant, such as a grass image collected for the whole of a certain grass plant, or a fruit image collected for the fruit of a certain plant, or a flower image collected for the flower of a certain plant.

[0069] Specifically in implementation, it is obtained by the user terminal collecting an image of the plant. After the image collection is completed to obtain the plant image, the collected plant image is uploaded to the server; specifically, to collect an image of the plant to obtain the plant image, the image collection can be performed by accessing the application installed on the user terminal. After the image collection is completed, the user terminal can upload the plant image to the server; or, the image collection can also be performed by accessing the service or subroutine provided by the application. After the image collection is completed, the user terminal can upload the plant image to the server.

[0070] Correspondingly, after the server obtains the uploaded plant image, it needs to perform shape recognition on the plant image and perform relevant graphic knowledge learning on the basis of the shape recognition. The process of performing shape recognition on the plant image can be achieved by calling a large language model. After obtaining the shape features by performing shape feature recognition on the plant image through the large language model, a geometric graph can be obtained by performing graphic conversion on the plant contour graph of the plant image based on the shape features; here, before calling the large language model, an identification prompt word for performing shape recognition on the plant image can be generated. For example, the generated identification prompt word contains the task description text for the task of performing shape recognition. On this basis, the plant image and the identification prompt word are input into the large language model for shape feature recognition to obtain the shape features.

[0071] In an actual scenario, the users who conduct knowledge learning based on plant shape recognition can be adolescent users. In this case, the guardian users of the adolescent users can collect plant images through a user terminal, or, if the adolescent users own a user terminal themselves, the adolescent users can also collect plant images of plants through the user terminal; in addition, the users who conduct knowledge learning during the plant recognition process can be adult users, and the adult users can collect plant images through the user terminal.

[0072] In practical applications, during the process of knowledge learning based on plant shape recognition, since the number of common plants is limited and the plant shapes of common plants are also limited, therefore, in order to enhance the richness of knowledge learning, it is possible to start from the user location information and recommend or remind the collection of plant images according to the user location information and the location information of the plants to be recommended, so as to remind the user to collect plant images and then conduct knowledge learning.

[0073] Specifically, in an optional implementation manner provided in this embodiment, receive an image collection reminder of the plant to be recommended sent by the server, and the image collection reminder is generated when the user location information is successfully matched with the location information of the plant to be recommended; during the specific execution process, match the user location information with the location information of the plant to be recommended. Specifically, it can be to calculate whether the location distance between the user location information and the location information of the plant to be recommended is less than a preset distance. If it is less, it is determined that the match is successful; if it is greater than or equal to, it is determined that the match fails; the connected device of the user terminal can be a wearable device that establishes a near-field communication or a wireless network connection with the user terminal; here, the plant image uploaded to the server can be a plant image obtained by collecting an image of the plant to be recommended; optionally, the plant to be recommended is determined according to the plant images and plant texts included in the user's social data.

[0074] In this embodiment, performing shape recognition on a plant image means recognizing the specific shape of the plant in the plant image, so as to be able to start corresponding graphic knowledge learning from the recognized plant shape. During the specific execution process, the plant image and the recognition prompt words can be input into a large language model for shape feature recognition to obtain shape features.

[0075] The large language model refers to a shape recognition model that can perform corresponding recognition processing on the input plant image with the input recognition prompt words, and this large language model is a multi-modal model that supports text and image input. The large language model can adopt a natural language model with a neural network architecture containing a large number of parameters, and can also adopt a pre-trained large language model (Large Language Model, LLM) or an open-source large language model. Or, it can also be a large language model obtained by fine-tuning the base large language model.

[0076] Specifically, during the shape feature recognition process, in order to improve the recognition success rate and accuracy of shape feature recognition for plant images, shape feature recognition can be carried out from two perspectives: the plant contour feature and the number of included angles / corner points in the plant contour. In an optional implementation provided in this embodiment, the shape feature recognition includes: Extract the plant contour feature of the plant image, and perform graphic fitting on the plant contour feature to obtain a plant contour graph; Perform included angle detection on the plant contour graph to obtain the number of included angles; the shape feature includes the plant contour graph and / or the number of included angles.

[0077] Among them, during the process of extracting the plant contour feature of the plant image, the plant contour feature of the plant image can be extracted through the contour extraction module or contour extraction algorithm of the large language model. Or, the plant image block can be extracted from the plant image through the image segmentation module or image segmentation algorithm of the large language model, and then the plant contour feature of the plant image block can be extracted through the contour extraction module or contour extraction algorithm of the large language model; further, the plant contour feature can be subjected to graphic fitting through the graphic fitting module of the large language model to obtain a plant contour graph, and then the included angle detection is performed on the plant contour graph to obtain the number of included angles. The specific method of included angle detection can be to first detect the vertices of the plant contour graph, and then calculate whether the included angle between the adjacent sides of each vertex is greater than a preset angle threshold. If so, it can be determined that the current vertex and the adjacent side form an included angle, and the current vertex is the included angle. The number of included angles represents the number of included angles contained in the plant contour graph.

[0078] It should be noted that for the specific method of the above-provided shape feature recognition, during the actual execution process, it can also be adjusted according to the actual execution needs. For example, the shape feature recognition includes extracting the plant contour feature of the plant image, performing graphic fitting on the plant contour feature to obtain a plant contour graph, and using the plant contour graph as the shape feature; or, extracting the plant contour graph of the plant image, performing included angle detection on the plant contour graph to obtain the number of included angles, and using the number of included angles as the shape feature.

[0079] In practical applications, during the process of plant image acquisition, the image blocks of plants in the acquired plant images may be missing due to improper acquisition operations, or may also be missing due to defects in the plants themselves. In view of this, in order to improve the recognition success rate and recognition accuracy of shape feature recognition, the image blocks of plants in the plant images can be image-restored, and then shape feature recognition can be performed on the basis of the image restoration. Here, the image restoration can be to perform plant species recognition based on the plant image blocks to obtain the plant species, and then perform image restoration on the plant image blocks based on the plant species.

[0080] Specifically, in an optional implementation manner provided in this embodiment, if it is detected that the image blocks of plants in the plant image are missing, plant species recognition is performed based on the plant image blocks to obtain the plant species; image restoration is performed on the plant image blocks based on the plant species, and the plant image is updated according to the restored plant image blocks.

[0081] During the specific execution process, image restoration can be performed before inputting the plant image and the recognition prompt word into the large language model for shape feature recognition. In this case, after obtaining the plant image uploaded by the user terminal, plant species recognition is performed based on the plant image blocks in the plant image to obtain the plant species, and image restoration is performed on the plant image blocks based on the plant species. Then, a recognition prompt word for shape recognition of the restored plant image is generated, that is: obtaining the plant image uploaded by the user terminal and generating a recognition prompt word for shape recognition of the plant image can be replaced by: performing plant species recognition based on the plant image blocks in the plant image to obtain the plant species, performing image restoration on the plant image blocks based on the plant species, and then generating a recognition prompt word for shape recognition of the restored plant image (restored plant image). Correspondingly, in this case, the plant image input into the large language model is the restored plant image; In addition, after inputting the plant image and the recognition prompt word into the large language model for shape feature recognition, the large language model can also perform image restoration on the plant image blocks in the plant image. In this case, a recognition prompt word for image restoration and shape recognition of the plant image can be generated. In this case, generating a recognition prompt word for shape recognition of the plant image can be replaced by generating a recognition prompt word for image restoration and shape recognition of the plant image, and inputting the plant image and the recognition prompt word into the large language model for shape feature recognition to obtain the shape feature can be replaced by: inputting the plant image and the recognition prompt word into the large language model for image restoration and shape feature recognition to obtain the shape feature; among which, the image restoration includes performing plant species recognition based on the plant image blocks to obtain the plant species, and performing image restoration on the plant image blocks based on the plant species.

[0082] After obtaining the shape features by performing shape feature recognition on the plant image through the large language model, the plant contour graph of the plant image is subjected to graph transformation to obtain a geometric graph. Specifically, based on the shape features obtained by shape feature recognition, the plant contour graph is transformed into a geometric graph, so as to make the matching degree between the transformed geometric image and the plant contour graph higher by combining the shape features.

[0083] Specifically, in the process of performing graph transformation on the plant contour graph of the plant image, the graph transformation model can be used to perform graph transformation of the plant contour graph into a geometric graph. In an optional implementation manner provided in this embodiment, based on the shape features, performing graph transformation on the plant contour graph of the plant image to obtain a geometric graph includes: inputting the shape features and the plant contour graph into the graph transformation model for geometric graph transformation to obtain a geometric graph.

[0084] Optionally, the geometric graph transformation includes: fitting and matching the above-mentioned shape features and the plant contour graph with the regular graphs in the graph library, and using the matched regular graph as the geometric graph.

[0085] For example, the user accesses the service for plant recognition interaction provided by the application installed on the user terminal. After entering the service page, an image of a ginkgo leaf (ginkgo leaf image) is collected as the plant image. As Figure 3 shown, after the plant image is collected, the user terminal uploads the plant image; Here, after receiving the plant image uploaded by the user terminal, an identification prompt word for performing shape feature recognition on the plant image is generated. The plant image and the identification prompt word are input into the large language model for shape feature recognition to obtain shape features, and based on the shape features, geometric graph transformation is performed on the plant contour graph of the plant image to obtain a geometric graph. The obtained geometric graph is Figure 4 the sector graph shown in.

[0086] It should be noted that the shape features obtained by performing shape feature recognition on the plant image include the plant contour graph and / or the number of included angles. Based on this, when the shape features include the plant contour graph and the number of included angles, the above-mentioned geometric graph obtained by performing graph transformation on the plant contour graph of the plant image based on the shape features can be replaced by performing graph transformation on the plant contour graph based on the number of included angles; in addition, when the shape features only include the plant contour graph, the above-mentioned geometric graph obtained by performing graph transformation on the plant contour graph of the plant image based on the shape features can be replaced by performing graph transformation on the plant contour graph; or, when the shape features only include the number of included angles, the above-mentioned geometric graph obtained by performing graph transformation on the plant contour graph of the plant image based on the shape features can be replaced by performing graph transformation on the plant contour graph of the plant image based on the number of included angles, and the plant contour graph is obtained by fitting the contour graph of the plant image.

[0087] Step S904, receive the graphic knowledge data of the geometric graph returned by the server and display it.

[0088] After uploading the plant image to the server, the server performs shape feature recognition on the plant image through a large language model to obtain shape features, and performs graph transformation on the plant contour graph of the plant image to obtain a geometric graph. On this basis, according to the obtained geometric graph, graphic knowledge data of the geometric graph is generated and returned. Here, the graphic knowledge data of the geometric graph returned by the server is received and displayed, so that the user on the user terminal side can learn knowledge related to the geometric graph.

[0089] In an optional implementation manner provided in this embodiment, the graphic knowledge data of the geometric graph is generated in the following manner: generating a plant knowledge field according to the plant recognition information of the plant image; calling a knowledge retrieval interface to retrieve the graphic knowledge field of the geometric graph, and generating a graphic knowledge text and / or a teaching knowledge text according to the plant knowledge field and the graphic knowledge field. Here, the generated graphic knowledge text and / or teaching knowledge text is the graphic knowledge data.

[0090] In the process of generating graphic knowledge data of geometric figures, the graphic knowledge data can be generated by calling the corresponding knowledge generation interface. Specifically, the plant species of the plant image can be identified, the plant knowledge fields can be generated according to the plant species, and the knowledge retrieval interface can be called to retrieve the graphic knowledge fields of the geometric figures. The plant knowledge fields and the graphic knowledge fields are used as the graphic knowledge data. Alternatively, the graphic knowledge data can be generated based on these two fields of the plant knowledge fields and the graphic knowledge fields. In addition, in the process of the graphic knowledge data of geometric figures, the graphic knowledge fields of geometric figures can also be retrieved through the knowledge retrieval interface, and the retrieved graphic knowledge fields are used as the graphic knowledge data. Among them, the graphic knowledge data can be the graphic knowledge data provided to adolescent users and / or graphic teaching knowledge data.

[0091] Continuing with the above example, after obtaining the sector-shaped geometric figure through geometric figure conversion of the plant contour figure of the plant image of ginkgo leaves, based on the recognition that the plant image is a ginkgo leaf image, the generated plant knowledge field is "The ginkgo leaf you found is a natural standard sector", and the graphic knowledge of the sector-shaped figure is retrieved by calling the data retrieval interface or the graphic knowledge retrieval interface. The retrieved graphic knowledge field of the sector-shaped figure is "In the geometric world, this 120° symmetric arc is called a'standard sector', and even Leonardo da Vinci used it to study the golden ratio~". These two parts together constitute the graphic knowledge data. After the graphic knowledge data is returned to the user terminal, the user terminal displays the returned graphic knowledge data, such as Figure 4 the graphic knowledge data displayed on the knowledge display page shown.

[0092] In this embodiment, after receiving the graphic knowledge data returned by the server, specifically in the process of displaying the graphic knowledge data, the returned graphic knowledge data can be displayed on the user terminal, and the graphic knowledge data can also be displayed through the user device connected to the user terminal, so as to improve the adaptability of the graphic knowledge data to the actual scene where the user is located. In an optional implementation manner provided by this embodiment, the graphic knowledge data is displayed in the following manner: the graphic knowledge data is displayed on the knowledge display page; or, the graphic knowledge data is sent to the connected wearable device to perform rendering display of the graphic knowledge data through the wearable device; the wearable device includes AR glasses.

[0093] In practical applications, when users on the user terminal side participate in the process of plant image recognition and knowledge learning, they may encounter plants with particularly special shapes or plants that users like. In this case, users often want to save the plant images. For this purpose, in order to enhance the user's sense of participation and interactive experience, the plant images can be personalized edited during the process of saving the plant images. Specifically, during the image editing process, the plant images can be edited by editing geometric figures, so as to improve the convenience of users for image editing. Specifically, after receiving and displaying the graphic knowledge data of the geometric figures returned by the server, in an optional implementation manner provided in this embodiment, obtain the editing instructions submitted for displaying the geometric figures on the upper layer of the plant image and submit them to the server; obtain and display the certified image or virtual voucher image from the server. Optionally, the certified image or virtual voucher image is obtained by rendering the plant image block obtained by editing according to the editing instructions according to the rendering parameters.

[0094] Among them, the certified image refers to the image used for storage after rendering the edited plant image block; the virtual voucher image refers to the image generated by storing the plant image in the form of a virtual voucher, such as generating a virtual badge image for the edited plant image block.

[0095] Based on this, after the user on the user terminal side completes the editing process of the plant image to obtain the certified image or virtual voucher image, the user can share the obtained certified image or virtual voucher image. Specifically, in an optional implementation manner provided in this embodiment, after obtaining and displaying the certified image or virtual voucher image from the server, submit the sharing instruction of the certified image or virtual voucher image to the server; Correspondingly, after the sharing instruction is submitted to the server, the server can generate a sharing message of the certified image or virtual voucher image according to the submitted sharing instruction and send the message; if it is detected that the sharing message is triggered, send the certified image or virtual voucher image to the user terminal that triggers the sharing message; in addition, the server can also generate a sharing message of the certified image or virtual voucher image according to the submitted sharing instruction and send the message; if it receives an access request submitted by scanning the identification code carried in the sharing message, send the certified image or virtual voucher image to the user terminal that submits the access request.

[0096] Still taking the recognition of the plant image of ginkgo leaves as an example above, after generating the graphic knowledge data of the fan-shaped figure and returning it to the user terminal, the fan-shaped figure can be displayed on the knowledge display page. The user on the user terminal side can edit the ginkgo leaves by editing the fan-shaped figure, or, after the display of the graphic knowledge data on the knowledge display page is completed, jump from the knowledge display page to the image editing page, such as Figure 5As shown, the image editing page displays a plant image, and a fan-shaped graphic is displayed on the upper layer of the plant image. The user can also edit the ginkgo leaf image by editing the fan-shaped graphic. In addition, a prompt text for guiding or reminding the user to perform graphic editing can be displayed on the image editing page, such as Figure 5 The prompt text displayed in the image editing page shown above.

[0097] In addition, in practical applications, in order to improve the convenience and editing efficiency of users on the user terminal side for plant image editing, the plant image can also be edited according to the user's previous preferences for plant image editing, so as to reduce the editing operations of the user during the plant image editing process, or the image obtained directly according to the user's previous preferences for plant image editing can be stored without the user performing editing operations. Specifically, in an optional implementation manner provided in this embodiment, after receiving and displaying the graphic knowledge data of the geometric figure returned by the server, a certified image or a virtual voucher image returned by the server is received; Among them, the certified image or the virtual voucher image can be obtained in the following way: read the stored editing preference data, and perform editing processing on the plant image blocks in the plant image according to the editing instruction sequence included in the editing preference data; Perform rendering processing on the plant image blocks obtained by the editing processing according to the rendering parameters included in the editing preference data to obtain a certified image or a virtual voucher image.

[0098] Among them, the geometric figure can be displayed on the upper layer of the plant image; the editing preference data refers to the records of the user terminal or the user on the user terminal side for previous plant recognition and graphic knowledge learning. Considering that the editing preference data is to a certain extent the user's privacy, user authorization can be obtained before obtaining the editing preference data.

[0099] In the specific execution process, after obtaining the certified image or the virtual voucher image, the certified image or the virtual voucher image can be stored or archived according to the archiving instruction submitted by the user. After obtaining the certified image or the virtual voucher image, the certified image or the virtual voucher image can also be directly stored or archived. During the storage or archiving process, the certified image or the virtual voucher image can be stored in the user storage space for the user. This user storage space can be the user storage space provided by an application program, the service provided by the application program, or a subroutine.

[0100] For example, in the above scenario of recognizing the plant image of the ginkgo leaf, according to the user's editing instruction for the geometric figure, the ginkgo leaf image block in the plant image is edited, and the ginkgo leaf image block obtained by the editing processing is rendered according to the rendering parameters to obtain a virtual badge image of the ginkgo leaf, such as Figure 6As shown; further, the virtual badge image can be stored in the user storage space, and the virtual badge image stored in the user storage space is as shown in Figure 7 ; Meanwhile, the user storage space is also configured with a sharing control, and the user can share the virtual badge image in the user storage space by triggering the sharing control.

[0101] The above steps S902 to S904 provided in this embodiment can be executed by the user terminal. It should be noted that the above steps S902 to S904 executed by the user terminal can cooperate with the steps S202 to S208 provided in the above method embodiment during the execution process. Therefore, when reading this embodiment, please refer to the corresponding content of the steps S202 to S208 provided in the above method embodiment, and when reading the above method embodiment, please refer to the corresponding content of the steps S902 to S904 provided in this embodiment.

[0102] The following takes the application of a plant recognition processing method provided in this embodiment in a plant recognition scenario as an example, and in combination with Figure 8 , the plant recognition processing method provided in this embodiment will be further described. Please refer to Figure 8 . The plant recognition processing method applied to the plant recognition scenario specifically includes the following steps.

[0103] Step S802, collect a plant image and upload it to the server.

[0104] Step S814, receive the geometric figure and graphic knowledge data returned by the server.

[0105] Step S816, display the geometric figure and graphic knowledge data.

[0106] Step S818, obtain an editing instruction for the geometric figure and submit it to the server.

[0107] Step S826, receive the virtual voucher image returned by the server and display it.

[0108] It should be noted that any one or any combination of steps S802, steps S814 to S816, and step S826 can be combined with any one or any combination of steps S902 to S904 according to the needs of implementation and deployment to form a new implementation manner; in addition, according to the actual deployment needs, any one or any combination of technical features in steps S802, steps S814 to S816, and step S826 can be selected and combined with any one or more technical features provided in the above steps S902 to S904 to form a new implementation manner; or, any one or any combination of technical features in steps S802, steps S814 to S816, and step S826 can also be replaced by any one or more technical feature combinations provided in the above steps S902 to S904 according to the actual deployment needs to form a new implementation manner, which will not be elaborated here one by one.

[0109] In addition, it should also be noted that the above steps S802, steps S814 to S816, and step S826 provided in this embodiment can be executed by the user terminal. It should be noted that the above steps S802, steps S814 to S816, and step S826 executed by the user terminal can cooperate with the steps S804 to S812, steps S820 to S826 executed by the server in the above embodiment during the execution process. Therefore, when reading this embodiment, please refer to the corresponding content of steps S804 to S812, steps S820 to S826 provided in the above method embodiment, and when reading the above method embodiment, please refer to the corresponding content of steps S802, steps S812 to S814, and steps S820 to S822 provided in this embodiment.

[0110] An embodiment of a plant recognition processing device provided in this specification is as follows: In the above embodiment, a plant recognition processing method is provided. Correspondingly, a plant recognition processing device is also provided. The following will be described with reference to the drawings.

[0111] Refer to Figure 10 , which shows a schematic diagram of an embodiment of a plant recognition processing device provided in this embodiment.

[0112] Since the device embodiment corresponds to the method embodiment, the description is relatively simple. For the relevant parts, please refer to the corresponding description of the method embodiment provided above. The device embodiments described below are only illustrative.

[0113] This embodiment provides a plant recognition processing device, and the device includes: The prompt word generation module 1002 is configured to obtain a plant image uploaded by a user terminal and generate an identification prompt word for shape recognition of the plant image; The shape recognition module 1004 is configured to input the plant image and the identification prompt word into a large language model for shape feature recognition to obtain shape features; The graphic conversion module 1006 is configured to perform graphic conversion on the plant contour graphic of the plant image based on the shape features to obtain geometric graphics; The graphic knowledge generation module 1008 is configured to generate graphic knowledge data of the geometric graphics and return it to the user terminal.

[0114] Another embodiment of the plant recognition processing device provided in this specification is as follows: In the above embodiment, another plant recognition processing method is provided. Correspondingly, another plant recognition processing device is also provided. The following will be described with reference to the accompanying drawings.

[0115] Refer to Figure 11 , which shows a schematic diagram of an embodiment of a plant recognition processing device provided in this embodiment.

[0116] Since the device embodiment corresponds to the method embodiment, the description is relatively simple. For the relevant parts, please refer to the corresponding description of the method embodiment provided above. The device embodiments described below are merely illustrative.

[0117] This embodiment provides a plant recognition processing device, and the device includes: The image acquisition and upload module 1102 is configured to acquire a plant image and upload it to the server, so as to perform shape feature recognition on the plant image through a large language model to obtain shape features, and perform graphic conversion on the plant contour graphic of the plant image based on the shape features to obtain geometric graphics; The graphic knowledge display module 1104 is configured to receive and display the graphic knowledge data of the geometric graphics returned by the server.

[0118] An embodiment of a plant recognition processing device provided in this specification is as follows: Corresponding to the above-described plant recognition processing method, based on the same technical concept, one or more embodiments of this specification also provide a plant recognition processing device, and this plant recognition processing device is used to execute the plant recognition processing method provided above. Figure 12 It is a schematic structural diagram of a plant recognition processing device provided by one or more embodiments of this specification.

[0119] A plant recognition processing device provided in this embodiment includes: AsFigure 12 As shown, plant recognition processing devices can vary significantly due to differences in configuration or performance. They can include one or more processors 1201 and a memory 1202. One or more application programs or data can be stored in the memory 1202. Among them, the memory 1202 can be for transient storage or persistent storage. The application programs stored in the memory 1202 can include one or more modules (not shown in the figure), and each module can include a series of computer-executable instructions in the plant recognition processing device. Further, the processor 1201 can be set to communicate with the memory 1202 and execute a series of computer-executable instructions in the memory 1202 on the plant recognition processing device. The plant recognition processing device can also include one or more power supplies 1203, one or more wired or wireless network interfaces 1204, one or more input / output interfaces 1205, etc.

[0120] In a specific embodiment, the plant recognition processing device includes a memory and one or more programs. One or more of the programs are stored in the memory, and one or more of the programs can include one or more modules, and each module can include a series of computer-executable instructions in the plant recognition processing device, and is configured to be executed by one or more processors. The one or more programs include the following computer-executable instructions: Obtain a plant image uploaded by a user terminal and generate a recognition prompt word for shape recognition of the plant image; Input the plant image and the recognition prompt word into a large language model for shape feature recognition to obtain shape features; Based on the shape features, perform graphic transformation on the plant contour graph of the plant image to obtain a geometric graph; Generate graphic knowledge data of the geometric graph and return it to the user terminal.

[0121] Another embodiment of the plant recognition processing device provided in this specification is as follows: Corresponding to the above-described another plant recognition processing method, based on the same technical concept, one or more embodiments of this specification also provide another plant recognition processing device. This plant recognition processing device is used to execute the above-provided plant recognition processing method. Figure 13 It is a schematic structural diagram of another plant recognition processing device provided by one or more embodiments of this specification.

[0122] A plant recognition processing device provided in this embodiment includes: As Figure 13As shown, plant recognition processing devices can vary significantly in configuration or performance. They can include one or more processors 1301 and a memory 1302. The memory 1302 can store one or more stored application programs or data. Among them, the memory 1302 can be short-term storage or persistent storage. The application programs stored in the memory 1302 can include one or more modules (not shown in the figure), and each module can include a series of computer-executable instructions in the plant recognition processing device. Further, the processor 1301 can be set to communicate with the memory 1302 and execute a series of computer-executable instructions in the memory 1302 on the plant recognition processing device. The plant recognition processing device can also include one or more power supplies 1303, one or more wired or wireless network interfaces 1304, one or more input / output interfaces 1305, one or more keyboards 1306, etc.

[0123] In a specific embodiment, the plant recognition processing device includes a memory and one or more programs. One or more of the programs are stored in the memory, and one or more of the programs can include one or more modules. Each module can include a series of computer-executable instructions in the plant recognition processing device and is configured to be executed by one or more processors. The one or more programs include the following computer-executable instructions: Collect a plant image and upload it to the server to perform shape feature recognition on the plant image through a large language model to obtain shape features, and perform graphic transformation on the plant contour graph of the plant image based on the shape features to obtain a geometric graph; Receive the graphic knowledge data of the geometric graph returned by the server and display it.

[0124] An embodiment of a computer-readable storage medium provided in this specification is as follows: Corresponding to the above-described plant recognition processing method, based on the same technical concept, one or more embodiments of this specification also provide a computer-readable storage medium.

[0125] The computer-readable storage medium provided in this embodiment is used to store computer-executable instructions, and the computer-executable instructions, when executed, implement the following process: Obtain a plant image uploaded by a user terminal and generate an identification prompt word for performing shape recognition on the plant image; Input the plant image and the identification prompt word into a large language model for shape feature recognition to obtain shape features; Perform graphic transformation on the plant contour graph of the plant image based on the shape features to obtain a geometric graph; Generate the graphic knowledge data of the geometric figure and return it to the user terminal.

[0126] It should be noted that the embodiments of a computer-readable storage medium in this specification and the embodiments of a plant recognition processing method in this specification are based on the same inventive concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the foregoing corresponding method, and the repeated parts will not be elaborated.

[0127] Another embodiment of the computer-readable storage medium provided in this specification is as follows: Corresponding to the above-described another plant recognition processing method, based on the same technical concept, one or more embodiments of this specification also provide another computer-readable storage medium.

[0128] The computer-readable storage medium provided in this embodiment is used to store computer-executable instructions, and when the computer-executable instructions are executed, the following processes are implemented: Collect a plant image and upload it to the server to perform shape feature recognition on the plant image through a large language model to obtain shape features, and perform graphic transformation on the plant contour graph of the plant image based on the shape features to obtain a geometric figure; Receive the graphic knowledge data of the geometric figure returned by the server and display it.

[0129] It should be noted that the embodiments of another computer-readable storage medium in this specification and the embodiments of another plant recognition processing method in this specification are based on the same inventive concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the foregoing corresponding method, and the repeated parts will not be elaborated.

[0130] An embodiment of a computer program product provided in this specification is as follows: Corresponding to the above-described plant recognition processing method, based on the same technical concept, one or more embodiments of this specification also provide a computer program product.

[0131] A computer program product includes a computer program / instructions, and when the computer program / instructions are executed by a processor, the following steps are implemented: Obtain a plant image uploaded by a user terminal and generate a recognition prompt for performing shape recognition on the plant image; Input the plant image and the recognition prompt into a large language model for shape feature recognition to obtain shape features; Perform graphic transformation on the plant contour graph of the plant image based on the shape features to obtain a geometric figure; Generate the graphic knowledge data of the geometric figure and return it to the user terminal.

[0132] It should be noted that the embodiments of a computer program product in this specification and the embodiments of a plant recognition processing method in this specification are based on the same inventive concept. Therefore, for the specific implementation of this embodiment, reference may be made to the implementation of the corresponding method described above, and repeated parts will not be elaborated.

[0133] Another embodiment of the computer program product provided in this specification is as follows: Corresponding to the above-described another plant recognition processing method, based on the same technical concept, one or more embodiments of this specification also provide another computer program product.

[0134] A computer program product includes a computer program / instructions, and when the computer program / instructions are executed by a processor, the following steps are implemented: Collect a plant image and upload it to a server to perform shape feature recognition on the plant image through a large language model to obtain shape features, and perform graphic conversion on the plant contour graph of the plant image based on the shape features to obtain a geometric graph; Receive and display the graphic knowledge data of the geometric graph returned by the server.

[0135] It should be noted that the embodiments of another computer program product in this specification and the embodiments of another plant recognition processing method in this specification are based on the same inventive concept. Therefore, for the specific implementation of this embodiment, reference may be made to the implementation of the corresponding method described above, and repeated parts will not be elaborated.

[0136] The various embodiments in this specification are all described in a progressive manner. For the same or similar parts between the various embodiments, reference can be made to each other. The key point of each embodiment is to illustrate the differences from other embodiments. For example, the device embodiments, equipment embodiments, computer-readable storage medium embodiments, and computer program product embodiments are all similar to the method embodiments, so the description is relatively simple. Please refer to the corresponding parts of the method embodiments for reading the relevant content in the device embodiments, equipment embodiments, computer-readable storage medium embodiments, and computer program product embodiments.

[0137] The above describes specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the drawings do not necessarily require the specific order or sequential order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0138] In the 1930s, it was obvious to distinguish whether an improvement in a technology was a hardware improvement (e.g., improvement in circuit structures such as diodes, transistors, switches, etc.) or a software improvement (improvement in method flows). However, with the development of technology, many improvements in method flows today can be regarded as direct improvements in hardware circuit structures. Almost all designers obtain the corresponding hardware circuit structures by programming the improved method flows into the hardware circuits. Therefore, it cannot be said that an improvement in a method flow cannot be implemented with a hardware entity module. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user's programming of the device. Designers can program themselves to "integrate" a digital system on a single PLD, without having to ask a chip manufacturer to design and fabricate a dedicated integrated circuit chip. Moreover, nowadays, instead of manually fabricating integrated circuit chips, this programming is mostly implemented using "logic compiler" software, which is similar to the software compiler used in program development and writing. The original code before compilation also has to be written in a specific programming language, which is called a Hardware Description Language (HDL). There is not only one kind of HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. Currently, the most commonly used ones are VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also be aware that as long as the method flow is slightly logically programmed with the above-mentioned several hardware description languages and programmed into the integrated circuit, it is easy to obtain the hardware circuit that implements the logical method flow.

[0139] The controller can be implemented in any suitable manner. For example, the controller can take the form of, for example, a microprocessor or a processor and a computer-readable medium storing computer-readable program code (such as software or firmware) executable by the (micro)processor, logic gates, switches, an application specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of the controller include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that, in addition to implementing the controller in the form of pure computer-readable program code, it is entirely possible to logically program the method steps to enable the controller to be implemented in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc. to achieve the same functions. Therefore, such a controller can be considered a hardware component, and the devices included therein for implementing various functions can also be regarded as the structures within the hardware component. Or even, the devices for implementing various functions can be regarded as either software modules for implementing the method or the structures within the hardware component.

[0140] The systems, devices, modules, or units illustrated in the above embodiments can be specifically implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0141] For the convenience of description, when describing the above devices, they are described separately as various units according to their functions. Of course, when implementing the embodiments of this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0142] Those skilled in the art should understand that one or more embodiments of this specification can be provided as a method, a system, or a computer program product. Therefore, one or more embodiments of this specification can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, this specification can take the form of a computer program product implemented on one or more computer-readable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program code.

[0143] This specification is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the specification. It should be understood that each flow and / or block in the flowchart and / or block diagram, and combinations of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable plant recognition processing devices to generate a machine, such that the instructions executed by the processors of the computer or other programmable plant recognition processing devices produce means for implementing the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 or means for implementing the functions specified in one block or multiple blocks.

[0144] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable plant recognition processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including instruction means that implement the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 or means for implementing the functions specified in one block or multiple blocks.

[0145] These computer program instructions can also be loaded onto a computer or other programmable plant recognition processing device, such that a series of operational steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 or means for implementing the functions specified in one block or multiple blocks.

[0146] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0147] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of computer-readable media.

[0148] Computer-readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer-readable storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0149] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of further restrictions, the elements defined by the sentence "includes at least one ..." do not exclude the presence of other identical elements in the process, method, commodity or device including the elements.

[0150] One or more embodiments of the present specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. One or more embodiments of the present specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0151] The above description is only an embodiment of this document and is not intended to limit this document. For those skilled in the art, this document may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this document should be included in the scope of the claims of this document.

Claims

1. A plant recognition processing method, comprising: Obtaining a plant image uploaded by a user terminal and generating a recognition prompt for shape recognition of the plant image; Inputting the plant image and the recognition prompt into a large language model for shape feature recognition to obtain shape features; Performing graphic transformation on the plant contour graphic of the plant image based on the shape features to obtain a geometric graphic; Generating graphic knowledge data of the geometric graphic and returning it to the user terminal.

2. The plant recognition processing method according to claim 1, wherein the shape feature recognition includes: Extracting the plant contour features of the plant image and performing graphic fitting on the plant contour features to obtain a plant contour graphic; Performing angle detection on the plant contour graphic to obtain the number of angles; the shape features include the plant contour graphic and the number of angles.

3. The plant recognition processing method according to claim 1, wherein the performing graphic transformation on the plant contour graphic of the plant image based on the shape features to obtain a geometric graphic includes: Inputting the shape features and the plant contour graphic into a graphic transformation model for geometric graphic transformation to obtain the geometric graphic; The geometric graphic transformation includes: fitting and matching the shape features and the plant contour graphic with regular graphics in a graphic library, and using the matched regular graphic as the geometric graphic.

4. The plant recognition processing method according to claim 1, wherein the generating the graphic knowledge data of the geometric graphic is generated in the following manner: Generating plant knowledge fields according to the plant recognition information of the plant image; Invoking a knowledge retrieval interface to retrieve the graphic knowledge fields of the geometric graphic, and generating graphic knowledge texts and / or teaching knowledge texts according to the plant knowledge fields and the graphic knowledge fields.

5. The plant recognition processing method according to claim 1, after the step of generating the graphic knowledge data of the geometric graphic and returning it to the user terminal, further comprising: Performing editing processing on the plant image blocks in the plant image according to the editing instructions of the geometric graphic submitted by the user terminal; the geometric graphic is displayed on the upper layer of the plant image; Performing rendering processing on the plant image blocks obtained by the editing processing according to the rendering parameters to obtain a certified image or a virtual voucher image.

6. The plant recognition processing method according to claim 5, after the step of performing rendering processing on the plant image blocks obtained by the editing processing according to the rendering parameters to obtain a certified image or a virtual voucher image, further comprising: Generating a sharing message of the certified image or the virtual voucher image according to the sharing instruction submitted by the user terminal and sending the message; If it is detected that the sharing message is triggered, sending the certified image or the virtual voucher image to the user terminal that triggered the sharing message; If an access request submitted by scanning the identification code carried in the sharing message is received, sending the certified image or the virtual voucher image to the user terminal that submitted the access request.

7. The plant recognition processing method according to claim 1, after the step of generating the graphic knowledge data of the geometric figure and returning it to the user terminal, further includes: Reading the stored editing preference data, and performing editing processing on the plant image blocks in the plant image according to the editing instruction sequence included in the editing preference data; the geometric figure is displayed on the upper layer of the plant image; Performing rendering processing on the plant image blocks obtained by the editing processing according to the rendering parameters included in the editing preference data to obtain a certified image or a virtual voucher image.

8. The plant recognition processing method according to claim 1, further includes: Matching the user location information collected by the user terminal with the location information of the plant to be recommended; If the matching is successful, sending an image acquisition reminder of the plant to be recommended to the user terminal or the connected device of the user terminal; the plant to be recommended is determined according to the plant images and plant texts included in the user social data.

9. The plant recognition processing method according to claim 1, further includes: If it is detected that there are missing plant image blocks in the plant image, performing plant species recognition based on the plant image blocks to obtain the plant species; Performing image repair on the plant image blocks based on the plant species, and updating the plant image according to the complemented plant image blocks.

10. According to the plant recognition processing method described in claim 1, after the graphic knowledge data is returned to the user terminal, the graphic knowledge data is sent to a wearable device connected to the user terminal, and the graphic knowledge data is rendered and displayed through the wearable device; wherein, The wearable device includes AR glasses.

11. A plant recognition processing method, including: Collecting a plant image and uploading it to a server to perform shape feature recognition on the plant image through a large language model to obtain shape features, and performing graphic transformation on the plant contour graphic of the plant image based on the shape features to obtain a geometric figure; Receiving and displaying the graphic knowledge data of the geometric figure returned by the server.

12. The plant recognition processing method according to claim 11, the shape feature recognition is implemented in the following manner: Extracting the plant contour features of the plant image, and performing graphic fitting on the plant contour features to obtain a plant contour graphic; Performing included angle detection on the plant contour graphic to obtain the number of included angles; the shape features include the plant contour graphic and the number of included angles.

13. The plant recognition processing method according to claim 11, the performing graphic transformation on the plant contour graphic of the plant image based on the shape features to obtain a geometric figure is implemented in the following manner: Inputting the shape features and the plant contour graphic into a graphic transformation model for geometric graphic transformation to obtain the geometric figure; The geometric figure conversion includes: Fitting and matching the shape features and the plant contour graphic with the regular graphics in the graphic library, and using the matched regular graphics as the geometric figure.

14. The plant recognition processing method according to claim 11, the graphic knowledge data of the geometric figure is generated in the following manner: Generating plant knowledge fields according to the plant recognition information of the plant image; Call the knowledge retrieval interface to retrieve the graphic knowledge fields of the geometric figure, and generate graphic knowledge text and / or teaching knowledge text based on the plant knowledge fields and the graphic knowledge fields.

15. According to the plant recognition processing method described in claim 11, after the step of receiving and displaying the graphic knowledge data of the geometric figure returned by the server, it further includes: Obtain an edit instruction submitted for displaying the geometric figure on the upper layer of the plant image and submit it to the server; Obtain and display the evidentiary image or virtual voucher image from the server; The evidentiary image or the virtual voucher image is obtained by rendering the plant image block obtained by editing according to the edit instruction according to the rendering parameters.

16. According to the plant recognition processing method described in claim 11, the graphic knowledge data is displayed in the following manner: Display the graphic knowledge data on the knowledge display page; or, Send the graphic knowledge data to the connected wearable device for rendering and displaying the graphic knowledge data through the wearable device; the wearable device includes AR glasses.

17. A plant recognition processing device includes: A prompt word generation module configured to obtain a plant image uploaded by a user terminal and generate an identification prompt word for shape recognition of the plant image; A shape recognition module configured to input the plant image and the identification prompt word into a large language model for shape feature recognition to obtain shape features; A graphic conversion module configured to perform graphic conversion on the plant contour graphic of the plant image based on the shape features to obtain a geometric figure; A graphic knowledge generation module configured to generate graphic knowledge data of the geometric figure and return it to the user terminal.

18. A plant recognition processing device includes: An image acquisition and upload module configured to acquire a plant image and upload it to a server to perform shape feature recognition on the plant image through a large language model to obtain shape features, and perform graphic conversion on the plant contour graphic of the plant image based on the shape features to obtain a geometric figure; A graphic knowledge display module configured to receive and display the graphic knowledge data of the geometric figure returned by the server.

19. A plant recognition processing device includes: A processor; And a memory configured to store computer-executable instructions, and when the computer-executable instructions are executed, the processor: Obtain a plant image uploaded by a user terminal and generate an identification prompt word for shape recognition of the plant image; Input the plant image and the identification prompt word into a large language model for shape feature recognition to obtain shape features; Perform graphic conversion on the plant contour graphic of the plant image based on the shape features to obtain a geometric figure; Generate graphic knowledge data of the geometric figure and return it to the user terminal.

20. A plant recognition processing device includes: A processor; And a memory configured to store computer-executable instructions, and when the computer-executable instructions are executed, the processor: Collect plant images and upload them to the server to identify shape features of the plant images through a large language model, and perform graphic conversion on the plant contour graph of the plant images based on the shape features to obtain geometric graphs; Receive and display the graphic knowledge data of the geometric graphs returned by the server.

21. A computer-readable storage medium for storing computer-executable instructions, which implement the steps of the method according to claim 1 or 11 when executed.

Images