Laser processing material processing method and device, readable medium and electronic equipment

Abstract

The invention provides a material processing method and device for laser processing, a readable medium and electronic equipment. The method comprises the steps that to-be-shared materials uploaded to a laser material sharing platform are acquired; identifying the content of the to-be-shared material, and generating a candidate material title corresponding to the to-be-shared material; generating a candidate material label corresponding to the to-be-shared material based on the candidate material title and the to-be-shared material; and determining a target material title corresponding to the to-be-shared material according to the candidate material title, and determining a target material tag corresponding to the to-be-shared material according to the candidate material tag. According to the technical scheme, automatic generation of the material title and the material label is realized, the complexity of user operation during material sharing is reduced, and the material sharing efficiency of a user is improved.

Description

Technical Field

[0001] This application belongs to the field of laser processing technology, and specifically relates to a method, apparatus, readable medium and electronic device for laser processing of materials. Background Technology

[0002] Laser processing technology is a processing technique that utilizes the interaction between a laser beam and matter to cut, weld, and treat surfaces of materials. Laser processing technology is widely used in various fields.

[0003] Laser processing typically involves processing materials based on user-provided laser processing templates. Currently, users can share their own templates on laser template sharing platforms for other users to access and use. During template sharing, users usually need to describe the template so other users can search based on that description. However, this method of users adding their own descriptions requires careful consideration of the specific content, complicating the user experience and reducing the efficiency of template sharing. Summary of the Invention

[0004] The purpose of this application is to provide a laser processing method, apparatus, readable medium, and electronic device for material processing, so as to improve the efficiency of users sharing materials.

[0005] Other features and advantages of this application will become apparent from the following detailed description, or may be learned in part from practice of this application.

[0006] According to one aspect of the embodiments of this application, a method for processing materials for laser processing is provided, comprising:

[0007] Obtain the materials uploaded to the laser material sharing platform that are ready to be shared;

[0008] The content of the material to be shared is identified, and candidate material titles corresponding to the material to be shared are generated;

[0009] Based on the candidate material titles and the materials to be shared, candidate material tags corresponding to the materials to be shared are generated;

[0010] The target material title corresponding to the material to be shared is determined based on the candidate material title, and the target material tag corresponding to the material to be shared is determined based on the candidate material tag.

[0011] According to one aspect of the embodiments of this application, a material processing apparatus for laser processing is provided, comprising:

[0012] The material acquisition module is used to acquire materials uploaded to the laser material sharing platform that are to be shared;

[0013] The title generation module is used to identify the content of the material to be shared and generate candidate material titles corresponding to the material to be shared.

[0014] The tag generation module is used to generate candidate material tags corresponding to the material to be shared based on the candidate material title and the material to be shared;

[0015] The target information determination module is used to determine the target material title corresponding to the material to be shared based on the candidate material title, and to determine the target material tag corresponding to the material to be shared based on the candidate material tag.

[0016] According to one aspect of the embodiments of this application, a computer-readable medium is provided having a computer program stored thereon, which, when executed by a processor, implements the material processing method for laser processing as described in the above technical solutions.

[0017] According to one aspect of the embodiments of this application, an electronic device is provided, the electronic device comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor executes the executable instructions to cause the electronic device to perform a laser processing material processing method as described in the above technical solutions.

[0018] According to one aspect of the embodiments of this application, a computer program product or computer program is provided, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the laser processing material processing method as described in the above technical solutions.

[0019] In the technical solution provided in this application embodiment, the materials to be shared are first acquired and uploaded to the laser material sharing platform; then, the content of the materials to be shared is identified, and candidate material titles corresponding to the materials to be shared are generated; subsequently, candidate material tags corresponding to the materials to be shared are generated based on the candidate material titles and the materials to be shared; finally, the target material title corresponding to the materials to be shared is determined based on the candidate material titles, and the target material tags corresponding to the materials to be shared are determined based on the candidate material tags. Thus, the technical solution of this application realizes the automatic generation of material titles and material tags. After uploading materials to be shared, users can select the desired target material title and target material tags from the automatically generated candidate material titles and candidate material tags, without requiring users to manually think of the corresponding material titles and material tags, thereby reducing the complexity of user operations when sharing materials and improving the efficiency of material sharing. Furthermore, the automatically generated material titles and material tags have a relatively uniform expression, avoiding the differences when different users add titles and tags themselves, enabling users to obtain more accurate search results when searching for materials using material titles and material tags.

[0020] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0021] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0022] Figure 1 An exemplary system architecture block diagram illustrating the application of the technical solution of this application is shown schematically.

[0023] Figure 2 An exemplary system architecture block diagram illustrating the application of the technical solution of this application is shown schematically.

[0024] Figure 3 A flowchart illustrating a laser processing material processing method according to an embodiment of this application is shown schematically.

[0025] Figure 4 This diagram illustrates a preset material tag mapping relationship provided in one embodiment of the present application.

[0026] Figure 5 A flowchart illustrating a laser processing material processing method according to an embodiment of this application is shown schematically.

[0027] Figures 6A to 6D A schematic diagram of a material sharing interface provided in one embodiment of this application is shown.

[0028] Figure 7 A flowchart illustrating a laser processing material processing method according to an embodiment of this application is shown schematically.

[0029] Figure 8 A schematic block diagram of the material processing apparatus for laser processing provided in an embodiment of this application is shown.

[0030] Figure 9 A schematic diagram of a computer system architecture suitable for implementing the embodiments of this application is shown. Detailed Implementation

[0031] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided to make this application more comprehensive and complete, and to fully convey the concept of the exemplary embodiments to those skilled in the art.

[0032] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this application.

[0033] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0034] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0035] In this application embodiment, the terms "module" or "unit" refer to a computer program or part of a computer program that has a predetermined function and works with other related parts to achieve a predetermined goal, and can be implemented wholly or partially using software, hardware (such as processing circuitry or memory), or a combination thereof. Similarly, a processor (or multiple processors or memory) can be used to implement one or more modules or units. Furthermore, each module or unit can be part of an overall module or unit that includes the functionality of that module or unit.

[0036] It is understood that in the specific implementation of this application, customer information (such as transaction information, reconciliation data) and other related data are involved. When the above embodiments of this application are applied to specific products or technologies, customer permission or consent is required, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0037] Figure 1 An exemplary system architecture block diagram illustrating the application of the technical solution of this application is shown schematically.

[0038] like Figure 1 As shown, the system architecture 100 may include terminal devices 110, a network 120, and a server 130. Terminal devices 110 may include smartphones, tablets, laptops, smart voice interaction devices, smart home appliances, vehicle terminals, laser processing equipment, etc. Server 130 may be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. Network 120 may be a communication medium of various connection types capable of providing a communication link between terminal devices 110 and server 130, such as a wired communication link or a wireless communication link.

[0039] Depending on the implementation requirements, the system architecture in this application embodiment can have any number of terminal devices, networks, and servers. For example, server 130 can be a server group composed of multiple server devices. In addition, the technical solutions provided in this application embodiment can be applied to terminal device 110, or to server 130, or can be implemented jointly by terminal device 110 and server 130. This application does not impose any special limitations on this.

[0040] Figure 2 A schematic diagram illustrating the application scenario of the technical solution of this application is shown.

[0041] like Figure 2 As shown, this application scenario includes two parts: a client and a server. The client can be deployed on a terminal device, such as... Figure 1 The terminal device 110 shown can be accessed by the server through, for example... Figure 1The server 130 shown is implemented as follows. The client refers to the client application of the laser material sharing platform, and the server also refers to the server application of the laser material sharing platform. The client can be a webpage, which users can open using a browser; the client can also be a standalone application, or it can be a hosted application hosted on another platform. Users upload the materials to be shared to the laser material sharing platform to the client. The client sends a request to the server, instructing the server to generate candidate material titles and tags corresponding to the materials to be shared. Upon receiving the request, the server identifies the content of the materials to be shared, generates candidate material titles, and generates candidate material tags based on the candidate material titles and the materials to be shared. The server returns the generated candidate material titles and tags to the client, allowing users to select the target material title and target material tag from the candidate material titles and tags displayed on the client. After determining the target material title and target material tag, users can share the materials with the target material title and target material tag to the laser material sharing platform through the sharing operation on the client. Users of the laser material sharing platform can then search for the materials to be shared using the target material title or target material tag.

[0042] The material processing method for laser processing provided in this application will be described in detail below with reference to specific embodiments.

[0043] Figure 3 A flowchart illustrating a laser processing material handling method according to an embodiment of this application is shown schematically. This method can be implemented by a terminal device or a server. Figure 3 As shown, the laser processing material processing method provided in this embodiment includes steps 310 to 340, as detailed below:

[0044] Step 310: Obtain the materials to be shared that have been uploaded to the laser material sharing platform.

[0045] Specifically, a laser material sharing platform is a platform for users to share, search, and obtain laser materials. Users can upload their own laser materials to the platform, or search for and obtain the laser materials they need. Laser materials are the objects processed by laser technology, representing the final form of the laser-processed material; they can be simply referred to as materials. Laser materials can be images, videos, or text. Users mark the laser materials they want to share as materials to be shared, and can upload them through the material upload interface provided by the laser material sharing platform.

[0046] In one embodiment of this application, the technical solution is implemented by a terminal device, in which case the terminal device can obtain the material to be shared based on the user's material upload operation.

[0047] In one embodiment of this application, the technical solution can be implemented by a server. After a user uploads materials to be shared to a terminal device, the terminal device can send the materials to be shared to the server, allowing the server to obtain the materials. The terminal device can generate a material processing request based on the materials to be shared. After receiving the material processing request, the server parses the request to obtain the materials to be shared and executes subsequent steps 320-330 to respond to the material processing request.

[0048] Step 320: Identify the content of the material to be shared and generate candidate material titles corresponding to the material to be shared.

[0049] Specifically, the title of a material is a concise and accurate summary of its content. Therefore, it's necessary to identify the content of the material to be shared to obtain candidate titles. The method for identifying the content varies depending on the material type. Material types include image materials, video materials, and text materials. Video materials are similar to image materials; they can be considered as laser-like materials containing multiple image images. Therefore, if the material to be shared is an image or video material, image recognition is needed to identify its content; if the material to be shared is text material, text recognition is needed.

[0050] In one embodiment of this application, the material type also includes audio material. When recognizing the material content, the audio material can be converted into text material. In this case, the material to be shared is text material, and therefore, text recognition is used to identify the content of the material to be shared. Optionally, after converting the audio material into text material, corresponding image or video material can be generated based on the text material according to user needs. In this case, the material to be shared is image or video material, and image recognition is used to identify the content of the material to be shared. For example, a text-to-image model can be used to generate corresponding image material from text material, that is, to generate an image based on a piece of text content. This material type conversion can be achieved by pre-training a text-to-image model.

[0051] In one embodiment of this application, the process of generating candidate material titles may include: encoding the material to be shared to obtain material encoding information; constructing first prompt information corresponding to the material to be shared; and processing the material encoding information and the first prompt information through a preset model to generate candidate material titles corresponding to the material to be shared.

[0052] Specifically, the encoding process here uses BASE64 encoding, which uses 64 ASCII characters to encode the material to be processed into a string, so that the preset model can better understand the material to be shared. In the encoding process, the material to be processed is first converted into binary data; then, the binary data is divided into multiple data groups of 6 bits each; next, two 0s are appended to the beginning of each data group to form a concatenated data group; finally, the ASCII characters represented by each concatenated data group are the encoded information of that concatenated data group, thus obtaining the material's encoded information.

[0053] A prompt is text or instruction provided to a model to guide it in generating a specific output. It describes the information, response, text, etc., that the user wants from the model. The purpose of a prompt is to guide the model to produce the desired response, allowing for better control over the model's output. Here, the first prompt can be a short question, a complete paragraph, or a set of instructions. For example, the first prompt could be "Summarize the content contained in the material to be processed to generate a title."

[0054] In this embodiment, candidate material titles are obtained through a preset model. This preset model is a pre-trained machine learning model, such as a Large Language Model (LLM). The material encoding information and the first prompt information are both used as input information (message) to the Large Language Model. The Large Language Model will attempt to understand the first prompt information and process the material encoding information accordingly to generate the corresponding candidate material titles.

[0055] Step 330: Based on the candidate material titles and the materials to be shared, generate candidate material tags corresponding to the materials to be shared.

[0056] Specifically, material tags indicate the category or attribute of a material in a certain dimension, such as the main content of the material, the applicable processing scenario, and the applicable processing object. The main content of the material refers to the content contained within the material itself, such as text content, image content, etc. For example, if the text content is "Happy New Year!", the corresponding tag could be "Happy New Year," and if the image content is a meadow, the corresponding tag could be "meadow." The applicable processing scenario indicates the kind of scenario the material is suitable for, such as holidays, specific anniversaries, etc. For example, if the text content is "Happy New Year!", the corresponding tags could be "New Year's Day," "Spring Festival," etc., and if the image content is hearts and flowers, the corresponding tags could be "Thanksgiving," "Valentine's Day," "space decoration," etc. The applicable processing object indicates what kind of object the material is suitable for processing on, such as greeting cards, holiday decorations, clothing, personalized gifts, signs, glassware, etc. For example, if the text content is "Happy New Year!", the corresponding tags could be "greeting cards," "holiday decorations," etc.; if the image content is hearts and flowers, the corresponding tags could be "greeting cards," "clothing," etc.

[0057] Material tags can effectively categorize materials, and the accuracy of these tags directly impacts the ease and accuracy of material searches. The act of assigning tags to materials is also known as material labeling. To generate more accurate material tags, this embodiment uses candidate material titles as a factor in generating candidate material tags, processing them together with the materials to be shared. This processing can be performed using a pre-trained machine learning model to obtain candidate material tags. It can be seen that a single material can have multiple types of material tags, and each type of material tag can have multiple tags. In this embodiment, the types of material tags at least include one of the following: the main content of the material, the applicable processing scenario, and the applicable processing object.

[0058] In one embodiment of this application, there may be multiple candidate material titles obtained in step 320. When generating candidate material tags, each candidate material title can be combined with the material to be shared and then input into a machine learning model to obtain the corresponding candidate material tags. It can be understood that there can also be multiple candidate material tags.

[0059] In one embodiment of this application, the process of generating candidate material tags may include: generating context information corresponding to the material to be shared based on the candidate material title; constructing second prompt information corresponding to the material to be shared based on the context information and the material to be shared; and processing the material to be shared and the second prompt information through a preset model to generate candidate material tags corresponding to the material to be shared.

[0060] Specifically, context information is used to reflect the environment in which the material to be shared exists. Adding context information to the material to be shared allows the preset model to better understand it, thereby generating more accurate candidate material tags. Here, the title of the candidate material can be directly used as context information. Then, based on the context information and the material to be shared, a second prompt is constructed. The second prompt is used to suggest what kind of material tags to generate. For example, the second prompt could be "identify the main content and information of the material," "identify suitable scene and holiday tags," or "identify what kind of object the material is suitable for processing." Finally, the second prompt information and the material to be shared are input into the preset model to obtain the corresponding candidate material tags.

[0061] In one embodiment of this application, to better match the generated candidate material tags with the laser processing scene, a preset material tag mapping relationship can be obtained first during the generation of context information. Then, by combining the candidate material title and the preset material tag mapping relationship, context information corresponding to the material to be shared is generated. This preset material tag mapping relationship refers to the pre-defined association between various laser materials and their corresponding material tags. This mapping relationship can be obtained based on RAG (Retrieval Augmented Generation) technology. Therefore, by adding context information to the material to be shared using RAG, laser scene knowledge can be supplemented to the preset model, making the candidate material tags generated by the preset model more closely match the laser scene. For example, Figure 4 The diagram illustrates a preset material tag mapping relationship provided in one embodiment of this application, such as... Figure 4 As shown, the first column contains preset materials in the form of images, while the second to fourth columns are material tags. One preset material can correspond to multiple material tags.

[0062] Step 340: Determine the target material title corresponding to the material to be shared based on the candidate material title, and determine the target material tag corresponding to the material to be shared based on the candidate material tag.

[0063] Specifically, the title and tags ultimately used for the shared material are denoted as the target material tag and target material label, respectively. Generally, the shared material corresponds to one target material title and at least one target material tag. Here, candidate material titles can be directly used as the target material title; when there are multiple candidate material titles, the user can also select one of them as the target material title. Alternatively, all candidate material tags can be used as the target material tags for the shared material, or the user can select some of the candidate material tags as the target material tags. The user ultimately uses the target material title and target material tags to share the material to the laser material sharing platform.

[0064] In the technical solution provided in this application embodiment, the materials to be shared are first acquired and uploaded to the laser material sharing platform; then, the content of the materials to be shared is identified, and candidate material titles corresponding to the materials to be shared are generated; subsequently, candidate material tags corresponding to the materials to be shared are generated based on the candidate material titles and the materials to be shared; finally, the target material title corresponding to the materials to be shared is determined based on the candidate material titles, and the target material tags corresponding to the materials to be shared are determined based on the candidate material tags. Thus, the technical solution of this application realizes the automatic generation of material titles and material tags. After uploading materials to be shared, users can select the desired target material title and target material tags from the automatically generated candidate material titles and candidate material tags, without requiring users to manually think of the corresponding material titles and material tags, thereby reducing the complexity of user operations when sharing materials and improving the efficiency of material sharing. Furthermore, the automatically generated material titles and material tags have a relatively uniform expression, avoiding the differences when different users add titles and tags themselves, enabling users to obtain more accurate search results when searching for materials using material titles and material tags.

[0065] Figure 5 A flowchart illustrating a laser processing material handling method according to an embodiment of this application is shown schematically. This method can be implemented by a terminal device or a server. Figure 5 As shown, the laser processing material processing method provided in this embodiment includes steps 510 to 560, as detailed below:

[0066] Step 510: Obtain the materials to be shared that have been uploaded to the laser material sharing platform.

[0067] Step 510 can be referred to the description of step 310 above, and will not be repeated here.

[0068] Step 520: Preprocess the materials to be shared according to their type to obtain preprocessed materials.

[0069] Specifically, preprocessing the materials to be shared is to ensure they conform to the format specifications of subsequent processing, thereby improving the accuracy of the results. Different types of materials require different preprocessing methods. As mentioned earlier, material types include image materials, video materials, and text materials. Image materials and video materials are similar; therefore, they can use the same preprocessing method.

[0070] In one embodiment of this application, if the material to be shared is text, it is segmented to obtain preprocessed material. If the text is too long, it can reduce the ability of the pre-defined model (such as a large language model) to understand the text. Therefore, text is segmented. For example, a character count threshold is set for each text segment. If the number of characters in the material to be shared exceeds this threshold, it is segmented according to this threshold. If the number of characters in the material does not exceed this threshold, it can be directly treated as a single text segment. Optionally, the preprocessing of the text also includes removing null values ​​and outliers.

[0071] In one embodiment of this application, if the material to be shared is an image or video, the image format and / or size of the material to be shared is adjusted to obtain pre-processed material. Image format refers to the way the image is displayed; for example, an image can be a vector graphic or a bitmap image, and a bitmap image can include RGB images, YUV images, etc. In this embodiment, image format adjustment refers to adjusting the image format to RGB image format. For example, if the image is a vector graphic, it is converted to an RGB image; if the image is a YUV image, it is converted to an RGB image. Size adjustment is to avoid the preset model's ability to understand the image decreasing due to excessively large image sizes. Therefore, when the image size exceeds a preset size, it is reduced to a preset duration. Size adjustment can be performed during the image format adjustment process. For example, during the conversion of a vector graphic to an RGB image, the size of the converted RGB image can be controlled simultaneously, thus achieving size adjustment while adjusting the image format.

[0072] Step 530: Identify the content of the pre-processed material and generate candidate material titles corresponding to the material to be shared.

[0073] Step 540: Based on the candidate material titles and pre-processed materials, generate candidate material tags corresponding to the materials to be shared.

[0074] Steps 530-540, which involve obtaining candidate material titles and tags based on preprocessed materials, are similar to the process of processing the materials to be processed in steps 320-330 above. The materials to be processed are simply replaced with preprocessed materials, and will not be described in detail here.

[0075] In one embodiment of this application, pre-processed materials can be directly input into a preset model to obtain candidate material tags. These candidate material tags are usually obtained by the preset model based on business dimensions to label the materials.

[0076] Step 550: Perform deduplication and sorting on multiple candidate material tags.

[0077] Specifically, the candidate material tags generated in step 540 may contain duplicate tags, so deduplication is necessary. Sorting can make the candidate material tags presented to the user more organized. The sorting rules can be set as needed, such as sorting by the first letter of the tag, sorting by the hierarchical relationship of the tag, or sorting by business rules.

[0078] Step 560: Determine the target material title corresponding to the material to be shared based on the candidate material title, and determine the target material tag corresponding to the material to be shared based on the candidate material tag.

[0079] Specifically, the client (or terminal device) can display candidate material titles and candidate material tags to the user through the display interface, from which the user can select appropriate titles and tags as target material titles and target material tags.

[0080] In the technical solution provided in this application embodiment, on the one hand, by preprocessing the material to be shared according to the type of the material to be shared, the presentation of the material to be shared can be standardized, thereby improving the understanding ability of the subsequent model of the material to be shared, and thus providing the accuracy of the obtained material title and tag; on the other hand, by performing deduplication and sorting processing on the candidate material tags, the candidate material tags finally presented to the user can be more beautiful and orderly, making it convenient for the user to select the target material tag they need.

[0081] In one embodiment of this application, there are multiple candidate material titles. When determining the target material title, the client (or terminal device) can display multiple candidate material titles through a display interface; then, in response to a selection operation on the candidate material title, the selected candidate material title is used as the target material title corresponding to the material to be shared. The display interface includes a title box for entering the target material title of the material to be shared. The client (or terminal device) can display multiple candidate material titles below the title box for the user to select. The user can also directly enter the material title in the title box.

[0082] In one embodiment of this application, when a target material title is entered in the title box, it is first detected whether there is any input content in the title box. If no input content is entered, the selected target material title is directly filled into the title box. If input content is detected in the title box, it means that the user has previously entered a material title. When the user selects the target material title from the candidate material titles, the target material title overwrites the input content in the title box. After the target material title overwrites the input content in the title box, the user can still edit and modify the target material title in the title box again.

[0083] In one embodiment of this application, there are multiple candidate material tags. When determining the target material tag, the client (or terminal device) first determines multiple material tags to be displayed based on the multiple candidate material tags; then, it displays the multiple material tags to be displayed through the display interface; finally, in response to the selection operation for the material tags to be displayed, at least one selected material tag to be displayed is used as the target material tag corresponding to the material to be shared. This is because too many candidate material tags are generated at once, and it is not suitable to display them all on the display interface. Therefore, some are selected from the multiple candidate material tags as material tags to be displayed on the display interface, and the user selects at least one target material tag from the multiple material tags to be displayed.

[0084] In one embodiment of this application, when determining the material tags to be displayed, a first preset number of recommended material tags can be obtained first; then, a second preset number of candidate material tags can be extracted from multiple candidate material tags; wherein, the sum of the first preset number and the second preset number is a predetermined value; finally, the first preset number of recommended material tags and the second preset number of candidate material tags are used as multiple material tags to be displayed. Recommended material tags can be material tags pre-set in the client (or terminal device), or they can be hotspot tags determined by the client (or terminal device) that are highly relevant to the material to be shared on the current laser material sharing platform. In this embodiment, the multiple material tags to be displayed are a combination of recommended material tags and automatically generated candidate material tags. The total number of material tags to be displayed is the sum of the number of recommended material tags and the number of candidate material tags. The total number of material tags to be displayed can be a predetermined value, such as 15, 30, etc. The number of recommended material tags and the number of candidate material tags can be set as needed; they can be equal or unequal. After determining the material tags to be displayed, the multiple material tags to be displayed can also be sorted, for example, the recommended material tags can be arranged first, and the candidate material tags can be arranged last.

[0085] In one embodiment of this application, the target material tag will eventually be filled into the tag box of the material to be shared. That is, when a material tag to be displayed is selected as the target material tag, the target material tag is filled into the tag box, and the material tag to be displayed is deleted from its original display position.

[0086] In one embodiment of this application, after a user selects a target material tag, they can also perform a deletion operation. When the terminal device detects a deletion operation on the target material tag in the tag box, it executes the deletion operation and displays the deleted target material tag as a material tag to be displayed on the display interface. That is, after deleting the target material tag in the tag box, the target material tag is displayed back in its original position as a material tag to be displayed, so that the user can select the tag again. Optionally, the deleted target material tag can be arranged at the end of each material tag to be displayed for display.

[0087] The implementation process of the technical solution of this application is illustrated below with a specific embodiment.

[0088] For example, Figure 6A The illustration schematically shows an initial interface for sharing materials provided in one embodiment of this application. Users can upload materials to be shared to the client (or terminal device) by clicking the material upload area in the interface. After the user uploads the materials to be shared, as follows... Figure 6B As shown, the client (or terminal device) automatically generates candidate material titles and tags. The title box and tag library below the material to be shared display "AI Genarating," and recommended material tags, such as "jpg," "Valentine's Day," and "sculpting," are also displayed below the tag box. The generated candidate material titles can be displayed below the title box, and the generated candidate material tags can be displayed below the tag box. For example,... Figure 6C As shown, the generated candidate material title is "Love Pierced by an Arrow: You and Me," and the generated candidate material tags include "design," "heart shape," "arrow," "romance," "you and me," and "love." It should be noted that... Figure 6C The material tags displayed have been reprocessed and are all considered as material tags to be displayed.

[0089] Users can click on the candidate material title itself, or click the "use" button corresponding to the candidate material title, such as... Figure 6C As shown, the candidate material title is selected as the target material title. After the user selects the target material title, the target material title is automatically filled into the title box. For example, as shown... Figure 6D As shown, the title box displays "Love Pierced by an Arrow: You and Me," while the corresponding candidate material titles below the title box are deleted. On the other hand, users can select a material tag as the target material tag by clicking on it, and the tag will be filled into the tag box. Simultaneously, the corresponding material tag below the tag box will be deleted. Figure 6D As shown.

[0090] like Figure 6DAs shown, the material tags also include "POD tags". These tags are further subdivided according to needs. Their generation process is the same as that of the aforementioned candidate material tags. Users can select them according to their own needs, or they can be automatically filled by the client (or terminal device).

[0091] In this embodiment, the client (or terminal device) can obtain the candidate material titles and candidate material tags by requesting the server (or server). For example, Figure 7 A flowchart illustrating a laser processing material handling method according to an embodiment of this application is shown schematically. Figure 7 As shown, the method includes the following steps:

[0092] 1. Server-side request entry point.

[0093] 2. Material Preprocessing. For image or video materials, determine the image type. If it's a non-RGB three-channel image, convert it to an RGB three-channel image. If the image size is too large, adjust it to improve the understanding and inference efficiency of the subsequent large language model.

[0094] 3. Construct the prompt. This involves creating the initial prompt message. This step also includes BASE64 encoding the material to be shared to obtain the material's encoding information.

[0095] 4. LLM Model Processing. The LLM model, or Large Language Model, takes the previously constructed initial prompt information and material encoding information as input information (message) and feeds them into the LLM model to generate suitable candidate material titles.

[0096] 5. Generate titles. The LLM model is processed to obtain candidate titles.

[0097] 6. Obtain RAG. This involves obtaining the preset material tag mapping relationship based on Retrieval Augmented Generation (RAG) processing.

[0098] 7. Construct the prompt. This involves building a second prompt message. Here, the RAG and the titles generated in the previous steps are used as contextual information to supplement the LLM with laser scene knowledge, enabling the LLM to generate appropriate labels.

[0099] 8. Generate tags. The LLM model processes the pre-processed footage and the second cue information to generate candidate footage tags.

[0100] 9. Result Optimization. This involves deduplicating and sorting multiple candidate material tags, and then returning the results to the client for display to the user.

[0101] 10. End.

[0102] For creators, this technical solution allows for rapid generation of titles and tags when uploading materials, improving efficiency and accuracy. For ordinary users, it enables faster and more precise searching for the materials they need. This technical solution can also help users find suitable holidays, scenarios, user groups, and consumables, bringing more possibilities to laser-related applications.

[0103] It should be noted that although the steps of the method in this application are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.

[0104] The following describes an embodiment of the apparatus of this application, which can be used to perform the material processing method for laser processing in the above embodiments of this application. Figure 8 A schematic block diagram of a material processing apparatus for laser processing provided in an embodiment of this application is shown. Figure 8 As shown, the laser processing material handling apparatus provided in this application embodiment includes:

[0105] The material acquisition module 810 is used to acquire materials uploaded to the laser material sharing platform for sharing.

[0106] The title generation module 820 is used to identify the content of the material to be shared and generate candidate material titles corresponding to the material to be shared.

[0107] The tag generation module 830 is used to generate candidate material tags corresponding to the material to be shared based on the candidate material title and the material to be shared;

[0108] The target information determination module 840 is used to determine the target material title corresponding to the material to be shared based on the candidate material title, and to determine the target material tag corresponding to the material to be shared based on the candidate material tag.

[0109] In one embodiment of this application, the title generation module 820 is specifically used for:

[0110] The material to be shared is encoded to obtain the material encoding information;

[0111] Construct the first prompt message corresponding to the material to be shared;

[0112] The material encoding information and the first prompt information are processed by a preset model to generate candidate material titles corresponding to the material to be shared.

[0113] In one embodiment of this application, the label generation module 830 is specifically used for:

[0114] Generate context information corresponding to the material to be shared based on the candidate material title;

[0115] Based on the context information and the material to be shared, construct the second prompt information corresponding to the material to be shared;

[0116] The shared material and the second prompt information are processed by a preset model to generate candidate material tags corresponding to the shared material.

[0117] In one embodiment of this application, the label generation module 830 is specifically used for:

[0118] Obtain a preset material tag mapping relationship, which is obtained based on retrieval enhancement generation processing;

[0119] The context information corresponding to the material to be shared is generated based on the mapping relationship between the candidate material title and the preset material tag.

[0120] In one embodiment of this application, the apparatus further includes:

[0121] The preprocessing module is used to preprocess the material to be shared according to its type to obtain preprocessed material;

[0122] The title generation module 820 is specifically used to: identify the content of the preprocessed material and generate candidate material titles corresponding to the material to be shared;

[0123] The tag generation module 830 is specifically used to: generate candidate material tags corresponding to the material to be shared based on the candidate material title and the preprocessed material.

[0124] In one embodiment of this application, the preprocessing module is specifically used for:

[0125] If the material to be shared is text material, then the material to be shared is segmented to obtain the preprocessed material;

[0126] If the material to be shared is an image or video, then the image format and / or size of the material to be shared is adjusted to obtain the pre-processed material.

[0127] In one embodiment of this application, the candidate material tags are multiple; the device further includes:

[0128] The deduplication module is used to perform deduplication and sorting processing on multiple candidate material tags.

[0129] In one embodiment of this application, the candidate material titles are multiple; the target information determination module 840 is specifically used for:

[0130] Multiple candidate material titles are displayed through the display interface;

[0131] In response to the selection operation for the candidate material title, the selected candidate material title is used as the target material title corresponding to the material to be shared.

[0132] In one embodiment of this application, the apparatus further includes:

[0133] The title filling module is used to fill the title box with the target material title if no input content is detected in the title box corresponding to the material to be shared; and to cover the input content in the title box with the target material title if no input content is detected in the title box corresponding to the material to be shared.

[0134] In one embodiment of this application, the candidate material tags are multiple; the target information determination module 840 is specifically used for:

[0135] Multiple material tags to be displayed are determined based on the multiple candidate material tags;

[0136] The multiple material tags to be displayed are shown through the display interface;

[0137] In response to the selection operation of the material tag to be displayed, at least one selected material tag to be displayed is used as the target material tag corresponding to the material to be shared.

[0138] In one embodiment of this application, the target information determination module 840 is specifically used for:

[0139] Get the first preset number of recommended material tags;

[0140] Extract a second preset number of candidate material tags from the plurality of candidate material tags; wherein the sum of the first preset number and the second preset number is a predetermined value;

[0141] The first preset number of recommended material tags and the second preset number of candidate material tags are used as multiple material tags to be displayed.

[0142] In one embodiment of this application, the apparatus further includes:

[0143] The tag filling module is used to fill the target material tag into the tag box corresponding to the material to be shared, and to delete the material tag to be displayed corresponding to the target material tag in the display interface.

[0144] In one embodiment of this application, the apparatus further includes:

[0145] The tag editing module is used to execute the deletion operation when a deletion operation is detected for the target material tag in the tag box, and to display the deleted target material tag as the material tag to be displayed on the display interface.

[0146] In one embodiment of this application, the material tag includes at least one of the main content of the material, the processing scenario to which the material is applicable, and the processing object to which the material is applicable.

[0147] The specific details of the material processing apparatus for laser processing provided in the various embodiments of this application have been described in detail in the corresponding method embodiments, and will not be repeated here.

[0148] Figure 9 A schematic block diagram of a computer system architecture for implementing an electronic device according to embodiments of the present application is shown.

[0149] It should be noted that, Figure 9 The computer system 900 of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0150] like Figure 9 As shown, the computer system 900 includes a central processing unit (CPU) 901, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 902 or programs loaded from storage section 908 into random access memory (RAM). The RAM 903 also stores various programs and data required for system operation. The CPU 901, ROM 902, and RAM 903 are interconnected via a bus 904. An input / output interface 905 (I / O interface) is also connected to the bus 904.

[0151] The following components are connected to the input / output interface 905: an input section 906 including a keyboard, mouse, etc.; an output section 907 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 908 including a hard disk, etc.; and a communication section 909 including a network interface card such as a local area network card, modem, etc. The communication section 909 performs communication processing via a network such as the Internet. A drive 910 is also connected to the input / output interface 905 as needed. A removable medium 911, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 910 as needed so that computer programs read from it can be installed into the storage section 908 as needed.

[0152] Specifically, according to embodiments of this application, the processes described in the various method flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 909, and / or installed from removable medium 911. When the computer program is executed by central processing unit 901, it performs various functions defined in the system of this application.

[0153] It should be noted that the computer-readable medium shown in the embodiments of this application can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such transmitted data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0154] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0155] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of this application, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0156] Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, touch terminal, or network device, etc.) to execute the method according to the embodiments of this application.

[0157] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein.

[0158] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A method for processing materials using laser processing, characterized in that, include: Obtain the materials uploaded to the laser material sharing platform that are ready to be shared; The content of the material to be shared is identified, and candidate material titles corresponding to the material to be shared are generated; Based on the candidate material titles and the materials to be shared, candidate material tags corresponding to the materials to be shared are generated; The target material title corresponding to the material to be shared is determined based on the candidate material title, and the target material tag corresponding to the material to be shared is determined based on the candidate material tag.

2. The material processing method for laser processing according to claim 1, characterized in that, The content of the material to be shared is identified, and candidate material titles corresponding to the material to be shared are generated, including: The material to be shared is encoded to obtain the material encoding information; Construct the first prompt message corresponding to the material to be shared; The material encoding information and the first prompt information are processed by a preset model to generate candidate material titles corresponding to the material to be shared.

3. The material processing method for laser processing according to claim 1, characterized in that, Based on the candidate material titles and the material to be shared, candidate material tags corresponding to the material to be shared are generated, including: Generate context information corresponding to the material to be shared based on the candidate material title; Based on the context information and the material to be shared, construct the second prompt information corresponding to the material to be shared; The shared material and the second prompt information are processed by a preset model to generate candidate material tags corresponding to the shared material.

4. The material processing method for laser processing according to claim 3, characterized in that, Generate context information corresponding to the material to be shared based on the candidate material title, including: Obtain a preset material tag mapping relationship, which is obtained based on retrieval enhancement generation processing; The context information corresponding to the material to be shared is generated based on the mapping relationship between the candidate material title and the preset material tag.

5. The material processing method for laser processing according to claim 1, characterized in that, After obtaining the materials to be shared uploaded to the laser material sharing platform, the method further includes: The materials to be shared are preprocessed according to their type to obtain preprocessed materials; The content of the material to be shared is identified, and candidate material titles corresponding to the material to be shared are generated, including: The content of the preprocessed material is identified to generate candidate material titles corresponding to the material to be shared; Based on the candidate material titles and the material to be shared, candidate material tags corresponding to the material to be shared are generated, including: Based on the candidate material titles and the preprocessed materials, candidate material tags corresponding to the materials to be shared are generated.

6. The material processing method for laser processing according to claim 5, characterized in that, The materials to be shared are preprocessed according to their type to obtain preprocessed materials, including: If the material to be shared is text material, then the material to be shared is segmented to obtain the preprocessed material; If the material to be shared is an image or video, then the image format and / or size of the material to be shared is adjusted to obtain the pre-processed material.

7. The material processing method for laser processing according to claim 1, characterized in that, The candidate material tags are multiple; before determining the target material tag corresponding to the material to be shared based on the candidate material tags, the method further includes: The candidate material tags are deduplicated and sorted.

8. The material processing method for laser processing according to claim 1, characterized in that, There are multiple candidate material titles; the target material title corresponding to the material to be shared is determined based on the candidate material titles, including: Multiple candidate material titles are displayed through the display interface; In response to the selection operation for the candidate material title, the selected candidate material title is used as the target material title corresponding to the material to be shared.

9. The material processing method for laser processing according to claim 8, characterized in that, After determining the target material title corresponding to the material to be shared based on the candidate material titles, the method further includes: If no input content is detected in the title box corresponding to the material to be shared, the title of the target material will be filled into the title box. If input content is detected in the title box corresponding to the material to be shared, the title of the target material will cover the input content in the title box.

10. The material processing method for laser processing according to claim 1, characterized in that, The candidate material tags are multiple; the target material title corresponding to the material to be shared is determined based on the candidate material titles, including: Multiple material tags to be displayed are determined based on the multiple candidate material tags; The multiple material tags to be displayed are shown through the display interface; In response to the selection operation of the material tag to be displayed, at least one selected material tag to be displayed is used as the target material tag corresponding to the material to be shared.

11. The material processing method for laser processing according to claim 10, characterized in that, Based on the multiple candidate material tags, multiple material tags to be displayed are determined, including: Get the first preset number of recommended material tags; Extract a second preset number of candidate material tags from the plurality of candidate material tags; wherein the sum of the first preset number and the second preset number is a predetermined value; The first preset number of recommended material tags and the second preset number of candidate material tags are used as multiple material tags to be displayed.

12. The material processing method for laser processing according to claim 10, characterized in that, After selecting at least one of the material tags to be displayed as the target material tags corresponding to the material to be shared, the method further includes: Fill the target material tag into the tag box corresponding to the material to be shared, and delete the material tag to be displayed corresponding to the target material tag in the display interface.

13. The material processing method for laser processing according to claim 12, characterized in that, After filling the target material tags into the tag boxes corresponding to the materials to be shared, the method further includes: When a deletion operation is detected for a target material tag in the tag box, the deletion operation is performed, and the deleted target material tag is displayed as a material tag to be displayed on the display interface.

14. The material processing method for laser processing according to any one of claims 1-13, characterized in that, Material tags include at least one of the following: the main content of the material, the processing scenario for which the material is applicable, and the object for which the material is applicable.

15. A material processing apparatus for laser processing, characterized in that, include: The material acquisition module is used to acquire materials uploaded to the laser material sharing platform that are to be shared; The title generation module is used to identify the content of the material to be shared and generate candidate material titles corresponding to the material to be shared. The tag generation module is used to generate candidate material tags corresponding to the material to be shared based on the candidate material title and the material to be shared; The target information determination module is used to determine the target material title corresponding to the material to be shared based on the candidate material title, and to determine the target material tag corresponding to the material to be shared based on the candidate material tag.

16. A computer-readable medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the material processing method for laser processing as described in any one of claims 1 to 14.

17. An electronic device, characterized in that, include: processor; as well as Memory for storing the executable instructions of the processor; The processor is configured to execute the executable instructions to implement the material processing method for laser processing as described in any one of claims 1 to 14.

18. A computer program product comprising computer instructions, characterized in that, When the computer instructions are executed by the processor, they implement the material processing method for laser processing as described in any one of claims 1 to 14.

Images