Design-drawing-free AI intelligent knife carving method, server, medium and program product

Abstract

The invention provides a design-drawing-free AI intelligent knife carving method, a server, a medium and a program product, and relates to the field of artificial intelligence. According to the method, three-dimensional point cloud information of a target object is obtained through scanning equipment, feature extraction is carried out on the three-dimensional point cloud information, and the contour line and internal structure information of the target object are obtained. And inputting the information into a preset deep learning model, and determining a knife carving path scheme of the to-be-knife-carved material. Then, according to the material information of the material to be subjected to knife carving, knife carving process parameters are determined; and finally, after the position and the angle of the material to be cut are determined, controlling the cutting device to cut according to the cutting path scheme and the process parameters. According to the scheme, full-process automation from three-dimensional point cloud information acquisition, knife carving path and process parameter determination and knife carving implementation is realized, and the knife carving efficiency and precision are improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence, and in particular to a design-free AI intelligent knife engraving method, server, medium and program product. Background Art

[0002] With the continuous development of artificial intelligence technology, knife engraving plays an important role in traditional fields such as handicraft making and industrial production, as well as emerging intelligent manufacturing fields. Its application scope is becoming increasingly wide. These fields have put forward higher requirements on the accuracy, efficiency and personalization of knife engraving.

[0003] In the prior art, knife engraving mostly relies on manually drawing a sketch of the engraving path on paper according to the shape and requirements of the target object, and then inputting the sketch into the computer, using relevant software for simple processing and optimization to obtain a preliminary engraving path. Then, the operator manually sets the engraving process parameters, such as engraving force, speed, etc., based on experience and material characteristics. In the actual engraving process, the operator manually controls the engraving device to engrave along the preset path.

[0004] However, this method has many defects. For example, the process of manually drawing sketches and setting parameters is cumbersome and inefficient, and is easily affected by human factors, resulting in large errors. For complex patterns and structures, manually designed paths and parameters are difficult to meet the requirements, and the accuracy and quality of engraving are difficult to guarantee. Therefore, it is difficult for existing technologies to achieve efficient engraving of materials without relying on design drawings. Summary of the invention

[0005] The present application provides an AI intelligent engraving method without design drawings, which is used to automatically obtain three-dimensional point cloud information of the target object, intelligently determine the engraving path and precise process parameters, and accurately control the engraving device to perform engraving, thereby improving the accuracy, efficiency and quality of engraving, while the existing technology relies on manual design drawings and experience to determine the engraving path and process parameters, resulting in low efficiency of the engraving process and difficulty in ensuring accuracy and quality.

[0006] In the first aspect, the present application provides an AI intelligent engraving method without design drawings, which is applied to a server, and the method includes: collecting three-dimensional point cloud information of the target object through a scanning device; performing feature extraction on the three-dimensional point cloud information to obtain the contour line and internal structure information of the target object; inputting the contour line and the internal structure information into a preset deep learning model to determine the engraving path scheme of the material to be engraved, and the deep learning model is trained and established based on the three-dimensional point cloud information and the corresponding optimal engraving path of multiple successful engraving works; determining the engraving process parameters according to the material information corresponding to the material to be engraved, the material information at least includes material hardness and material texture, and the engraving process parameters at least include engraving force and engraving speed; after determining the position and angle of the material to be engraved through the scanning device, controlling the engraving device to engrave the material to be engraved according to the engraving path scheme and the engraving process parameters.

[0007] By adopting the above technical solution, it is possible to accurately collect and process the three-dimensional point cloud information of the target object, thereby providing an accurate data basis for the subsequent determination of the engraving path plan and process parameters. The use of deep learning models can intelligently determine the optimal engraving path plan based on the experience of previous successful engraving works, thereby improving the quality and efficiency of engraving. At the same time, determining the engraving process parameters based on the material information of the material to be engraved can ensure more accurate material processing during the engraving process, reduce material waste and damage, and improve the quality of the engraved product.

[0008] In combination with some embodiments of the first aspect, in some embodiments, after determining the position and angle of the material to be engraved by a scanning device, before the step of controlling the engraving device to engrave the material to be engraved according to the engraving path plan and the engraving process parameters, it also includes: obtaining the user's selection information on the material to be engraved and the engraving style through the interactive end, the material to be engraved refers to the relevant parameters obtained from the material property database, and the engraving style refers to the style digital model determined from the engraving style database, the material property database stores the material property parameters of a variety of materials for engraving, and the engraving style database stores the digital models of a variety of engraving styles; adjusting the engraving process parameters according to the selection information; controlling the engraving device to engrave the selected material to be engraved according to the generated engraving process parameters to obtain a personalized engraved product.

[0009] By adopting the above technical solution, users can independently select the material and style to be engraved through the interactive terminal to meet their personalized needs. Adjusting the engraving process parameters according to the selected information can make the engraving device better adapt to different materials and styles, thereby producing personalized engraved products that meet user expectations. This personalized customization capability not only improves user satisfaction, but also adds unique value to the product.

[0010] In combination with some embodiments of the first aspect, in some embodiments, after the step of adjusting the engraving process parameters according to the selection information, it also includes: obtaining a pattern generation request from the user through the interactive end, the pattern generation request includes pattern parameters input by the user through voice or text at the interactive end; determining a engraving pattern that matches the pattern generation request; obtaining the user's editing operation on the engraving pattern, the editing operation including adjusting the color, size, and shape of a set part of the engraving pattern; editing the engraving pattern according to the editing operation to obtain final pattern data; after determining the engraving instruction according to the final pattern data and the engraving process parameters, controlling the engraving device to engrave the engraving material according to the engraving instruction to obtain a personalized engraving product.

[0011] By adopting the above technical solution, users can input pattern parameters through voice or text, generate or match the required engraving pattern, and edit it to obtain the final pattern data. Determining the engraving instructions based on the final pattern data and engraving process parameters can ensure that the engraving device accurately engraves according to the user's needs and produce highly personalized engraved products. This process fully reflects the flexibility and innovation of the technical solution and provides users with more creative space.

[0012] In combination with some embodiments of the first aspect, in some embodiments, the step of determining a knife-engraved pattern that matches the pattern generation request specifically includes: if an autonomous pattern generation instruction is received from the interactive end, generating the corresponding knife-engraved pattern according to the pattern parameters in the pattern generation request, and the pattern parameters include pattern type, pattern specifications, and arrangement spacing between multiple identical patterns; if a matching pattern generation instruction is received from the interactive end, searching a cloud pattern library for a knife-engraved pattern that matches the pattern generation request, and the cloud pattern library stores a variety of pattern resources.

[0013] By adopting the above technical solution, the diverse needs of users for knife-carved patterns can be met. When receiving an autonomous pattern generation instruction, the corresponding knife-carved pattern is generated according to the pattern parameters. Users can customize unique patterns according to their own creativity and needs to achieve personalized knife-carved products. If a matching pattern generation instruction is received, a matching knife-carved pattern is searched in the cloud pattern library, and the rich pattern resources in the cloud are used to provide users with more choices. This flexible pattern generation method not only improves user participation and satisfaction, but also expands the design space of knife-carved products, making them more innovative and competitive in the market.

[0014] In combination with some embodiments of the first aspect, in some embodiments, after determining the position and angle of the material to be engraved by a scanning device, and controlling the engraving device to engrave the material to be engraved according to the engraving path plan and the engraving process parameters, it also includes: inputting the engraving process parameters and the engraving path plan into the cutting time prediction model to obtain a corresponding estimated cutting cycle, and the cutting time prediction model is trained based on the training set of the engraving process parameters, the engraving path data and the corresponding actual cutting time data collected in advance; when it is determined that the engraving target is a plurality of continuous identical engraving products, the overall cutting time is determined according to the cutting time prediction model; and the estimated cutting cycle and the overall cutting time are sent to the display end for display.

[0015] By adopting the above technical solution, the cutting time prediction model can accurately predict the estimated cutting cycle and overall cutting time based on the cutting process parameters and cutting path data. Sending this time information to the display terminal for display can help users better plan production progress and improve production efficiency. At the same time, for multiple consecutive identical cutting products, it can reasonably arrange production time, reduce production costs, and improve production efficiency.

[0016] In combination with some embodiments of the first aspect, in some embodiments, after the step of determining the engraving process parameters according to the material information corresponding to the material to be engraved, it also includes: adjusting the engraving process parameters according to the material characteristic parameters in the material information according to an automatic adjustment method, and the material characteristic parameters include at least a material hardness parameter of the material to be engraved. The automatic adjustment method includes increasing the engraving force in the engraving process parameters and reducing the engraving speed in the engraving process parameters when the material hardness parameter is higher than a preset threshold value.

[0017] By adopting the above technical solution, the knife engraving process parameters are automatically adjusted according to the material characteristic parameters, which can ensure that the knife engraving device can work at the most appropriate force and speed when engraving materials of different hardness. When the material hardness is higher than the preset threshold, the knife engraving force is increased and the knife engraving speed is reduced, which can effectively avoid problems such as excessive wear of the tool and material damage, improve the stability and reliability of the knife engraving, extend the service life of the tool, and reduce production costs.

[0018] In combination with some embodiments of the first aspect, in some embodiments, after the step of controlling the engraving device to engrave the material to be engraved according to the engraving path plan and the engraving process parameters, it also includes: collecting force feedback data of the engraving device during the engraving process in real time through a sensor; comparing the force feedback data with a preset force threshold range; if the force feedback data exceeds the force threshold range, determining that there is an abnormality in the engraving device during the engraving process; and controlling the alarm device to issue an alarm message.

[0019] By adopting the above technical solution, during the engraving process, the sensor collects the force feedback data of the engraving device in real time and compares it with the preset force threshold range. If the force feedback data exceeds the force threshold range, it means that there is an abnormality in the engraving device. At this time, the control alarm device sends an alarm message, which can promptly remind the operator to check and deal with it, avoid production accidents and product quality problems caused by equipment abnormalities, and improve production safety and stability.

[0020] In a second aspect, the present application provides a server, comprising: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to cause the server to execute the method described in the first aspect and any possible implementation of the first aspect.

[0021] In a third aspect, the present application provides a computer-readable storage medium comprising instructions, which, when executed on a server, causes the server to execute the method described in the first aspect and any possible implementation of the first aspect.

[0022] In a fourth aspect, the present application provides a computer program product, which, when executed on a server, enables the server to execute the method described in the first aspect and any possible implementation manner of the first aspect.

[0023] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. Due to the technical means of collecting three-dimensional point cloud information of the target object through scanning equipment, extracting features of the three-dimensional point cloud information, and using a deep learning model to determine the knife engraving path plan, the problem of large errors and low efficiency caused by relying on manual design and experience in the existing technology is effectively solved, thereby achieving the technical effect of improving knife engraving accuracy and efficiency.

[0024] 2. Due to the technical means of obtaining user pattern generation requests through the interactive terminal, determining the matching knife engraving patterns and processing according to the user editing operations, the problem of the existing technology being difficult to meet the personalized needs of users is effectively solved, thereby achieving the technical effect of producing highly personalized knife engraving products.

[0025] 3. Since the technical means of automatically adjusting the engraving process parameters according to the material characteristic parameters of the material to be engraved is adopted, the problem of difficulty in accurately matching the process parameters of different materials in the existing technology is effectively solved, thereby achieving the technical effect of improving the stability and reliability of engraving, extending the service life of the tool, and reducing the production cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a flow chart of the AI ​​intelligent knife engraving method without design drawing in the embodiment of the present application; Figure 2 It is another flow chart of the AI ​​intelligent knife engraving method without design drawing in the embodiment of the present application; Figure 3 It is a schematic diagram of a physical device structure of a server in an embodiment of the present application. DETAILED DESCRIPTION

[0027] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification and appended claims of the present application, the singular expressions "one", "a kind of", "said", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to and includes any or all possible combinations of one or more listed items.

[0028] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0029] In the related art, the design and production of knife carving mainly rely on manually drawing design drawings and determining knife carving parameters based on experience. However, this manual design drawing and the way of formulating parameters based on experience have many problems: first, drawing design drawings and determining parameters completely rely on personal experience, which is prone to large errors. For complex target structures, it is difficult to draw the optimal path manually; secondly, the parameters determined by experience are difficult to adapt to the characteristics of different materials and are not accurate enough; furthermore, the entire knife carving process is inefficient and cannot meet the timeliness requirements. Therefore, it is difficult to improve the accuracy, efficiency and quality of knife carving by relying on manual design drawings and experience in the prior art. However, the design-free AI intelligent knife carving method in the embodiment of the present application is adopted, and the three-dimensional data of the target object is automatically obtained through AI technology, the knife carving path is intelligently planned, and the knife carving process parameters are accurately matched to realize the automation of the entire knife carving process, which not only greatly improves the accuracy and efficiency of knife carving, but also can adjust parameters according to the characteristics of different materials to ensure the quality of knife carving.

[0030] For ease of understanding, the following is a description of the process of the method provided by this implementation. Figure 1 , which is a flow chart of the AI ​​intelligent knife engraving method without design drawing in the embodiment of the present application.

[0031] S101, collecting three-dimensional point cloud information of the target object through a scanning device; The target object is a physical object that the user wants to engrave. After the user places the physical object in the scanning area of ​​the engraving device, the user can control the engraving device to start scanning the physical object in a manner similar to a start button or other wireless manner. The server of the engraving device is connected to various types of scanning devices, such as laser 3D scanners, structured light 3D scanners, etc. Before engraving, the server will control the scanning device to perform a 3D scan of the target object to obtain the 3D point cloud data of the target object. The 3D scanning process is that the scanning device emits a laser or structured light, which is reflected after being irradiated on the surface of the target object. By analyzing the position, angle and other information of the reflected light, the 3D coordinates of each point on the surface of the target object are calculated, and finally the 3D point cloud information of the target object is formed.

[0032] In some embodiments, the target object may also be a picture template provided by the user. In this case, the scanning device may be an image recognition scanner, which can scan and analyze the picture template, extract key features and information from the picture, and convert it into three-dimensional point cloud information.

[0033] Compared with traditional manual measurement of physical size or photographic stereoscopic images, 3D scanning can quickly and efficiently obtain the 3D geometric information of the target object.

[0034] S102, extracting features from the three-dimensional point cloud information to obtain the contour and internal structure information of the target object; Specifically, the server can call the semantic segmentation algorithm to divide the 3D point cloud into different semantic areas. For example, the face point cloud can be divided into the eye area, nose area, mouth area, etc. Then the boundary extraction algorithm is applied to detect the boundaries between adjacent semantic areas and obtain the outline of the object. In addition to the contour information, the server can also identify the distribution of concave and convex areas on the surface of the object through the concave-convex structure detection algorithm. For example, the eye sockets and nose in the face point cloud are concave structures, and the muscle nasal bones are convex structures. Detecting the distribution of these internal structures is conducive to the subsequent determination of the knife path and process parameters.

[0035] S103, inputting the contour line and the internal structure information into a preset deep learning model to determine a knife engraving path solution for the material to be engraved, wherein the deep learning model is trained and established based on three-dimensional point cloud information of multiple set successful knife engraving works and corresponding optimal knife engraving paths; The server has a large number of 3D point clouds and corresponding carving path databases of successful carving works. These carving paths are the optimal paths determined by repeated trials by senior knife workers. Based on these data sets, the server uses a deep learning algorithm to train a carving path generation model. After obtaining the contour and internal structure information of the target object, the server will input it into the pre-trained deep learning model. The model will automatically analyze the input information, find the most matching case in the stored sample library, and refer to its corresponding carving path to calculate the optimal carving plan for the target object. For example, suppose the model has learned a lot of carving data about human statues. When the server inputs the contour and internal structure information of a new human statue, the model will analyze this information and determine the shape and position relationship of various parts of the figure, such as the head, body, limbs, etc. Then, based on the experience learned in the past, the model will determine where to start carving, how to carve along the contour of the figure, and how much force and speed should be used in different parts. In this way, the model can generate a specific carving path plan for this human statue. In practical applications, deep learning models will be continuously optimized and improved. The server will collect more data on successful carving works and input this data into the model so that the model can continue to learn and improve.

[0036] Compared with manual experience, the deep learning model has comprehensively learned a large number of successful cases and can intelligently determine the best solution based on the actual situation. Unlike a single algorithm, the deep learning model has the ability to continuously learn and iterate and optimize, making the knife path solution more intelligent.

[0037] S104, determining a cutting process parameter according to material information corresponding to the material to be cut, wherein the material information at least includes material hardness and material texture, and the cutting process parameter at least includes cutting force and cutting speed; The server collects relevant information about the material to be engraved in advance, which requires necessary testing and measurement of the material to obtain the main performance parameters of the material. For hardness and texture, it can be obtained through the test report provided by the material supplier, or it can be obtained by self-testing with relevant testing equipment, such as testing hardness with a Brinell hardness tester.

[0038] Then consult the process database to obtain the range of knife carving process parameters that match the material. The server side will connect to the knife carving process database, which stores the correspondence between different materials and knife carving parameters. According to the obtained material hardness and texture parameters, the reasonable range of matching knife carving force and speed parameters can be found. The server will comprehensively consider the material parameters, the range provided by the process database, and the actual knife carving requirements to determine an initial, satisfactory combination of knife carving force and speed parameters. Then control the knife carving device to test the knife, observe the blade quality, chip morphology, etc. on the material sample. If the effect is not good, continue to adjust the optimization parameters until the best knife carving force and speed parameters are found. The determined parameters will be saved by the server for subsequent knife carving device calls in the production process.

[0039] In some embodiments, when the server detects that the material hardness parameter is higher than a preset threshold, it automatically starts the adjustment mechanism. Specifically, the engraving force in the engraving process parameters is increased. This is because materials with higher hardness require greater force for effective engraving, otherwise the tool may not be able to leave a clear mark on the surface of the material. For example, when engraving a piece of metal material with higher hardness, if the engraving force is insufficient, the tool may slip on the surface of the material and fail to engrave the desired pattern or shape. By increasing the engraving force, it can be ensured that the tool can smoothly cut into the material and achieve precise engraving.

[0040] At the same time, the server will reduce the cutting speed in the cutting process parameters. This is because when facing materials with higher hardness, too fast cutting speed may cause the tool to wear more severely or even damage the tool. In addition, too fast cutting speed may also cause too much heat to be generated on the surface of the material, thus affecting the quality of cutting and the performance of the material. For example, when cutting a piece of cemented carbide, if the cutting speed is too fast, the temperature of the tool will rise rapidly, which may cause the hardness of the tool to decrease, making it more susceptible to wear. Therefore, reducing the cutting speed can reduce the wear of the tool, extend the service life of the tool, and also help improve the quality of cutting.

[0041] In order to adjust the engraving process parameters more accurately, the server will refer to a large amount of historical data and experience. It will store the process parameter records of previous engraving of materials of different hardness, and make analogies and adjustments based on the hardness parameters of the current material. For example, if the server finds that the hardness of the current material is similar to that of a material that was successfully engraved before, it will refer to the previous engraving process parameters and make appropriate adjustments to the current parameters. In addition, the server will also take into account the impact of other material characteristic parameters on the engraving process. During the actual engraving process, the server will monitor the operating status and engraving effect of the engraving device in real time through scanning equipment. If the engraving effect is found to be unsatisfactory, such as unclear marks, excessive wear of the tool, etc., it will adjust the engraving process parameters in time to ensure the quality and efficiency of the engraving.

[0042] By automatically adjusting the engraving process parameters according to the material characteristic parameters, the server can ensure that the engraving device can work at the most appropriate force and speed when engraving materials of different hardness, thereby effectively improving the stability and reliability of engraving, extending the service life of the tool, and reducing production costs.

[0043] S105, after determining the position and angle of the material to be engraved by the scanning device, controlling the engraving device to engrave the material to be engraved according to the engraving path plan and the engraving process parameters.

[0044] The operator clamps and fixes the material on the workbench of the engraving device according to the size and positioning parameters of the material to be engraved. Accurate positioning can be achieved through various methods, such as using a mechanical clamp to align the lower left corner of the material with the coordinate origin of the workbench; or marking the position coordinates of the material on the workbench and manually placing the material at the specified position. The material can be fixed by bolt connection, vacuum suction cup, etc. After the clamping is completed, it is necessary to verify whether the material matches the set parameters and engraving path. The server will control the scanning device to scan the material to be engraved placed on the workbench of the engraving device to obtain the three-dimensional information of the material. Then, the image analysis algorithm is used to detect the edge contour of the material and calculate the length, width, and thickness parameters of the material. At the same time, the three-dimensional information of the scanned material can be aligned with the set coordinate system through the registration algorithm to determine the position coordinates and spatial orientation angle of the material.

[0045] The server instructs the engraving device to control the tool to perform the engraving action according to the imported engraving path plan while ensuring the positioning accuracy of each axis. At the same time, the spindle speed and feed speed are precisely controlled to ensure that they are consistent with the set engraving process parameters. When the tool accurately cuts the material according to the calculated path, the designed three-dimensional pattern is gradually formed. After the automatic tool path is completed, the quality of the engraved surface can be inspected by the mirror processing machine. If there are minor defects, they can also be manually trimmed and improved. Then, spraying, inlaying and other post-beautification treatments are carried out to complete the engraving work.

[0046] In some embodiments, when it is determined that the engraving target is a continuous plurality of identical engraving products, the server will determine the overall cutting time according to the cutting time prediction model. Specifically, the server will install an intelligent cutting time prediction system in the engraving device. The system includes a cutting time prediction model, which is trained by the server based on a large amount of historical engraving data. The historical data includes the engraving process parameters (tool speed, feed speed, etc.) of each engraving, the engraving path information (knife length, number of turns, etc.) and the corresponding actual cutting time. The server will use these data to train the cutting time prediction model and establish a relationship model between engraving parameters, paths and cutting time. Each time a new engraving task is performed, the server will input the current engraving process parameters and path scheme into the cutting time prediction model, and the model can accurately predict the estimated cutting cycle of the engraving. For example, if the cutting speed set by the engraving parameters is very fast and the path is very complex, the model can estimate a longer cutting time. For multiple repeated engraving products that need to be mass-produced, the server can also calculate the overall cutting time of the entire mass production based on the cutting time estimate of a single product. For example, if the estimated cutting time for a single product is 50 minutes and 100 pieces need to be produced, the total cutting time is 100*50=5000 minutes. Finally, the server will send the predicted cutting cycle of a single product and the total cutting time of batch production to the display end of the engraving device for display to the user. Users can reasonably arrange the production process based on these time estimation data to improve production efficiency. If the time is too long, the plan and parameters can be adjusted in time to shorten the engraving time.

[0047] In this way, by establishing a cutting time prediction model, the effect of accurately predicting the cutting time is achieved. Time information can be obtained without actually completing the cutting, which can better support production planning. Compared with rough manual estimation of time, it can improve the prediction effect and reduce production costs.

[0048] In the embodiment of the present application, the three-dimensional point cloud information of the target object is obtained by scanning equipment, and the deep learning model is used to intelligently determine the knife path plan and process parameters, so the effect of automatically obtaining the target object data and intelligently planning the knife carving plan is achieved. This effectively solves the problem of low knife carving efficiency and large errors caused by relying on manual design drawings and experience in the prior art, and thus achieves the technical effect of improving the automation, accuracy and efficiency of knife carving.

[0049] In some embodiments, in order to continuously monitor the working state of the tool, a temperature sensor can be installed at the spindle end of the tool to detect the temperature change of the tool in real time in a contactless manner. In principle, an increase in the temperature of the tool will change the cutting performance of the tool. Under the same cutting force and rotation speed, the higher the temperature of the tool, the easier it is to overcut the material and cut deeper. This is because high temperature softens the cutting edge of the tool and reduces the hardness of the blade. In order to compensate for the impact of temperature changes on the cutting effect, a mapping model of temperature and cutting parameters can be established. The model can be obtained by testing the cutting effect of the tool at different temperatures. For example, the cutting depth at 50°C is recorded as 5mm, and the cutting depth at 80°C is recorded as 5.5mm. During actual cutting, the server will obtain the tool temperature data in real time. If a temperature rise is detected, the temperature mapping model is used to predict how much the cutting depth will increase at the current temperature.

[0050] The server will then reduce the cutting force parameters to compensate for the increased cutting depth caused by the temperature rise. At the same time, it will also reduce the spindle speed, extend the cutting time of each tool position, and reduce the amount of cutting per unit time. For example, if the current tool temperature is measured to be 80°C, the model predicts that the cutting depth will be 10% deeper than normal. The server will reduce the cutting force by 5%, reduce the spindle speed by 10%, and recalculate the tool position time to offset the impact of the temperature rise.

[0051] In this way, by modeling and timely compensating for the impact of tool temperature changes on cutting parameters, the deviation in cutting effect caused by temperature rise can be effectively reduced to ensure accuracy.

[0052] In some embodiments, the force feedback data of the engraving device during the engraving process can also be collected in real time by sensors arranged at appropriate positions of the engraving device. These sensors can accurately sense the magnitude and direction of the force exerted on the engraving device during operation. The server compares the received force feedback data with a preset force threshold range. This force threshold range is preset based on factors such as the performance of the engraving device, the characteristics of the material to be engraved, and the requirements of the engraving process. For example, for a specific material and engraving process, it may be stipulated that the pressure exerted on the tool should be within a certain range, and the torque should also be maintained in a reasonable range. If the force feedback data is within this preset force threshold range, it means that the working state of the engraving device is normal and the engraving operation can continue. However, if the force feedback data exceeds the force threshold range, it is determined that there is an abnormality in the engraving device during the engraving process. The server will store the historical operation data of the engraving device in advance, including force feedback data and position data under normal circumstances. When an abnormality occurs, the server will compare the current data with the historical data, analyze the characteristics of the abnormal data, and thus infer the possible cause of the abnormality. For example, if the current force feedback data pattern is similar to the data pattern when the tool was worn before, it may be inferred that the abnormality is caused by tool wear. When the server determines that there is an abnormality in the cutting device, it will immediately control the alarm device to issue an alarm message. The alarm device can be an audible and visual alarm, which emits a loud sound and flashing lights to alert the operator, and displays specific abnormal information on the control terminal, such as "excessive tool pressure" or "abnormal torque".

[0053] In some embodiments, when a user has personalized needs for knife-carved products, he or she hopes to be able to choose materials, styles, and patterns according to his or her preferences, and make customized edits and adjustments. Alternatively, in art education or handicraft courses, students can learn knife-carving techniques in the program and create their own personalized works through customized editing to cultivate creativity and hands-on ability.

[0054] After combining the above embodiments, the method provided by this embodiment is further described in more detail below. Figure 2 , which is another flow chart of the design-free AI intelligent knife engraving method in the embodiment of the present application.

[0055] S201, obtaining, through the interactive terminal, selection information of a user on a material to be engraved and an engraving style, wherein the material to be engraved refers to relevant parameters obtained from a material property database, and the engraving style refers to a style digital model determined from an engraving style database, wherein the material property database stores material property parameters of a plurality of materials for engraving, and the engraving style database stores digital models of a plurality of engraving styles; The server side will connect to the material property database and the carving style database. The material property database stores various types of materials that can be used for carving, such as wood, stone, metal, etc., and gives the relevant property parameters of each material. These parameters can include physical parameters such as density, hardness, compressive strength, thermal conductivity, etc. of the material, or appearance and performance parameters such as color, texture, touch, etc. of the material. The carving style database stores digital models of various styles of carving styles, such as intaglio, hollow carving, thick and thin lines, etc.

[0056] The server will set two options, material and style, in the interactive end, such as a web page or APP. The user can click on the material control, browse the pictures and parameters of different materials in the material database, and select the knife-carved material they need, such as mahogany. Then browse the style database in the style option and select the knife-carved style model they like, such as a spiral abstract line style. Finally, the user clicks "Confirm Selection", and the selected material parameters and style model ID are sent to the server through the network. The server will search for all the material property parameters of the mahogany and the three-dimensional digital model of the abstract line style from the database.

[0057] S202, adjusting the engraving process parameters according to the selection information; The server will consult the process database, such as obtaining the hardness, density and other parameters of the material selected by the user, and then match the appropriate tool material and model. For example, for materials with higher hardness, carbide tools are required to ensure that the tool hardness is greater than the material hardness. Then the optimized tool parameters such as cutting edge angle, helix angle, cutting speed and cutting force are calculated. Secondly, the server will import the three-dimensional digital model of the cutting style selected by the user, and determine the optimal cutting parameters for each area by analyzing the surface features of different parts.

[0058] S203, obtaining a pattern generation request from a user through the interactive terminal, where the pattern generation request includes pattern parameters input by the user through voice or text at the interactive terminal; The server can obtain the user's knife pattern generation request in advance through the voice input and text input functions deployed on the interactive terminal.

[0059] S204, if an autonomous pattern generation instruction is received from the interactive terminal, the corresponding knife pattern is generated according to the pattern parameters in the pattern generation request, where the pattern parameters include pattern type, pattern specification, and arrangement spacing between multiple identical patterns; If the server receives an instruction from the interactive end to generate a pattern autonomously, the automatic pattern generation process will be initiated. The server will call the natural language processing module to parse the user's voice or text input in the pattern generation request and extract parameters such as pattern type, size specifications, and spacing arrangement.

[0060] S205: if a matching pattern generation instruction is received from the interactive terminal, a knife engraving pattern matching the pattern generation request is searched in a cloud pattern library, where a variety of pattern resources are stored; If the server receives an instruction to match the generated pattern, the cloud-based pattern retrieval process will be enabled. The server will extract keywords from the user's pattern generation request, such as "peony" and "butterfly". Then, the server will use these words as search keywords and conduct a full-text search in the connected cloud-based pattern library to find relevant knife-carved pattern models. These cloud-based pattern resources can be shared by other users or provided by professional designers. From the results returned by the search, the server will sort and filter them based on word semantic similarity, knife-carving complexity, etc., to find several knife-carved pattern templates that best match the user's pattern generation request.

[0061] Finally, the server will extract the digital model information of these patterns, including the precise pattern outline coordinates and the structural hierarchical relationship of the pattern components, and store it temporarily.

[0062] S206, obtaining the user's editing operation on the knife-carved pattern, where the editing operation includes adjusting the color, size, and shape of a set part of the knife-carved pattern; The server will obtain the user's editing operations on the knife-carved pattern in real time. When the user edits the knife-carved pattern on the interactive end, the server will receive and parse the operation information. For example, the user may choose to adjust the color of a certain part of the knife-carved pattern. The server will identify the part selected by the user and obtain the color value specified by the user. For size adjustment, the user may drag a part of the pattern, or enter a specific size value. The server will calculate the size ratio or specific size that needs to be adjusted based on the user's operation. For example, if the user wants to double the diameter of a circular pattern, the server will calculate the corresponding adjustment parameters.

[0063] In terms of shape adjustment, users may stretch, twist or deform a part of the pattern. The server will accurately capture the trajectory and force of these operations to determine the specific changes in the pattern shape. For example, if a user wants to round one corner of a rectangular pattern, the server will calculate the degree of curvature and shape change of the rectangular corner based on the user's operation trajectory and force.

[0064] In addition, the server considers the order and combination of user operations. If the user edits multiple parts at the same time, the server processes each operation in the order in which the user edited it and ensures that the interaction between them is handled correctly. For example, if the user first adjusts the color of the pattern and then adjusts its size, the server will consider the state of the pattern after the color adjustment when performing the size adjustment.

[0065] The server also provides a real-time preview function, allowing users to instantly see the effect of pattern changes during the editing process. In this way, users can further adjust the editing operation according to the preview results until they are satisfied.

[0066] S207, editing the engraved pattern according to the editing operation to obtain final pattern data; The server performs detailed editing of the engraved pattern based on the user's editing operations. Taking color adjustment as an example, the server will replace the color of the corresponding part of the pattern according to the color value specified by the user, scale the pattern according to the calculated size ratio or specific size, and deform the shape of the pattern according to the user's operation trajectory and strength. During the editing process, the server will ensure the quality and integrity of the pattern. In order to ensure the accuracy of the final pattern data, the server will perform multiple checks and verifications. For example, the server will check whether there are missing pixels or abnormal colors in the pattern, and whether the shape of the pattern meets the user's expectations. If problems are found, the server will repair and adjust them in a timely manner.

[0067] S208, after determining the engraving instruction according to the final pattern data and the engraving process parameters, control the engraving device to engrave the engraving material according to the engraving instruction to obtain a personalized engraved product.

[0068] After obtaining the final pattern data and engraving process parameters, the server will begin to determine the engraving instructions. It will conduct a comprehensive analysis of the pattern data and process parameters to calculate the specific actions and parameters that the engraving device needs to perform during the engraving process. For example, the movement trajectory and cutting depth of the engraving device are determined based on the shape and size of the pattern; the strength and speed of the engraving are determined based on the hardness and texture of the material. After determining the engraving instructions, the server will send a control signal to the engraving device to instruct the engraving device to perform engraving according to the instructions. During the engraving process, the server can monitor the operating status of the engraving device in real time through a scanning device to ensure that it accurately executes the engraving instructions. If the engraving device is found to be abnormal or deviates from the instructions, the server will adjust the control signal in time to ensure the smooth progress of the engraving.

[0069] When the engraving is completed, the server will check and evaluate the engraved product. It will check whether the engraved product meets the requirements of the final pattern data and whether there are any flaws or defects. If any problems are found, the server will record them and analyze the reasons so that improvements can be made in the subsequent engraving process.

[0070] In the embodiment of the present application, due to the use of technical means that allow users to independently select knife engraving materials and styles, generate or match knife engraving patterns, and perform personalized editing, it is possible to produce a unique customized knife engraving product according to the personalized needs and aesthetics of each user. This effectively solves the problem that the degree of personalization of knife engraving product design and production in the prior art is not high and it is difficult to meet the needs of different users, thereby achieving a technical effect of greatly improving the personalized customization ability of knife engraving products and user experience.

[0071] The following describes the server in the embodiment of the present invention from the perspective of hardware processing. Figure 3 , is a schematic diagram of a physical device structure of a server in an embodiment of the present application.

[0072] It should be noted that Figure 3 The structure of the server shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0073] like Figure 3 As shown, the server includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 to the random access memory (RAM) 303, such as executing the method described in the above embodiment. In RAM 303, various programs and data required for system operation are also stored. CPU 301, ROM 302 and RAM 303 are connected to each other through bus 304. Input / output (I / O) interface 305 is also connected to bus 304.

[0074] The following components are connected to the I / O interface 305: an input section 306 including an audio input device, a button switch, etc.; an output section 307 including a liquid crystal display (LCD) and an audio output device, an indicator light, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read therefrom is installed into the storage section 308 as needed.

[0075] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 309, and / or installed from a removable medium 311. When the computer program is executed by the central processing unit (CPU) 301, various functions defined in the present invention are performed.

[0076] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, apparatus, or device.

[0077] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings.

[0078] Specifically, the server of this embodiment includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, the design-free AI intelligent knife engraving method provided in the above embodiment is implemented.

[0079] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the server described in the above embodiment; or may exist independently without being assembled into the server. The above storage medium carries one or more computer programs, and when the above one or more computer programs are executed by a processor of the server, the server implements the design-free AI intelligent knife engraving method provided in the above embodiment.

[0080] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0081] As used in the above embodiments, the term "when..." may be interpreted to mean "if..." or "after..." or "in response to determining..." or "in response to detecting...", depending on the context. Similarly, the phrases "upon determining..." or "if (the stated condition or event) is detected" may be interpreted to mean "if determining..." or "in response to determining..." or "upon detecting (the stated condition or event)" or "in response to detecting (the stated condition or event)", depending on the context.

[0082] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

Claims

1. A design-free AI intelligent knife engraving method, applied to a server, characterized in that: The method comprises: Collect three-dimensional point cloud information of the target object through scanning equipment; Extracting features from the three-dimensional point cloud information to obtain the contour and internal structure information of the target object; According to the contour line and the internal structure information, a preset deep learning model is input to determine a knife engraving path scheme for the material to be engraved, wherein the deep learning model is trained and established based on the three-dimensional point cloud information of multiple successful knife engraving works and the corresponding optimal knife engraving paths; Determine the engraving process parameters according to the material information corresponding to the material to be engraved, wherein the material information at least includes material hardness and material texture, and the engraving process parameters at least include engraving force and engraving speed; After the position and angle of the material to be engraved are determined by a scanning device, the engraving device is controlled to engrave the material to be engraved according to the engraving path scheme and the engraving process parameters.

2. The method according to claim 1, characterized in that After determining the position and angle of the material to be engraved by a scanning device, before controlling the engraving device to engrave the material to be engraved according to the engraving path scheme and the engraving process parameters, the method further includes: Obtaining, through the interactive terminal, selection information of the user on the material to be engraved and the engraving style, wherein the material to be engraved refers to relevant parameters obtained from a material property database, and the engraving style refers to a style digital model determined from an engraving style database, wherein the material property database stores material property parameters of a plurality of engraving materials, and the engraving style database stores digital models of a plurality of engraving styles; Adjust the engraving process parameters according to the selection information; The engraving device is controlled to engrave the selected material to be engraved according to the generated engraving process parameters to obtain a personalized engraved product.

3. The method according to claim 2, characterized in that After the step of adjusting the cutting process parameters according to the selection information, the method further includes: Acquiring a pattern generation request from a user through the interactive terminal, wherein the pattern generation request includes pattern parameters input by the user through voice or text at the interactive terminal; Determining a knife engraving pattern that matches the pattern generation request; Acquiring a user's editing operation on the knife-carved pattern, wherein the editing operation includes adjusting the color, size, and shape of a set part of the knife-carved pattern; Edit the engraved pattern according to the editing operation to obtain final pattern data; After the engraving instructions are determined according to the final pattern data and the engraving process parameters, the engraving device is controlled to engrave the engraving material according to the engraving instructions to obtain a personalized engraved product.

4. The method according to claim 3, characterized in that: The step of determining a knife engraving pattern matching the pattern generation request specifically comprises: If an autonomous pattern generation instruction is received from the interactive terminal, the corresponding knife-engraved pattern is generated according to the pattern parameters in the pattern generation request, wherein the pattern parameters include pattern type, pattern specification and arrangement spacing between multiple identical patterns; If a matching pattern generation instruction is received from the interactive end, a knife engraving pattern matching the pattern generation request is searched in a cloud pattern library, where a variety of pattern resources are stored.

5. The method according to claim 1, characterized in that After determining the position and angle of the material to be engraved by a scanning device, and controlling the engraving device to engrave the material to be engraved according to the engraving path scheme and the engraving process parameters, the method further includes: Input the cutting process parameters and cutting path plan into the cutting time prediction model to obtain the corresponding estimated cutting cycle, wherein the cutting time prediction model is obtained by training the cutting process parameters, the cutting path data and the corresponding actual cutting time data collected in advance as a training set; When it is determined that the cutting target is a plurality of continuous identical cutting products, the overall cutting time is determined according to the cutting time prediction model; The estimated cutting cycle and the overall cutting time are sent to a display terminal for display.

6. The method according to claim 1, characterized in that After the step of determining the engraving process parameters according to the material information corresponding to the material to be engraved, the method further includes: According to the material characteristic parameters in the material information, the engraving process parameters are adjusted in an automatic adjustment manner, wherein the material characteristic parameters at least include the material hardness parameter of the material to be engraved, and the automatic adjustment method includes increasing the engraving force in the engraving process parameters and reducing the engraving speed in the engraving process parameters when the material hardness parameter is higher than a preset threshold.

7. The method according to claim 1, characterized in that After the step of controlling the engraving device to engrave the material to be engraved according to the engraving path scheme and the engraving process parameters, the method further includes: The force feedback data of the engraving device during the engraving process is collected in real time by means of a sensor; comparing the force feedback data with a preset force threshold range; If the force feedback data exceeds the force threshold range, it is determined that an abnormality exists in the engraving device during the engraving process; Control the alarm device to send out an alarm message.

8. A server, characterized in that: The server includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the server to execute the method described in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instructions are executed on a server, the server is caused to execute the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product is run on a server, the server is caused to execute the method according to any one of claims 1 to 7.

Images