Model Synchronization Processing Method and System for Slice Data Management

Abstract

The present invention discloses a model synchronization processing method and system for slice data management. The method includes: obtaining in real time the modification operations of a target user on target model slice data; predicting, based on multiple modification operations of the target user, the possible modification operations of the target user in the next time period; determining, according to the possible modification operations and based on a prediction algorithm, the corresponding model modification method and model modification position; and generating modification synchronization data corresponding to the model modification method and the model modification position in the cloud model data of the target model slice data in a cloud server. It can be seen that the present invention can fully combine user modification operation prediction to improve the efficiency of cloud model data modification synchronization, improve the intelligence and automation levels of user model modification operations, and give users a better use experience.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a model synchronization processing method and system for slice data management. Background Art

[0002] With the development of 3D printing technology, more and more users or organizations have begun to pay attention to technical issues such as the management and transmission of slice data of printed models. Some organizations have begun to develop platforms that can manage and modify slice data. Among them, how to effectively improve the convenience and user experience of users' slice data modification operations on the platform is a technical issue that has received much attention. However, most of the existing slice data processing technologies still only update the model data in the cloud based on the modification results of the user's direct modification operations, and do not use the range prediction of the user's modification operation to predict the data modification method and modification location in the cloud in advance. Therefore, the cloud data synchronization efficiency of the user's model modification operation is low, and the user experience is poor. It can be seen that the existing technology has defects that need to be solved urgently. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a model synchronization processing method and system for slice data management, which can fully combine user modification operation prediction to improve the efficiency of cloud model data modification synchronization, improve the intelligence and automation of user model modification operations, and provide users with a better user experience.

[0004] In order to solve the above technical problems, the first aspect of the present invention discloses a model synchronization processing method for slice data management, the method comprising:

[0005] Obtain the target user's modification operations on the target model slice data in real time;

[0006] Based on the multiple modification operations of the target user, predicting possible modification operations of the target user in the next time period;

[0007] According to the possible modification operation, based on the prediction algorithm, determine the corresponding model modification method and model modification position;

[0008] Generate modification synchronization data corresponding to the model modification method and the model modification position in the cloud model data of the target model slice data in the cloud server; the modification synchronization data is used to modify the cloud model data in response to the next modification operation of the target user being the same as the possible modification operation.

[0009] As an optional implementation, in the first aspect of the present invention, the modification operation includes at least one of modifying a selected model portion, modifying an operation type, modifying a movement trajectory, modifying a time point, and modifying a number of undo operations.

[0010] As an optional implementation manner, in the first aspect of the present invention, predicting the possible modification operations of the target user in the next time period based on the multiple modification operations of the target user includes:

[0011] Sorting the multiple modification operations of the target user obtained at multiple historical time points from earliest to latest based on the corresponding historical time points to obtain an operation sequence;

[0012] Based on a prediction neural network, predicting the possible modification operations of the target user in the next time period according to the operation sequence, the user parameters of the target user, and the data parameters of the target model slice data.

[0013] As an optional implementation manner, in the first aspect of the present invention, the user parameters include at least one of user physiological parameters, user permissions, user historical operation records, and user historical access records; the data parameters include at least one of the data volume size, the model representation object type, the model physical parameters, and the model space complexity distribution curve.

[0014] As an optional implementation manner, in the first aspect of the present invention, predicting the possible modification operations of the target user in the next time period based on the prediction neural network, according to the operation sequence, the user parameters of the target user, and the data parameters of the target model slice data, includes:

[0015] Regarding the user parameters of the target user and the data parameters of the target model slice data as operation-related information;

[0016] Inputting the operation sequence and the operation-related information into a trained LSTM neural network to obtain the possible modification operations of the target user in the next time period as the output; the LSTM neural network is trained through a training data set including multiple training user operation sequences and corresponding operation-related information annotations.

[0017] As an optional implementation manner, in the first aspect of the present invention, determining the corresponding model modification method and model modification position based on the prediction algorithm according to the possible modification operations includes:

[0018] Determining multiple possible model modification methods and multiple possible model modification positions corresponding to the possible modification operations according to the preset correspondence between operations and model changes;

[0019] Determining the modification operation corresponding to the historical time point closest to the current time point as the reference modification operation;

[0020] Determine the reference model modification method and the reference model modification position corresponding to the reference modification operation;

[0021] For each possible model modification method, input the possible model modification method and the reference model modification method into the trained continuous modification rationality prediction model to obtain the first rationality parameter corresponding to the possible model modification method;

[0022] For each possible model modification position, input the possible model modification position and the reference model modification position into the continuous modification rationality prediction model to obtain the second rationality parameter corresponding to the possible model modification position; the continuous modification rationality prediction model is trained by a training data set including a plurality of training continuous modification operation sequences and corresponding rationality annotations;

[0023] Determine the model modification method corresponding to the possible modification operation as the possible model modification method with the highest first rationality parameter;

[0024] Determine the model modification position corresponding to the possible modification operation as the possible model modification position with the highest second rationality parameter.

[0025] As an optional implementation manner, in the first aspect of the present invention, the modification synchronization data corresponding to the model modification method and the model modification position in the cloud model data for generating the target model slice data in the cloud server includes:

[0026] Determine the cloud model data corresponding to the target model slice data in the cloud server;

[0027] Determine the data part corresponding to the model modification position of the cloud model data as the model data to be modified;

[0028] Modify the model data to be modified based on the model modification method to obtain the modification synchronization data.

[0029] As an optional implementation manner, in the first aspect of the present invention, the method further includes:

[0030] Respond to obtaining a new modification operation of the target user;

[0031] Calculate the operation similarity between the new modification operation and the possible modification operation;

[0032] When the operation similarity is greater than a preset similarity threshold, display the possible modification operation to the target user;

[0033] When obtaining the instruction that the target user agrees to apply the possible modification operation, directly update the modified synchronization data to the cloud model data.

[0034] The second aspect of the embodiments of the present invention discloses a model synchronization processing system for slice data management, and the system includes:

[0035] An acquisition module, configured to acquire in real time the modification operations of the target user on the target model slice data;

[0036] A prediction module, configured to predict the possible modification operations of the target user in the next time period based on multiple modification operations of the target user;

[0037] A determination module, configured to determine the corresponding model modification method and model modification position based on the prediction algorithm according to the possible modification operations;

[0038] A generation module, configured to generate the modified synchronization data corresponding to the model modification method and the model modification position in the cloud model data of the target model slice data in the cloud server; the modified synchronization data is used to modify the cloud model data when the next modification operation of the target user is the same as the possible modification operation.

[0039] As an optional implementation manner, in the second aspect of the present invention, the modification operation includes at least one of modifying the selected model part, modifying the operation type, modifying the movement trajectory, modifying the time point, and modifying the number of undo operations.

[0040] As an optional implementation manner, in the second aspect of the present invention, the specific manner in which the prediction module predicts the possible modification operations of the target user in the next time period based on multiple modification operations of the target user includes:

[0041] Sort the multiple modification operations of the target user obtained at multiple historical time points from early to late based on the corresponding historical time points to obtain an operation sequence;

[0042] Based on a prediction neural network, predict the possible modification operations of the target user in the next time period according to the operation sequence, the user parameters of the target user, and the data parameters of the target model slice data.

[0043] As an optional implementation manner, in the second aspect of the present invention, the user parameters include at least one of user physiological parameters, user permissions, user historical operation records, and user historical access records; the data parameters include at least one of the data volume size, the model representation object type, the model physical parameters, and the model space complexity distribution curve.

[0044] As an alternative implementation, in the second aspect of the present invention, the prediction module, based on a prediction neural network, predicts the specific manner of the possible modification operation of the target user in the next time period according to the operation sequence, the user parameters of the target user, and the data parameters of the target model slice data, including:

[0045] Use the user parameters of the target user and the data parameters of the target model slice data as operation-related information;

[0046] Input the operation sequence and the operation-related information into the trained LSTM neural network to obtain the possible modification operation of the target user in the next time period as the output; the LSTM neural network is trained through a training data set including multiple training user operation sequences and corresponding operation-related information annotations.

[0047] As an alternative implementation, in the second aspect of the present invention, the determination module determines the specific manner of the corresponding model modification method and model modification position based on the prediction algorithm according to the possible modification operation, including:

[0048] According to the preset correspondence between operations and model changes, determine multiple possible model modification methods and multiple possible model modification positions corresponding to the possible modification operation;

[0049] Determine the modification operation corresponding to the nearest historical time point to the current time point as the reference modification operation;

[0050] Determine the reference model modification method and reference model modification position corresponding to the reference modification operation;

[0051] For each of the possible model modification methods, input the possible model modification method and the reference model modification method into the trained continuous modification rationality prediction model to obtain the first rationality parameter corresponding to the possible model modification method;

[0052] For each of the possible model modification positions, input the possible model modification position and the reference model modification position into the continuous modification rationality prediction model to obtain the second rationality parameter corresponding to the possible model modification position; the continuous modification rationality prediction model is trained through a training data set including multiple training continuous modification operation sequences and corresponding rationality annotations;

[0053] Determine the possible model modification method with the highest first rationality parameter as the model modification method corresponding to the possible modification operation;

[0054] Determine the possible model modification position with the highest second rationality parameter as the model modification position corresponding to the possible modification operation.

[0055] As an alternative embodiment, in the second aspect of the present invention, the specific manner in which the generating module generates modification synchronization data corresponding to the model modification manner and the model modification position in the cloud model data of the target model slice data in the cloud server includes:

[0056] Determine the cloud model data corresponding to the target model slice data in the cloud server;

[0057] Determine the data part corresponding to the model modification position of the cloud model data as the model data to be modified;

[0058] Modify the model data to be modified based on the model modification manner to obtain modification synchronization data.

[0059] As an alternative embodiment, in the second aspect of the present invention, the system is further configured to perform the following steps:

[0060] Respond to obtaining a new modification operation of the target user;

[0061] Calculate the operation similarity between the new modification operation and the possible modification operation;

[0062] When the operation similarity is greater than a preset similarity threshold, display the possible modification operation to the target user;

[0063] When obtaining an instruction from the target user to agree to apply the possible modification operation, directly update the modification synchronization data to the cloud model data.

[0064] The third aspect of the present invention discloses another model synchronization processing system for slice data management, and the system includes:

[0065] A memory storing executable program code;

[0066] A processor coupled to the memory;

[0067] The processor calls the executable program code stored in the memory and executes some or all of the steps in the model synchronization processing method for slice data management disclosed in the first aspect of the present invention.

[0068] The fourth aspect of the present invention discloses a computer storage medium, and the computer storage medium stores computer instructions, which when called, are used to execute some or all of the steps in the model synchronization processing method for slice data management disclosed in the first aspect of the present invention.

[0069] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0070] The present invention can predict the possible modification operations of a target user in the next time period based on multiple modification operations of the target user, and then determine the corresponding model modification method and model modification position according to a prediction algorithm to generate modification synchronization data corresponding to the cloud model data in the cloud server to achieve early synchronization of modifications. Therefore, it can fully combine the prediction of user modification operations to improve the efficiency of cloud model data modification synchronization, improve the intelligence and automation of user model modification operations, and give users a better usage experience. Brief Description of the Drawings

[0071] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0072] Figure 1 It is a schematic flowchart of a model synchronization processing method for slice data management disclosed in an embodiment of the present invention.

[0073] Figure 2 It is a schematic structural diagram of a model synchronization processing system for slice data management disclosed in an embodiment of the present invention.

[0074] Figure 3 It is a schematic structural diagram of another model synchronization processing system for slice data management disclosed in an embodiment of the present invention. Detailed Embodiments

[0075] In order to enable those skilled in the art to better understand the solution of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0076] The terms "first", "second", etc. in the specification and claims of the present invention and the above drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, device, product, or equipment that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products, or equipment.

[0077] As used herein, the mention of "embodiment" means that the specific features, structures, or characteristics described in connection with the embodiment may be included in at least one embodiment of the present invention. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein may be combined with other embodiments.

[0078] The present invention discloses a model synchronization processing method and system for slice data management, which can predict the possible modification operations of the target user in the next time period based on multiple modification operations of the target user, and then determine the corresponding model modification method and model modification position according to the prediction algorithm to generate modification synchronization data corresponding to the cloud model data in the cloud server to achieve early synchronization of modifications. Thus, it can fully combine the prediction of user modification operations to improve the efficiency of cloud model data modification synchronization, improve the intelligence and automation of user model modification operations, and give users a better use experience. The following will be described in detail respectively.

[0079] Embodiment 1

[0080] Please refer to Figure 1 , Figure 1 , which is a schematic flowchart of a model synchronization processing method for slice data management disclosed in an embodiment of the present invention. Among them, Figure 1 the described model synchronization processing method for slice data management can be applied to a data processing system / data processing device / data processing server (wherein, the server includes a local processing server or a cloud processing server). As Figure 1 shown, the model synchronization processing method for slice data management may include the following operations:

[0081] 101. Real-time obtain the modification operations of the target user on the target model slice data.

[0082] 102. Based on multiple modification operations of the target user, predict the possible modification operations of the target user in the next time period.

[0083] 103. According to the possible modification operations, based on the prediction algorithm, determine the corresponding model modification method and model modification position.

[0084] 104. Generate modification synchronization data corresponding to the model modification method and model modification position in the cloud model data of the target model slice data in the cloud server.

[0085] Optionally, the modification synchronization data is used to modify the cloud model data when the next modification operation of the target user is the same as the possible modification operation.

[0086] It can be seen that the above-described invention embodiments can predict the possible modification operations of the target user in the next time period based on multiple modification operations of the target user, and then determine the corresponding model modification method and model modification position according to the prediction algorithm to generate modification synchronization data corresponding to the cloud model data in the cloud server to achieve early synchronization of modifications. Thereby, it can fully combine user modification operation prediction to improve the efficiency of cloud model data modification synchronization, improve the intelligence and automation of user model modification operations, and give users a better usage experience.

[0087] As an optional embodiment, in the above steps, the modification operations include at least one of modifying the selected model part, modifying the operation type, modifying the movement trajectory, modifying the time point, and modifying the number of undo operations.

[0088] It can be seen that through the above optional embodiment, the content of the modification operations is defined to accurately represent the modification characteristics of the user, assisting in fully combining user modification operation prediction to improve the efficiency of cloud model data modification synchronization, improve the intelligence and automation of user model modification operations, and give users a better usage experience.

[0089] As an optional embodiment, in the above steps, predicting the possible modification operations of the target user in the next time period based on multiple modification operations of the target user includes:

[0090] Sorting the multiple modification operations of the target user obtained at multiple historical time points from earliest to latest based on the corresponding historical time points to obtain an operation sequence;

[0091] Based on a prediction neural network, according to the operation sequence, the user parameters of the target user, and the data parameters of the target model slice data, predicting the possible modification operations of the target user in the next time period.

[0092] It can be seen that through the above optional embodiment, the operations can be sorted based on the time points to obtain an operation sequence, and then the next possible modification operation can be predicted based on the neural network according to the operation sequence and the user model-related parameters, so as to facilitate subsequent prediction of the modification range and synchronization data, assisting in fully combining user modification operation prediction to improve the efficiency of cloud model data modification synchronization, improve the intelligence and automation of user model modification operations, and give users a better usage experience.

[0093] As an optional embodiment, in the above steps, the user parameters include at least one of user physiological parameters, user permissions, user historical operation records, and user historical access records; the data parameters include at least one of the data volume size, the model representation object type, the model physical parameters, and the model space complexity distribution curve.

[0094] It can be seen that through the above optional embodiments, the contents of user parameters and data parameters are defined to effectively characterize the characteristics of users and model data, predict the next possible modification operation, assist in improving the efficiency of synchronizing the modification of cloud model data by fully combining the prediction of user modification operations, and improve the intelligence and automation of user model modification operations, giving users a better usage experience.

[0095] As an optional embodiment, in the above steps, based on a prediction neural network, according to the operation sequence, the user parameters of the target user, and the data parameters of the target model slice data, predicting the possible modification operation of the target user in the next time period includes:

[0096] Taking the user parameters of the target user and the data parameters of the target model slice data as operation-related information;

[0097] Inputting the operation sequence and the operation-related information into the trained LSTM neural network to obtain the possible modification operation of the target user in the next time period output; the LSTM neural network is trained through a training data set including multiple training user operation sequences and corresponding operation-related information annotations.

[0098] In a specific implementation, first obtain the modification operation records of the target user from multiple historical time points. Each record includes the specific content of the operation and the time when the operation occurred. By sorting these operation records from the earliest to the latest time point, an ordered operation sequence can be generated. For example, assume that the target user performed modification operations at these time points: time : Modify the model head size; time : Delete the model head; time : Drag the second part of the model to the original head position. After sorting, these operations are organized into a sequence from the earliest to the latest for subsequent analysis and processing.

[0099] Then, construct operation-related information including the user parameters of the target user and the data parameters of the target model slice data, while considering the personalized parameters of the target user and the data parameters related to the target model. For example, user parameters may include the user's identifier (such as user ID), operation behavior preferences (such as common editing operation types), and recent activity levels, etc., while model data parameters may include information related to the system state such as the current version number of the model and the size of the model slice. For example, the parameters of a user may be expressed as: "User ID is 12345, role is editor, recent activity level is high"; the corresponding model parameters may be: "Version number is 2.1, slice size is 10MB". This information will be input into the prediction model as additional context data.

[0100] Input the operation sequence and operation-related information into the trained LSTM neural network. By analyzing the time patterns and context information of the operation sequence, this network predicts the modification operations that the target user may perform in the next time period. The training process of the LSTM neural network is based on a labeled training dataset that contains the historical operation sequences and related information of multiple users. By continuously optimizing the training parameters of the network, it can learn the operation rules of different users.

[0101] It can be seen that through the above optional embodiments, it is possible to predict the operation sequence and operation-related information based on the trained LSTM neural network to obtain the possible modification operations of the target user in the next time period, so as to facilitate the subsequent prediction of the modification range and synchronization of data, assist in improving the efficiency of cloud model data modification synchronization by fully combining user modification operation prediction, improve the intelligence and automation of user model modification operations, and give users a better usage experience.

[0102] As an optional embodiment, in the above steps, according to the possible modification operations, based on the prediction algorithm, determining the corresponding model modification method and model modification position includes:

[0103] According to the preset correspondence between operations and model changes, determine multiple possible model modification methods and multiple possible model modification positions corresponding to the possible modification operations;

[0104] Determine the modification operation corresponding to the historical time point closest to the current time point as the reference modification operation;

[0105] Determine the reference model modification method and reference model modification position corresponding to the reference modification operation;

[0106] For each possible model modification method, input the possible model modification method and the reference model modification method into the trained continuous modification rationality prediction model to obtain the first rationality parameter corresponding to the possible model modification method;

[0107] For each possible model modification position, input the possible model modification position and the reference model modification position into the continuous modification rationality prediction model to obtain the second rationality parameter corresponding to the possible model modification position; Optionally, the continuous modification rationality prediction model is trained through a training dataset including multiple training continuous modification operation sequences and corresponding rationality annotations;

[0108] Determine the possible model modification method with the highest first rationality parameter as the model modification method corresponding to the possible modification operation;

[0109] Determine the possible model modification position with the highest second rationality parameter as the model modification position corresponding to the possible modification operation.

[0110] It can be seen that through the above optional embodiments, multiple possible modification methods and modification positions of possible modification operations can be determined based on the corresponding relationship, and then based on the prediction of the continuous modification rationality between the modification methods and modification positions of the reference operation, the corresponding optimal modification methods and modification positions can be screened out, so as to subsequently predict the modified synchronization data, assist in realizing the improvement of the efficiency of cloud model data modification synchronization by fully combining user modification operation prediction, improve the intelligence and automation of user model modification operations, and give users a better use experience.

[0111] As an optional embodiment, in the above steps, generating the modified synchronization data corresponding to the model modification method and model modification position in the cloud model data of the target model slice data in the cloud server includes:

[0112] Determine the cloud model data corresponding to the target model slice data in the cloud server;

[0113] Determine the data part corresponding to the model modification position of the cloud model data as the model data to be modified;

[0114] Modify the model data to be modified based on the model modification method to obtain the modified synchronization data.

[0115] It can be seen that through the above optional embodiments, the cloud model data of the target model slice data in the cloud server can be modified based on the model modification method and model modification position to obtain the modified synchronization data, realizing the improvement of the efficiency of cloud model data modification synchronization by fully combining user modification operation prediction, improving the intelligence and automation of user model modification operations, and giving users a better use experience.

[0116] As an optional embodiment, in the above steps, the method further includes:

[0117] Respond to obtaining a new modification operation of the target user;

[0118] Calculate the operation similarity between the new modification operation and the possible modification operation;

[0119] When the operation similarity is greater than a preset similarity threshold, display the possible modification operation to the target user;

[0120] When obtaining an instruction from the target user to agree to apply the possible modification operation, directly update the modified synchronization data to the cloud model data.

[0121] It can be seen that through the above optional embodiments, it is possible to recommend modification operations to the user based on similarity calculation when the target user actually makes modifications, and directly apply the modification synchronization when the user agrees, so as to achieve a more seamless and intelligent model modification experience, fully combine the prediction of the user's modification operations to improve the efficiency of synchronizing the modification of the cloud model data, improve the intelligence and automation of the user's model modification operations, and give the user a better usage experience.

[0122] Embodiment 2

[0123] Please refer to Figure 2 , Figure 2 which is a schematic structural diagram of a model synchronization processing system for slice data management disclosed in an embodiment of the present invention. Among them, Figure 2 the described model synchronization processing system for slice data management can be applied to a data processing system / data processing device / data processing server (wherein, the server includes a local processing server or a cloud processing server). As Figure 2 shown, the model synchronization processing system for slice data management may include:

[0124] An acquisition module 201, configured to acquire in real time the modification operations of the target user on the target model slice data.

[0125] A prediction module 202, configured to predict the possible modification operations of the target user in the next time period based on multiple modification operations of the target user.

[0126] A determination module 203, configured to determine the corresponding model modification method and model modification position based on the possible modification operations and a prediction algorithm.

[0127] A generation module 204, configured to generate modification synchronization data corresponding to the model modification method and model modification position in the cloud model data of the target model slice data in the cloud server.

[0128] Optionally, the modification synchronization data is used to modify the cloud model data in response to the next modification operation of the target user being the same as the possible modification operation.

[0129] It can be seen that the above embodiments of the present invention can predict the possible modification operations of the target user in the next time period based on multiple modification operations of the target user, and then determine the corresponding model modification method and model modification position according to the prediction algorithm to generate the modification synchronization data corresponding to the cloud model data in the cloud server to achieve early synchronization of modifications, so as to be able to fully combine the prediction of the user's modification operations to improve the efficiency of synchronizing the modification of the cloud model data, improve the intelligence and automation of the user's model modification operations, and give the user a better usage experience.

[0130] As an alternative embodiment, the modification operation includes modifying at least one of the selected model part, the modification operation type, the movement trajectory, the time point, and the number of undo operations.

[0131] It can be seen that through the above alternative embodiments, the content of the modification operation is defined to accurately represent the user's modification features, assist in improving the efficiency of synchronizing the modification of cloud model data by fully combining user modification operation prediction, improve the intelligence and automation of the user's model modification operation, and give the user a better usage experience.

[0132] As an alternative embodiment, the prediction module predicts the specific manner of the possible modification operation of the target user in the next time period based on multiple modification operations of the target user, including:

[0133] Sort the multiple modification operations of the target user obtained at multiple historical time points from earliest to latest based on the corresponding historical time points to obtain an operation sequence;

[0134] Based on the prediction neural network, according to the operation sequence, the user parameters of the target user, and the data parameters of the target model slice data, predict the possible modification operation of the target user in the next time period.

[0135] It can be seen that through the above alternative embodiments, the operations can be sorted based on the time points to obtain an operation sequence, and then based on the neural network, the next possible modification operation can be predicted according to the operation sequence and the relevant parameters of the user model, so as to facilitate predicting the modification range and synchronizing data in the subsequent process, assist in improving the efficiency of synchronizing the modification of cloud model data by fully combining user modification operation prediction, improve the intelligence and automation of the user's model modification operation, and give the user a better usage experience.

[0136] As an alternative embodiment, the user parameters include at least one of user physiological parameters, user permissions, user historical operation records, and user historical access records; the data parameters include at least one of the data volume size, the type of model representation object, the model physical parameters, and the model space complexity distribution curve.

[0137] It can be seen that through the above alternative embodiments, the content of the user parameters and the data parameters is defined to effectively represent the characteristics of the user and the model data, predict the next possible modification operation, assist in improving the efficiency of synchronizing the modification of cloud model data by fully combining user modification operation prediction, improve the intelligence and automation of the user's model modification operation, and give the user a better usage experience.

[0138] As an alternative embodiment, the prediction module predicts the specific manner of the possible modification operation of the target user in the next time period based on the prediction neural network, according to the operation sequence, the user parameters of the target user, and the data parameters of the target model slice data, including:

[0139] Use the user parameters of the target user and the data parameters of the target model slice data as operation-related information;

[0140] Input the operation sequence and operation-related information into the trained LSTM neural network to obtain the possible modification operations of the target user in the next time period; the LSTM neural network is trained through a training data set including multiple training user operation sequences and corresponding operation-related information annotations.

[0141] It can be seen that through the above optional embodiments, it is possible to predict the operation sequence and operation-related information based on the trained LSTM neural network to obtain the possible modification operations of the target user in the next time period, so as to facilitate subsequent prediction of the modification range and synchronization of data, assist in improving the efficiency of cloud model data modification synchronization by fully combining user modification operation prediction, improve the intelligence and automation of user model modification operations, and give users a better usage experience.

[0142] As an optional embodiment, the specific manner in which the determination module determines the corresponding model modification method and model modification position based on the possible modification operations according to the prediction algorithm includes:

[0143] According to the preset correspondence between operations and model changes, determine multiple possible model modification methods and multiple possible model modification positions corresponding to the possible modification operations;

[0144] Determine the modification operation corresponding to the historical time point closest to the current time point as the reference modification operation;

[0145] Determine the reference model modification method and reference model modification position corresponding to the reference modification operation;

[0146] For each possible model modification method, input the possible model modification method and the reference model modification method into the trained continuous modification rationality prediction model to obtain the first rationality parameter corresponding to the possible model modification method;

[0147] For each possible model modification position, input the possible model modification position and the reference model modification position into the continuous modification rationality prediction model to obtain the second rationality parameter corresponding to the possible model modification position; optionally, the continuous modification rationality prediction model is trained through a training data set including multiple training continuous modification operation sequences and corresponding rationality annotations;

[0148] Determine the possible model modification method with the highest first rationality parameter as the model modification method corresponding to the possible modification operation;

[0149] Determine the possible modification position of the model with the highest second rationality parameter as the model modification position corresponding to the possible modification operation.

[0150] It can be seen that through the above optional embodiments, multiple possible modification methods and modification positions of the possible modification operation can be determined based on the corresponding relationship, and then the corresponding optimal modification method and modification position can be screened out based on the prediction of the continuous modification rationality between the modification method and modification position of the reference operation, so as to facilitate the subsequent prediction of the modification synchronization data, assist in improving the efficiency of the cloud model data modification synchronization by fully combining the prediction of the user's modification operation, improve the intelligence and automation of the user's model modification operation, and give the user a better use experience.

[0151] As an optional embodiment, the specific method for the generation module to generate the modification synchronization data corresponding to the model modification method and model modification position in the cloud model data of the target model slice data in the cloud server includes:

[0152] Determine the cloud model data corresponding to the target model slice data in the cloud server;

[0153] Determine the data part corresponding to the model modification position of the cloud model data as the model data to be modified;

[0154] Modify the model data to be modified based on the model modification method to obtain the modification synchronization data.

[0155] It can be seen that through the above optional embodiments, the cloud model data of the target model slice data in the cloud server can be modified based on the model modification method and model modification position to obtain the modification synchronization data, realizing the improvement of the efficiency of the cloud model data modification synchronization by fully combining the prediction of the user's modification operation, improving the intelligence and automation of the user's model modification operation, and giving the user a better use experience.

[0156] As an optional embodiment, the system is further configured to perform the following steps:

[0157] Respond to obtaining a new modification operation of the target user;

[0158] Calculate the operation similarity between the new modification operation and the possible modification operation;

[0159] When the operation similarity is greater than the preset similarity threshold, display the possible modification operation to the target user;

[0160] When obtaining an instruction from the target user to agree to apply the possible modification operation, directly update the modification synchronization data to the cloud model data.

[0161] It can be seen that through the above optional embodiments, it is possible to recommend modification operations to the user based on similarity calculation when the target user actually makes modifications, and directly apply the modification synchronization when the user agrees, so as to achieve a more seamless and intelligent model modification experience, fully combine the prediction of the user's modification operations to improve the efficiency of cloud model data modification synchronization, improve the intelligence and automation of the user's model modification operations, and give the user a better usage experience.

[0162] Embodiment III

[0163] Please refer to Figure 3 , Figure 3 which is another model synchronization processing system for slice data management disclosed in the embodiments of the present invention. Figure 3 The model synchronization processing system for slice data management described is applied in a data processing system / data processing device / data processing server (wherein, the server includes a local processing server or a cloud processing server). As Figure 3 shown, the model synchronization processing system for slice data management may include:

[0164] A memory 301 storing executable program code;

[0165] A processor 302 coupled to the memory 301;

[0166] Wherein, the processor 302 calls the executable program code stored in the memory 301 to execute the steps of the model synchronization processing method for slice data management described in Embodiment I.

[0167] Embodiment IV

[0168] The embodiments of the present invention disclose a computer-readable storage medium, which stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the model synchronization processing method for slice data management described in Embodiment I.

[0169] Embodiment V

[0170] The embodiments of the present invention disclose a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the model synchronization processing method for slice data management described in Embodiment I.

[0171] The above description of specific embodiments of this specification, other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the figures do not necessarily have to be performed in the specific order or sequential order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0172] The systems, devices, modules, or units illustrated in the above embodiments can specifically be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0173] For convenience of description, when describing the above devices, they are described as various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0174] Those skilled in the art should understand that the embodiments of this specification can be provided as a method, system, or computer program product. Therefore, the embodiments of this specification can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0175] This specification is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing device to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing device generate a device for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0176] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction means that implements the function specified in one or more of the processes and / or blocks Figure 1 in the process or processes and / or blocks Figure 1 specified in the block or blocks.

[0177] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing steps for implementing the function specified in one or more of the processes and / or blocks Figure 1 in the process or processes and / or blocks Figure 1 specified in the block or blocks.

[0178] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0179] The memory may include non-permanent memory in the computer-readable medium, random access memory (RAM) and / or non-volatile memory such as read only memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

[0180] Computer-readable media includes both permanent and non-permanent, removable and non-removable media implemented by any method or technology for storing information. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other memory technologies, compact disc read only memory (CD-ROM), digital versatile discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0181] It should also be noted that the term "comprise", "include" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, commodity or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "comprising an …" does not exclude the presence of additional identical elements in the process, method, commodity or device comprising said element.

[0182] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. This specification may also be practiced in a distributed computing environment where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media including storage devices.

[0183] Each embodiment in this specification is described in a progressive manner, and the same or similar parts among the embodiments may be referred to each other. Each embodiment focuses on the differences from other embodiments. In particular, for system embodiments, since they are basically similar to method embodiments, they are described relatively simply, and the relevant parts may be referred to the description of the method embodiments.

[0184] Finally, it should be noted that the model synchronization processing method and system for slice data management disclosed in the embodiments of the present invention only disclose the preferred embodiments of the present invention, and are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A model synchronization processing method for slice data management, characterized in that, The method includes: Obtaining in real time the modification operations of the target user on the sliced data of the target model; Predicting the possible modification operations of the target user in the next time period based on multiple modification operations of the target user; Determining the corresponding model modification method and model modification position based on the predicted algorithm according to the possible modification operations, including: Determining multiple possible model modification methods and multiple possible model modification positions corresponding to the possible modification operations according to the corresponding relationship between the preset operations and the model changes; Determining the modification operation corresponding to the nearest historical time point to the current time point as the reference modification operation; Determining the reference model modification method and the reference model modification position corresponding to the reference modification operation; For each of the possible model modification methods, inputting the possible model modification method and the reference model modification method into the trained continuous modification rationality prediction model to obtain a first rationality parameter corresponding to the possible model modification method; For each of the possible model modification positions, inputting the possible model modification position and the reference model modification position into the continuous modification rationality prediction model to obtain a second rationality parameter corresponding to the possible model modification position; the continuous modification rationality prediction model is trained by a training data set including multiple training continuous modification operation sequences and corresponding rationality annotations; Determining the possible model modification method with the highest first rationality parameter as the model modification method corresponding to the possible modification operation; Determining the possible model modification position with the highest second rationality parameter as the model modification position corresponding to the possible modification operation; Generating modification synchronization data corresponding to the model modification method and the model modification position in the cloud model data of the sliced data of the target model in the cloud server; the modification synchronization data is used to modify the cloud model data when the next modification operation of the target user is the same as the possible modification operation.

2. The model synchronization processing method for slice data management according to claim 1, wherein, The modification operations include at least one of modifying the selected model part, modifying the operation type, modifying the movement trajectory, modifying the time point, and modifying the number of undo operations.

3. The model synchronization processing method for slice data management according to claim 1, wherein, The predicting the possible modification operations of the target user in the next time period based on multiple modification operations of the target user includes: Sorting the multiple modification operations of the target user obtained at multiple historical time points from earliest to latest based on the corresponding historical time points to obtain an operation sequence; Predicting the possible modification operations of the target user in the next time period based on the operation sequence, the user parameters of the target user, and the data parameters of the sliced data of the target model by a prediction neural network.

4. The model synchronization processing method for slice data management according to claim 3, characterized in that, The user parameters include at least one of user physiological parameters, user permissions, user historical operation records, and user historical access records; the data parameters include at least one of the data volume size, the type of model representation object, the model physical parameters, and the model space complexity distribution curve.

5. The model synchronization processing method for slice data management according to claim 3, characterized in that, Based on the prediction neural network, predicting the possible modification operations of the target user in the next time period according to the operation sequence, the user parameters of the target user, and the data parameters of the target model slice data, including: Regarding the user parameters of the target user and the data parameters of the target model slice data as operation-related information; Inputting the operation sequence and the operation-related information into the trained LSTM neural network to obtain the possible modification operations of the target user in the next time period output by the LSTM neural network; the LSTM neural network is trained through a training data set including multiple training user operation sequences and corresponding operation-related information annotations.

6. The model synchronization processing method for slice data management according to claim 1, wherein, Generating modification synchronization data corresponding to the model modification method and the model modification position in the cloud model data of the target model slice data in the cloud server, including: Determining the cloud model data corresponding to the target model slice data in the cloud server; Determining the data part corresponding to the model modification position of the cloud model data as the model data to be modified; Modifying the model data to be modified based on the model modification method to obtain the modification synchronization data.

7. The model synchronization processing method for slice data management according to claim 6, characterized in that The method further includes: Responding to obtaining a new modification operation of the target user; Calculating the operation similarity between the new modification operation and the possible modification operation; When the operation similarity is greater than a preset similarity threshold, presenting the possible modification operation to the target user; When obtaining an instruction from the target user to agree to apply the possible modification operation, directly updating the modification synchronization data to the cloud model data.

8. A model synchronization processing system for slice data management, characterized in that, The system includes: An acquisition module, configured to acquire in real time the modification operations of the target user on the target model slice data; A prediction module, configured to predict the possible modification operations of the target user in the next time period based on multiple modification operations of the target user; A determination module, configured to determine the corresponding model modification method and model modification position based on a prediction algorithm according to the possible modification operations, including: Determining multiple possible model modification methods and multiple possible model modification positions corresponding to the possible modification operations according to a preset correspondence between operations and model changes; Determining the modification operation corresponding to the nearest historical time point to the current time point as the reference modification operation; Determining the reference model modification method and reference model modification position corresponding to the reference modification operation; For each of the possible model modification methods, inputting the possible model modification method and the reference model modification method into the trained continuous modification rationality prediction model to obtain a first rationality parameter corresponding to the possible model modification method; For each of the possible model modification positions, inputting the possible model modification position and the reference model modification position into the continuous modification rationality prediction model to obtain a second rationality parameter corresponding to the possible model modification position; the continuous modification rationality prediction model is trained through a training data set including multiple training continuous modification operation sequences and corresponding rationality annotations. Determine the model modification method corresponding to the possible modification operation by taking the model possible modification method with the highest first rationality parameter; Determine the model possible modification location with the highest second rationality parameter as the model modification location corresponding to the possible modification operation; A generation module, configured to generate modification synchronization data corresponding to the model modification method and the model modification location in the cloud model data of the target model slice data in the cloud server; the modification synchronization data is used to modify the cloud model data when the next modification operation of the target user is the same as the possible modification operation.

9. A model synchronization processing system for slice data management, characterized in that, The system includes: A memory storing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory and executes the model synchronization processing method for slice data management according to any one of claims 1-7.

Images